jssky commited on
Commit
8c07a24
·
verified ·
1 Parent(s): bd9ea5f

Training in progress, step 296, checkpoint

Browse files
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: EleutherAI/gpt-neo-125m
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 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "EleutherAI/gpt-neo-125m",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
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": [
21
+ "lm_head"
22
+ ],
23
+ "peft_type": "LORA",
24
+ "r": 8,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "q_proj",
29
+ "k_proj",
30
+ "v_proj",
31
+ "c_proj",
32
+ "out_proj",
33
+ "c_fc"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "use_dora": false,
37
+ "use_rslora": true
38
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24e32063049d3a3838fc15c4bf394695c77dbba016fe6e4547f94bd4937a8b0
3
+ size 82522352
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904d6692de88e33977e32221223204db58bb21cd178eae6076b7d10f63fddca6
3
+ size 81259962
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d2f6e70ef208bc0c59df217a9b7e70b22d34e13f643ce82ed52acdeed8bfad9
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d546be25cc701a57cf0d987af463b0388c18919d24648dae3f64261208cfdc35
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
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_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "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 %}",
16
+ "clean_up_tokenization_spaces": true,
17
+ "eos_token": "<|endoftext|>",
18
+ "errors": "replace",
19
+ "model_max_length": 2048,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,2113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.250515736577625,
5
+ "eval_steps": 296,
6
+ "global_step": 296,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0008463369478973816,
13
+ "grad_norm": 74.46723937988281,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.686,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0016926738957947632,
20
+ "grad_norm": 87.14585876464844,
21
+ "learning_rate": 4e-05,
22
+ "loss": 1.9316,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0025390108436921448,
27
+ "grad_norm": 125.84043884277344,
28
+ "learning_rate": 6e-05,
29
+ "loss": 2.756,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0033853477915895265,
34
+ "grad_norm": 158.6361541748047,
35
+ "learning_rate": 8e-05,
36
+ "loss": 3.2544,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.004231684739486909,
41
+ "grad_norm": 193.18316650390625,
42
+ "learning_rate": 0.0001,
43
+ "loss": 3.7347,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.0050780216873842895,
48
+ "grad_norm": 168.4342803955078,
49
+ "learning_rate": 0.00012,
50
+ "loss": 3.0451,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.005924358635281671,
55
+ "grad_norm": 135.61651611328125,
56
+ "learning_rate": 0.00014,
57
+ "loss": 2.0432,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.006770695583179053,
62
+ "grad_norm": 133.69590759277344,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.9678,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.007617032531076435,
69
+ "grad_norm": 138.0289764404297,
70
+ "learning_rate": 0.00018,
71
+ "loss": 1.931,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.008463369478973817,
76
+ "grad_norm": 161.1634063720703,
77
+ "learning_rate": 0.0002,
78
+ "loss": 2.0495,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.009309706426871197,
83
+ "grad_norm": 136.35235595703125,
84
+ "learning_rate": 0.00019999964073553233,
85
+ "loss": 1.733,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.010156043374768579,
90
+ "grad_norm": 103.60092163085938,
91
+ "learning_rate": 0.0001999985629447107,
92
+ "loss": 1.4056,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.01100238032266596,
97
+ "grad_norm": 83.1572494506836,
98
+ "learning_rate": 0.0001999967666352794,
99
+ "loss": 1.2848,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.011848717270563342,
104
+ "grad_norm": 94.966552734375,
105
+ "learning_rate": 0.0001999942518201454,
106
+ "loss": 1.237,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.012695054218460724,
111
+ "grad_norm": 98.76087951660156,
112
+ "learning_rate": 0.0001999910185173784,
113
+ "loss": 1.1532,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.013541391166358106,
118
+ "grad_norm": 80.15461730957031,
119
+ "learning_rate": 0.00019998706675021052,
120
+ "loss": 0.8821,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.014387728114255488,
125
+ "grad_norm": 79.4908218383789,
126
+ "learning_rate": 0.00019998239654703647,
127
+ "loss": 0.8409,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.01523406506215287,
132
+ "grad_norm": 60.96306228637695,
133
+ "learning_rate": 0.000199977007941413,
134
+ "loss": 0.5869,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.016080402010050253,
139
+ "grad_norm": 45.81327819824219,
140
+ "learning_rate": 0.00019997090097205873,
141
+ "loss": 0.4739,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.016926738957947635,
146
+ "grad_norm": 62.55532455444336,
147
+ "learning_rate": 0.000199964075682854,
148
+ "loss": 0.4032,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.017773075905845013,
153
+ "grad_norm": 105.0770034790039,
154
+ "learning_rate": 0.00019995653212284063,
155
+ "loss": 0.378,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.018619412853742395,
160
+ "grad_norm": 99.4818344116211,
161
+ "learning_rate": 0.0001999482703462211,
162
+ "loss": 0.3709,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.019465749801639776,
167
+ "grad_norm": 102.58175659179688,
168
+ "learning_rate": 0.00019993929041235874,
169
+ "loss": 0.3393,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.020312086749537158,
174
+ "grad_norm": 84.75938415527344,
175
+ "learning_rate": 0.00019992959238577705,
176
+ "loss": 0.2595,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.02115842369743454,
181
+ "grad_norm": 35.45841979980469,
182
+ "learning_rate": 0.000199919176336159,
183
