jssky commited on
Commit
54e3b36
·
verified ·
1 Parent(s): ea28a9a

Training in progress, step 134, checkpoint

Browse files
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/mistral-7b-instruct-v0.2
3
+ library_name: peft
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 0.14.0
last-checkpoint/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.2",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": null,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 8,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "gate_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "o_proj",
30
+ "down_proj",
31
+ "v_proj",
32
+ "k_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e1fcd4ff926ec53b80ffc3484d68781bbc23865e0167c3791fdbaff1d51086
3
+ size 83945296
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2c7e3832b75d2ab386b461b6c34214ea36274894a0400a4a46ec4fd5442e06
3
+ size 43122580
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e4a508c210f3678665751554f93513b35d1e61d63a17e6d33014427fbafee0a
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628cca28b1004e5df2cd1ac61f3b999170f63104506de0b793960269005b0711
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
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
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": false,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": "<unk>",
39
+ "padding_side": "left",
40
+ "sp_model_kwargs": {},
41
+ "spaces_between_special_tokens": false,
42
+ "tokenizer_class": "LlamaTokenizer",
43
+ "unk_token": "<unk>",
44
+ "use_default_system_prompt": false
45
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,979 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2505843852267415,
5
+ "eval_steps": 134,
6
+ "global_step": 134,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0018700327255726976,
13
+ "grad_norm": 13.994741439819336,
14
+ "learning_rate": 2e-05,
15
+ "loss": 3.2962,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0037400654511453952,
20
+ "grad_norm": 16.602272033691406,
21
+ "learning_rate": 4e-05,
22
+ "loss": 3.6632,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.005610098176718092,
27
+ "grad_norm": 21.41153335571289,
28
+ "learning_rate": 6e-05,
29
+ "loss": 3.8852,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0074801309022907905,
34
+ "grad_norm": 15.502434730529785,
35
+ "learning_rate": 8e-05,
36
+ "loss": 3.8645,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.009350163627863487,
41
+ "grad_norm": 14.494356155395508,
42
+ "learning_rate": 0.0001,
43
+ "loss": 3.868,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.011220196353436185,
48
+ "grad_norm": 20.01993751525879,
49
+ "learning_rate": 0.00012,
50
+ "loss": 3.5737,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.013090229079008883,
55
+ "grad_norm": 14.023553848266602,
56
+ "learning_rate": 0.00014,
57
+ "loss": 3.2279,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.014960261804581581,
62
+ "grad_norm": 15.476705551147461,
63
+ "learning_rate": 0.00016,
64
+ "loss": 3.8968,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.016830294530154277,
69
+ "grad_norm": 14.212241172790527,
70
+ "learning_rate": 0.00018,
71
+ "loss": 3.401,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.018700327255726974,
76
+ "grad_norm": 14.703544616699219,
77
+ "learning_rate": 0.0002,
78
+ "loss": 3.4936,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.020570359981299673,
83
+ "grad_norm": 14.499024391174316,
84
+ "learning_rate": 0.00019999820960091608,
85
+ "loss": 2.5218,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.02244039270687237,
90
+ "grad_norm": 16.242597579956055,
91
+ "learning_rate": 0.00019999283846777488,
92
+ "loss": 3.0075,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.02431042543244507,
97
+ "grad_norm": 16.940950393676758,
98
+ "learning_rate": 0.00019998388679290583,
99
+ "loss": 2.8596,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.026180458158017766,
104
+ "grad_norm": 13.73834228515625,
105
+ "learning_rate": 0.00019997135489685034,
106
+ "loss": 3.0382,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.028050490883590462,
111
+ "grad_norm": 16.882173538208008,
112
+ "learning_rate": 0.00019995524322835034,
113
+ "loss": 3.4678,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.029920523609163162,
118
+ "grad_norm": 15.432026863098145,
119
+ "learning_rate": 0.00019993555236433213,
