Taiel26 commited on
Commit
6a46f8c
·
verified ·
1 Parent(s): 92cd1d8

Upload 51 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +143 -3
  2. adapter_config.json +34 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-100/README.md +202 -0
  5. checkpoint-100/adapter_config.json +34 -0
  6. checkpoint-100/adapter_model.safetensors +3 -0
  7. checkpoint-100/optimizer.pt +3 -0
  8. checkpoint-100/rng_state.pth +3 -0
  9. checkpoint-100/scheduler.pt +3 -0
  10. checkpoint-100/special_tokens_map.json +24 -0
  11. checkpoint-100/tokenizer.model +3 -0
  12. checkpoint-100/tokenizer_config.json +44 -0
  13. checkpoint-100/trainer_state.json +797 -0
  14. checkpoint-100/training_args.bin +3 -0
  15. checkpoint-150/README.md +202 -0
  16. checkpoint-150/adapter_config.json +34 -0
  17. checkpoint-150/adapter_model.safetensors +3 -0
  18. checkpoint-150/optimizer.pt +3 -0
  19. checkpoint-150/rng_state.pth +3 -0
  20. checkpoint-150/scheduler.pt +3 -0
  21. checkpoint-150/special_tokens_map.json +24 -0
  22. checkpoint-150/tokenizer.model +3 -0
  23. checkpoint-150/tokenizer_config.json +44 -0
  24. checkpoint-150/trainer_state.json +1179 -0
  25. checkpoint-150/training_args.bin +3 -0
  26. checkpoint-200/README.md +202 -0
  27. checkpoint-200/adapter_config.json +34 -0
  28. checkpoint-200/adapter_model.safetensors +3 -0
  29. checkpoint-200/optimizer.pt +3 -0
  30. checkpoint-200/rng_state.pth +3 -0
  31. checkpoint-200/scheduler.pt +3 -0
  32. checkpoint-200/special_tokens_map.json +24 -0
  33. checkpoint-200/tokenizer.model +3 -0
  34. checkpoint-200/tokenizer_config.json +44 -0
  35. checkpoint-200/trainer_state.json +1561 -0
  36. checkpoint-200/training_args.bin +3 -0
  37. checkpoint-50/README.md +202 -0
  38. checkpoint-50/adapter_config.json +34 -0
  39. checkpoint-50/adapter_model.safetensors +3 -0
  40. checkpoint-50/optimizer.pt +3 -0
  41. checkpoint-50/rng_state.pth +3 -0
  42. checkpoint-50/scheduler.pt +3 -0
  43. checkpoint-50/special_tokens_map.json +24 -0
  44. checkpoint-50/tokenizer.model +3 -0
  45. checkpoint-50/tokenizer_config.json +44 -0
  46. checkpoint-50/trainer_state.json +415 -0
  47. checkpoint-50/training_args.bin +3 -0
  48. config.json +44 -0
  49. special_tokens_map.json +24 -0
  50. tokenizer.model +3 -0
README.md CHANGED
@@ -1,3 +1,143 @@
1
- ---
2
- license: unknown
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
7
+ model-index:
8
+ - name: outputs/qlora-out
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.1`
19
+ ```yaml
20
+ adapter: qlora
21
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
22
+ bf16: auto
23
+ dataset_prepared_path: null
24
+ datasets:
25
+ - path: Taiel26/plm_2500_uniref
26
+ type: alpaca
27
+ debug: null
28
+ deepspeed: null
29
+ early_stopping_patience: null
30
+ eval_sample_packing: false
31
+ evals_per_epoch: 4
32
+ flash_attention: true
33
+ fp16: null
34
+ fsdp: null
35
+ fsdp_config: null
36
+ gradient_accumulation_steps: 4
37
+ gradient_checkpointing: true
38
+ group_by_length: false
39
+ learning_rate: 0.0002
40
+ load_in_4bit: true
41
+ load_in_8bit: false
42
+ local_rank: null
43
+ logging_steps: 1
44
+ lora_alpha: 16
45
+ lora_dropout: 0.05
46
+ lora_fan_in_fan_out: null
47
+ lora_model_dir: null
48
+ lora_r: 32
49
+ lora_target_linear: true
50
+ lora_target_modules: null
51
+ lr_scheduler: cosine
52
+ micro_batch_size: 2
53
+ model_type: LlamaForCausalLM
54
+ num_epochs: 4
55
+ optimizer: paged_adamw_32bit
56
+ output_dir: ./outputs/qlora-out
57
+ pad_to_sequence_len: true
58
+ resume_from_checkpoint: null
59
+ sample_packing: true
60
+ saves_per_epoch: 1
61
+ sequence_len: 4096
62
+ special_tokens: null
63
+ strict: false
64
+ tf32: false
65
+ tokenizer_type: LlamaTokenizer
66
+ train_on_inputs: false
67
+ val_set_size: 0.05
68
+ wandb_entity: null
69
+ wandb_log_model: null
70
+ wandb_name: null
71
+ wandb_project: null
72
+ wandb_watch: null
73
+ warmup_steps: 10
74
+ weight_decay: 0.0
75
+ xformers_attention: null
76
+
77
+ ```
78
+
79
+ </details><br>
80
+
81
+ # outputs/qlora-out
82
+
83
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset.
84
+ It achieves the following results on the evaluation set:
85
+ - Loss: 0.8586
86
+
87
+ ## Model description
88
+
89
+ More information needed
90
+
91
+ ## Intended uses & limitations
92
+
93
+ More information needed
94
+
95
+ ## Training and evaluation data
96
+
97
+ More information needed
98
+
99
+ ## Training procedure
100
+
101
+ ### Training hyperparameters
102
+
103
+ The following hyperparameters were used during training:
104
+ - learning_rate: 0.0002
105
+ - train_batch_size: 2
106
+ - eval_batch_size: 2
107
+ - seed: 42
108
+ - gradient_accumulation_steps: 4
109
+ - total_train_batch_size: 8
110
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
111
+ - lr_scheduler_type: cosine
112
+ - lr_scheduler_warmup_steps: 10
113
+ - num_epochs: 4
114
+
115
+ ### Training results
116
+
117
+ | Training Loss | Epoch | Step | Validation Loss |
118
+ |:-------------:|:------:|:----:|:---------------:|
119
+ | 2.0919 | 0.0198 | 1 | 2.0800 |
120
+ | 1.5479 | 0.2574 | 13 | 1.5341 |
121
+ | 1.2083 | 0.5149 | 26 | 1.2245 |
122
+ | 1.0851 | 0.7723 | 39 | 1.0607 |
123
+ | 0.9432 | 1.0297 | 52 | 0.9755 |
124
+ | 0.9007 | 1.2178 | 65 | 0.9334 |
125
+ | 0.8765 | 1.4752 | 78 | 0.9084 |
126
+ | 0.8789 | 1.7327 | 91 | 0.8891 |
127
+ | 0.8304 | 1.9901 | 104 | 0.8779 |
128
+ | 0.8194 | 2.1782 | 117 | 0.8714 |
129
+ | 0.848 | 2.4356 | 130 | 0.8665 |
130
+ | 0.8354 | 2.6931 | 143 | 0.8627 |
131
+ | 0.8476 | 2.9505 | 156 | 0.8605 |
132
+ | 0.811 | 3.1386 | 169 | 0.8590 |
133
+ | 0.8178 | 3.3960 | 182 | 0.8588 |
134
+ | 0.8073 | 3.6535 | 195 | 0.8586 |
135
+
136
+
137
+ ### Framework versions
138
+
139
+ - PEFT 0.11.1
140
+ - Transformers 4.41.1
141
+ - Pytorch 2.1.2+cu121
142
+ - Datasets 2.19.1
143
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "down_proj",
25
+ "gate_proj",
26
+ "v_proj",
27
+ "q_proj",
28
+ "o_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffc2779c22b7eae997dc6203abde8f60a5e25d728ff0372f233c318ba1fdff97
3
+ size 50573978
checkpoint-100/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "down_proj",
25
+ "gate_proj",
26
+ "v_proj",
27
+ "q_proj",
28
+ "o_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b85a4fdc0abdb0ae863b99d8dbbc0f4de78e0d9fbd7bcb1ddcd7575e55dd73e
3
+ size 50503848
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b8f5c81e295185d82b95402d9e8aa5ba7f3db7c0d3626b29a8ce3a7f38899ae
3
+ size 202035450
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b71df2f60f93f95a69126d2a7bc1e1cccfa69f1b8fa8d99a58b0ccfa00747f6f
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc7800513a1b4dd006c457152c700dd768bb49ee4ed8e4d9665a4e42095b054
3
+ size 1064
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-100/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "use_fast": true
44
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,797 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9108910891089108,
5
+ "eval_steps": 13,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.019801980198019802,
13
+ "grad_norm": 1.15625,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.0919,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.019801980198019802,
20
+ "eval_loss": 2.079954147338867,
21
+ "eval_runtime": 13.8908,
22
+ "eval_samples_per_second": 8.999,
23
+ "eval_steps_per_second": 4.535,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.039603960396039604,
28
+ "grad_norm": 1.203125,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.0814,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0594059405940594,
35
+ "grad_norm": 1.1953125,
36
+ "learning_rate": 6e-05,
37
+ "loss": 2.0499,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.07920792079207921,
42
+ "grad_norm": 1.0859375,
43
+ "learning_rate": 8e-05,
44
+ "loss": 2.0153,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.09900990099009901,
49
+ "grad_norm": 1.0390625,
50
+ "learning_rate": 0.0001,
51
+ "loss": 1.9548,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.1188118811881188,
56
+ "grad_norm": 0.89453125,
57
+ "learning_rate": 0.00012,
58
+ "loss": 1.8982,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.13861386138613863,
63
+ "grad_norm": 0.67578125,
64
+ "learning_rate": 0.00014,
65
+ "loss": 1.8226,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.15841584158415842,
70
+ "grad_norm": 0.66796875,
71
+ "learning_rate": 0.00016,
72
+ "loss": 1.7572,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.1782178217821782,
77
+ "grad_norm": 0.78515625,
78
+ "learning_rate": 0.00018,
79
+ "loss": 1.7074,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.19801980198019803,
84
+ "grad_norm": 0.73828125,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.6317,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.21782178217821782,
91
+ "grad_norm": 0.484375,
92
+ "learning_rate": 0.0001999863304992469,
93
+ "loss": 1.5801,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.2376237623762376,
98
+ "grad_norm": 0.53125,
99
+ "learning_rate": 0.00019994532573409262,
100
+ "loss": 1.5721,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.25742574257425743,
105
+ "grad_norm": 0.6953125,
106
+ "learning_rate": 0.00019987699691483048,
107
+ "loss": 1.5479,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.25742574257425743,
112
+ "eval_loss": 1.5341482162475586,
113
+ "eval_runtime": 13.8795,
114
+ "eval_samples_per_second": 9.006,
115
+ "eval_steps_per_second": 4.539,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.27722772277227725,
120
+ "grad_norm": 0.65234375,
121
+ "learning_rate": 0.00019978136272187747,
122
+ "loss": 1.534,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.297029702970297,
127
+ "grad_norm": 0.515625,
128
+ "learning_rate": 0.000199658449300667,
129
+ "loss": 1.4804,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.31683168316831684,
134
+ "grad_norm": 0.439453125,
135
+ "learning_rate": 0.00019950829025450114,
136
+ "loss": 1.4805,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.33663366336633666,
141
+ "grad_norm": 0.361328125,
142
+ "learning_rate": 0.00019933092663536382,
143
+ "loss": 1.3809,
144
+ "step": 17
145
+ },
146
+ {
147
+ "epoch": 0.3564356435643564,
148
+ "grad_norm": 0.3125,
149
+ "learning_rate": 0.00019912640693269752,
150
+ "loss": 1.3837,
151
+ "step": 18
152
+ },
153
+ {
154
+ "epoch": 0.37623762376237624,
155
+ "grad_norm": 0.337890625,
156
+ "learning_rate": 0.00019889478706014687,
157
+ "loss": 1.3673,
158
+ "step": 19
159
+ },
160
+ {
161
+ "epoch": 0.39603960396039606,
162
+ "grad_norm": 0.298828125,
163
+ "learning_rate": 0.00019863613034027224,
164
+ "loss": 1.366,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.4158415841584158,
169
+ "grad_norm": 0.34375,
170
+ "learning_rate": 0.00019835050748723824,
171
+ "loss": 1.3318,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.43564356435643564,
176
+ "grad_norm": 0.341796875,
177
+ "learning_rate": 0.00019803799658748094,
178
+ "loss": 1.2741,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.45544554455445546,
183
+ "grad_norm": 0.326171875,
184
+ "learning_rate": 0.00019769868307835994,
185
+ "loss": 1.2978,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 0.4752475247524752,
190
+ "grad_norm": 0.291015625,
191
+ "learning_rate": 0.0001973326597248006,
192
+ "loss": 1.2733,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.49504950495049505,
197
+ "grad_norm": 0.306640625,
198
+ "learning_rate": 0.00019694002659393305,
199
+ "loss": 1.2302,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.5148514851485149,
204
+ "grad_norm": 0.318359375,
205
+ "learning_rate": 0.00019652089102773488,
206
+ "loss": 1.2083,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.5148514851485149,
211
+ "eval_loss": 1.224540114402771,
212
+ "eval_runtime": 13.8695,
213
+ "eval_samples_per_second": 9.013,
214
+ "eval_steps_per_second": 4.542,
215
+ "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.5346534653465347,
219
+ "grad_norm": 0.26953125,
220
+ "learning_rate": 0.00019607536761368484,
221
+ "loss": 1.1761,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.5544554455445545,
226
+ "grad_norm": 0.296875,
227
+ "learning_rate": 0.00019560357815343577,
228
+ "loss": 1.1751,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.5742574257425742,
233
+ "grad_norm": 0.310546875,
234
+ "learning_rate": 0.00019510565162951537,
235
+ "loss": 1.2002,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.594059405940594,
240
+ "grad_norm": 0.287109375,
241
+ "learning_rate": 0.00019458172417006347,
242
+ "loss": 1.1544,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.6138613861386139,
247
+ "grad_norm": 0.365234375,
248
+ "learning_rate": 0.00019403193901161613,
249
+ "loss": 1.1384,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.6336633663366337,
254
+ "grad_norm": 0.236328125,
255
+ "learning_rate": 0.0001934564464599461,
256
+ "loss": 1.0999,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.6534653465346535,
261
+ "grad_norm": 0.326171875,
262
+ "learning_rate": 0.00019285540384897073,
263
+ "loss": 1.1576,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.6732673267326733,
268
+ "grad_norm": 0.310546875,
269
+ "learning_rate": 0.00019222897549773848,
270
+ "loss": 1.091,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 0.693069306930693,
275
+ "grad_norm": 0.2578125,
276
+ "learning_rate": 0.00019157733266550575,