+ "loss": 0.2684,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.02200476064533192,
188
+ "grad_norm": 43.51015090942383,
189
+ "learning_rate": 0.00019990804233834705,
190
+ "loss": 0.1653,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.022851097593229303,
195
+ "grad_norm": 57.4715576171875,
196
+ "learning_rate": 0.00019989619047234216,
197
+ "loss": 0.1699,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.023697434541126685,
202
+ "grad_norm": 45.49979782104492,
203
+ "learning_rate": 0.0001998836208233034,
204
+ "loss": 0.1342,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.024543771489024067,
209
+ "grad_norm": 48.7567138671875,
210
+ "learning_rate": 0.0001998703334815473,
211
+ "loss": 0.2004,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.02539010843692145,
216
+ "grad_norm": 22.59009552001953,
217
+ "learning_rate": 0.00019985632854254735,
218
+ "loss": 0.1187,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.02623644538481883,
223
+ "grad_norm": 42.264198303222656,
224
+ "learning_rate": 0.00019984160610693303,
225
+ "loss": 0.1624,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.027082782332716212,
230
+ "grad_norm": 66.26699829101562,
231
+ "learning_rate": 0.0001998261662804893,
232
+ "loss": 0.1597,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.027929119280613594,
237
+ "grad_norm": 51.72114944458008,
238
+ "learning_rate": 0.00019981000917415577,
239
+ "loss": 0.1137,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.028775456228510975,
244
+ "grad_norm": 31.176406860351562,
245
+ "learning_rate": 0.00019979313490402597,
246
+ "loss": 0.0776,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.029621793176408357,
251
+ "grad_norm": 19.646127700805664,
252
+ "learning_rate": 0.00019977554359134638,
253
+ "loss": 0.1053,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.03046813012430574,
258
+ "grad_norm": 32.98014831542969,
259
+ "learning_rate": 0.00019975723536251567,
260
+ "loss": 0.0493,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.031314467072203124,
265
+ "grad_norm": 24.1268310546875,
266
+ "learning_rate": 0.00019973821034908375,
267
+ "loss": 0.0692,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.032160804020100506,
272
+ "grad_norm": 15.55493450164795,
273
+ "learning_rate": 0.0001997184686877509,
274
+ "loss": 0.0543,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.03300714096799789,
279
+ "grad_norm": 18.887033462524414,
280
+ "learning_rate": 0.0001996980105203666,
281
+ "loss": 0.0275,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.03385347791589527,
286
+ "grad_norm": 10.44262981414795,
287
+ "learning_rate": 0.00019967683599392876,
288
+ "loss": 0.0162,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.034699814863792644,
293
+ "grad_norm": 8.52265739440918,
294
+ "learning_rate": 0.00019965494526058246,
295
+ "loss": 0.0245,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.035546151811690026,
300
+ "grad_norm": 11.946599960327148,
301
+ "learning_rate": 0.00019963233847761894,
302
+ "loss": 0.028,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.03639248875958741,
307
+ "grad_norm": 6.178277015686035,
308
+ "learning_rate": 0.00019960901580747448,
309
+ "loss": 0.013,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.03723882570748479,
314
+ "grad_norm": 5.187213897705078,
315
+ "learning_rate": 0.00019958497741772924,
316
+ "loss": 0.0104,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.03808516265538217,
321
+ "grad_norm": 3.2645328044891357,
322
+ "learning_rate": 0.00019956022348110596,
323
+ "loss": 0.0089,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.03893149960327955,
328
+ "grad_norm": 1.7075039148330688,
329
+ "learning_rate": 0.0001995347541754689,
330
+ "loss": 0.0052,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.039777836551176934,
335
+ "grad_norm": 3.5826594829559326,
336
+ "learning_rate": 0.00019950856968382232,
337
+ "loss": 0.0092,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.040624173499074316,
342
+ "grad_norm": 4.57949686050415,
343
+ "learning_rate": 0.00019948167019430941,
344
+ "loss": 0.0084,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.0414705104469717,
349
+ "grad_norm": 13.784544944763184,
350
+ "learning_rate": 0.0001994540559002108,
351
+ "loss": 0.0308,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.04231684739486908,
356
+ "grad_norm": 34.07741165161133,
357
+ "learning_rate": 0.0001994257269999431,
358
+ "loss": 0.0469,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.04316318434276646,
363
+ "grad_norm": 31.998857498168945,
364
+ "learning_rate": 0.00019939668369705778,
365
+ "loss": 0.4136,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.04400952129066384,
370
+ "grad_norm": 44.679222106933594,
371
+ "learning_rate": 0.00019936692620023928,
372
+ "loss": 0.4861,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.044855858238561225,
377
+ "grad_norm": 59.955745697021484,
378
+ "learning_rate": 0.00019933645472330387,
379
+ "loss": 0.7331,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.045702195186458607,
384
+ "grad_norm": 62.51538848876953,
385
+ "learning_rate": 0.00019930526948519793,
386
+ "loss": 0.5997,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.04654853213435599,
391
+ "grad_norm": 71.37804412841797,
392
+ "learning_rate": 0.0001992733707099964,
393
+ "loss": 0.6939,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.04739486908225337,
398
+ "grad_norm": 84.57373046875,
399
+ "learning_rate": 0.00019924075862690118,
400
+ "loss": 0.1067,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.04824120603015075,
405
+ "grad_norm": 84.29151916503906,
406
+ "learning_rate": 0.00019920743347023957,
407
+ "loss": 0.1359,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.04908754297804813,
412
+ "grad_norm": 67.71774291992188,
413
+ "learning_rate": 0.00019917339547946246,
414
+ "loss": 0.143,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.049933879925945515,
419
+ "grad_norm": 48.20841979980469,
420
+ "learning_rate": 0.00019913864489914268,