120
+ "loss": 3.4976,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.031790556334735855,
125
+ "grad_norm": 16.355684280395508,
126
+ "learning_rate": 0.00019991228300988585,
127
+ "loss": 3.3903,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.033660589060308554,
132
+ "grad_norm": 13.33781909942627,
133
+ "learning_rate": 0.00019988543599824005,
134
+ "loss": 3.1913,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.035530621785881254,
139
+ "grad_norm": 18.799007415771484,
140
+ "learning_rate": 0.0001998550122907321,
141
+ "loss": 3.2008,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.03740065451145395,
146
+ "grad_norm": 13.545116424560547,
147
+ "learning_rate": 0.0001998210129767735,
148
+ "loss": 2.8425,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.03927068723702665,
153
+ "grad_norm": 14.966565132141113,
154
+ "learning_rate": 0.00019978343927381113,
155
+ "loss": 2.8036,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.04114071996259935,
160
+ "grad_norm": 17.932737350463867,
161
+ "learning_rate": 0.00019974229252728342,
162
+ "loss": 2.9432,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.043010752688172046,
167
+ "grad_norm": 16.62327766418457,
168
+ "learning_rate": 0.0001996975742105723,
169
+ "loss": 3.0234,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.04488078541374474,
174
+ "grad_norm": 17.949251174926758,
175
+ "learning_rate": 0.00019964928592495045,
176
+ "loss": 3.0715,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.04675081813931744,
181
+ "grad_norm": 18.255725860595703,
182
+ "learning_rate": 0.00019959742939952392,
183
+ "loss": 3.155,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.04862085086489014,
188
+ "grad_norm": 22.37006187438965,
189
+ "learning_rate": 0.0001995420064911702,
190
+ "loss": 3.0856,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.05049088359046283,
195
+ "grad_norm": 23.708791732788086,
196
+ "learning_rate": 0.00019948301918447183,
197
+ "loss": 3.1826,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.05236091631603553,
202
+ "grad_norm": 21.139902114868164,
203
+ "learning_rate": 0.00019942046959164515,
204
+ "loss": 3.1289,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.05423094904160823,
209
+ "grad_norm": 18.88515281677246,
210
+ "learning_rate": 0.0001993543599524649,
211
+ "loss": 3.2124,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.056100981767180924,
216
+ "grad_norm": 22.860271453857422,
217
+ "learning_rate": 0.00019928469263418374,
218
+ "loss": 3.1165,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.057971014492753624,
223
+ "grad_norm": 25.16404151916504,
224
+ "learning_rate": 0.0001992114701314478,
225
+ "loss": 3.6229,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.059841047218326324,
230
+ "grad_norm": 20.945270538330078,
231
+ "learning_rate": 0.00019913469506620707,
232
+ "loss": 3.2879,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.061711079943899017,
237
+ "grad_norm": 19.237075805664062,
238
+ "learning_rate": 0.0001990543701876217,
239
+ "loss": 2.9019,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.06358111266947171,
244
+ "grad_norm": 21.761228561401367,
245
+ "learning_rate": 0.0001989704983719635,
246
+ "loss": 2.7975,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.06545114539504442,
251
+ "grad_norm": 18.43031120300293,
252
+ "learning_rate": 0.00019888308262251285,
253
+ "loss": 2.6259,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.06732117812061711,
258
+ "grad_norm": 29.478282928466797,
259
+ "learning_rate": 0.00019879212606945136,
260
+ "loss": 3.4395,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.0691912108461898,
265
+ "grad_norm": 20.588619232177734,
266
+ "learning_rate": 0.00019869763196974957,
267
+ "loss": 2.4942,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.07106124357176251,
272
+ "grad_norm": 25.75873374938965,
273
+ "learning_rate": 0.0001985996037070505,
274
+ "loss": 3.6293,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.0729312762973352,
279
+ "grad_norm": 23.140533447265625,
280
+ "learning_rate": 0.00019849804479154837,
281
+ "loss": 2.928,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.0748013090229079,
286
+ "grad_norm": 25.42648696899414,
287
+ "learning_rate": 0.00019839295885986296,
288
+ "loss": 3.1603,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.0766713417484806,