277
+ "loss": 1.056,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 0.7128712871287128,
282
+ "grad_norm": 0.267578125,
283
+ "learning_rate": 0.00019090065350491626,
284
+ "loss": 1.1068,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 0.7326732673267327,
289
+ "grad_norm": 0.2490234375,
290
+ "learning_rate": 0.00019019912301329592,
291
+ "loss": 1.0583,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 0.7524752475247525,
296
+ "grad_norm": 0.2734375,
297
+ "learning_rate": 0.00018947293298207635,
298
+ "loss": 1.0671,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 0.7722772277227723,
303
+ "grad_norm": 0.2490234375,
304
+ "learning_rate": 0.0001887222819443612,
305
+ "loss": 1.0851,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 0.7722772277227723,
310
+ "eval_loss": 1.060703158378601,
311
+ "eval_runtime": 13.878,
312
+ "eval_samples_per_second": 9.007,
313
+ "eval_steps_per_second": 4.54,
314
+ "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.7920792079207921,
318
+ "grad_norm": 0.22265625,
319
+ "learning_rate": 0.0001879473751206489,
320
+ "loss": 1.0343,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.8118811881188119,
325
+ "grad_norm": 0.1796875,
326
+ "learning_rate": 0.00018714842436272773,
327
+ "loss": 0.9789,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.8316831683168316,
332
+ "grad_norm": 0.248046875,
333
+ "learning_rate": 0.00018632564809575742,
334
+ "loss": 1.0174,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.8514851485148515,
339
+ "grad_norm": 0.2294921875,
340
+ "learning_rate": 0.0001854792712585539,
341
+ "loss": 1.0004,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.8712871287128713,
346
+ "grad_norm": 0.228515625,
347
+ "learning_rate": 0.00018460952524209355,
348
+ "loss": 1.0281,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.8910891089108911,
353
+ "grad_norm": 0.220703125,
354
+ "learning_rate": 0.00018371664782625287,
355
+ "loss": 0.9992,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.9108910891089109,
360
+ "grad_norm": 0.2138671875,
361
+ "learning_rate": 0.00018280088311480201,
362
+ "loss": 0.9635,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.9306930693069307,
367
+ "grad_norm": 0.265625,
368
+ "learning_rate": 0.00018186248146866927,
369
+ "loss": 1.006,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.9504950495049505,
374
+ "grad_norm": 0.2451171875,
375
+ "learning_rate": 0.00018090169943749476,
376
+ "loss": 0.9891,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.9702970297029703,
381
+ "grad_norm": 0.28515625,
382
+ "learning_rate": 0.0001799187996894925,
383
+ "loss": 0.9809,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.9900990099009901,
388
+ "grad_norm": 0.212890625,
389
+ "learning_rate": 0.00017891405093963938,
390
+ "loss": 0.9646,
391
+ "step": 50
392
+ },
393
+ {
394
+ "epoch": 1.00990099009901,
395
+ "grad_norm": 0.2451171875,
396
+ "learning_rate": 0.00017788772787621126,
397
+ "loss": 0.9553,
398
+ "step": 51
399
+ },
400
+ {
401
+ "epoch": 1.0297029702970297,
402
+ "grad_norm": 0.2578125,
403
+ "learning_rate": 0.00017684011108568592,
404
+ "loss": 0.9432,
405
+ "step": 52
406
+ },
407
+ {
408
+ "epoch": 1.0297029702970297,
409
+ "eval_loss": 0.9755253195762634,
410
+ "eval_runtime": 13.879,
411
+ "eval_samples_per_second": 9.006,
412
+ "eval_steps_per_second": 4.539,
413
+ "step": 52
414
+ },
415
+ {
416
+ "epoch": 1.0495049504950495,
417
+ "grad_norm": 0.2021484375,
418
+ "learning_rate": 0.0001757714869760335,
419
+ "loss": 0.9631,
420
+ "step": 53
421
+ },
422
+ {
423
+ "epoch": 1.0693069306930694,
424
+ "grad_norm": 0.3046875,
425
+ "learning_rate": 0.0001746821476984154,
426
+ "loss": 0.9539,
427
+ "step": 54
428
+ },
429
+ {
430
+ "epoch": 1.0198019801980198,
431
+ "grad_norm": 0.232421875,
432
+ "learning_rate": 0.00017357239106731317,
433
+ "loss": 0.9559,
434
+ "step": 55
435
+ },
436
+ {
437
+ "epoch": 1.0396039603960396,
438
+ "grad_norm": 0.283203125,
439
+ "learning_rate": 0.00017244252047910892,
440
+ "loss": 0.9111,
441
+ "step": 56
442
+ },
443
+ {
444
+ "epoch": 1.0594059405940595,
445
+ "grad_norm": 0.30859375,
446
+ "learning_rate": 0.00017129284482913972,
447
+ "loss": 0.9503,
448
+ "step": 57
449
+ },
450
+ {
451
+ "epoch": 1.0792079207920793,
452
+ "grad_norm": 0.2265625,
453
+ "learning_rate": 0.00017012367842724887,
454
+ "loss": 0.911,
455
+ "step": 58
456
+ },
457
+ {
458
+ "epoch": 1.099009900990099,
459
+ "grad_norm": 0.3515625,
460
+ "learning_rate": 0.0001689353409118566,
461
+ "loss": 0.9041,
462
+ "step": 59
463
+ },
464
+ {
465
+ "epoch": 1.118811881188119,
466
+ "grad_norm": 0.26171875,
467
+ "learning_rate": 0.00016772815716257412,
468
+ "loss": 0.9117,
469
+ "step": 60
470
+ },
471
+ {
472
+ "epoch": 1.1386138613861387,
473
+ "grad_norm": 0.2890625,
474
+ "learning_rate": 0.0001665024572113848,
475
+ "loss": 0.9351,
476
+ "step": 61
477
+ },
478
+ {
479
+ "epoch": 1.1584158415841583,
480
+ "grad_norm": 0.251953125,
481
+ "learning_rate": 0.00016525857615241687,
482
+ "loss": 0.9438,
483
+ "step": 62
484
+ },
485
+ {
486
+ "epoch": 1.1782178217821782,
487
+ "grad_norm": 0.2138671875,
488
+ "learning_rate": 0.00016399685405033167,
489
+ "loss": 0.9075,
490
+ "step": 63
491
+ },
492
+ {
493
+ "epoch": 1.198019801980198,
494
+ "grad_norm": 0.2490234375,
495
+ "learning_rate": 0.0001627176358473537,
496
+ "loss": 0.8983,
497
+ "step": 64
498
+ },
499
+ {
500
+ "epoch": 1.2178217821782178,
501
+ "grad_norm": 0.2021484375,
502
+ "learning_rate": 0.0001614212712689668,
503
+ "loss": 0.9007,
504
+ "step": 65
505
+ },
506
+ {
507
+ "epoch": 1.2178217821782178,
508
+ "eval_loss": 0.9333999156951904,
509
+ "eval_runtime": 13.8668,
510
+ "eval_samples_per_second": 9.014,
511
+ "eval_steps_per_second": 4.543,
512
+ "step": 65
513
+ },
514
+ {
515
+ "epoch": 1.2376237623762376,
516
+ "grad_norm": 0.2431640625,
517
+ "learning_rate": 0.00016010811472830252,
518
+ "loss": 0.9108,
519
+ "step": 66
520
+ },
521
+ {
522
+ "epoch": 1.2574257425742574,
523
+ "grad_norm": 0.232421875,
524
+ "learning_rate": 0.00015877852522924732,
525
+ "loss": 0.9177,
526
+ "step": 67
527
+ },
528
+ {
529
+ "epoch": 1.2772277227722773,
530
+ "grad_norm": 0.271484375,
531
+ "learning_rate": 0.00015743286626829437,
532
+ "loss": 0.9,
533
+ "step": 68
534
+ },
535
+ {
536
+ "epoch": 1.297029702970297,
537
+ "grad_norm": 0.2431640625,
538
+ "learning_rate": 0.0001560715057351673,
539
+ "loss": 0.9096,
540
+ "step": 69
541
+ },
542
+ {
543
+ "epoch": 1.316831683168317,
544
+ "grad_norm": 0.22265625,
545
+ "learning_rate": 0.00015469481581224272,
546
+ "loss": 0.8946,
547
+ "step": 70
548
+ },
549
+ {
550
+ "epoch": 1.3366336633663367,
551
+ "grad_norm": 0.31640625,
552
+ "learning_rate": 0.0001533031728727994,
553
+ "loss": 0.8995,
554
+ "step": 71
555
+ },
556
+ {
557
+ "epoch": 1.3564356435643563,
558
+ "grad_norm": 0.2197265625,
559
+ "learning_rate": 0.00015189695737812152,
560
+ "loss": 0.922,
561
+ "step": 72
562
+ },
563
+ {
564
+ "epoch": 1.3762376237623761,
565
+ "grad_norm": 0.22265625,
566
+ "learning_rate": 0.0001504765537734844,
567
+ "loss": 0.885,
568
+ "step": 73
569
+ },
570
+ {
571
+ "epoch": 1.396039603960396,
572
+ "grad_norm": 0.248046875,
573
+ "learning_rate": 0.00014904235038305083,
574
+ "loss": 0.895,
575
+ "step": 74
576
+ },
577
+ {
578
+ "epoch": 1.4158415841584158,
579
+ "grad_norm": 0.2431640625,
580
+ "learning_rate": 0.00014759473930370736,
581
+ "loss": 0.892,
582
+ "step": 75
583
+ },
584
+ {
585
+ "epoch": 1.4356435643564356,
586
+ "grad_norm": 0.216796875,
587
+ "learning_rate": 0.0001461341162978688,
588
+ "loss": 0.8277,
589
+ "step": 76
590
+ },
591
+ {
592
+ "epoch": 1.4554455445544554,
593
+ "grad_norm": 0.23828125,
594
+ "learning_rate": 0.00014466088068528068,
595
+ "loss": 0.8687,
596
+ "step": 77
597
+ },
598
+ {
599
+ "epoch": 1.4752475247524752,
600
+ "grad_norm": 0.228515625,
601
+ "learning_rate": 0.00014317543523384928,
602
+ "loss": 0.8765,
603
+ "step": 78
604
+ },
605
+ {
606
+ "epoch": 1.4752475247524752,
607
+ "eval_loss": 0.9083698391914368,
608
+ "eval_runtime": 13.8834,
609
+ "eval_samples_per_second": 9.004,
610
+ "eval_steps_per_second": 4.538,
611
+ "step": 78
612
+ },
613
+ {
614
+ "epoch": 1.495049504950495,
615
+ "grad_norm": 0.228515625,
616
+ "learning_rate": 0.00014167818604952906,
617
+ "loss": 0.8797,
618
+ "step": 79
619
+ },
620
+ {
621
+ "epoch": 1.5148514851485149,
622
+ "grad_norm": 0.1982421875,
623
+ "learning_rate": 0.00014016954246529696,
624
+ "loss": 0.905,
625
+ "step": 80
626
+ },
627
+ {
628
+ "epoch": 1.5346534653465347,
629
+ "grad_norm": 0.25390625,
630
+ "learning_rate": 0.00013864991692924523,
631
+ "loss": 0.8575,
632
+ "step": 81
633
+ },
634
+ {
635
+ "epoch": 1.5544554455445545,
636
+ "grad_norm": 0.2451171875,
637
+ "learning_rate": 0.00013711972489182208,
638
+ "loss": 0.8957,
639
+ "step": 82
640
+ },
641
+ {
642
+ "epoch": 1.5742574257425743,
643
+ "grad_norm": 0.2216796875,
644
+ "learning_rate": 0.00013557938469225167,
645
+ "loss": 0.8792,
646
+ "step": 83
647
+ },
648
+ {
649
+ "epoch": 1.5940594059405941,
650
+ "grad_norm": 0.21484375,
651
+ "learning_rate": 0.00013402931744416433,
652
+ "loss": 0.889,
653
+ "step": 84
654
+ },
655
+ {
656
+ "epoch": 1.613861386138614,
657
+ "grad_norm": 0.228515625,
658
+ "learning_rate": 0.00013246994692046836,
659
+ "loss": 0.8657,
660
+ "step": 85
661
+ },
662
+ {
663
+ "epoch": 1.6336633663366338,
664
+ "grad_norm": 0.20703125,
665
+ "learning_rate": 0.00013090169943749476,
666
+ "loss": 0.8784,
667
+ "step": 86
668
+ },
669
+ {
670
+ "epoch": 1.6534653465346536,
671
+ "grad_norm": 0.265625,
672
+ "learning_rate": 0.0001293250037384465,
673
+ "loss": 0.8822,
674
+ "step": 87
675
+ },
676
+ {
677
+ "epoch": 1.6732673267326734,
678
+ "grad_norm": 0.2197265625,
679
+ "learning_rate": 0.00012774029087618446,
680
+ "loss": 0.9092,
681
+ "step": 88
682
+ },
683
+ {
684
+ "epoch": 1.693069306930693,
685
+ "grad_norm": 0.234375,
686
+ "learning_rate": 0.00012614799409538198,
687
+ "loss": 0.8813,
688
+ "step": 89
689
+ },
690
+ {
691
+ "epoch": 1.7128712871287128,
692
+ "grad_norm": 0.2294921875,
693
+ "learning_rate": 0.00012454854871407994,
694
+ "loss": 0.8975,
695
+ "step": 90
696
+ },
697
+ {
698
+ "epoch": 1.7326732673267327,
699
+ "grad_norm": 0.259765625,
700
+ "learning_rate": 0.00012294239200467516,
701
+ "loss": 0.8789,
702
+ "step": 91
703
+ },
704
+ {
705
+ "epoch": 1.7326732673267327,
706
+ "eval_loss": 0.8891416788101196,
707
+ "eval_runtime": 13.872,
708
+ "eval_samples_per_second": 9.011,
709
+ "eval_steps_per_second": 4.542,
710
+ "step": 91
711
+ },
712
+ {
713
+ "epoch": 1.7524752475247525,
714
+ "grad_norm": 0.26171875,
715
+ "learning_rate": 0.0001213299630743747,
716
+ "loss": 0.9184,
717
+ "step": 92
718
+ },
719
+ {
720
+ "epoch": 1.7722772277227723,
721
+ "grad_norm": 0.337890625,
722
+ "learning_rate": 0.00011971170274514802,
723
+ "loss": 0.8854,
724
+ "step": 93
725
+ },
726
+ {
727
+ "epoch": 1.7920792079207921,
728
+ "grad_norm": 0.2890625,
729
+ "learning_rate": 0.000118088053433211,
730
+ "loss": 0.8688,
731
+ "step": 94
732
+ },
733
+ {
734
+ "epoch": 1.811881188118812,
735
+ "grad_norm": 0.3515625,
736
+ "learning_rate": 0.00011645945902807341,
737
+ "loss": 0.8281,
738
+ "step": 95
739
+ },
740
+ {
741
+ "epoch": 1.8316831683168315,
742
+ "grad_norm": 0.26953125,
743
+ "learning_rate": 0.0001148263647711842,
744
+ "loss": 0.8488,
745
+ "step": 96
746
+ },
747
+ {
748
+ "epoch": 1.8514851485148514,
749
+ "grad_norm": 0.2490234375,
750
+ "learning_rate": 0.00011318921713420691,
751
+ "loss": 0.8742,
752
+ "step": 97
753
+ },
754
+ {
755
+ "epoch": 1.8712871287128712,
756
+ "grad_norm": 0.265625,
757
+ "learning_rate": 0.00011154846369695863,
758
+ "loss": 0.8586,
759
+ "step": 98
760
+ },
761
+ {
762
+ "epoch": 1.891089108910891,
763
+ "grad_norm": 0.265625,
764
+ "learning_rate": 0.0001099045530250463,
765
+ "loss": 0.8776,
766
+ "step": 99
767
+ },
768
+ {
769
+ "epoch": 1.9108910891089108,
770
+ "grad_norm": 0.259765625,
771
+ "learning_rate": 0.00010825793454723325,
772
+ "loss": 0.8563,
773
+ "step": 100
774
+ }
775
+ ],
776
+ "logging_steps": 1,
777
+ "max_steps": 200,
778
+ "num_input_tokens_seen": 0,
779
+ "num_train_epochs": 4,
780
+ "save_steps": 50,
781
+ "stateful_callbacks": {
782
+ "TrainerControl": {
783
+ "args": {
784
+ "should_epoch_stop": false,
785
+ "should_evaluate": false,
786
+ "should_log": false,
787
+ "should_save": true,
788
+ "should_training_stop": false
789
+ },
790
+ "attributes": {}
791
+ }
792
+ },
793
+ "total_flos": 2.08354098020352e+16,
794
+ "train_batch_size": 2,
795
+ "trial_name": null,
796
+ "trial_params": null
797
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab891527a9343c5fed33fded5a4528864e72798598b8a74f11bf9b63e79e156f
3
+ size 5944
checkpoint-150/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-150/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "down_proj",
25
+ "gate_proj",
26
+ "v_proj",
27
+ "q_proj",
28
+ "o_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-150/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97264f01540b1ad5acd25f27b627a7352dbda77c960c2b3c7b157d05035d6ac6
3
+ size 50503848
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e5de270e966edc3891231b22ee3b34b5d5573183750ce1a8ecca10a2b62423
3
+ size 202035450
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3129c63169712c776c1e0e28d8711e276143acd2c2f061fb6eb052c04856ba72