421
+ "loss": 0.101,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.0507802168738429,
426
+ "grad_norm": 51.68072509765625,
427
+ "learning_rate": 0.00019910318197897319,
428
+ "loss": 0.0844,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.05162655382174028,
433
+ "grad_norm": 46.60186767578125,
434
+ "learning_rate": 0.00019906700697376527,
435
+ "loss": 0.0648,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.05247289076963766,
440
+ "grad_norm": 27.53974723815918,
441
+ "learning_rate": 0.00019903012014344686,
442
+ "loss": 0.0393,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.05331922771753504,
447
+ "grad_norm": 6.218672752380371,
448
+ "learning_rate": 0.0001989925217530605,
449
+ "loss": 0.0125,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.054165564665432424,
454
+ "grad_norm": 6.7888360023498535,
455
+ "learning_rate": 0.00019895421207276155,
456
+ "loss": 0.0133,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.055011901613329806,
461
+ "grad_norm": 7.5940961837768555,
462
+ "learning_rate": 0.00019891519137781608,
463
+ "loss": 0.0106,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.05585823856122719,
468
+ "grad_norm": 5.461939811706543,
469
+ "learning_rate": 0.0001988754599485991,
470
+ "loss": 0.0087,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.05670457550912457,
475
+ "grad_norm": 6.9425740242004395,
476
+ "learning_rate": 0.0001988350180705924,
477
+ "loss": 0.0174,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.05755091245702195,
482
+ "grad_norm": 6.4617533683776855,
483
+ "learning_rate": 0.00019879386603438261,
484
+ "loss": 0.0103,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.05839724940491933,
489
+ "grad_norm": 8.377887725830078,
490
+ "learning_rate": 0.00019875200413565903,
491
+ "loss": 0.0095,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.059243586352816714,
496
+ "grad_norm": 4.740405559539795,
497
+ "learning_rate": 0.00019870943267521145,
498
+ "loss": 0.005,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.060089923300714096,
503
+ "grad_norm": 1.870723843574524,
504
+ "learning_rate": 0.0001986661519589282,
505
+ "loss": 0.0049,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.06093626024861148,
510
+ "grad_norm": 2.44498872756958,
511
+ "learning_rate": 0.0001986221622977937,
512
+ "loss": 0.0043,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.06178259719650886,
517
+ "grad_norm": 6.047572612762451,
518
+ "learning_rate": 0.00019857746400788644,
519
+ "loss": 0.01,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.06262893414440625,
524
+ "grad_norm": 8.071754455566406,
525
+ "learning_rate": 0.00019853205741037652,
526
+ "loss": 0.0172,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.06347527109230362,
531
+ "grad_norm": 8.4547700881958,
532
+ "learning_rate": 0.00019848594283152353,
533
+ "loss": 0.0116,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.06432160804020101,
538
+ "grad_norm": 2.2582836151123047,
539
+ "learning_rate": 0.00019843912060267402,
540
+ "loss": 0.0038,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.06516794498809839,
545
+ "grad_norm": 2.5930304527282715,
546
+ "learning_rate": 0.0001983915910602593,
547
+ "loss": 0.0048,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.06601428193599577,
552
+ "grad_norm": 7.182027339935303,
553
+ "learning_rate": 0.0001983433545457928,
554
+ "loss": 0.0151,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.06686061888389315,
559
+ "grad_norm": 4.962230682373047,
560
+ "learning_rate": 0.00019829441140586793,
561
+ "loss": 0.008,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.06770695583179054,
566
+ "grad_norm": 3.9201576709747314,
567
+ "learning_rate": 0.00019824476199215525,
568
+ "loss": 0.0054,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.06855329277968791,
573
+ "grad_norm": 9.251102447509766,
574
+ "learning_rate": 0.0001981944066614002,
575
+ "loss": 0.0057,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.06939962972758529,
580
+ "grad_norm": 0.8075349926948547,
581
+ "learning_rate": 0.00019814334577542038,
582
+ "loss": 0.0018,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.07024596667548268,
587
+ "grad_norm": 5.284769535064697,
588
+ "learning_rate": 0.00019809157970110302,
589
+ "loss": 0.0031,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.07109230362338005,
594
+ "grad_norm": 7.295186996459961,
595
+ "learning_rate": 0.0001980391088104024,
596
+ "loss": 0.015,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.07193864057127744,
601
+ "grad_norm": 3.265753984451294,
602
+ "learning_rate": 0.00019798593348033697,
603
+ "loss": 0.0034,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.07278497751917481,
608
+ "grad_norm": 0.6690754890441895,
609
+ "learning_rate": 0.00019793205409298693,
610
+ "loss": 0.0017,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.0736313144670722,
615
+ "grad_norm": 2.377958059310913,
616
+ "learning_rate": 0.00019787747103549124,
617
+ "loss": 0.0022,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.07447765141496958,
622
+ "grad_norm": 3.079671621322632,
623
+ "learning_rate": 0.00019782218470004498,
624
+ "loss": 0.0049,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.07532398836286697,
629
+ "grad_norm": 0.35262423753738403,
630
+ "learning_rate": 0.00019776619548389642,
631
+ "loss": 0.001,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.07617032531076434,
636
+ "grad_norm": 0.8201667666435242,
637
+ "learning_rate": 0.00019770950378934435,
638
+ "loss": 0.0019,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.07701666225866173,
643
+ "grad_norm": 0.3472432792186737,
644
+ "learning_rate": 0.00019765211002373493,
645
+ "loss": 0.0012,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.0778629992065591,
650
+ "grad_norm": 1.4362425804138184,
651
+ "learning_rate": 0.00019759401459945898,
652
+ "loss": 0.0019,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.0787093361544565,
657
+ "grad_norm": 1.478244662284851,
658