293
+ "grad_norm": 25.744718551635742,
294
+ "learning_rate": 0.00019828434967490943,
295
+ "loss": 3.3389,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.0785413744740533,
300
+ "grad_norm": 39.95504379272461,
301
+ "learning_rate": 0.0001981722211257634,
302
+ "loss": 3.6146,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.08041140719962599,
307
+ "grad_norm": 32.589569091796875,
308
+ "learning_rate": 0.00019805657722752202,
309
+ "loss": 2.9932,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.0822814399251987,
314
+ "grad_norm": 48.44812774658203,
315
+ "learning_rate": 0.00019793742212115978,
316
+ "loss": 3.2977,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.08415147265077139,
321
+ "grad_norm": 46.82399368286133,
322
+ "learning_rate": 0.00019781476007338058,
323
+ "loss": 3.3127,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.08602150537634409,
328
+ "grad_norm": 35.45515441894531,
329
+ "learning_rate": 0.00019768859547646478,
330
+ "loss": 3.409,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.08789153810191679,
335
+ "grad_norm": 28.829622268676758,
336
+ "learning_rate": 0.00019755893284811196,
337
+ "loss": 3.4779,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.08976157082748948,
342
+ "grad_norm": 42.49812316894531,
343
+ "learning_rate": 0.00019742577683127911,
344
+ "loss": 3.7014,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.09163160355306219,
349
+ "grad_norm": 77.00621795654297,
350
+ "learning_rate": 0.0001972891321940145,
351
+ "loss": 5.1841,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.09350163627863488,
356
+ "grad_norm": 46.6325798034668,
357
+ "learning_rate": 0.00019714900382928675,
358
+ "loss": 3.8944,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.09537166900420757,
363
+ "grad_norm": 118.46067810058594,
364
+ "learning_rate": 0.0001970053967548098,
365
+ "loss": 5.2813,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.09724170172978028,
370
+ "grad_norm": 94.66202545166016,
371
+ "learning_rate": 0.0001968583161128631,
372
+ "loss": 4.5682,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.09911173445535297,
377
+ "grad_norm": 60.450828552246094,
378
+ "learning_rate": 0.00019670776717010767,
379
+ "loss": 3.9013,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.10098176718092566,
384
+ "grad_norm": 25.923925399780273,
385
+ "learning_rate": 0.0001965537553173972,
386
+ "loss": 3.6057,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.10285179990649837,
391
+ "grad_norm": 14.4677152633667,
392
+ "learning_rate": 0.00019639628606958533,
393
+ "loss": 3.0911,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.10472183263207106,
398
+ "grad_norm": 12.290410041809082,
399
+ "learning_rate": 0.000196235365065328,
400
+ "loss": 2.6739,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.10659186535764376,
405
+ "grad_norm": 14.281597137451172,
406
+ "learning_rate": 0.0001960709980668816,
407
+ "loss": 2.8039,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.10846189808321646,
412
+ "grad_norm": 12.305088996887207,
413
+ "learning_rate": 0.0001959031909598966,
414
+ "loss": 2.8797,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.11033193080878916,
419
+ "grad_norm": 12.407671928405762,
420
+ "learning_rate": 0.00019573194975320673,
421
+ "loss": 2.402,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.11220196353436185,
426
+ "grad_norm": 12.547879219055176,
427
+ "learning_rate": 0.0001955572805786141,
428
+ "loss": 2.5572,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.11407199625993455,
433
+ "grad_norm": 15.23267650604248,
434
+ "learning_rate": 0.0001953791896906692,
435
+ "loss": 3.1069,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.11594202898550725,
440
+ "grad_norm": 14.644232749938965,
441
+ "learning_rate": 0.00019519768346644737,
442
+ "loss": 2.4441,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.11781206171107994,
447
+ "grad_norm": 14.574198722839355,
448
+ "learning_rate": 0.00019501276840532016,
449
+ "loss": 3.1865,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.11968209443665265,
454
+ "grad_norm": 15.284114837646484,
455
+ "learning_rate": 0.00019482445112872264,
456
+ "loss": 2.7122,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.12155212716222534,
461
+ "grad_norm": 14.484579086303711,
462
+ "learning_rate": 0.00019463273837991643,
463