3
+ size 14244
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5d42bb0afda20ec4c83d38c6af1131541c335ecab229c74e7f418894f3c13b
3
+ size 1064
checkpoint-150/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-150/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-150/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "use_fast": true
44
+ }
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,1179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.8316831683168315,
5
+ "eval_steps": 13,
6
+ "global_step": 150,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.019801980198019802,
13
+ "grad_norm": 1.15625,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.0919,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.019801980198019802,
20
+ "eval_loss": 2.079954147338867,
21
+ "eval_runtime": 13.8908,
22
+ "eval_samples_per_second": 8.999,
23
+ "eval_steps_per_second": 4.535,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.039603960396039604,
28
+ "grad_norm": 1.203125,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.0814,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0594059405940594,
35
+ "grad_norm": 1.1953125,
36
+ "learning_rate": 6e-05,
37
+ "loss": 2.0499,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.07920792079207921,
42
+ "grad_norm": 1.0859375,
43
+ "learning_rate": 8e-05,
44
+ "loss": 2.0153,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.09900990099009901,
49
+ "grad_norm": 1.0390625,
50
+ "learning_rate": 0.0001,
51
+ "loss": 1.9548,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.1188118811881188,
56
+ "grad_norm": 0.89453125,
57
+ "learning_rate": 0.00012,
58
+ "loss": 1.8982,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.13861386138613863,
63
+ "grad_norm": 0.67578125,
64
+ "learning_rate": 0.00014,
65
+ "loss": 1.8226,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.15841584158415842,
70
+ "grad_norm": 0.66796875,
71
+ "learning_rate": 0.00016,
72
+ "loss": 1.7572,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.1782178217821782,
77
+ "grad_norm": 0.78515625,
78
+ "learning_rate": 0.00018,
79
+ "loss": 1.7074,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.19801980198019803,
84
+ "grad_norm": 0.73828125,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.6317,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.21782178217821782,
91
+ "grad_norm": 0.484375,
92
+ "learning_rate": 0.0001999863304992469,
93
+ "loss": 1.5801,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.2376237623762376,
98
+ "grad_norm": 0.53125,
99
+ "learning_rate": 0.00019994532573409262,
100
+ "loss": 1.5721,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.25742574257425743,
105
+ "grad_norm": 0.6953125,
106
+ "learning_rate": 0.00019987699691483048,
107
+ "loss": 1.5479,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.25742574257425743,
112
+ "eval_loss": 1.5341482162475586,
113
+ "eval_runtime": 13.8795,
114
+ "eval_samples_per_second": 9.006,
115
+ "eval_steps_per_second": 4.539,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.27722772277227725,
120
+ "grad_norm": 0.65234375,
121
+ "learning_rate": 0.00019978136272187747,
122
+ "loss": 1.534,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.297029702970297,
127
+ "grad_norm": 0.515625,
128
+ "learning_rate": 0.000199658449300667,
129
+ "loss": 1.4804,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.31683168316831684,
134
+ "grad_norm": 0.439453125,
135
+ "learning_rate": 0.00019950829025450114,
136
+ "loss": 1.4805,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.33663366336633666,
141
+ "grad_norm": 0.361328125,
142
+ "learning_rate": 0.00019933092663536382,
143
+ "loss": 1.3809,
144
+ "step": 17
145
+ },
146
+ {
147
+ "epoch": 0.3564356435643564,
148
+ "grad_norm": 0.3125,
149
+ "learning_rate": 0.00019912640693269752,
150
+ "loss": 1.3837,
151
+ "step": 18
152
+ },
153
+ {
154
+ "epoch": 0.37623762376237624,
155
+ "grad_norm": 0.337890625,
156
+ "learning_rate": 0.00019889478706014687,
157
+ "loss": 1.3673,
158
+ "step": 19
159
+ },
160
+ {
161
+ "epoch": 0.39603960396039606,
162
+ "grad_norm": 0.298828125,
163
+ "learning_rate": 0.00019863613034027224,
164
+ "loss": 1.366,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.4158415841584158,
169
+ "grad_norm": 0.34375,
170
+ "learning_rate": 0.00019835050748723824,
171
+ "loss": 1.3318,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.43564356435643564,
176
+ "grad_norm": 0.341796875,
177
+ "learning_rate": 0.00019803799658748094,
178
+ "loss": 1.2741,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.45544554455445546,
183
+ "grad_norm": 0.326171875,
184
+ "learning_rate": 0.00019769868307835994,
185
+ "loss": 1.2978,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 0.4752475247524752,
190
+ "grad_norm": 0.291015625,
191
+ "learning_rate": 0.0001973326597248006,
192
+ "loss": 1.2733,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.49504950495049505,
197
+ "grad_norm": 0.306640625,
198
+ "learning_rate": 0.00019694002659393305,
199
+ "loss": 1.2302,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.5148514851485149,
204
+ "grad_norm": 0.318359375,
205
+ "learning_rate": 0.00019652089102773488,
206
+ "loss": 1.2083,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.5148514851485149,
211
+ "eval_loss": 1.224540114402771,
212
+ "eval_runtime": 13.8695,
213
+ "eval_samples_per_second": 9.013,
214
+ "eval_steps_per_second": 4.542,
215
+ "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.5346534653465347,
219
+ "grad_norm": 0.26953125,
220
+ "learning_rate": 0.00019607536761368484,
221
+ "loss": 1.1761,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.5544554455445545,
226
+ "grad_norm": 0.296875,
227
+ "learning_rate": 0.00019560357815343577,
228
+ "loss": 1.1751,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.5742574257425742,
233
+ "grad_norm": 0.310546875,
234
+ "learning_rate": 0.00019510565162951537,
235
+ "loss": 1.2002,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.594059405940594,
240
+ "grad_norm": 0.287109375,
241
+ "learning_rate": 0.00019458172417006347,
242
+ "loss": 1.1544,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.6138613861386139,
247
+ "grad_norm": 0.365234375,
248
+ "learning_rate": 0.00019403193901161613,
249
+ "loss": 1.1384,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.6336633663366337,
254
+ "grad_norm": 0.236328125,
255
+ "learning_rate": 0.0001934564464599461,
256
+ "loss": 1.0999,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.6534653465346535,
261
+ "grad_norm": 0.326171875,
262
+ "learning_rate": 0.00019285540384897073,
263
+ "loss": 1.1576,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.6732673267326733,
268
+ "grad_norm": 0.310546875,
269
+ "learning_rate": 0.00019222897549773848,
270
+ "loss": 1.091,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 0.693069306930693,
275
+ "grad_norm": 0.2578125,
276
+ "learning_rate": 0.00019157733266550575,
277
+ "loss": 1.056,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 0.7128712871287128,
282
+ "grad_norm": 0.267578125,
283
+ "learning_rate": 0.00019090065350491626,
284
+ "loss": 1.1068,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 0.7326732673267327,
289
+ "grad_norm": 0.2490234375,
290
+ "learning_rate": 0.00019019912301329592,
291
+ "loss": 1.0583,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 0.7524752475247525,
296
+ "grad_norm": 0.2734375,
297
+ "learning_rate": 0.00018947293298207635,
298
+ "loss": 1.0671,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 0.7722772277227723,
303
+ "grad_norm": 0.2490234375,
304
+ "learning_rate": 0.0001887222819443612,
305
+ "loss": 1.0851,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 0.7722772277227723,
310
+ "eval_loss": 1.060703158378601,
311
+ "eval_runtime": 13.878,
312
+ "eval_samples_per_second": 9.007,
313
+ "eval_steps_per_second": 4.54,
314
+ "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.7920792079207921,
318
+ "grad_norm": 0.22265625,
319
+ "learning_rate": 0.0001879473751206489,
320
+ "loss": 1.0343,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.8118811881188119,
325
+ "grad_norm": 0.1796875,
326
+ "learning_rate": 0.00018714842436272773,
327
+ "loss": 0.9789,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.8316831683168316,
332
+ "grad_norm": 0.248046875,
333
+ "learning_rate": 0.00018632564809575742,
334
+ "loss": 1.0174,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.8514851485148515,
339
+ "grad_norm": 0.2294921875,
340
+ "learning_rate": 0.0001854792712585539,
341
+ "loss": 1.0004,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.8712871287128713,
346
+ "grad_norm": 0.228515625,
347
+ "learning_rate": 0.00018460952524209355,
348
+ "loss": 1.0281,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.8910891089108911,
353
+ "grad_norm": 0.220703125,
354
+ "learning_rate": 0.00018371664782625287,
355
+ "loss": 0.9992,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.9108910891089109,
360
+ "grad_norm": 0.2138671875,
361
+ "learning_rate": 0.00018280088311480201,
362
+ "loss": 0.9635,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.9306930693069307,
367
+ "grad_norm": 0.265625,
368
+ "learning_rate": 0.00018186248146866927,
369
+ "loss": 1.006,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.9504950495049505,
374
+ "grad_norm": 0.2451171875,
375
+ "learning_rate": 0.00018090169943749476,
376
+ "loss": 0.9891,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.9702970297029703,
381
+ "grad_norm": 0.28515625,
382
+ "learning_rate": 0.0001799187996894925,
383
+ "loss": 0.9809,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.9900990099009901,
388
+ "grad_norm": 0.212890625,
389
+ "learning_rate": 0.00017891405093963938,
390
+ "loss": 0.9646,
391
+ "step": 50
392
+ },
393
+ {
394
+ "epoch": 1.00990099009901,
395
+ "grad_norm": 0.2451171875,
396
+ "learning_rate": 0.00017788772787621126,
397
+ "loss": 0.9553,
398
+ "step": 51
399
+ },
400
+ {
401
+ "epoch": 1.0297029702970297,
402
+ "grad_norm": 0.2578125,
403
+ "learning_rate": 0.00017684011108568592,
404
+ "loss": 0.9432,
405
+ "step": 52
406
+ },
407
+ {
408
+ "epoch": 1.0297029702970297,
409
+ "eval_loss": 0.9755253195762634,
410
+ "eval_runtime": 13.879,
411
+ "eval_samples_per_second": 9.006,
412
+ "eval_steps_per_second": 4.539,
413
+ "step": 52
414
+ },
415
+ {
416
+ "epoch": 1.0495049504950495,
417
+ "grad_norm": 0.2021484375,
418
+ "learning_rate": 0.0001757714869760335,
419
+ "loss": 0.9631,
420
+ "step": 53
421
+ },
422
+ {
423
+ "epoch": 1.0693069306930694,
424
+ "grad_norm": 0.3046875,
425
+ "learning_rate": 0.0001746821476984154,
426
+ "loss": 0.9539,
427
+ "step": 54
428
+ },
429
+ {
430
+ "epoch": 1.0198019801980198,
431
+ "grad_norm": 0.232421875,
432
+ "learning_rate": 0.00017357239106731317,
433
+ "loss": 0.9559,
434
+ "step": 55
435
+ },
436
+ {
437
+ "epoch": 1.0396039603960396,
438
+ "grad_norm": 0.283203125,
439
+ "learning_rate": 0.00017244252047910892,
440
+ "loss": 0.9111,
441
+ "step": 56
442
+ },
443
+ {
444
+ "epoch": 1.0594059405940595,
445
+ "grad_norm": 0.30859375,
446
+ "learning_rate": 0.00017129284482913972,
447
+ "loss": 0.9503,
448
+ "step": 57
449
+ },
450
+ {
451
+ "epoch": 1.0792079207920793,
452
+ "grad_norm": 0.2265625,
453
+ "learning_rate": 0.00017012367842724887,
454
+ "loss": 0.911,
455
+ "step": 58
456
+ },
457
+ {
458
+ "epoch": 1.099009900990099,
459
+ "grad_norm": 0.3515625,
460
+ "learning_rate": 0.0001689353409118566,
461
+ "loss": 0.9041,
462
+ "step": 59
463
+ },
464
+ {
465
+ "epoch": 1.118811881188119,
466
+ "grad_norm": 0.26171875,
467
+ "learning_rate": 0.00016772815716257412,
468
+ "loss": 0.9117,
469
+ "step": 60
470
+ },
471
+ {
472
+ "epoch": 1.1386138613861387,
473
+ "grad_norm": 0.2890625,
474
+ "learning_rate": 0.0001665024572113848,
475
+ "loss": 0.9351,
476
+ "step": 61
477
+ },
478
+ {
479
+ "epoch": 1.1584158415841583,
480
+ "grad_norm": 0.251953125,
481
+ "learning_rate": 0.00016525857615241687,
482
+ "loss": 0.9438,
483
+ "step": 62
484
+ },
485
+ {
486
+ "epoch": 1.1782178217821782,
487
+ "grad_norm": 0.2138671875,
488
+ "learning_rate": 0.00016399685405033167,
489
+ "loss": 0.9075,
490
+ "step": 63
491
+ },
492
+ {
493
+ "epoch": 1.198019801980198,
494
+ "grad_norm": 0.2490234375,
495
+ "learning_rate": 0.0001627176358473537,
496
+ "loss": 0.8983,
497
+ "step": 64
498
+ },
499
+ {
500
+ "epoch": 1.2178217821782178,
501
+ "grad_norm": 0.2021484375,
502
+ "learning_rate": 0.0001614212712689668,
503
+ "loss": 0.9007,
504
+ "step": 65
505
+ },
506
+ {
507
+ "epoch": 1.2178217821782178,
508
+ "eval_loss": 0.9333999156951904,
509
+ "eval_runtime": 13.8668,
510
+ "eval_samples_per_second": 9.014,
511
+ "eval_steps_per_second": 4.543,
512
+ "step": 65
513
+ },
514
+ {
515
+ "epoch": 1.2376237623762376,
516
+ "grad_norm": 0.2431640625,
517
+ "learning_rate": 0.00016010811472830252,
518
+ "loss": 0.9108,
519
+ "step": 66
520
+ },
521
+ {
522
+ "epoch": 1.2574257425742574,
523
+ "grad_norm": 0.232421875,
524
+ "learning_rate": 0.00015877852522924732,
525
+ "loss": 0.9177,
526
+ "step": 67
527
+ },
528
+ {
529
+ "epoch": 1.2772277227722773,
530
+ "grad_norm": 0.271484375,
531
+ "learning_rate": 0.00015743286626829437,
532
+ "loss": 0.9,
533
+ "step": 68
534
+ },
535
+ {
536
+ "epoch": 1.297029702970297,
537
+ "grad_norm": 0.2431640625,
538
+ "learning_rate": 0.0001560715057351673,