+ "learning_rate": 0.000197535217933949,
659
+ "loss": 0.0024,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.07955567310235387,
664
+ "grad_norm": 4.533934116363525,
665
+ "learning_rate": 0.000197475720449676,
666
+ "loss": 0.0036,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.08040201005025126,
671
+ "grad_norm": 0.8504026532173157,
672
+ "learning_rate": 0.00019741552257414663,
673
+ "loss": 0.0015,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.08124834699814863,
678
+ "grad_norm": 2.9103963375091553,
679
+ "learning_rate": 0.00019735462473989998,
680
+ "loss": 0.0046,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.08209468394604602,
685
+ "grad_norm": 2.422717571258545,
686
+ "learning_rate": 0.0001972930273845047,
687
+ "loss": 0.0032,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.0829410208939434,
692
+ "grad_norm": 1.085134744644165,
693
+ "learning_rate": 0.00019723073095055557,
694
+ "loss": 0.0018,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.08378735784184078,
699
+ "grad_norm": 2.692281484603882,
700
+ "learning_rate": 0.00019716773588567053,
701
+ "loss": 0.0039,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.08463369478973816,
706
+ "grad_norm": 1.1898086071014404,
707
+ "learning_rate": 0.0001971040426424873,
708
+ "loss": 0.0016,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.08548003173763555,
713
+ "grad_norm": 23.142412185668945,
714
+ "learning_rate": 0.0001970396516786603,
715
+ "loss": 0.3362,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.08632636868553292,
720
+ "grad_norm": 26.89776039123535,
721
+ "learning_rate": 0.0001969745634568572,
722
+ "loss": 0.4391,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.08717270563343031,
727
+ "grad_norm": 27.5157470703125,
728
+ "learning_rate": 0.00019690877844475574,
729
+ "loss": 0.391,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.08801904258132769,
734
+ "grad_norm": 54.70764923095703,
735
+ "learning_rate": 0.00019684229711504025,
736
+ "loss": 0.637,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.08886537952922507,
741
+ "grad_norm": 93.04987335205078,
742
+ "learning_rate": 0.0001967751199453983,
743
+ "loss": 0.988,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.08971171647712245,
748
+ "grad_norm": 55.99843978881836,
749
+ "learning_rate": 0.00019670724741851735,
750
+ "loss": 0.1856,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.09055805342501984,
755
+ "grad_norm": 14.445696830749512,
756
+ "learning_rate": 0.0001966386800220811,
757
+ "loss": 0.0225,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.09140439037291721,
762
+ "grad_norm": 10.762388229370117,
763
+ "learning_rate": 0.00019656941824876617,
764
+ "loss": 0.0169,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.0922507273208146,
769
+ "grad_norm": 10.171407699584961,
770
+ "learning_rate": 0.00019649946259623838,
771
+ "loss": 0.0198,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.09309706426871198,
776
+ "grad_norm": 10.556538581848145,
777
+ "learning_rate": 0.0001964288135671494,
778
+ "loss": 0.0182,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.09394340121660937,
783
+ "grad_norm": 5.872833728790283,
784
+ "learning_rate": 0.0001963574716691329,
785
+ "loss": 0.0142,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.09478973816450674,
790
+ "grad_norm": 3.532670259475708,
791
+ "learning_rate": 0.00019628543741480108,
792
+ "loss": 0.0068,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.09563607511240413,
797
+ "grad_norm": 8.299254417419434,
798
+ "learning_rate": 0.0001962127113217409,
799
+ "loss": 0.0082,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.0964824120603015,
804
+ "grad_norm": 1.9848963022232056,
805
+ "learning_rate": 0.0001961392939125104,
806
+ "loss": 0.0038,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.09732874900819889,
811
+ "grad_norm": 1.5647845268249512,
812
+ "learning_rate": 0.00019606518571463487,
813
+ "loss": 0.0022,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.09817508595609627,
818
+ "grad_norm": 0.4753362238407135,
819
+ "learning_rate": 0.0001959903872606032,
820
+ "loss": 0.0015,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.09902142290399366,
825
+ "grad_norm": 0.9765241146087646,
826
+ "learning_rate": 0.00019591489908786386,
827
+ "loss": 0.0021,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.09986775985189103,
832
+ "grad_norm": 1.2018309831619263,
833
+ "learning_rate": 0.00019583872173882129,
834
+ "loss": 0.0025,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.10071409679978842,
839
+ "grad_norm": 0.5523298382759094,
840
+ "learning_rate": 0.00019576185576083174,
841
+ "loss": 0.0014,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.1015604337476858,
846
+ "grad_norm": 0.46725499629974365,
847
+ "learning_rate": 0.00019568430170619953,
848
+ "loss": 0.0013,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.10240677069558318,
853
+ "grad_norm": 1.9901517629623413,
854
+ "learning_rate": 0.00019560606013217297,
855
+ "loss": 0.0024,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.10325310764348056,
860
+ "grad_norm": 0.9264715313911438,
861
+ "learning_rate": 0.00019552713160094038,
862
+ "loss": 0.0019,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.10409944459137795,
867
+ "grad_norm": 0.8873511552810669,
868
+ "learning_rate": 0.00019544751667962613,
869
+ "loss": 0.0016,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.10494578153927532,
874
+ "grad_norm": 3.455312967300415,
875
+ "learning_rate": 0.0001953672159402865,
876
+ "loss": 0.0025,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.10579211848717271,
881
+ "grad_norm": 0.6087542772293091,
882
+ "learning_rate": 0.00019528622995990545,
883
+ "loss": 0.0015,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.10663845543507008,
888
+ "grad_norm": 9.587512016296387,
889
+ "learning_rate": 0.0001952045593203907,
890
+ "loss": 0.0056,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.10748479238296747,
895
+ "grad_norm": 2.0214486122131348,