+ "loss": 2.9405,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.12342215988779803,
468
+ "grad_norm": 13.775676727294922,
469
+ "learning_rate": 0.00019443763702374812,
470
+ "loss": 2.8403,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.12529219261337074,
475
+ "grad_norm": 14.479483604431152,
476
+ "learning_rate": 0.0001942391540464035,
477
+ "loss": 2.9306,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.12716222533894342,
482
+ "grad_norm": 13.77834701538086,
483
+ "learning_rate": 0.00019403729655515737,
484
+ "loss": 2.7441,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.12903225806451613,
489
+ "grad_norm": 17.22318458557129,
490
+ "learning_rate": 0.0001938320717781191,
491
+ "loss": 2.793,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.13090229079008883,
496
+ "grad_norm": 14.486649513244629,
497
+ "learning_rate": 0.00019362348706397373,
498
+ "loss": 2.8446,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.1327723235156615,
503
+ "grad_norm": 19.49801254272461,
504
+ "learning_rate": 0.0001934115498817189,
505
+ "loss": 3.0295,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.13464235624123422,
510
+ "grad_norm": 17.23444938659668,
511
+ "learning_rate": 0.00019319626782039734,
512
+ "loss": 2.9814,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.13651238896680692,
517
+ "grad_norm": 18.949792861938477,
518
+ "learning_rate": 0.00019297764858882514,
519
+ "loss": 3.0234,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.1383824216923796,
524
+ "grad_norm": 18.541202545166016,
525
+ "learning_rate": 0.00019275570001531578,
526
+ "loss": 3.1777,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.1402524544179523,
531
+ "grad_norm": 21.238248825073242,
532
+ "learning_rate": 0.00019253043004739968,
533
+ "loss": 3.677,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.14212248714352502,
538
+ "grad_norm": 24.113332748413086,
539
+ "learning_rate": 0.00019230184675153976,
540
+ "loss": 3.2631,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.1439925198690977,
545
+ "grad_norm": 17.838098526000977,
546
+ "learning_rate": 0.00019206995831284242,
547
+ "loss": 2.728,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.1458625525946704,
552
+ "grad_norm": 18.885387420654297,
553
+ "learning_rate": 0.00019183477303476467,
554
+ "loss": 2.9679,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.1477325853202431,
559
+ "grad_norm": 19.87195587158203,
560
+ "learning_rate": 0.00019159629933881666,
561
+ "loss": 2.9025,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.1496026180458158,
566
+ "grad_norm": 19.265392303466797,
567
+ "learning_rate": 0.0001913545457642601,
568
+ "loss": 3.4623,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.1514726507713885,
573
+ "grad_norm": 19.50520133972168,
574
+ "learning_rate": 0.00019110952096780258,
575
+ "loss": 3.1419,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.1533426834969612,
580
+ "grad_norm": 20.407455444335938,
581
+ "learning_rate": 0.00019086123372328746,
582
+ "loss": 2.5145,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.15521271622253388,
587
+ "grad_norm": 42.79829788208008,
588
+ "learning_rate": 0.00019060969292137992,
589
+ "loss": 3.0625,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.1570827489481066,
594
+ "grad_norm": 20.8466796875,
595
+ "learning_rate": 0.00019035490756924832,
596
+ "loss": 2.9626,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.1589527816736793,
601
+ "grad_norm": 21.628929138183594,
602
+ "learning_rate": 0.0001900968867902419,
603
+ "loss": 2.8822,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.16082281439925197,
608
+ "grad_norm": 29.18246078491211,
609
+ "learning_rate": 0.00018983563982356405,
610
+ "loss": 3.4651,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.16269284712482468,
615
+ "grad_norm": 26.07509422302246,
616
+ "learning_rate": 0.0001895711760239413,
617
+ "loss": 3.0619,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.1645628798503974,
622
+ "grad_norm": 39.00653076171875,
623
+ "learning_rate": 0.00018930350486128856,
624
+ "loss": 3.1362,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.16643291257597007,
629
+ "grad_norm": 23.455015182495117,
630
+ "learning_rate": 0.00018903263592036989,
631
+ "loss": 3.4385,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.16830294530154277,
636
+ "grad_norm": 29.16703224182129,
637
+ "learning_rate": 0.00018875857890045543,