539
+ "loss": 0.9096,
540
+ "step": 69
541
+ },
542
+ {
543
+ "epoch": 1.316831683168317,
544
+ "grad_norm": 0.22265625,
545
+ "learning_rate": 0.00015469481581224272,
546
+ "loss": 0.8946,
547
+ "step": 70
548
+ },
549
+ {
550
+ "epoch": 1.3366336633663367,
551
+ "grad_norm": 0.31640625,
552
+ "learning_rate": 0.0001533031728727994,
553
+ "loss": 0.8995,
554
+ "step": 71
555
+ },
556
+ {
557
+ "epoch": 1.3564356435643563,
558
+ "grad_norm": 0.2197265625,
559
+ "learning_rate": 0.00015189695737812152,
560
+ "loss": 0.922,
561
+ "step": 72
562
+ },
563
+ {
564
+ "epoch": 1.3762376237623761,
565
+ "grad_norm": 0.22265625,
566
+ "learning_rate": 0.0001504765537734844,
567
+ "loss": 0.885,
568
+ "step": 73
569
+ },
570
+ {
571
+ "epoch": 1.396039603960396,
572
+ "grad_norm": 0.248046875,
573
+ "learning_rate": 0.00014904235038305083,
574
+ "loss": 0.895,
575
+ "step": 74
576
+ },
577
+ {
578
+ "epoch": 1.4158415841584158,
579
+ "grad_norm": 0.2431640625,
580
+ "learning_rate": 0.00014759473930370736,
581
+ "loss": 0.892,
582
+ "step": 75
583
+ },
584
+ {
585
+ "epoch": 1.4356435643564356,
586
+ "grad_norm": 0.216796875,
587
+ "learning_rate": 0.0001461341162978688,
588
+ "loss": 0.8277,
589
+ "step": 76
590
+ },
591
+ {
592
+ "epoch": 1.4554455445544554,
593
+ "grad_norm": 0.23828125,
594
+ "learning_rate": 0.00014466088068528068,
595
+ "loss": 0.8687,
596
+ "step": 77
597
+ },
598
+ {
599
+ "epoch": 1.4752475247524752,
600
+ "grad_norm": 0.228515625,
601
+ "learning_rate": 0.00014317543523384928,
602
+ "loss": 0.8765,
603
+ "step": 78
604
+ },
605
+ {
606
+ "epoch": 1.4752475247524752,
607
+ "eval_loss": 0.9083698391914368,
608
+ "eval_runtime": 13.8834,
609
+ "eval_samples_per_second": 9.004,
610
+ "eval_steps_per_second": 4.538,
611
+ "step": 78
612
+ },
613
+ {
614
+ "epoch": 1.495049504950495,
615
+ "grad_norm": 0.228515625,
616
+ "learning_rate": 0.00014167818604952906,
617
+ "loss": 0.8797,
618
+ "step": 79
619
+ },
620
+ {
621
+ "epoch": 1.5148514851485149,
622
+ "grad_norm": 0.1982421875,
623
+ "learning_rate": 0.00014016954246529696,
624
+ "loss": 0.905,
625
+ "step": 80
626
+ },
627
+ {
628
+ "epoch": 1.5346534653465347,
629
+ "grad_norm": 0.25390625,
630
+ "learning_rate": 0.00013864991692924523,
631
+ "loss": 0.8575,
632
+ "step": 81
633
+ },
634
+ {
635
+ "epoch": 1.5544554455445545,
636
+ "grad_norm": 0.2451171875,
637
+ "learning_rate": 0.00013711972489182208,
638
+ "loss": 0.8957,
639
+ "step": 82
640
+ },
641
+ {
642
+ "epoch": 1.5742574257425743,
643
+ "grad_norm": 0.2216796875,
644
+ "learning_rate": 0.00013557938469225167,
645
+ "loss": 0.8792,
646
+ "step": 83
647
+ },
648
+ {
649
+ "epoch": 1.5940594059405941,
650
+ "grad_norm": 0.21484375,
651
+ "learning_rate": 0.00013402931744416433,
652
+ "loss": 0.889,
653
+ "step": 84
654
+ },
655
+ {
656
+ "epoch": 1.613861386138614,
657
+ "grad_norm": 0.228515625,
658
+ "learning_rate": 0.00013246994692046836,
659
+ "loss": 0.8657,
660
+ "step": 85
661
+ },
662
+ {
663
+ "epoch": 1.6336633663366338,
664
+ "grad_norm": 0.20703125,
665
+ "learning_rate": 0.00013090169943749476,
666
+ "loss": 0.8784,
667
+ "step": 86
668
+ },
669
+ {
670
+ "epoch": 1.6534653465346536,
671
+ "grad_norm": 0.265625,
672
+ "learning_rate": 0.0001293250037384465,
673
+ "loss": 0.8822,
674
+ "step": 87
675
+ },
676
+ {
677
+ "epoch": 1.6732673267326734,
678
+ "grad_norm": 0.2197265625,
679
+ "learning_rate": 0.00012774029087618446,
680
+ "loss": 0.9092,
681
+ "step": 88
682
+ },
683
+ {
684
+ "epoch": 1.693069306930693,
685
+ "grad_norm": 0.234375,
686
+ "learning_rate": 0.00012614799409538198,
687
+ "loss": 0.8813,
688
+ "step": 89
689
+ },
690
+ {
691
+ "epoch": 1.7128712871287128,
692
+ "grad_norm": 0.2294921875,
693
+ "learning_rate": 0.00012454854871407994,
694
+ "loss": 0.8975,
695
+ "step": 90
696
+ },
697
+ {
698
+ "epoch": 1.7326732673267327,
699
+ "grad_norm": 0.259765625,
700
+ "learning_rate": 0.00012294239200467516,
701
+ "loss": 0.8789,
702
+ "step": 91
703
+ },
704
+ {
705
+ "epoch": 1.7326732673267327,
706
+ "eval_loss": 0.8891416788101196,
707
+ "eval_runtime": 13.872,
708
+ "eval_samples_per_second": 9.011,
709
+ "eval_steps_per_second": 4.542,
710
+ "step": 91
711
+ },
712
+ {
713
+ "epoch": 1.7524752475247525,
714
+ "grad_norm": 0.26171875,
715
+ "learning_rate": 0.0001213299630743747,
716
+ "loss": 0.9184,
717
+ "step": 92
718
+ },
719
+ {
720
+ "epoch": 1.7722772277227723,
721
+ "grad_norm": 0.337890625,
722
+ "learning_rate": 0.00011971170274514802,
723
+ "loss": 0.8854,
724
+ "step": 93
725
+ },
726
+ {
727
+ "epoch": 1.7920792079207921,
728
+ "grad_norm": 0.2890625,
729
+ "learning_rate": 0.000118088053433211,
730
+ "loss": 0.8688,
731
+ "step": 94
732
+ },
733
+ {
734
+ "epoch": 1.811881188118812,
735
+ "grad_norm": 0.3515625,
736
+ "learning_rate": 0.00011645945902807341,
737
+ "loss": 0.8281,
738
+ "step": 95
739
+ },
740
+ {
741
+ "epoch": 1.8316831683168315,
742
+ "grad_norm": 0.26953125,
743
+ "learning_rate": 0.0001148263647711842,
744
+ "loss": 0.8488,
745
+ "step": 96
746
+ },
747
+ {
748
+ "epoch": 1.8514851485148514,
749
+ "grad_norm": 0.2490234375,
750
+ "learning_rate": 0.00011318921713420691,
751
+ "loss": 0.8742,
752
+ "step": 97
753
+ },
754
+ {
755
+ "epoch": 1.8712871287128712,
756
+ "grad_norm": 0.265625,
757
+ "learning_rate": 0.00011154846369695863,
758
+ "loss": 0.8586,
759
+ "step": 98
760
+ },
761
+ {
762
+ "epoch": 1.891089108910891,
763
+ "grad_norm": 0.265625,
764
+ "learning_rate": 0.0001099045530250463,
765
+ "loss": 0.8776,
766
+ "step": 99
767
+ },
768
+ {
769
+ "epoch": 1.9108910891089108,
770
+ "grad_norm": 0.259765625,
771
+ "learning_rate": 0.00010825793454723325,
772
+ "loss": 0.8563,
773
+ "step": 100
774
+ },
775
+ {
776
+ "epoch": 1.9306930693069306,
777
+ "grad_norm": 0.283203125,
778
+ "learning_rate": 0.00010660905843256994,
779
+ "loss": 0.8381,
780
+ "step": 101
781
+ },
782
+ {
783
+ "epoch": 1.9504950495049505,
784
+ "grad_norm": 0.201171875,
785
+ "learning_rate": 0.00010495837546732224,
786
+ "loss": 0.847,
787
+ "step": 102
788
+ },
789
+ {
790
+ "epoch": 1.9702970297029703,
791
+ "grad_norm": 0.23828125,
792
+ "learning_rate": 0.00010330633693173082,
793
+ "loss": 0.8512,
794
+ "step": 103
795
+ },
796
+ {
797
+ "epoch": 1.99009900990099,
798
+ "grad_norm": 0.283203125,
799
+ "learning_rate": 0.00010165339447663587,
800
+ "loss": 0.8304,
801
+ "step": 104
802
+ },
803
+ {
804
+ "epoch": 1.99009900990099,
805
+ "eval_loss": 0.8779018521308899,
806
+ "eval_runtime": 13.8827,
807
+ "eval_samples_per_second": 9.004,
808
+ "eval_steps_per_second": 4.538,
809
+ "step": 104
810
+ },
811
+ {
812
+ "epoch": 2.00990099009901,
813
+ "grad_norm": 0.283203125,
814
+ "learning_rate": 0.0001,
815
+ "loss": 0.8523,
816
+ "step": 105
817
+ },
818
+ {
819
+ "epoch": 2.0297029702970297,
820
+ "grad_norm": 0.2392578125,
821
+ "learning_rate": 9.834660552336415e-05,
822
+ "loss": 0.8109,
823
+ "step": 106
824
+ },
825
+ {
826
+ "epoch": 2.0495049504950495,
827
+ "grad_norm": 0.224609375,
828
+ "learning_rate": 9.669366306826919e-05,
829
+ "loss": 0.8394,
830
+ "step": 107
831
+ },
832
+ {
833
+ "epoch": 2.0693069306930694,
834
+ "grad_norm": 0.283203125,
835
+ "learning_rate": 9.504162453267777e-05,
836
+ "loss": 0.8524,
837
+ "step": 108
838
+ },
839
+ {
840
+ "epoch": 2.01980198019802,
841
+ "grad_norm": 0.22265625,
842
+ "learning_rate": 9.339094156743007e-05,
843
+ "loss": 0.8391,
844
+ "step": 109
845
+ },
846
+ {
847
+ "epoch": 2.0396039603960396,
848
+ "grad_norm": 0.2001953125,
849
+ "learning_rate": 9.174206545276677e-05,
850
+ "loss": 0.8317,
851
+ "step": 110
852
+ },
853
+ {
854
+ "epoch": 2.0594059405940595,
855
+ "grad_norm": 0.22265625,
856
+ "learning_rate": 9.009544697495374e-05,
857
+ "loss": 0.833,
858
+ "step": 111
859
+ },
860
+ {
861
+ "epoch": 2.0792079207920793,
862
+ "grad_norm": 0.2041015625,
863
+ "learning_rate": 8.845153630304139e-05,
864
+ "loss": 0.8408,
865
+ "step": 112
866
+ },
867
+ {
868
+ "epoch": 2.099009900990099,
869
+ "grad_norm": 0.2080078125,
870
+ "learning_rate": 8.681078286579311e-05,
871
+ "loss": 0.8459,
872
+ "step": 113
873
+ },
874
+ {
875
+ "epoch": 2.118811881188119,
876
+ "grad_norm": 0.2021484375,
877
+ "learning_rate": 8.517363522881579e-05,
878
+ "loss": 0.8177,
879
+ "step": 114
880
+ },
881
+ {
882
+ "epoch": 2.1386138613861387,
883
+ "grad_norm": 0.2265625,
884
+ "learning_rate": 8.35405409719266e-05,
885
+ "loss": 0.8451,
886
+ "step": 115
887
+ },
888
+ {
889
+ "epoch": 2.1584158415841586,
890
+ "grad_norm": 0.2294921875,
891
+ "learning_rate": 8.191194656678904e-05,
892
+ "loss": 0.8543,
893
+ "step": 116
894
+ },
895
+ {
896
+ "epoch": 2.1782178217821784,
897
+ "grad_norm": 0.22265625,
898
+ "learning_rate": 8.028829725485199e-05,
899
+ "loss": 0.8194,
900
+ "step": 117
901
+ },
902
+ {
903
+ "epoch": 2.1782178217821784,
904
+ "eval_loss": 0.8713971972465515,
905
+ "eval_runtime": 13.8976,
906
+ "eval_samples_per_second": 8.994,
907
+ "eval_steps_per_second": 4.533,
908
+ "step": 117
909
+ },
910
+ {
911
+ "epoch": 2.198019801980198,
912
+ "grad_norm": 0.2333984375,
913
+ "learning_rate": 7.867003692562534e-05,
914
+ "loss": 0.808,
915
+ "step": 118
916
+ },
917
+ {
918
+ "epoch": 2.217821782178218,
919
+ "grad_norm": 0.2470703125,
920
+ "learning_rate": 7.705760799532485e-05,
921
+ "loss": 0.8073,
922
+ "step": 119
923
+ },
924
+ {
925
+ "epoch": 2.237623762376238,
926
+ "grad_norm": 0.201171875,
927
+ "learning_rate": 7.54514512859201e-05,
928
+ "loss": 0.8392,
929
+ "step": 120
930
+ },
931
+ {
932
+ "epoch": 2.2574257425742577,
933
+ "grad_norm": 0.25,
934
+ "learning_rate": 7.385200590461803e-05,
935
+ "loss": 0.8574,
936
+ "step": 121
937
+ },
938
+ {
939
+ "epoch": 2.2772277227722775,
940
+ "grad_norm": 0.271484375,
941
+ "learning_rate": 7.225970912381556e-05,
942
+ "loss": 0.8338,
943
+ "step": 122
944
+ },
945
+ {
946
+ "epoch": 2.297029702970297,
947
+ "grad_norm": 0.294921875,
948
+ "learning_rate": 7.067499626155354e-05,
949
+ "loss": 0.8788,
950
+ "step": 123
951
+ },
952
+ {
953
+ "epoch": 2.3168316831683167,
954
+ "grad_norm": 0.2265625,
955
+ "learning_rate": 6.909830056250527e-05,
956
+ "loss": 0.8297,
957
+ "step": 124
958
+ },
959
+ {
960
+ "epoch": 2.3366336633663365,
961
+ "grad_norm": 0.267578125,
962
+ "learning_rate": 6.753005307953167e-05,
963
+ "loss": 0.8125,
964
+ "step": 125
965
+ },
966
+ {
967
+ "epoch": 2.3564356435643563,
968
+ "grad_norm": 0.2431640625,
969
+ "learning_rate": 6.59706825558357e-05,
970
+ "loss": 0.814,
971
+ "step": 126
972
+ },
973
+ {
974
+ "epoch": 2.376237623762376,
975
+ "grad_norm": 0.27734375,
976
+ "learning_rate": 6.442061530774834e-05,
977
+ "loss": 0.8335,
978
+ "step": 127
979
+ },
980
+ {
981
+ "epoch": 2.396039603960396,
982
+ "grad_norm": 0.2216796875,
983
+ "learning_rate": 6.28802751081779e-05,
984
+ "loss": 0.8512,
985
+ "step": 128
986
+ },
987
+ {
988
+ "epoch": 2.4158415841584158,
989
+ "grad_norm": 0.224609375,
990
+ "learning_rate": 6.135008307075481e-05,
991
+ "loss": 0.8297,
992
+ "step": 129
993
+ },
994
+ {
995
+ "epoch": 2.4356435643564356,
996
+ "grad_norm": 0.2412109375,
997
+ "learning_rate": 5.983045753470308e-05,
998
+ "loss": 0.848,
999
+ "step": 130
1000
+ },
1001
+ {
1002
+ "epoch": 2.4356435643564356,
1003
+ "eval_loss": 0.8665071129798889,
1004
+ "eval_runtime": 13.8735,
1005
+ "eval_samples_per_second": 9.01,
1006
+ "eval_steps_per_second": 4.541,
1007
+ "step": 130
1008
+ },
1009
+ {
1010
+ "epoch": 2.4554455445544554,
1011
+ "grad_norm": 0.2265625,
1012
+ "learning_rate": 5.832181395047098e-05,
1013
+ "loss": 0.8203,
1014
+ "step": 131
1015
+ },
1016
+ {
1017
+ "epoch": 2.4752475247524752,
1018
+ "grad_norm": 0.287109375,
1019
+ "learning_rate": 5.6824564766150726e-05,
1020
+ "loss": 0.8519,
1021
+ "step": 132
1022
+ },
1023
+ {
1024
+ "epoch": 2.495049504950495,
1025
+ "grad_norm": 0.21484375,
1026
+ "learning_rate": 5.533911931471936e-05,
1027
+ "loss": 0.83,
1028
+ "step": 133
1029
+ },
1030
+ {
1031
+ "epoch": 2.514851485148515,
1032
+ "grad_norm": 0.2109375,
1033
+ "learning_rate": 5.386588370213124e-05,
1034
+ "loss": 0.842,
1035
+ "step": 134
1036
+ },
1037
+ {
1038
+ "epoch": 2.5346534653465347,
1039
+ "grad_norm": 0.2412109375,
1040
+ "learning_rate": 5.240526069629265e-05,
1041
+ "loss": 0.8419,
1042
+ "step": 135
1043
+ },
1044
+ {
1045
+ "epoch": 2.5544554455445545,
1046
+ "grad_norm": 0.267578125,
1047
+ "learning_rate": 5.095764961694922e-05,
1048
+ "loss": 0.8458,
1049
+ "step": 136
1050
+ },
1051
+ {
1052
+ "epoch": 2.5742574257425743,
1053
+ "grad_norm": 0.203125,
1054
+ "learning_rate": 4.952344622651566e-05,
1055
+ "loss": 0.8133,
1056
+ "step": 137
1057
+ },
1058
+ {
1059
+ "epoch": 2.594059405940594,
1060
+ "grad_norm": 0.2060546875,
1061
+ "learning_rate": 4.810304262187852e-05,
1062
+ "loss": 0.8103,
1063
+ "step": 138
1064
+ },
1065
+ {
1066
+ "epoch": 2.613861386138614,
1067
+ "grad_norm": 0.20703125,
1068
+ "learning_rate": 4.669682712720065e-05,
1069
+ "loss": 0.8105,
1070
+ "step": 139
1071
+ },
1072
+ {
1073
+ "epoch": 2.633663366336634,
1074
+ "grad_norm": 0.2060546875,
1075
+ "learning_rate": 4.530518418775733e-05,
1076
+ "loss": 0.8305,
1077
+ "step": 140
1078
+ },
1079
+ {
1080
+ "epoch": 2.6534653465346536,
1081
+ "grad_norm": 0.2080078125,
1082
+ "learning_rate": 4.392849426483274e-05,
1083
+ "loss": 0.7881,
1084
+ "step": 141
1085
+ },
1086
+ {
1087
+ "epoch": 2.6732673267326734,
1088
+ "grad_norm": 0.2216796875,