896
+ "learning_rate": 0.0001951222046085695,
897
+ "loss": 0.0016,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.10833112933086485,
902
+ "grad_norm": 0.48625630140304565,
903
+ "learning_rate": 0.00019503916641618426,
904
+ "loss": 0.0013,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.10917746627876224,
909
+ "grad_norm": 0.3964328169822693,
910
+ "learning_rate": 0.00019495544533988833,
911
+ "loss": 0.0009,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.11002380322665961,
916
+ "grad_norm": 0.8259016871452332,
917
+ "learning_rate": 0.000194871041981242,
918
+ "loss": 0.0014,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.110870140174557,
923
+ "grad_norm": 1.184308648109436,
924
+ "learning_rate": 0.00019478595694670775,
925
+ "loss": 0.0022,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.11171647712245437,
930
+ "grad_norm": 0.7664253115653992,
931
+ "learning_rate": 0.00019470019084764613,
932
+ "loss": 0.0014,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.11256281407035176,
937
+ "grad_norm": 4.297515869140625,
938
+ "learning_rate": 0.0001946137443003115,
939
+ "loss": 0.0076,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.11340915101824914,
944
+ "grad_norm": 0.5345470309257507,
945
+ "learning_rate": 0.0001945266179258472,
946
+ "loss": 0.0008,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.11425548796614653,
951
+ "grad_norm": 0.8852401971817017,
952
+ "learning_rate": 0.0001944388123502815,
953
+ "loss": 0.0008,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.1151018249140439,
958
+ "grad_norm": 4.631274700164795,
959
+ "learning_rate": 0.0001943503282045229,
960
+ "loss": 0.0152,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.11594816186194129,
965
+ "grad_norm": 0.5090851783752441,
966
+ "learning_rate": 0.0001942611661243555,
967
+ "loss": 0.0011,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.11679449880983866,
972
+ "grad_norm": 0.993028461933136,
973
+ "learning_rate": 0.00019417132675043471,
974
+ "loss": 0.0013,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.11764083575773605,
979
+ "grad_norm": 6.0296101570129395,
980
+ "learning_rate": 0.0001940808107282824,
981
+ "loss": 0.0059,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.11848717270563343,
986
+ "grad_norm": 0.35436925292015076,
987
+ "learning_rate": 0.00019398961870828238,
988
+ "loss": 0.0009,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.11933350965353082,
993
+ "grad_norm": 0.3110350966453552,
994
+ "learning_rate": 0.0001938977513456757,
995
+ "loss": 0.0008,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.12017984660142819,
1000
+ "grad_norm": 0.6243657469749451,
1001
+ "learning_rate": 0.00019380520930055602,
1002
+ "loss": 0.001,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.12102618354932558,
1007
+ "grad_norm": 0.31351810693740845,
1008
+ "learning_rate": 0.0001937119932378646,
1009
+ "loss": 0.0008,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.12187252049722296,
1014
+ "grad_norm": 1.0445241928100586,
1015
+ "learning_rate": 0.00019361810382738585,
1016
+ "loss": 0.0011,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.12271885744512034,
1021
+ "grad_norm": 0.5057194232940674,
1022
+ "learning_rate": 0.0001935235417437424,
1023
+ "loss": 0.001,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.12356519439301772,
1028
+ "grad_norm": 0.16824191808700562,
1029
+ "learning_rate": 0.00019342830766639013,
1030
+ "loss": 0.0006,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.12441153134091511,
1035
+ "grad_norm": 0.15476548671722412,
1036
+ "learning_rate": 0.00019333240227961345,
1037
+ "loss": 0.0005,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.1252578682888125,
1042
+ "grad_norm": 0.8760647177696228,
1043
+ "learning_rate": 0.00019323582627252036,
1044
+ "loss": 0.001,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.12610420523670987,
1049
+ "grad_norm": 0.5927007794380188,
1050
+ "learning_rate": 0.00019313858033903736,
1051
+ "loss": 0.0011,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.12695054218460725,
1056
+ "grad_norm": 3.346593141555786,
1057
+ "learning_rate": 0.00019304066517790465,
1058
+ "loss": 0.0136,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.12779687913250462,
1063
+ "grad_norm": 21.881933212280273,
1064
+ "learning_rate": 0.00019294208149267102,
1065
+ "loss": 0.3441,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.12864321608040202,
1070
+ "grad_norm": 27.779556274414062,
1071
+ "learning_rate": 0.0001928428299916887,
1072
+ "loss": 0.4038,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.1294895530282994,
1077
+ "grad_norm": 41.42377471923828,
1078
+ "learning_rate": 0.00019274291138810852,
1079
+ "loss": 0.4076,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.13033588997619677,
1084
+ "grad_norm": 65.22334289550781,
1085
+ "learning_rate": 0.0001926423263998745,
1086
+ "loss": 0.4623,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.13118222692409415,
1091
+ "grad_norm": 92.79143524169922,
1092
+ "learning_rate": 0.0001925410757497189,
1093
+ "loss": 0.5263,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.13202856387199155,
1098
+ "grad_norm": 13.545234680175781,
1099
+ "learning_rate": 0.00019243916016515697,
1100
+ "loss": 0.0362,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.13287490081988892,
1105
+ "grad_norm": 2.329796075820923,
1106
+ "learning_rate": 0.00019233658037848167,
1107
+ "loss": 0.0055,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.1337212377677863,
1112
+ "grad_norm": 2.7054457664489746,
1113
+ "learning_rate": 0.00019223333712675838,
1114
+ "loss": 0.0072,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.13456757471568367,
1119
+ "grad_norm": 5.102527618408203,
1120
+ "learning_rate": 0.00019212943115181982,
1121
+ "loss": 0.0095,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.13541391166358108,
1126
+ "grad_norm": 2.725212812423706,
1127
+ "learning_rate": 0.00019202486320026046,
1128