638
+ "loss": 3.1283,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.17017297802711548,
643
+ "grad_norm": 29.75694465637207,
644
+ "learning_rate": 0.00018848134361497385,
645
+ "loss": 3.0399,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.17204301075268819,
650
+ "grad_norm": 28.572084426879883,
651
+ "learning_rate": 0.00018820093999116124,
652
+ "loss": 3.8989,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.17391304347826086,
657
+ "grad_norm": 50.12794876098633,
658
+ "learning_rate": 0.00018791737806970538,
659
+ "loss": 3.6389,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.17578307620383357,
664
+ "grad_norm": 23.859804153442383,
665
+ "learning_rate": 0.00018763066800438636,
666
+ "loss": 3.1504,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.17765310892940628,
671
+ "grad_norm": 44.48038864135742,
672
+ "learning_rate": 0.00018734082006171299,
673
+ "loss": 3.1353,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.17952314165497896,
678
+ "grad_norm": 26.45856475830078,
679
+ "learning_rate": 0.00018704784462055503,
680
+ "loss": 2.7182,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.18139317438055166,
685
+ "grad_norm": 30.120588302612305,
686
+ "learning_rate": 0.00018675175217177175,
687
+ "loss": 3.6129,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.18326320710612437,
692
+ "grad_norm": 61.866886138916016,
693
+ "learning_rate": 0.00018645255331783617,
694
+ "loss": 5.1282,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.18513323983169705,
699
+ "grad_norm": 39.70136260986328,
700
+ "learning_rate": 0.00018615025877245523,
701
+ "loss": 3.8535,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.18700327255726976,
706
+ "grad_norm": 51.10054397583008,
707
+ "learning_rate": 0.00018584487936018661,
708
+ "loss": 3.8204,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.18887330528284246,
713
+ "grad_norm": 160.09117126464844,
714
+ "learning_rate": 0.00018553642601605068,
715
+ "loss": 5.7671,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.19074333800841514,
720
+ "grad_norm": 126.96265411376953,
721
+ "learning_rate": 0.0001852249097851391,
722
+ "loss": 5.543,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.19261337073398785,
727
+ "grad_norm": 79.90239715576172,
728
+ "learning_rate": 0.0001849103418222194,
729
+ "loss": 4.1758,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.19448340345956056,
734
+ "grad_norm": 48.66373062133789,
735
+ "learning_rate": 0.00018459273339133537,
736
+ "loss": 3.4729,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.19635343618513323,
741
+ "grad_norm": 31.121978759765625,
742
+ "learning_rate": 0.0001842720958654039,
743
+ "loss": 3.2988,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.19822346891070594,
748
+ "grad_norm": 15.884181022644043,
749
+ "learning_rate": 0.00018394844072580773,
750
+ "loss": 3.4934,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.20009350163627865,
755
+ "grad_norm": 13.574240684509277,
756
+ "learning_rate": 0.00018362177956198408,
757
+ "loss": 2.6176,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.20196353436185133,
762
+ "grad_norm": 11.254271507263184,
763
+ "learning_rate": 0.00018329212407100994,
764
+ "loss": 2.3752,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.20383356708742403,
769
+ "grad_norm": 11.554123878479004,
770
+ "learning_rate": 0.00018295948605718314,
771
+ "loss": 2.295,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.20570359981299674,
776
+ "grad_norm": 11.747841835021973,
777
+ "learning_rate": 0.0001826238774315995,
778
+ "loss": 2.378,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.20757363253856942,
783
+ "grad_norm": 13.485661506652832,
784
+ "learning_rate": 0.00018228531021172658,
785
+ "loss": 2.6167,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.20944366526414213,
790
+ "grad_norm": 12.09218692779541,
791
+ "learning_rate": 0.0001819437965209732,
792
+ "loss": 2.1478,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.21131369798971483,
797
+ "grad_norm": 15.334200859069824,
798
+ "learning_rate": 0.0001815993485882553,
799
+ "loss": 2.7231,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.2131837307152875,
804
+ "grad_norm": 14.982645988464355,
805
+ "learning_rate": 0.0001812519787475582,
806
+ "loss": 2.7762,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.21505376344086022,
811