1089
+ "learning_rate": 4.256713373170564e-05,
1090
+ "loss": 0.8204,
1091
+ "step": 142
1092
+ },
1093
+ {
1094
+ "epoch": 2.693069306930693,
1095
+ "grad_norm": 0.263671875,
1096
+ "learning_rate": 4.12214747707527e-05,
1097
+ "loss": 0.8354,
1098
+ "step": 143
1099
+ },
1100
+ {
1101
+ "epoch": 2.693069306930693,
1102
+ "eval_loss": 0.8626759648323059,
1103
+ "eval_runtime": 13.8585,
1104
+ "eval_samples_per_second": 9.02,
1105
+ "eval_steps_per_second": 4.546,
1106
+ "step": 143
1107
+ },
1108
+ {
1109
+ "epoch": 2.7128712871287126,
1110
+ "grad_norm": 0.2138671875,
1111
+ "learning_rate": 3.9891885271697496e-05,
1112
+ "loss": 0.8441,
1113
+ "step": 144
1114
+ },
1115
+ {
1116
+ "epoch": 2.7326732673267324,
1117
+ "grad_norm": 0.2197265625,
1118
+ "learning_rate": 3.857872873103322e-05,
1119
+ "loss": 0.8084,
1120
+ "step": 145
1121
+ },
1122
+ {
1123
+ "epoch": 2.7524752475247523,
1124
+ "grad_norm": 0.18359375,
1125
+ "learning_rate": 3.7282364152646297e-05,
1126
+ "loss": 0.8184,
1127
+ "step": 146
1128
+ },
1129
+ {
1130
+ "epoch": 2.772277227722772,
1131
+ "grad_norm": 0.1904296875,
1132
+ "learning_rate": 3.600314594966834e-05,
1133
+ "loss": 0.8302,
1134
+ "step": 147
1135
+ },
1136
+ {
1137
+ "epoch": 2.792079207920792,
1138
+ "grad_norm": 0.2041015625,
1139
+ "learning_rate": 3.4741423847583134e-05,
1140
+ "loss": 0.8503,
1141
+ "step": 148
1142
+ },
1143
+ {
1144
+ "epoch": 2.8118811881188117,
1145
+ "grad_norm": 0.2265625,
1146
+ "learning_rate": 3.349754278861517e-05,
1147
+ "loss": 0.8273,
1148
+ "step": 149
1149
+ },
1150
+ {
1151
+ "epoch": 2.8316831683168315,
1152
+ "grad_norm": 0.1943359375,
1153
+ "learning_rate": 3.227184283742591e-05,
1154
+ "loss": 0.8332,
1155
+ "step": 150
1156
+ }
1157
+ ],
1158
+ "logging_steps": 1,
1159
+ "max_steps": 200,
1160
+ "num_input_tokens_seen": 0,
1161
+ "num_train_epochs": 4,
1162
+ "save_steps": 50,
1163
+ "stateful_callbacks": {
1164
+ "TrainerControl": {
1165
+ "args": {
1166
+ "should_epoch_stop": false,
1167
+ "should_evaluate": false,
1168
+ "should_log": false,
1169
+ "should_save": true,
1170
+ "should_training_stop": false
1171
+ },
1172
+ "attributes": {}
1173
+ }
1174
+ },
1175
+ "total_flos": 3.1227070440800256e+16,
1176
+ "train_batch_size": 2,
1177
+ "trial_name": null,
1178
+ "trial_params": null
1179
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab891527a9343c5fed33fded5a4528864e72798598b8a74f11bf9b63e79e156f
3
+ size 5944
checkpoint-200/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "down_proj",
25
+ "gate_proj",
26
+ "v_proj",
27
+ "q_proj",
28
+ "o_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-200/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:800103a9f27876d14f8e9f0fb64fb81af3a478d54bbaea5587ecbd0592ad4142
3
+ size 50503848
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dafd7ff9d5c3c564b22c4a0593f1078a408837f37261ad73caf0c7e062c6a39
3
+ size 202035450
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ca197c3706eaaadf2931079a5ebf26b215b3f60f60a6755cc111301c7ac7f6
3
+ size 14244
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
3
+ size 1064
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-200/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "use_fast": true
44
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,1561 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.7524752475247523,
5
+ "eval_steps": 13,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.019801980198019802,
13
+ "grad_norm": 1.15625,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.0919,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.019801980198019802,
20
+ "eval_loss": 2.079954147338867,
21
+ "eval_runtime": 13.8908,
22
+ "eval_samples_per_second": 8.999,
23
+ "eval_steps_per_second": 4.535,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.039603960396039604,
28
+ "grad_norm": 1.203125,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.0814,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0594059405940594,
35
+ "grad_norm": 1.1953125,
36
+ "learning_rate": 6e-05,
37
+ "loss": 2.0499,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.07920792079207921,
42
+ "grad_norm": 1.0859375,
43
+ "learning_rate": 8e-05,
44
+ "loss": 2.0153,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.09900990099009901,
49
+ "grad_norm": 1.0390625,
50
+ "learning_rate": 0.0001,
51
+ "loss": 1.9548,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.1188118811881188,
56
+ "grad_norm": 0.89453125,
57
+ "learning_rate": 0.00012,
58
+ "loss": 1.8982,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.13861386138613863,
63
+ "grad_norm": 0.67578125,
64
+ "learning_rate": 0.00014,
65
+ "loss": 1.8226,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.15841584158415842,
70
+ "grad_norm": 0.66796875,
71
+ "learning_rate": 0.00016,
72
+ "loss": 1.7572,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.1782178217821782,
77
+ "grad_norm": 0.78515625,
78
+ "learning_rate": 0.00018,
79
+ "loss": 1.7074,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.19801980198019803,
84
+ "grad_norm": 0.73828125,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.6317,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.21782178217821782,
91
+ "grad_norm": 0.484375,
92
+ "learning_rate": 0.0001999863304992469,
93
+ "loss": 1.5801,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.2376237623762376,
98
+ "grad_norm": 0.53125,
99
+ "learning_rate": 0.00019994532573409262,
100
+ "loss": 1.5721,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.25742574257425743,
105
+ "grad_norm": 0.6953125,
106
+ "learning_rate": 0.00019987699691483048,
107
+ "loss": 1.5479,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.25742574257425743,
112
+ "eval_loss": 1.5341482162475586,
113
+ "eval_runtime": 13.8795,
114
+ "eval_samples_per_second": 9.006,
115
+ "eval_steps_per_second": 4.539,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.27722772277227725,
120
+ "grad_norm": 0.65234375,
121
+ "learning_rate": 0.00019978136272187747,
122
+ "loss": 1.534,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.297029702970297,
127
+ "grad_norm": 0.515625,
128
+ "learning_rate": 0.000199658449300667,
129
+ "loss": 1.4804,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.31683168316831684,
134
+ "grad_norm": 0.439453125,
135
+ "learning_rate": 0.00019950829025450114,
136
+ "loss": 1.4805,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.33663366336633666,
141
+ "grad_norm": 0.361328125,
142
+ "learning_rate": 0.00019933092663536382,
143
+ "loss": 1.3809,
144
+ "step": 17
145
+ },
146
+ {
147
+ "epoch": 0.3564356435643564,
148
+ "grad_norm": 0.3125,
149
+ "learning_rate": 0.00019912640693269752,
150
+ "loss": 1.3837,
151
+ "step": 18
152
+ },
153
+ {
154
+ "epoch": 0.37623762376237624,
155
+ "grad_norm": 0.337890625,
156
+ "learning_rate": 0.00019889478706014687,
157
+ "loss": 1.3673,
158
+ "step": 19
159
+ },
160
+ {
161
+ "epoch": 0.39603960396039606,
162
+ "grad_norm": 0.298828125,
163
+ "learning_rate": 0.00019863613034027224,
164
+ "loss": 1.366,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.4158415841584158,
169
+ "grad_norm": 0.34375,
170
+ "learning_rate": 0.00019835050748723824,
171
+ "loss": 1.3318,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.43564356435643564,
176
+ "grad_norm": 0.341796875,
177
+ "learning_rate": 0.00019803799658748094,
178
+ "loss": 1.2741,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.45544554455445546,
183
+ "grad_norm": 0.326171875,
184
+ "learning_rate": 0.00019769868307835994,
185
+ "loss": 1.2978,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 0.4752475247524752,
190
+ "grad_norm": 0.291015625,
191
+ "learning_rate": 0.0001973326597248006,
192
+ "loss": 1.2733,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.49504950495049505,
197
+ "grad_norm": 0.306640625,
198
+ "learning_rate": 0.00019694002659393305,
199
+ "loss": 1.2302,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.5148514851485149,
204
+ "grad_norm": 0.318359375,
205
+ "learning_rate": 0.00019652089102773488,
206
+ "loss": 1.2083,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.5148514851485149,
211
+ "eval_loss": 1.224540114402771,
212
+ "eval_runtime": 13.8695,
213
+ "eval_samples_per_second": 9.013,
214
+ "eval_steps_per_second": 4.542,
215
+ "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.5346534653465347,
219
+ "grad_norm": 0.26953125,
220
+ "learning_rate": 0.00019607536761368484,
221
+ "loss": 1.1761,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.5544554455445545,
226
+ "grad_norm": 0.296875,
227
+ "learning_rate": 0.00019560357815343577,
228
+ "loss": 1.1751,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.5742574257425742,
233
+ "grad_norm": 0.310546875,
234
+ "learning_rate": 0.00019510565162951537,
235
+ "loss": 1.2002,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.594059405940594,
240
+ "grad_norm": 0.287109375,
241
+ "learning_rate": 0.00019458172417006347,
242
+ "loss": 1.1544,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.6138613861386139,
247
+ "grad_norm": 0.365234375,
248
+ "learning_rate": 0.00019403193901161613,
249
+ "loss": 1.1384,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.6336633663366337,
254
+ "grad_norm": 0.236328125,
255
+ "learning_rate": 0.0001934564464599461,
256
+ "loss": 1.0999,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.6534653465346535,
261
+ "grad_norm": 0.326171875,
262
+ "learning_rate": 0.00019285540384897073,
263
+ "loss": 1.1576,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.6732673267326733,
268
+ "grad_norm": 0.310546875,
269
+ "learning_rate": 0.00019222897549773848,
270
+ "loss": 1.091,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 0.693069306930693,
275
+ "grad_norm": 0.2578125,
276
+ "learning_rate": 0.00019157733266550575,
277
+ "loss": 1.056,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 0.7128712871287128,
282
+ "grad_norm": 0.267578125,
283
+ "learning_rate": 0.00019090065350491626,
284
+ "loss": 1.1068,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 0.7326732673267327,
289
+ "grad_norm": 0.2490234375,
290
+ "learning_rate": 0.00019019912301329592,
291
+ "loss": 1.0583,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 0.7524752475247525,
296
+ "grad_norm": 0.2734375,
297
+ "learning_rate": 0.00018947293298207635,
298
+ "loss": 1.0671,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 0.7722772277227723,
303
+ "grad_norm": 0.2490234375,
304
+ "learning_rate": 0.0001887222819443612,
305
+ "loss": 1.0851,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 0.7722772277227723,
310
+ "eval_loss": 1.060703158378601,
311
+ "eval_runtime": 13.878,
312
+ "eval_samples_per_second": 9.007,
313
+ "eval_steps_per_second": 4.54,
314
+ "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.7920792079207921,
318
+ "grad_norm": 0.22265625,
319
+ "learning_rate": 0.0001879473751206489,
320
+ "loss": 1.0343,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.8118811881188119,
325
+ "grad_norm": 0.1796875,
326
+ "learning_rate": 0.00018714842436272773,
327
+ "loss": 0.9789,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.8316831683168316,
332
+ "grad_norm": 0.248046875,
333
+ "learning_rate": 0.00018632564809575742,
334
+ "loss": 1.0174,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.8514851485148515,
339
+ "grad_norm": 0.2294921875,
340
+ "learning_rate": 0.0001854792712585539,
341
+ "loss": 1.0004,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.8712871287128713,
346
+ "grad_norm": 0.228515625,
347
+ "learning_rate": 0.00018460952524209355,
348
+ "loss": 1.0281,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.8910891089108911,
353
+ "grad_norm": 0.220703125,
354
+ "learning_rate": 0.00018371664782625287,
355
+ "loss": 0.9992,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.9108910891089109,
360
+ "grad_norm": 0.2138671875,
361
+ "learning_rate": 0.00018280088311480201,
362
+ "loss": 0.9635,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.9306930693069307,
367
+ "grad_norm": 0.265625,
368
+ "learning_rate": 0.00018186248146866927,
369
+ "loss": 1.006,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.9504950495049505,
374
+ "grad_norm": 0.2451171875,
375
+ "learning_rate": 0.00018090169943749476,
376
+ "loss": 0.9891,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.9702970297029703,
381
+ "grad_norm": 0.28515625,
382
+ "learning_rate": 0.0001799187996894925,
383
+ "loss": 0.9809,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.9900990099009901,
388
+ "grad_norm": 0.212890625,
389
+ "learning_rate": 0.00017891405093963938,
390
+ "loss": 0.9646,
391
+ "step": 50
392
+ },
393
+ {
394
+ "epoch": 1.00990099009901,
395
+ "grad_norm": 0.2451171875,
396
+ "learning_rate": 0.00017788772787621126,
397
+ "loss": 0.9553,
398
+ "step": 51
399
+ },
400
+ {
401
+ "epoch": 1.0297029702970297,
402
+ "grad_norm": 0.2578125,
403
+ "learning_rate": 0.00017684011108568592,
404
+ "loss": 0.9432,
405
+ "step": 52
406
+ },
407
+ {
408
+ "epoch": 1.0297029702970297,
409
+ "eval_loss": 0.9755253195762634,
410
+ "eval_runtime": 13.879,
411
+ "eval_samples_per_second": 9.006,
412
+ "eval_steps_per_second": 4.539,
413
+ "step": 52
414
+ },
415
+ {
416
+ "epoch": 1.0495049504950495,
417
+ "grad_norm": 0.2021484375,
418
+ "learning_rate": 0.0001757714869760335,
419
+ "loss": 0.9631,
420
+ "step": 53
421
+ },
422
+ {
423