+ "loss": 0.0049,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.13626024861147845,
1133
+ "grad_norm": 3.888731002807617,
1134
+ "learning_rate": 0.00019191963402343128,
1135
+ "loss": 0.0064,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.13710658555937583,
1140
+ "grad_norm": 0.5881321430206299,
1141
+ "learning_rate": 0.00019181374437743438,
1142
+ "loss": 0.0018,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.1379529225072732,
1147
+ "grad_norm": 0.47292956709861755,
1148
+ "learning_rate": 0.00019170719502311747,
1149
+ "loss": 0.0013,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.13879925945517058,
1154
+ "grad_norm": 0.24725215137004852,
1155
+ "learning_rate": 0.00019159998672606853,
1156
+ "loss": 0.0006,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.13964559640306798,
1161
+ "grad_norm": 0.3073093891143799,
1162
+ "learning_rate": 0.00019149212025661017,
1163
+ "loss": 0.0008,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.14049193335096535,
1168
+ "grad_norm": 0.21486443281173706,
1169
+ "learning_rate": 0.0001913835963897942,
1170
+ "loss": 0.0006,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.14133827029886273,
1175
+ "grad_norm": 0.3804973363876343,
1176
+ "learning_rate": 0.00019127441590539602,
1177
+ "loss": 0.0007,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.1421846072467601,
1182
+ "grad_norm": 0.3088591694831848,
1183
+ "learning_rate": 0.00019116457958790893,
1184
+ "loss": 0.0008,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.1430309441946575,
1189
+ "grad_norm": 0.2884930670261383,
1190
+ "learning_rate": 0.00019105408822653875,
1191
+ "loss": 0.0007,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.14387728114255488,
1196
+ "grad_norm": 2.3264033794403076,
1197
+ "learning_rate": 0.00019094294261519785,
1198
+ "loss": 0.0016,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.14472361809045226,
1203
+ "grad_norm": 0.7139752507209778,
1204
+ "learning_rate": 0.00019083114355249956,
1205
+ "loss": 0.0012,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.14556995503834963,
1210
+ "grad_norm": 4.276805400848389,
1211
+ "learning_rate": 0.00019071869184175255,
1212
+ "loss": 0.003,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.14641629198624703,
1217
+ "grad_norm": 0.36595144867897034,
1218
+ "learning_rate": 0.00019060558829095487,
1219
+ "loss": 0.0009,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.1472626289341444,
1224
+ "grad_norm": 3.2072956562042236,
1225
+ "learning_rate": 0.00019049183371278828,
1226
+ "loss": 0.0024,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.14810896588204178,
1231
+ "grad_norm": 0.3659462332725525,
1232
+ "learning_rate": 0.0001903774289246123,
1233
+ "loss": 0.0008,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.14895530282993916,
1238
+ "grad_norm": 2.719895362854004,
1239
+ "learning_rate": 0.00019026237474845852,
1240
+ "loss": 0.0015,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.14980163977783656,
1245
+ "grad_norm": 2.4224469661712646,
1246
+ "learning_rate": 0.0001901466720110244,
1247
+ "loss": 0.0032,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.15064797672573393,
1252
+ "grad_norm": 0.13008993864059448,
1253
+ "learning_rate": 0.0001900303215436676,
1254
+ "loss": 0.0004,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.1514943136736313,
1259
+ "grad_norm": 4.346362113952637,
1260
+ "learning_rate": 0.00018991332418239994,
1261
+ "loss": 0.0014,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.15234065062152868,
1266
+ "grad_norm": 1.0230494737625122,
1267
+ "learning_rate": 0.0001897956807678813,
1268
+ "loss": 0.001,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.1531869875694261,
1273
+ "grad_norm": 7.090376377105713,
1274
+ "learning_rate": 0.00018967739214541363,
1275
+ "loss": 0.003,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.15403332451732346,
1280
+ "grad_norm": 0.2335856556892395,
1281
+ "learning_rate": 0.0001895584591649349,
1282
+ "loss": 0.0006,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.15487966146522084,
1287
+ "grad_norm": 4.240998268127441,
1288
+ "learning_rate": 0.00018943888268101305,
1289
+ "loss": 0.0033,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.1557259984131182,
1294
+ "grad_norm": 0.1109471321105957,
1295
+ "learning_rate": 0.00018931866355283963,
1296
+ "loss": 0.0004,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.1565723353610156,
1301
+ "grad_norm": 2.551114559173584,
1302
+ "learning_rate": 0.00018919780264422395,
1303
+ "loss": 0.0018,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.157418672308913,
1308
+ "grad_norm": 2.3841819763183594,
1309
+ "learning_rate": 0.00018907630082358657,
1310
+ "loss": 0.0011,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.15826500925681036,
1315
+ "grad_norm": 0.3431253135204315,
1316
+ "learning_rate": 0.0001889541589639532,
1317
+ "loss": 0.0006,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.15911134620470774,
1322
+ "grad_norm": 0.7966493964195251,
1323
+ "learning_rate": 0.00018883137794294848,
1324
+ "loss": 0.0012,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.15995768315260514,
1329
+ "grad_norm": 0.26179561018943787,
1330
+ "learning_rate": 0.00018870795864278956,
1331
+ "loss": 0.0007,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.16080402010050251,
1336
+ "grad_norm": 0.40261805057525635,
1337
+ "learning_rate": 0.00018858390195027985,
1338
+ "loss": 0.0007,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.1616503570483999,
1343
+ "grad_norm": 0.38073089718818665,
1344
+ "learning_rate": 0.00018845920875680254,
1345
+ "loss": 0.0007,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.16249669399629726,
1350
+ "grad_norm": 3.7871763706207275,
1351
+ "learning_rate": 0.00018833387995831436,
1352
+ "loss": 0.0012,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.16334303094419467,
1357
+ "grad_norm": 0.08530396223068237,
1358
+ "learning_rate": 0.0001882079164553389,
1359
+ "loss": 0.0003,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.16418936789209204,