+ "grad_norm": 15.121198654174805,
812
+ "learning_rate": 0.00018090169943749476,
813
+ "loss": 2.6204,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.21692379616643293,
818
+ "grad_norm": 12.098959922790527,
819
+ "learning_rate": 0.0001805485232008601,
820
+ "loss": 2.6039,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.2187938288920056,
825
+ "grad_norm": 13.73119068145752,
826
+ "learning_rate": 0.0001801924626841824,
827
+ "loss": 2.7469,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.2206638616175783,
832
+ "grad_norm": 14.34265422821045,
833
+ "learning_rate": 0.00017983353063727016,
834
+ "loss": 3.0645,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.22253389434315102,
839
+ "grad_norm": 13.765779495239258,
840
+ "learning_rate": 0.00017947173991275555,
841
+ "loss": 3.014,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.2244039270687237,
846
+ "grad_norm": 17.305545806884766,
847
+ "learning_rate": 0.00017910710346563416,
848
+ "loss": 2.9139,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.2262739597942964,
853
+ "grad_norm": 13.76815414428711,
854
+ "learning_rate": 0.00017873963435280121,
855
+ "loss": 2.6729,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.2281439925198691,
860
+ "grad_norm": 16.517879486083984,
861
+ "learning_rate": 0.000178369345732584,
862
+ "loss": 3.1773,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.2300140252454418,
867
+ "grad_norm": 18.648420333862305,
868
+ "learning_rate": 0.00017799625086427064,
869
+ "loss": 3.5063,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.2318840579710145,
874
+ "grad_norm": 19.074386596679688,
875
+ "learning_rate": 0.00017762036310763532,
876
+ "loss": 2.743,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.2337540906965872,
881
+ "grad_norm": 16.391334533691406,
882
+ "learning_rate": 0.00017724169592245995,
883
+ "loss": 2.7288,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.23562412342215988,
888
+ "grad_norm": 26.434553146362305,
889
+ "learning_rate": 0.0001768602628680522,
890
+ "loss": 2.6386,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.2374941561477326,
895
+ "grad_norm": 18.820554733276367,
896
+ "learning_rate": 0.00017647607760275987,
897
+ "loss": 3.3189,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.2393641888733053,
902
+ "grad_norm": 18.246240615844727,
903
+ "learning_rate": 0.00017608915388348187,
904
+ "loss": 2.9794,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.24123422159887797,
909
+ "grad_norm": 24.38311004638672,
910
+ "learning_rate": 0.00017569950556517566,
911
+ "loss": 2.9017,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.24310425432445068,
916
+ "grad_norm": 17.729557037353516,
917
+ "learning_rate": 0.00017530714660036112,
918
+ "loss": 2.7735,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.2449742870500234,
923
+ "grad_norm": 20.780271530151367,
924
+ "learning_rate": 0.00017491209103862084,
925
+ "loss": 3.2586,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.24684431977559607,
930
+ "grad_norm": 25.706838607788086,
931
+ "learning_rate": 0.00017451435302609714,
932
+ "loss": 2.9574,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.24871435250116877,
937
+ "grad_norm": 17.675687789916992,
938
+ "learning_rate": 0.0001741139468049855,
939
+ "loss": 2.6356,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.2505843852267415,
944
+ "grad_norm": 23.035436630249023,
945
+ "learning_rate": 0.0001737108867130245,
946
+ "loss": 3.3455,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.2505843852267415,
951
+ "eval_loss": 3.025357723236084,
952
+ "eval_runtime": 12.856,
953
+ "eval_samples_per_second": 17.579,
954
+ "eval_steps_per_second": 8.79,
955
+ "step": 134
956
+ }
957
+ ],
958
+ "logging_steps": 1,
959
+ "max_steps": 535,
960
+ "num_input_tokens_seen": 0,
961
+ "num_train_epochs": 2,
962
+ "save_steps": 134,
963
+ "stateful_callbacks": {
964
+ "TrainerControl": {
965
+ "args": {
966
+ "should_epoch_stop": false,
967
+ "should_evaluate": false,
968
+ "should_log": false,
969
+ "should_save": true,
970
+ "should_training_stop": false
971
+ },
972
+ "attributes": {}
973
+ }
974
+ },
975
+ "total_flos": 4.697155026341069e+16,
976
+ "train_batch_size": 2,
977
+ "trial_name": null,
978
+ "trial_params": null
979
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47654faf524d1c2d1e4ce0fa3635e3452c174b5ceb9abe83e440c9172e9f9189
3
+ size 6904