+ "epoch": 1.0693069306930694,
424
+ "grad_norm": 0.3046875,
425
+ "learning_rate": 0.0001746821476984154,
426
+ "loss": 0.9539,
427
+ "step": 54
428
+ },
429
+ {
430
+ "epoch": 1.0198019801980198,
431
+ "grad_norm": 0.232421875,
432
+ "learning_rate": 0.00017357239106731317,
433
+ "loss": 0.9559,
434
+ "step": 55
435
+ },
436
+ {
437
+ "epoch": 1.0396039603960396,
438
+ "grad_norm": 0.283203125,
439
+ "learning_rate": 0.00017244252047910892,
440
+ "loss": 0.9111,
441
+ "step": 56
442
+ },
443
+ {
444
+ "epoch": 1.0594059405940595,
445
+ "grad_norm": 0.30859375,
446
+ "learning_rate": 0.00017129284482913972,
447
+ "loss": 0.9503,
448
+ "step": 57
449
+ },
450
+ {
451
+ "epoch": 1.0792079207920793,
452
+ "grad_norm": 0.2265625,
453
+ "learning_rate": 0.00017012367842724887,
454
+ "loss": 0.911,
455
+ "step": 58
456
+ },
457
+ {
458
+ "epoch": 1.099009900990099,
459
+ "grad_norm": 0.3515625,
460
+ "learning_rate": 0.0001689353409118566,
461
+ "loss": 0.9041,
462
+ "step": 59
463
+ },
464
+ {
465
+ "epoch": 1.118811881188119,
466
+ "grad_norm": 0.26171875,
467
+ "learning_rate": 0.00016772815716257412,
468
+ "loss": 0.9117,
469
+ "step": 60
470
+ },
471
+ {
472
+ "epoch": 1.1386138613861387,
473
+ "grad_norm": 0.2890625,
474
+ "learning_rate": 0.0001665024572113848,
475
+ "loss": 0.9351,
476
+ "step": 61
477
+ },
478
+ {
479
+ "epoch": 1.1584158415841583,
480
+ "grad_norm": 0.251953125,
481
+ "learning_rate": 0.00016525857615241687,
482
+ "loss": 0.9438,
483
+ "step": 62
484
+ },
485
+ {
486
+ "epoch": 1.1782178217821782,
487
+ "grad_norm": 0.2138671875,
488
+ "learning_rate": 0.00016399685405033167,
489
+ "loss": 0.9075,
490
+ "step": 63
491
+ },
492
+ {
493
+ "epoch": 1.198019801980198,
494
+ "grad_norm": 0.2490234375,
495
+ "learning_rate": 0.0001627176358473537,
496
+ "loss": 0.8983,
497
+ "step": 64
498
+ },
499
+ {
500
+ "epoch": 1.2178217821782178,
501
+ "grad_norm": 0.2021484375,
502
+ "learning_rate": 0.0001614212712689668,
503
+ "loss": 0.9007,
504
+ "step": 65
505
+ },
506
+ {
507
+ "epoch": 1.2178217821782178,
508
+ "eval_loss": 0.9333999156951904,
509
+ "eval_runtime": 13.8668,
510
+ "eval_samples_per_second": 9.014,
511
+ "eval_steps_per_second": 4.543,
512
+ "step": 65
513
+ },
514
+ {
515
+ "epoch": 1.2376237623762376,
516
+ "grad_norm": 0.2431640625,
517
+ "learning_rate": 0.00016010811472830252,
518
+ "loss": 0.9108,
519
+ "step": 66
520
+ },
521
+ {
522
+ "epoch": 1.2574257425742574,
523
+ "grad_norm": 0.232421875,
524
+ "learning_rate": 0.00015877852522924732,
525
+ "loss": 0.9177,
526
+ "step": 67
527
+ },
528
+ {
529
+ "epoch": 1.2772277227722773,
530
+ "grad_norm": 0.271484375,
531
+ "learning_rate": 0.00015743286626829437,
532
+ "loss": 0.9,
533
+ "step": 68
534
+ },
535
+ {
536
+ "epoch": 1.297029702970297,
537
+ "grad_norm": 0.2431640625,
538
+ "learning_rate": 0.0001560715057351673,
539
+ "loss": 0.9096,
540
+ "step": 69
541
+ },
542
+ {
543
+ "epoch": 1.316831683168317,
544
+ "grad_norm": 0.22265625,
545
+ "learning_rate": 0.00015469481581224272,
546
+ "loss": 0.8946,
547
+ "step": 70
548
+ },
549
+ {
550
+ "epoch": 1.3366336633663367,
551
+ "grad_norm": 0.31640625,
552
+ "learning_rate": 0.0001533031728727994,
553
+ "loss": 0.8995,
554
+ "step": 71
555
+ },
556
+ {
557
+ "epoch": 1.3564356435643563,
558
+ "grad_norm": 0.2197265625,
559
+ "learning_rate": 0.00015189695737812152,
560
+ "loss": 0.922,
561
+ "step": 72
562
+ },
563
+ {
564
+ "epoch": 1.3762376237623761,
565
+ "grad_norm": 0.22265625,
566
+ "learning_rate": 0.0001504765537734844,
567
+ "loss": 0.885,
568
+ "step": 73
569
+ },
570
+ {
571
+ "epoch": 1.396039603960396,
572
+ "grad_norm": 0.248046875,
573
+ "learning_rate": 0.00014904235038305083,
574
+ "loss": 0.895,
575
+ "step": 74
576
+ },
577
+ {
578
+ "epoch": 1.4158415841584158,
579
+ "grad_norm": 0.2431640625,
580
+ "learning_rate": 0.00014759473930370736,
581
+ "loss": 0.892,
582
+ "step": 75
583
+ },
584
+ {
585
+ "epoch": 1.4356435643564356,
586
+ "grad_norm": 0.216796875,
587
+ "learning_rate": 0.0001461341162978688,
588
+ "loss": 0.8277,
589
+ "step": 76
590
+ },
591
+ {
592
+ "epoch": 1.4554455445544554,
593
+ "grad_norm": 0.23828125,
594
+ "learning_rate": 0.00014466088068528068,
595
+ "loss": 0.8687,
596
+ "step": 77
597
+ },
598
+ {
599
+ "epoch": 1.4752475247524752,
600
+ "grad_norm": 0.228515625,
601
+ "learning_rate": 0.00014317543523384928,
602
+ "loss": 0.8765,
603
+ "step": 78
604
+ },
605
+ {
606
+ "epoch": 1.4752475247524752,
607
+ "eval_loss": 0.9083698391914368,
608
+ "eval_runtime": 13.8834,
609
+ "eval_samples_per_second": 9.004,
610
+ "eval_steps_per_second": 4.538,
611
+ "step": 78
612
+ },
613
+ {
614
+ "epoch": 1.495049504950495,
615
+ "grad_norm": 0.228515625,
616
+ "learning_rate": 0.00014167818604952906,
617
+ "loss": 0.8797,
618
+ "step": 79
619
+ },
620
+ {
621
+ "epoch": 1.5148514851485149,
622
+ "grad_norm": 0.1982421875,
623
+ "learning_rate": 0.00014016954246529696,
624
+ "loss": 0.905,
625
+ "step": 80
626
+ },
627
+ {
628
+ "epoch": 1.5346534653465347,
629
+ "grad_norm": 0.25390625,
630
+ "learning_rate": 0.00013864991692924523,
631
+ "loss": 0.8575,
632
+ "step": 81
633
+ },
634
+ {
635
+ "epoch": 1.5544554455445545,
636
+ "grad_norm": 0.2451171875,
637
+ "learning_rate": 0.00013711972489182208,
638
+ "loss": 0.8957,
639
+ "step": 82
640
+ },
641
+ {
642
+ "epoch": 1.5742574257425743,
643
+ "grad_norm": 0.2216796875,
644
+ "learning_rate": 0.00013557938469225167,
645
+ "loss": 0.8792,
646
+ "step": 83
647
+ },
648
+ {
649
+ "epoch": 1.5940594059405941,
650
+ "grad_norm": 0.21484375,
651
+ "learning_rate": 0.00013402931744416433,
652
+ "loss": 0.889,
653
+ "step": 84
654
+ },
655
+ {
656
+ "epoch": 1.613861386138614,
657
+ "grad_norm": 0.228515625,
658
+ "learning_rate": 0.00013246994692046836,
659
+ "loss": 0.8657,
660
+ "step": 85
661
+ },
662
+ {
663
+ "epoch": 1.6336633663366338,
664
+ "grad_norm": 0.20703125,
665
+ "learning_rate": 0.00013090169943749476,
666
+ "loss": 0.8784,
667
+ "step": 86
668
+ },
669
+ {
670
+ "epoch": 1.6534653465346536,
671
+ "grad_norm": 0.265625,
672
+ "learning_rate": 0.0001293250037384465,
673
+ "loss": 0.8822,
674
+ "step": 87
675
+ },
676
+ {
677
+ "epoch": 1.6732673267326734,
678
+ "grad_norm": 0.2197265625,
679
+ "learning_rate": 0.00012774029087618446,
680
+ "loss": 0.9092,
681
+ "step": 88
682
+ },
683
+ {
684
+ "epoch": 1.693069306930693,
685
+ "grad_norm": 0.234375,
686
+ "learning_rate": 0.00012614799409538198,
687
+ "loss": 0.8813,
688
+ "step": 89
689
+ },
690
+ {
691
+ "epoch": 1.7128712871287128,
692
+ "grad_norm": 0.2294921875,
693
+ "learning_rate": 0.00012454854871407994,
694
+ "loss": 0.8975,
695
+ "step": 90
696
+ },
697
+ {
698
+ "epoch": 1.7326732673267327,
699
+ "grad_norm": 0.259765625,
700
+ "learning_rate": 0.00012294239200467516,
701
+ "loss": 0.8789,
702
+ "step": 91
703
+ },
704
+ {
705
+ "epoch": 1.7326732673267327,
706
+ "eval_loss": 0.8891416788101196,
707
+ "eval_runtime": 13.872,
708
+ "eval_samples_per_second": 9.011,
709
+ "eval_steps_per_second": 4.542,
710
+ "step": 91
711
+ },
712
+ {
713
+ "epoch": 1.7524752475247525,
714
+ "grad_norm": 0.26171875,
715
+ "learning_rate": 0.0001213299630743747,
716
+ "loss": 0.9184,
717
+ "step": 92
718
+ },
719
+ {
720
+ "epoch": 1.7722772277227723,
721
+ "grad_norm": 0.337890625,
722
+ "learning_rate": 0.00011971170274514802,
723
+ "loss": 0.8854,
724
+ "step": 93
725
+ },
726
+ {
727
+ "epoch": 1.7920792079207921,
728
+ "grad_norm": 0.2890625,
729
+ "learning_rate": 0.000118088053433211,
730
+ "loss": 0.8688,
731
+ "step": 94
732
+ },
733
+ {
734
+ "epoch": 1.811881188118812,
735
+ "grad_norm": 0.3515625,
736
+ "learning_rate": 0.00011645945902807341,
737
+ "loss": 0.8281,
738
+ "step": 95
739
+ },
740
+ {
741
+ "epoch": 1.8316831683168315,
742
+ "grad_norm": 0.26953125,
743
+ "learning_rate": 0.0001148263647711842,
744
+ "loss": 0.8488,
745
+ "step": 96
746
+ },
747
+ {
748
+ "epoch": 1.8514851485148514,
749
+ "grad_norm": 0.2490234375,
750
+ "learning_rate": 0.00011318921713420691,
751
+ "loss": 0.8742,
752
+ "step": 97
753
+ },
754
+ {
755
+ "epoch": 1.8712871287128712,
756
+ "grad_norm": 0.265625,
757
+ "learning_rate": 0.00011154846369695863,
758
+ "loss": 0.8586,
759
+ "step": 98
760
+ },
761
+ {
762
+ "epoch": 1.891089108910891,
763
+ "grad_norm": 0.265625,
764
+ "learning_rate": 0.0001099045530250463,
765
+ "loss": 0.8776,
766
+ "step": 99
767
+ },
768
+ {
769
+ "epoch": 1.9108910891089108,
770
+ "grad_norm": 0.259765625,
771
+ "learning_rate": 0.00010825793454723325,
772
+ "loss": 0.8563,
773
+ "step": 100
774
+ },
775
+ {
776
+ "epoch": 1.9306930693069306,
777
+ "grad_norm": 0.283203125,
778
+ "learning_rate": 0.00010660905843256994,
779
+ "loss": 0.8381,
780
+ "step": 101
781
+ },
782
+ {
783
+ "epoch": 1.9504950495049505,
784
+ "grad_norm": 0.201171875,
785
+ "learning_rate": 0.00010495837546732224,
786
+ "loss": 0.847,
787
+ "step": 102
788
+ },
789
+ {
790
+ "epoch": 1.9702970297029703,
791
+ "grad_norm": 0.23828125,
792
+ "learning_rate": 0.00010330633693173082,
793
+ "loss": 0.8512,
794
+ "step": 103
795
+ },
796
+ {
797
+ "epoch": 1.99009900990099,
798
+ "grad_norm": 0.283203125,
799
+ "learning_rate": 0.00010165339447663587,
800
+ "loss": 0.8304,
801
+ "step": 104
802
+ },
803
+ {
804
+ "epoch": 1.99009900990099,
805
+ "eval_loss": 0.8779018521308899,
806
+ "eval_runtime": 13.8827,
807
+ "eval_samples_per_second": 9.004,
808
+ "eval_steps_per_second": 4.538,
809
+ "step": 104
810
+ },
811
+ {
812
+ "epoch": 2.00990099009901,
813
+ "grad_norm": 0.283203125,
814
+ "learning_rate": 0.0001,
815
+ "loss": 0.8523,
816
+ "step": 105
817
+ },
818
+ {
819
+ "epoch": 2.0297029702970297,
820
+ "grad_norm": 0.2392578125,
821
+ "learning_rate": 9.834660552336415e-05,
822
+ "loss": 0.8109,
823
+ "step": 106
824
+ },
825
+ {
826
+ "epoch": 2.0495049504950495,
827
+ "grad_norm": 0.224609375,
828
+ "learning_rate": 9.669366306826919e-05,
829
+ "loss": 0.8394,
830
+ "step": 107
831
+ },
832
+ {
833
+ "epoch": 2.0693069306930694,
834
+ "grad_norm": 0.283203125,
835
+ "learning_rate": 9.504162453267777e-05,
836
+ "loss": 0.8524,
837
+ "step": 108
838
+ },
839
+ {
840
+ "epoch": 2.01980198019802,
841
+ "grad_norm": 0.22265625,
842
+ "learning_rate": 9.339094156743007e-05,
843
+ "loss": 0.8391,
844
+ "step": 109
845
+ },
846
+ {
847
+ "epoch": 2.0396039603960396,
848
+ "grad_norm": 0.2001953125,
849
+ "learning_rate": 9.174206545276677e-05,
850
+ "loss": 0.8317,
851
+ "step": 110
852
+ },
853
+ {
854
+ "epoch": 2.0594059405940595,
855
+ "grad_norm": 0.22265625,
856
+ "learning_rate": 9.009544697495374e-05,
857
+ "loss": 0.833,
858
+ "step": 111
859
+ },
860
+ {
861
+ "epoch": 2.0792079207920793,
862
+ "grad_norm": 0.2041015625,
863
+ "learning_rate": 8.845153630304139e-05,
864
+ "loss": 0.8408,
865
+ "step": 112
866
+ },
867
+ {
868
+ "epoch": 2.099009900990099,
869
+ "grad_norm": 0.2080078125,
870
+ "learning_rate": 8.681078286579311e-05,
871
+ "loss": 0.8459,
872
+ "step": 113
873
+ },
874
+ {
875
+ "epoch": 2.118811881188119,
876
+ "grad_norm": 0.2021484375,
877
+ "learning_rate": 8.517363522881579e-05,
878
+ "loss": 0.8177,
879
+ "step": 114
880
+ },
881
+ {
882
+ "epoch": 2.1386138613861387,
883
+ "grad_norm": 0.2265625,
884
+ "learning_rate": 8.35405409719266e-05,
885
+ "loss": 0.8451,
886
+ "step": 115
887
+ },
888
+ {
889
+ "epoch": 2.1584158415841586,
890
+ "grad_norm": 0.2294921875,
891
+ "learning_rate": 8.191194656678904e-05,
892
+ "loss": 0.8543,
893
+ "step": 116
894
+ },
895
+ {
896
+ "epoch": 2.1782178217821784,
897
+ "grad_norm": 0.22265625,
898
+ "learning_rate": 8.028829725485199e-05,
899
+ "loss": 0.8194,
900
+ "step": 117
901
+ },
902
+ {
903
+ "epoch": 2.1782178217821784,
904
+ "eval_loss": 0.8713971972465515,
905
+ "eval_runtime": 13.8976,
906
+ "eval_samples_per_second": 8.994,
907
+ "eval_steps_per_second": 4.533,
908
+ "step": 117
909
+ },
910
+ {
911
+ "epoch": 2.198019801980198,
912
+ "grad_norm": 0.2333984375,
913
+ "learning_rate": 7.867003692562534e-05,
914
+ "loss": 0.808,
915
+ "step": 118
916
+ },
917
+ {
918
+ "epoch": 2.217821782178218,
919
+ "grad_norm": 0.2470703125,
920
+ "learning_rate": 7.705760799532485e-05,
921
+ "loss": 0.8073,
922
+ "step": 119
923
+ },
924
+ {
925
+ "epoch": 2.237623762376238,
926
+ "grad_norm": 0.201171875,
927
+ "learning_rate": 7.54514512859201e-05,
928
+ "loss": 0.8392,
929
+ "step": 120
930
+ },
931
+ {
932
+ "epoch": 2.2574257425742577,
933
+ "grad_norm": 0.25,
934
+ "learning_rate": 7.385200590461803e-05,
935
+ "loss": 0.8574,
936
+ "step": 121
937
+ },
938
+ {
939
+ "epoch": 2.2772277227722775,
940
+ "grad_norm": 0.271484375,
941
+ "learning_rate": 7.225970912381556e-05,
942
+ "loss": 0.8338,
943
+ "step": 122
944
+ },
945
+ {
946
+ "epoch": 2.297029702970297,
947
+ "grad_norm": 0.294921875,
948
+ "learning_rate": 7.067499626155354e-05,
949
+ "loss": 0.8788,
950
+ "step": 123
951
+ },
952
+ {
953
+ "epoch": 2.3168316831683167,
954
+ "grad_norm": 0.2265625,
955
+ "learning_rate": 6.909830056250527e-05,
956
+ "loss": 0.8297,
957
+ "step": 124
958
+ },
959
+ {
960
+ "epoch": 2.3366336633663365,
961
+ "grad_norm": 0.267578125,
962
+ "learning_rate": 6.753005307953167e-05,
963
+ "loss": 0.8125,
964
+ "step": 125
965
+ },
966
+ {
967
+ "epoch": 2.3564356435643563,
968
+ "grad_norm": 0.2431640625,
969
+ "learning_rate": 6.59706825558357e-05,
970
+ "loss": 0.814,
971
+ "step": 126
972
+ },
973
+ {
974
+ "epoch": 2.376237623762376,
975
+ "grad_norm": 0.27734375,
976