1364
+ "grad_norm": 0.15287600457668304,
1365
+ "learning_rate": 0.00018808131915296045,
1366
+ "loss": 0.0004,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.16503570483998942,
1371
+ "grad_norm": 0.49411728978157043,
1372
+ "learning_rate": 0.00018795408896081728,
1373
+ "loss": 0.0007,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.1658820417878868,
1378
+ "grad_norm": 0.15277883410453796,
1379
+ "learning_rate": 0.00018782622679309506,
1380
+ "loss": 0.0004,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.1667283787357842,
1385
+ "grad_norm": 0.11514627188444138,
1386
+ "learning_rate": 0.0001876977335685205,
1387
+ "loss": 0.0004,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.16757471568368157,
1392
+ "grad_norm": 0.26564082503318787,
1393
+ "learning_rate": 0.00018756861021035462,
1394
+ "loss": 0.0005,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.16842105263157894,
1399
+ "grad_norm": 0.21045762300491333,
1400
+ "learning_rate": 0.0001874388576463861,
1401
+ "loss": 0.0006,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.16926738957947632,
1406
+ "grad_norm": 0.3532085120677948,
1407
+ "learning_rate": 0.0001873084768089246,
1408
+ "loss": 0.0008,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.17011372652737372,
1413
+ "grad_norm": 29.670534133911133,
1414
+ "learning_rate": 0.00018717746863479423,
1415
+ "loss": 0.2364,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.1709600634752711,
1420
+ "grad_norm": 35.507972717285156,
1421
+ "learning_rate": 0.00018704583406532662,
1422
+ "loss": 0.2491,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.17180640042316847,
1427
+ "grad_norm": 39.08292770385742,
1428
+ "learning_rate": 0.00018691357404635424,
1429
+ "loss": 0.2042,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.17265273737106585,
1434
+ "grad_norm": 40.570125579833984,
1435
+ "learning_rate": 0.00018678068952820355,
1436
+ "loss": 0.1984,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.17349907431896325,
1441
+ "grad_norm": 65.52487182617188,
1442
+ "learning_rate": 0.0001866471814656883,
1443
+ "loss": 0.2995,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.17434541126686062,
1448
+ "grad_norm": 28.42360496520996,
1449
+ "learning_rate": 0.0001865130508181026,
1450
+ "loss": 0.0856,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.175191748214758,
1455
+ "grad_norm": 0.7669479846954346,
1456
+ "learning_rate": 0.00018637829854921387,
1457
+ "loss": 0.0011,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.17603808516265537,
1462
+ "grad_norm": 11.103653907775879,
1463
+ "learning_rate": 0.0001862429256272562,
1464
+ "loss": 0.0107,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.17688442211055277,
1469
+ "grad_norm": 12.320133209228516,
1470
+ "learning_rate": 0.0001861069330249232,
1471
+ "loss": 0.0146,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.17773075905845015,
1476
+ "grad_norm": 1.1529252529144287,
1477
+ "learning_rate": 0.00018597032171936104,
1478
+ "loss": 0.0016,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.17857709600634752,
1483
+ "grad_norm": 0.7125049829483032,
1484
+ "learning_rate": 0.00018583309269216156,
1485
+ "loss": 0.0014,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.1794234329542449,
1490
+ "grad_norm": 15.23595905303955,
1491
+ "learning_rate": 0.00018569524692935496,
1492
+ "loss": 0.0056,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.1802697699021423,
1497
+ "grad_norm": 0.48333868384361267,
1498
+ "learning_rate": 0.0001855567854214029,
1499
+ "loss": 0.0008,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.18111610685003968,
1504
+ "grad_norm": 0.19277918338775635,
1505
+ "learning_rate": 0.0001854177091631915,
1506
+ "loss": 0.0006,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.18196244379793705,
1511
+ "grad_norm": 0.9802500009536743,
1512
+ "learning_rate": 0.0001852780191540238,
1513
+ "loss": 0.0013,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.18280878074583443,
1518
+ "grad_norm": 0.16036200523376465,
1519
+ "learning_rate": 0.00018513771639761298,
1520
+ "loss": 0.0005,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.18365511769373183,
1525
+ "grad_norm": 0.32250264286994934,
1526
+ "learning_rate": 0.00018499680190207495,
1527
+ "loss": 0.0009,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.1845014546416292,
1532
+ "grad_norm": 0.777240514755249,
1533
+ "learning_rate": 0.00018485527667992115,
1534
+ "loss": 0.001,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.18534779158952658,
1539
+ "grad_norm": 0.3555632531642914,
1540
+ "learning_rate": 0.0001847131417480512,
1541
+ "loss": 0.0009,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.18619412853742395,
1546
+ "grad_norm": 0.5618864297866821,
1547
+ "learning_rate": 0.00018457039812774575,
1548
+ "loss": 0.0006,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.18704046548532136,
1553
+ "grad_norm": 0.43013933300971985,
1554
+ "learning_rate": 0.00018442704684465899,
1555
+ "loss": 0.0008,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.18788680243321873,
1560
+ "grad_norm": 0.2362668365240097,
1561
+ "learning_rate": 0.0001842830889288114,
1562
+ "loss": 0.0006,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.1887331393811161,
1567
+ "grad_norm": 0.21618768572807312,
1568
+ "learning_rate": 0.00018413852541458226,
1569
+ "loss": 0.0006,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.18957947632901348,
1574
+ "grad_norm": 4.4554901123046875,
1575
+ "learning_rate": 0.0001839933573407022,
1576
+ "loss": 0.0033,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.19042581327691088,
1581
+ "grad_norm": 0.2934055030345917,
1582
+ "learning_rate": 0.00018384758575024586,
1583
+ "loss": 0.0006,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.19127215022480826,
1588
+ "grad_norm": 0.13466045260429382,
1589
+ "learning_rate": 0.00018370121169062435,
1590
+ "loss": 0.0004,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.19211848717270563,
1595
+ "grad_norm": 0.11464786529541016,
1596