+ "learning_rate": 6.442061530774834e-05,
977
+ "loss": 0.8335,
978
+ "step": 127
979
+ },
980
+ {
981
+ "epoch": 2.396039603960396,
982
+ "grad_norm": 0.2216796875,
983
+ "learning_rate": 6.28802751081779e-05,
984
+ "loss": 0.8512,
985
+ "step": 128
986
+ },
987
+ {
988
+ "epoch": 2.4158415841584158,
989
+ "grad_norm": 0.224609375,
990
+ "learning_rate": 6.135008307075481e-05,
991
+ "loss": 0.8297,
992
+ "step": 129
993
+ },
994
+ {
995
+ "epoch": 2.4356435643564356,
996
+ "grad_norm": 0.2412109375,
997
+ "learning_rate": 5.983045753470308e-05,
998
+ "loss": 0.848,
999
+ "step": 130
1000
+ },
1001
+ {
1002
+ "epoch": 2.4356435643564356,
1003
+ "eval_loss": 0.8665071129798889,
1004
+ "eval_runtime": 13.8735,
1005
+ "eval_samples_per_second": 9.01,
1006
+ "eval_steps_per_second": 4.541,
1007
+ "step": 130
1008
+ },
1009
+ {
1010
+ "epoch": 2.4554455445544554,
1011
+ "grad_norm": 0.2265625,
1012
+ "learning_rate": 5.832181395047098e-05,
1013
+ "loss": 0.8203,
1014
+ "step": 131
1015
+ },
1016
+ {
1017
+ "epoch": 2.4752475247524752,
1018
+ "grad_norm": 0.287109375,
1019
+ "learning_rate": 5.6824564766150726e-05,
1020
+ "loss": 0.8519,
1021
+ "step": 132
1022
+ },
1023
+ {
1024
+ "epoch": 2.495049504950495,
1025
+ "grad_norm": 0.21484375,
1026
+ "learning_rate": 5.533911931471936e-05,
1027
+ "loss": 0.83,
1028
+ "step": 133
1029
+ },
1030
+ {
1031
+ "epoch": 2.514851485148515,
1032
+ "grad_norm": 0.2109375,
1033
+ "learning_rate": 5.386588370213124e-05,
1034
+ "loss": 0.842,
1035
+ "step": 134
1036
+ },
1037
+ {
1038
+ "epoch": 2.5346534653465347,
1039
+ "grad_norm": 0.2412109375,
1040
+ "learning_rate": 5.240526069629265e-05,
1041
+ "loss": 0.8419,
1042
+ "step": 135
1043
+ },
1044
+ {
1045
+ "epoch": 2.5544554455445545,
1046
+ "grad_norm": 0.267578125,
1047
+ "learning_rate": 5.095764961694922e-05,
1048
+ "loss": 0.8458,
1049
+ "step": 136
1050
+ },
1051
+ {
1052
+ "epoch": 2.5742574257425743,
1053
+ "grad_norm": 0.203125,
1054
+ "learning_rate": 4.952344622651566e-05,
1055
+ "loss": 0.8133,
1056
+ "step": 137
1057
+ },
1058
+ {
1059
+ "epoch": 2.594059405940594,
1060
+ "grad_norm": 0.2060546875,
1061
+ "learning_rate": 4.810304262187852e-05,
1062
+ "loss": 0.8103,
1063
+ "step": 138
1064
+ },
1065
+ {
1066
+ "epoch": 2.613861386138614,
1067
+ "grad_norm": 0.20703125,
1068
+ "learning_rate": 4.669682712720065e-05,
1069
+ "loss": 0.8105,
1070
+ "step": 139
1071
+ },
1072
+ {
1073
+ "epoch": 2.633663366336634,
1074
+ "grad_norm": 0.2060546875,
1075
+ "learning_rate": 4.530518418775733e-05,
1076
+ "loss": 0.8305,
1077
+ "step": 140
1078
+ },
1079
+ {
1080
+ "epoch": 2.6534653465346536,
1081
+ "grad_norm": 0.2080078125,
1082
+ "learning_rate": 4.392849426483274e-05,
1083
+ "loss": 0.7881,
1084
+ "step": 141
1085
+ },
1086
+ {
1087
+ "epoch": 2.6732673267326734,
1088
+ "grad_norm": 0.2216796875,
1089
+ "learning_rate": 4.256713373170564e-05,
1090
+ "loss": 0.8204,
1091
+ "step": 142
1092
+ },
1093
+ {
1094
+ "epoch": 2.693069306930693,
1095
+ "grad_norm": 0.263671875,
1096
+ "learning_rate": 4.12214747707527e-05,
1097
+ "loss": 0.8354,
1098
+ "step": 143
1099
+ },
1100
+ {
1101
+ "epoch": 2.693069306930693,
1102
+ "eval_loss": 0.8626759648323059,
1103
+ "eval_runtime": 13.8585,
1104
+ "eval_samples_per_second": 9.02,
1105
+ "eval_steps_per_second": 4.546,
1106
+ "step": 143
1107
+ },
1108
+ {
1109
+ "epoch": 2.7128712871287126,
1110
+ "grad_norm": 0.2138671875,
1111
+ "learning_rate": 3.9891885271697496e-05,
1112
+ "loss": 0.8441,
1113
+ "step": 144
1114
+ },
1115
+ {
1116
+ "epoch": 2.7326732673267324,
1117
+ "grad_norm": 0.2197265625,
1118
+ "learning_rate": 3.857872873103322e-05,
1119
+ "loss": 0.8084,
1120
+ "step": 145
1121
+ },
1122
+ {
1123
+ "epoch": 2.7524752475247523,
1124
+ "grad_norm": 0.18359375,
1125
+ "learning_rate": 3.7282364152646297e-05,
1126
+ "loss": 0.8184,
1127
+ "step": 146
1128
+ },
1129
+ {
1130
+ "epoch": 2.772277227722772,
1131
+ "grad_norm": 0.1904296875,
1132
+ "learning_rate": 3.600314594966834e-05,
1133
+ "loss": 0.8302,
1134
+ "step": 147
1135
+ },
1136
+ {
1137
+ "epoch": 2.792079207920792,
1138
+ "grad_norm": 0.2041015625,
1139
+ "learning_rate": 3.4741423847583134e-05,
1140
+ "loss": 0.8503,
1141
+ "step": 148
1142
+ },
1143
+ {
1144
+ "epoch": 2.8118811881188117,
1145
+ "grad_norm": 0.2265625,
1146
+ "learning_rate": 3.349754278861517e-05,
1147
+ "loss": 0.8273,
1148
+ "step": 149
1149
+ },
1150
+ {
1151
+ "epoch": 2.8316831683168315,
1152
+ "grad_norm": 0.1943359375,
1153
+ "learning_rate": 3.227184283742591e-05,
1154
+ "loss": 0.8332,
1155
+ "step": 150
1156
+ },
1157
+ {
1158
+ "epoch": 2.8514851485148514,
1159
+ "grad_norm": 0.185546875,
1160
+ "learning_rate": 3.106465908814342e-05,
1161
+ "loss": 0.8391,
1162
+ "step": 151
1163
+ },
1164
+ {
1165
+ "epoch": 2.871287128712871,
1166
+ "grad_norm": 0.1982421875,
1167
+ "learning_rate": 2.9876321572751144e-05,
1168
+ "loss": 0.8029,
1169
+ "step": 152
1170
+ },
1171
+ {
1172
+ "epoch": 2.891089108910891,
1173
+ "grad_norm": 0.224609375,
1174
+ "learning_rate": 2.87071551708603e-05,
1175
+ "loss": 0.8561,
1176
+ "step": 153
1177
+ },
1178
+ {
1179
+ "epoch": 2.910891089108911,
1180
+ "grad_norm": 0.2275390625,
1181
+ "learning_rate": 2.7557479520891104e-05,
1182
+ "loss": 0.8055,
1183
+ "step": 154
1184
+ },
1185
+ {
1186
+ "epoch": 2.9306930693069306,
1187
+ "grad_norm": 0.16796875,
1188
+ "learning_rate": 2.6427608932686843e-05,
1189
+ "loss": 0.8301,
1190
+ "step": 155
1191
+ },
1192
+ {
1193
+ "epoch": 2.9504950495049505,
1194
+ "grad_norm": 0.1943359375,
1195
+ "learning_rate": 2.5317852301584643e-05,
1196
+ "loss": 0.8476,
1197
+ "step": 156
1198
+ },
1199
+ {
1200
+ "epoch": 2.9504950495049505,
1201
+ "eval_loss": 0.8605256080627441,
1202
+ "eval_runtime": 13.8794,
1203
+ "eval_samples_per_second": 9.006,
1204
+ "eval_steps_per_second": 4.539,
1205
+ "step": 156
1206
+ },
1207
+ {
1208
+ "epoch": 2.9702970297029703,
1209
+ "grad_norm": 0.2138671875,
1210
+ "learning_rate": 2.422851302396655e-05,
1211
+ "loss": 0.8483,
1212
+ "step": 157
1213
+ },
1214
+ {
1215
+ "epoch": 2.99009900990099,
1216
+ "grad_norm": 0.2216796875,
1217
+ "learning_rate": 2.315988891431412e-05,
1218
+ "loss": 0.8379,
1219
+ "step": 158
1220
+ },
1221
+ {
1222
+ "epoch": 3.00990099009901,
1223
+ "grad_norm": 0.2373046875,
1224
+ "learning_rate": 2.2112272123788768e-05,
1225
+ "loss": 0.8042,
1226
+ "step": 159
1227
+ },
1228
+ {
1229
+ "epoch": 3.0297029702970297,
1230
+ "grad_norm": 0.416015625,
1231
+ "learning_rate": 2.1085949060360654e-05,
1232
+ "loss": 0.8597,
1233
+ "step": 160
1234
+ },
1235
+ {
1236
+ "epoch": 3.0495049504950495,
1237
+ "grad_norm": 0.1806640625,
1238
+ "learning_rate": 2.008120031050753e-05,
1239
+ "loss": 0.8327,
1240
+ "step": 161
1241
+ },
1242
+ {
1243
+ "epoch": 3.0693069306930694,
1244
+ "grad_norm": 0.212890625,
1245
+ "learning_rate": 1.9098300562505266e-05,
1246
+ "loss": 0.7991,
1247
+ "step": 162
1248
+ },
1249
+ {
1250
+ "epoch": 3.01980198019802,
1251
+ "grad_norm": 0.1875,
1252
+ "learning_rate": 1.8137518531330767e-05,
1253
+ "loss": 0.8083,
1254
+ "step": 163
1255
+ },
1256
+ {
1257
+ "epoch": 3.0396039603960396,
1258
+ "grad_norm": 0.1982421875,
1259
+ "learning_rate": 1.7199116885197995e-05,
1260
+ "loss": 0.8321,
1261
+ "step": 164
1262
+ },
1263
+ {
1264
+ "epoch": 3.0594059405940595,
1265
+ "grad_norm": 0.193359375,
1266
+ "learning_rate": 1.6283352173747145e-05,
1267
+ "loss": 0.8596,
1268
+ "step": 165
1269
+ },
1270
+ {
1271
+ "epoch": 3.0792079207920793,
1272
+ "grad_norm": 0.1826171875,
1273
+ "learning_rate": 1.5390474757906446e-05,
1274
+ "loss": 0.82,
1275
+ "step": 166
1276
+ },
1277
+ {
1278
+ "epoch": 3.099009900990099,
1279
+ "grad_norm": 0.1806640625,
1280
+ "learning_rate": 1.4520728741446089e-05,
1281
+ "loss": 0.8245,
1282
+ "step": 167
1283
+ },
1284
+ {
1285
+ "epoch": 3.118811881188119,
1286
+ "grad_norm": 0.1923828125,
1287
+ "learning_rate": 1.3674351904242611e-05,
1288
+ "loss": 0.8174,
1289
+ "step": 168
1290
+ },
1291
+ {
1292
+ "epoch": 3.1386138613861387,
1293
+ "grad_norm": 0.1787109375,
1294
+ "learning_rate": 1.2851575637272262e-05,
1295
+ "loss": 0.811,
1296
+ "step": 169
1297
+ },
1298
+ {
1299
+ "epoch": 3.1386138613861387,
1300
+ "eval_loss": 0.8589804768562317,
1301
+ "eval_runtime": 13.8605,
1302
+ "eval_samples_per_second": 9.018,
1303
+ "eval_steps_per_second": 4.545,
1304
+ "step": 169
1305
+ },
1306
+ {
1307
+ "epoch": 3.1584158415841586,
1308
+ "grad_norm": 0.1865234375,
1309
+ "learning_rate": 1.2052624879351104e-05,
1310
+ "loss": 0.8043,
1311
+ "step": 170
1312
+ },
1313
+ {
1314
+ "epoch": 3.1782178217821784,
1315
+ "grad_norm": 0.181640625,
1316
+ "learning_rate": 1.1277718055638819e-05,
1317
+ "loss": 0.8117,
1318
+ "step": 171
1319
+ },
1320
+ {
1321
+ "epoch": 3.198019801980198,
1322
+ "grad_norm": 0.205078125,
1323
+ "learning_rate": 1.0527067017923654e-05,
1324
+ "loss": 0.8176,
1325
+ "step": 172
1326
+ },
1327
+ {
1328
+ "epoch": 3.217821782178218,
1329
+ "grad_norm": 0.1904296875,
1330
+ "learning_rate": 9.80087698670411e-06,
1331
+ "loss": 0.7919,
1332
+ "step": 173
1333
+ },
1334
+ {
1335
+ "epoch": 3.237623762376238,
1336
+ "grad_norm": 0.177734375,
1337
+ "learning_rate": 9.09934649508375e-06,
1338
+ "loss": 0.8099,
1339
+ "step": 174
1340
+ },
1341
+ {
1342
+ "epoch": 3.2574257425742577,
1343
+ "grad_norm": 0.203125,
1344
+ "learning_rate": 8.422667334494249e-06,
1345
+ "loss": 0.8161,
1346
+ "step": 175
1347
+ },
1348
+ {
1349
+ "epoch": 3.2772277227722775,
1350
+ "grad_norm": 0.208984375,
1351
+ "learning_rate": 7.771024502261526e-06,
1352
+ "loss": 0.8199,
1353
+ "step": 176
1354
+ },
1355
+ {
1356
+ "epoch": 3.297029702970297,
1357
+ "grad_norm": 0.1923828125,
1358
+ "learning_rate": 7.144596151029303e-06,
1359
+ "loss": 0.8077,
1360
+ "step": 177
1361
+ },
1362
+ {
1363
+ "epoch": 3.3168316831683167,
1364
+ "grad_norm": 0.298828125,
1365
+ "learning_rate": 6.543553540053926e-06,
1366
+ "loss": 0.8532,
1367
+ "step": 178
1368
+ },
1369
+ {
1370
+ "epoch": 3.3366336633663365,
1371
+ "grad_norm": 0.1826171875,
1372
+ "learning_rate": 5.968060988383883e-06,
1373
+ "loss": 0.8062,
1374
+ "step": 179
1375
+ },
1376
+ {
1377
+ "epoch": 3.3564356435643563,
1378
+ "grad_norm": 0.1689453125,
1379
+ "learning_rate": 5.418275829936537e-06,
1380
+ "loss": 0.802,
1381
+ "step": 180
1382
+ },
1383
+ {
1384
+ "epoch": 3.376237623762376,
1385
+ "grad_norm": 0.2001953125,
1386
+ "learning_rate": 4.8943483704846475e-06,
1387
+ "loss": 0.8189,
1388
+ "step": 181
1389
+ },
1390
+ {
1391
+ "epoch": 3.396039603960396,
1392
+ "grad_norm": 0.169921875,
1393
+ "learning_rate": 4.3964218465642355e-06,
1394
+ "loss": 0.8178,
1395
+ "step": 182
1396
+ },
1397
+ {
1398
+ "epoch": 3.396039603960396,
1399
+ "eval_loss": 0.858788788318634,
1400
+ "eval_runtime": 13.8817,
1401
+ "eval_samples_per_second": 9.005,
1402
+ "eval_steps_per_second": 4.538,
1403
+ "step": 182
1404
+ },
1405
+ {
1406
+ "epoch": 3.4158415841584158,
1407
+ "grad_norm": 0.16796875,
1408
+ "learning_rate": 3.924632386315186e-06,
1409
+ "loss": 0.8307,
1410
+ "step": 183
1411
+ },
1412
+ {
1413
+ "epoch": 3.4356435643564356,
1414
+ "grad_norm": 0.181640625,
1415
+ "learning_rate": 3.4791089722651436e-06,
1416
+ "loss": 0.8255,
1417
+ "step": 184
1418
+ },
1419
+ {
1420
+ "epoch": 3.4554455445544554,
1421
+ "grad_norm": 0.185546875,
1422
+ "learning_rate": 3.059973406066963e-06,
1423
+ "loss": 0.8222,
1424
+ "step": 185
1425
+ },
1426
+ {
1427
+ "epoch": 3.4752475247524752,
1428
+ "grad_norm": 0.19140625,
1429
+ "learning_rate": 2.667340275199426e-06,
1430
+ "loss": 0.8054,
1431
+ "step": 186
1432
+ },
1433
+ {
1434
+ "epoch": 3.495049504950495,
1435
+ "grad_norm": 0.1826171875,
1436
+ "learning_rate": 2.3013169216400733e-06,
1437
+ "loss": 0.8628,
1438
+ "step": 187
1439
+ },
1440
+ {
1441
+ "epoch": 3.514851485148515,
1442
+ "grad_norm": 0.1796875,
1443
+ "learning_rate": 1.9620034125190644e-06,
1444
+ "loss": 0.8338,
1445
+ "step": 188
1446
+ },
1447
+ {
1448
+ "epoch": 3.5346534653465347,
1449
+ "grad_norm": 0.1728515625,
1450
+ "learning_rate": 1.6494925127617634e-06,
1451
+ "loss": 0.809,
1452
+ "step": 189
1453
+ },
1454
+ {
1455
+ "epoch": 3.5544554455445545,
1456
+ "grad_norm": 0.1904296875,
1457
+ "learning_rate": 1.3638696597277679e-06,
1458
+ "loss": 0.8328,
1459
+ "step": 190
1460
+ },
1461
+ {
1462
+ "epoch": 3.5742574257425743,
1463
+ "grad_norm": 0.17578125,
1464
+ "learning_rate": 1.1052129398531507e-06,
1465
+ "loss": 0.8062,
1466
+ "step": 191
1467
+ },
1468
+ {
1469
+ "epoch": 3.594059405940594,
1470
+ "grad_norm": 0.1884765625,
1471
+ "learning_rate": 8.735930673024806e-07,
1472
+ "loss": 0.832,
1473
+ "step": 192
1474
+ },
1475
+ {
1476
+ "epoch": 3.613861386138614,
1477
+ "grad_norm": 0.17578125,
1478
+ "learning_rate": 6.690733646361857e-07,
1479
+ "loss": 0.8107,
1480
+ "step": 193
1481
+ },
1482
+ {
1483
+ "epoch": 3.633663366336634,
1484
+ "grad_norm": 0.1875,
1485
+ "learning_rate": 4.917097454988584e-07,
1486
+ "loss": 0.8315,
1487
+ "step": 194
1488
+ },
1489
+ {
1490
+ "epoch": 3.6534653465346536,
1491
+ "grad_norm": 0.1845703125,
1492
+ "learning_rate": 3.415506993330153e-07,
1493
+ "loss": 0.8073,
1494
+ "step": 195
1495
+ },
1496
+ {
1497
+ "epoch": 3.6534653465346536,
1498
+ "eval_loss": 0.858626127243042,
1499
+ "eval_runtime": 13.8621,
1500
+ "eval_samples_per_second": 9.017,
1501
+ "eval_steps_per_second": 4.545,
1502
+ "step": 195
1503
+ },
1504
+ {
1505
+ "epoch": 3.6732673267326734,
1506
+ "grad_norm": 0.197265625,
1507
+ "learning_rate": 2.1863727812254653e-07,
1508
+ "loss": 0.8403,
1509
+ "step": 196
1510
+ },
1511
+ {
1512
+ "epoch": 3.693069306930693,
1513
+ "grad_norm": 0.189453125,
1514
+ "learning_rate": 1.230030851695263e-07,
1515
+ "loss": 0.8116,
1516
+ "step": 197
1517
+ },
1518
+ {
1519
+ "epoch": 3.7128712871287126,
1520
+ "grad_norm": 0.173828125,
1521
+ "learning_rate": 5.467426590739511e-08,
1522
+ "loss": 0.8115,
1523
+ "step": 198
1524
+ },
1525
+ {
1526
+ "epoch": 3.7326732673267324,
1527
+ "grad_norm": 0.177734375,
1528
+ "learning_rate": 1.3669500753099585e-08,
1529
+ "loss": 0.7962,
1530
+ "step": 199
1531
+ },
1532
+ {
1533
+ "epoch": 3.7524752475247523,
1534
+ "grad_norm": 0.2099609375,
1535
+ "learning_rate": 0.0,
1536
+ "loss": 0.8031,
1537
+ "step": 200
1538
+ }
1539
+ ],
1540
+ "logging_steps": 1,
1541
+ "max_steps": 200,
1542
+ "num_input_tokens_seen": 0,
1543
+ "num_train_epochs": 4,
1544
+ "save_steps": 50,
1545
+ "stateful_callbacks": {
1546
+ "TrainerControl": {
1547
+ "args": {
1548
+ "should_epoch_stop": false,
1549
+ "should_evaluate": false,
1550
+ "should_log": false,
1551
+ "should_save": true,
1552
+ "should_training_stop": true
1553
+ },
1554
+ "attributes": {}
1555
+ }
1556
+ },
1557
+ "total_flos": 4.164477534181786e+16,
1558
+ "train_batch_size": 2,
1559
+ "trial_name": null,
1560
+ "trial_params": null
1561
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab891527a9343c5fed33fded5a4528864e72798598b8a74f11bf9b63e79e156f
3
+ size 5944
checkpoint-50/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.11.1
checkpoint-50/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "down_proj",
25
+ "gate_proj",
26
+ "v_proj",
27
+ "q_proj",
28
+ "o_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-50/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02032e4ced1f76caa201d55031ab5925f6d0fb66b5d8f3092b8c5d785219b37
3
+ size 50503848
checkpoint-50/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff58348f44e2bde44ab7f9193c61e20dd0f8d95e056c7a292421ffd95a8c7d3
3
+ size 202035450
checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b35231a2c551e6ed40111614cd789a64fe47b38c49d5b21bea0aa24df8b78d2
3
+ size 14244
checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9e02dc10b7239989ab9b4418ee704e53fad611ad6b77ad633028bb8eb5238dd
3
+ size 1064
checkpoint-50/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-50/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-50/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "use_fast": true
44
+ }
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,415 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9900990099009901,
5
+ "eval_steps": 13,
6
+ "global_step": 50,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.019801980198019802,
13
+ "grad_norm": 1.15625,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.0919,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.019801980198019802,
20
+ "eval_loss": 2.079954147338867,
21
+ "eval_runtime": 13.8908,
22
+ "eval_samples_per_second": 8.999,
23
+ "eval_steps_per_second": 4.535,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.039603960396039604,
28
+ "grad_norm": 1.203125,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.0814,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0594059405940594,
35
+ "grad_norm": 1.1953125,
36
+ "learning_rate": 6e-05,
37
+ "loss": 2.0499,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.07920792079207921,
42
+ "grad_norm": 1.0859375,
43
+ "learning_rate": 8e-05,
44
+ "loss": 2.0153,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.09900990099009901,
49
+ "grad_norm": 1.0390625,
50
+ "learning_rate": 0.0001,
51
+ "loss": 1.9548,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.1188118811881188,
56
+ "grad_norm": 0.89453125,
57
+ "learning_rate": 0.00012,
58
+ "loss": 1.8982,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.13861386138613863,
63
+ "grad_norm": 0.67578125,
64
+ "learning_rate": 0.00014,
65
+ "loss": 1.8226,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.15841584158415842,
70
+ "grad_norm": 0.66796875,
71
+ "learning_rate": 0.00016,
72
+ "loss": 1.7572,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.1782178217821782,
77
+ "grad_norm": 0.78515625,
78
+ "learning_rate": 0.00018,
79
+ "loss": 1.7074,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.19801980198019803,
84
+ "grad_norm": 0.73828125,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.6317,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.21782178217821782,
91
+ "grad_norm": 0.484375,
92
+ "learning_rate": 0.0001999863304992469,
93
+ "loss": 1.5801,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.2376237623762376,
98
+ "grad_norm": 0.53125,
99
+ "learning_rate": 0.00019994532573409262,
100
+ "loss": 1.5721,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.25742574257425743,
105
+ "grad_norm": 0.6953125,
106
+ "learning_rate": 0.00019987699691483048,
107
+ "loss": 1.5479,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.25742574257425743,
112
+ "eval_loss": 1.5341482162475586,
113
+ "eval_runtime": 13.8795,
114
+ "eval_samples_per_second": 9.006,
115
+ "eval_steps_per_second": 4.539,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.27722772277227725,
120
+ "grad_norm": 0.65234375,
121
+ "learning_rate": 0.00019978136272187747,
122
+ "loss": 1.534,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.297029702970297,
127
+ "grad_norm": 0.515625,
128
+ "learning_rate": 0.000199658449300667,
129
+ "loss": 1.4804,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.31683168316831684,
134
+ "grad_norm": 0.439453125,
135
+ "learning_rate": 0.00019950829025450114,
136
+ "loss": 1.4805,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.33663366336633666,
141
+ "grad_norm": 0.361328125,
142
+ "learning_rate": 0.00019933092663536382,
143
+ "loss": 1.3809,
144
+ "step": 17
145
+ },
146
+ {
147
+ "epoch": 0.3564356435643564,
148
+ "grad_norm": 0.3125,
149
+ "learning_rate": 0.00019912640693269752,
150
+ "loss": 1.3837,
151
+ "step": 18
152
+ },
153
+ {
154
+ "epoch": 0.37623762376237624,
155
+ "grad_norm": 0.337890625,
156
+ "learning_rate": 0.00019889478706014687,
157
+ "loss": 1.3673,
158
+ "step": 19
159
+ },
160
+ {
161
+ "epoch": 0.39603960396039606,
162
+ "grad_norm": 0.298828125,
163
+ "learning_rate": 0.00019863613034027224,
164
+ "loss": 1.366,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.4158415841584158,
169
+ "grad_norm": 0.34375,
170
+ "learning_rate": 0.00019835050748723824,
171
+ "loss": 1.3318,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.43564356435643564,
176
+ "grad_norm": 0.341796875,
177
+ "learning_rate": 0.00019803799658748094,
178
+ "loss": 1.2741,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.45544554455445546,
183
+ "grad_norm": 0.326171875,
184
+ "learning_rate": 0.00019769868307835994,
185
+ "loss": 1.2978,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 0.4752475247524752,
190
+ "grad_norm": 0.291015625,
191
+ "learning_rate": 0.0001973326597248006,
192
+ "loss": 1.2733,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.49504950495049505,
197
+ "grad_norm": 0.306640625,
198
+ "learning_rate": 0.00019694002659393305,
199
+ "loss": 1.2302,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.5148514851485149,
204
+ "grad_norm": 0.318359375,
205
+ "learning_rate": 0.00019652089102773488,
206
+ "loss": 1.2083,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.5148514851485149,
211
+ "eval_loss": 1.224540114402771,
212
+ "eval_runtime": 13.8695,
213
+ "eval_samples_per_second": 9.013,
214
+ "eval_steps_per_second": 4.542,
215
+ "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.5346534653465347,
219
+ "grad_norm": 0.26953125,
220
+ "learning_rate": 0.00019607536761368484,
221
+ "loss": 1.1761,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.5544554455445545,
226
+ "grad_norm": 0.296875,
227
+ "learning_rate": 0.00019560357815343577,
228
+ "loss": 1.1751,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.5742574257425742,
233
+ "grad_norm": 0.310546875,
234
+ "learning_rate": 0.00019510565162951537,
235
+ "loss": 1.2002,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.594059405940594,
240
+ "grad_norm": 0.287109375,
241
+ "learning_rate": 0.00019458172417006347,
242
+ "loss": 1.1544,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.6138613861386139,
247
+ "grad_norm": 0.365234375,
248
+ "learning_rate": 0.00019403193901161613,
249
+ "loss": 1.1384,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.6336633663366337,
254
+ "grad_norm": 0.236328125,
255
+ "learning_rate": 0.0001934564464599461,
256
+ "loss": 1.0999,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.6534653465346535,
261
+ "grad_norm": 0.326171875,
262
+ "learning_rate": 0.00019285540384897073,
263
+ "loss": 1.1576,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.6732673267326733,
268
+ "grad_norm": 0.310546875,
269
+ "learning_rate": 0.00019222897549773848,
270
+ "loss": 1.091,
271
+ "step": 34
272
+ },
273
+ {
274
+ "epoch": 0.693069306930693,
275
+ "grad_norm": 0.2578125,
276
+ "learning_rate": 0.00019157733266550575,
277
+ "loss": 1.056,
278
+ "step": 35
279
+ },
280
+ {
281
+ "epoch": 0.7128712871287128,
282
+ "grad_norm": 0.267578125,
283
+ "learning_rate": 0.00019090065350491626,
284
+ "loss": 1.1068,
285
+ "step": 36
286
+ },
287
+ {
288
+ "epoch": 0.7326732673267327,
289
+ "grad_norm": 0.2490234375,
290
+ "learning_rate": 0.00019019912301329592,
291
+ "loss": 1.0583,
292
+ "step": 37
293
+ },
294
+ {
295
+ "epoch": 0.7524752475247525,
296
+ "grad_norm": 0.2734375,
297
+ "learning_rate": 0.00018947293298207635,
298
+ "loss": 1.0671,
299
+ "step": 38
300
+ },
301
+ {
302
+ "epoch": 0.7722772277227723,
303
+ "grad_norm": 0.2490234375,
304
+ "learning_rate": 0.0001887222819443612,
305
+ "loss": 1.0851,
306
+ "step": 39
307
+ },
308
+ {
309
+ "epoch": 0.7722772277227723,
310
+ "eval_loss": 1.060703158378601,
311
+ "eval_runtime": 13.878,
312
+ "eval_samples_per_second": 9.007,
313
+ "eval_steps_per_second": 4.54,
314
+ "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.7920792079207921,
318
+ "grad_norm": 0.22265625,
319
+ "learning_rate": 0.0001879473751206489,
320
+ "loss": 1.0343,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.8118811881188119,
325
+ "grad_norm": 0.1796875,
326
+ "learning_rate": 0.00018714842436272773,
327
+ "loss": 0.9789,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.8316831683168316,
332
+ "grad_norm": 0.248046875,
333
+ "learning_rate": 0.00018632564809575742,
334
+ "loss": 1.0174,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.8514851485148515,
339
+ "grad_norm": 0.2294921875,
340
+ "learning_rate": 0.0001854792712585539,
341
+ "loss": 1.0004,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.8712871287128713,
346
+ "grad_norm": 0.228515625,
347
+ "learning_rate": 0.00018460952524209355,
348
+ "loss": 1.0281,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.8910891089108911,
353
+ "grad_norm": 0.220703125,
354
+ "learning_rate": 0.00018371664782625287,
355
+ "loss": 0.9992,
356
+ "step": 45
357
+ },
358
+ {
359
+ "epoch": 0.9108910891089109,
360
+ "grad_norm": 0.2138671875,
361
+ "learning_rate": 0.00018280088311480201,
362
+ "loss": 0.9635,
363
+ "step": 46
364
+ },
365
+ {
366
+ "epoch": 0.9306930693069307,
367
+ "grad_norm": 0.265625,
368
+ "learning_rate": 0.00018186248146866927,
369
+ "loss": 1.006,
370
+ "step": 47
371
+ },
372
+ {
373
+ "epoch": 0.9504950495049505,
374
+ "grad_norm": 0.2451171875,
375
+ "learning_rate": 0.00018090169943749476,
376
+ "loss": 0.9891,
377
+ "step": 48
378
+ },
379
+ {
380
+ "epoch": 0.9702970297029703,
381
+ "grad_norm": 0.28515625,
382
+ "learning_rate": 0.0001799187996894925,
383
+ "loss": 0.9809,
384
+ "step": 49
385
+ },
386
+ {
387
+ "epoch": 0.9900990099009901,
388
+ "grad_norm": 0.212890625,
389
+ "learning_rate": 0.00017891405093963938,
390
+ "loss": 0.9646,
391
+ "step": 50
392
+ }
393
+ ],
394
+ "logging_steps": 1,
395
+ "max_steps": 200,
396
+ "num_input_tokens_seen": 0,
397
+ "num_train_epochs": 4,
398
+ "save_steps": 50,
399
+ "stateful_callbacks": {
400
+ "TrainerControl": {
401
+ "args": {
402
+ "should_epoch_stop": false,
403
+ "should_evaluate": false,
404
+ "should_log": false,
405
+ "should_save": true,
406
+ "should_training_stop": false
407
+ },
408
+ "attributes": {}
409
+ }
410
+ },
411
+ "total_flos": 1.04177049010176e+16,
412
+ "train_batch_size": 2,
413
+ "trial_name": null,
414
+ "trial_params": null
415
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab891527a9343c5fed33fded5a4528864e72798598b8a74f11bf9b63e79e156f
3
+ size 5944
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 22,
19
+ "num_key_value_heads": 4,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "_load_in_4bit": true,
23
+ "_load_in_8bit": false,
24
+ "bnb_4bit_compute_dtype": "bfloat16",
25
+ "bnb_4bit_quant_storage": "bfloat16",
26
+ "bnb_4bit_quant_type": "nf4",
27
+ "bnb_4bit_use_double_quant": true,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": true,
33
+ "load_in_8bit": false,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rms_norm_eps": 1e-05,
37
+ "rope_scaling": null,
38
+ "rope_theta": 10000.0,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.41.1",
42
+ "use_cache": false,
43
+ "vocab_size": 32000
44
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723