+ "learning_rate": 0.00018355423621357759,
1597
+ "loss": 0.0004,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.192964824120603,
1602
+ "grad_norm": 0.6053487062454224,
1603
+ "learning_rate": 0.00018340666037516693,
1604
+ "loss": 0.0007,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.1938111610685004,
1609
+ "grad_norm": 0.09634432196617126,
1610
+ "learning_rate": 0.00018325848523576742,
1611
+ "loss": 0.0003,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.19465749801639778,
1616
+ "grad_norm": 3.126617908477783,
1617
+ "learning_rate": 0.00018310971186006038,
1618
+ "loss": 0.0012,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.19550383496429516,
1623
+ "grad_norm": 0.1292370706796646,
1624
+ "learning_rate": 0.00018296034131702553,
1625
+ "loss": 0.0004,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.19635017191219253,
1630
+ "grad_norm": 0.18858526647090912,
1631
+ "learning_rate": 0.00018281037467993345,
1632
+ "loss": 0.0004,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.19719650886008994,
1637
+ "grad_norm": 3.9159443378448486,
1638
+ "learning_rate": 0.00018265981302633782,
1639
+ "loss": 0.0101,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.1980428458079873,
1644
+ "grad_norm": 0.46279361844062805,
1645
+ "learning_rate": 0.00018250865743806767,
1646
+ "loss": 0.0006,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.19888918275588469,
1651
+ "grad_norm": 0.1234947219491005,
1652
+ "learning_rate": 0.00018235690900121965,
1653
+ "loss": 0.0004,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.19973551970378206,
1658
+ "grad_norm": 0.6481117606163025,
1659
+ "learning_rate": 0.0001822045688061502,
1660
+ "loss": 0.001,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.20058185665167946,
1665
+ "grad_norm": 0.09670120477676392,
1666
+ "learning_rate": 0.00018205163794746772,
1667
+ "loss": 0.0003,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.20142819359957684,
1672
+ "grad_norm": 0.19068674743175507,
1673
+ "learning_rate": 0.00018189811752402458,
1674
+ "loss": 0.0003,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.2022745305474742,
1679
+ "grad_norm": 1.4126213788986206,
1680
+ "learning_rate": 0.0001817440086389096,
1681
+ "loss": 0.0013,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.2031208674953716,
1686
+ "grad_norm": 0.12282940745353699,
1687
+ "learning_rate": 0.00018158931239943958,
1688
+ "loss": 0.0003,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.203967204443269,
1693
+ "grad_norm": 0.08084618300199509,
1694
+ "learning_rate": 0.00018143402991715183,
1695
+ "loss": 0.0003,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.20481354139116636,
1700
+ "grad_norm": 0.13239997625350952,
1701
+ "learning_rate": 0.0001812781623077959,
1702
+ "loss": 0.0003,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.20565987833906374,
1707
+ "grad_norm": 0.6071043014526367,
1708
+ "learning_rate": 0.00018112171069132566,
1709
+ "loss": 0.0009,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.20650621528696111,
1714
+ "grad_norm": 0.39527714252471924,
1715
+ "learning_rate": 0.00018096467619189123,
1716
+ "loss": 0.0006,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.2073525522348585,
1721
+ "grad_norm": 0.17460699379444122,
1722
+ "learning_rate": 0.00018080705993783096,
1723
+ "loss": 0.0004,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.2081988891827559,
1728
+ "grad_norm": 0.20895503461360931,
1729
+ "learning_rate": 0.00018064886306166323,
1730
+ "loss": 0.0004,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.20904522613065327,
1735
+ "grad_norm": 0.5428494811058044,
1736
+ "learning_rate": 0.00018049008670007835,
1737
+ "loss": 0.0004,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.20989156307855064,
1742
+ "grad_norm": 0.139656662940979,
1743
+ "learning_rate": 0.00018033073199393048,
1744
+ "loss": 0.0003,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.21073790002644802,
1749
+ "grad_norm": 0.12410479784011841,
1750
+ "learning_rate": 0.0001801708000882292,
1751
+ "loss": 0.0003,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.21158423697434542,
1756
+ "grad_norm": 1.5398989915847778,
1757
+ "learning_rate": 0.00018001029213213162,
1758
+ "loss": 0.0008,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.2124305739222428,
1763
+ "grad_norm": 83.7887191772461,
1764
+ "learning_rate": 0.00017984920927893377,
1765
+ "loss": 0.0822,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.21327691087014017,
1770
+ "grad_norm": 26.819786071777344,
1771
+ "learning_rate": 0.00017968755268606262,
1772
+ "loss": 0.0551,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.21412324781803754,
1777
+ "grad_norm": 17.227445602416992,
1778
+ "learning_rate": 0.00017952532351506753,
1779
+ "loss": 0.0476,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.21496958476593495,
1784
+ "grad_norm": 12.969980239868164,
1785
+ "learning_rate": 0.00017936252293161204,
1786
+ "loss": 0.0395,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.21581592171383232,
1791
+ "grad_norm": 28.53566551208496,
1792
+ "learning_rate": 0.00017919915210546546,
1793
+ "loss": 0.0698,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.2166622586617297,
1798
+ "grad_norm": 0.27628636360168457,
1799
+ "learning_rate": 0.00017903521221049448,
1800
+ "loss": 0.0007,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.21750859560962707,
1805
+ "grad_norm": 0.11199865490198135,
1806
+ "learning_rate": 0.00017887070442465462,
1807
+ "loss": 0.0004,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.21835493255752447,
1812
+ "grad_norm": 0.18436667323112488,
1813
+ "learning_rate": 0.00017870562992998193,
1814
+ "loss": 0.0005,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.21920126950542185,
1819
+ "grad_norm": 0.3930487632751465,
1820
+ "learning_rate": 0.00017853998991258449,
1821
+ "loss": 0.0007,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.22004760645331922,
1826
+ "grad_norm": 0.37658360600471497,
1827
+ "learning_rate": 0.00017837378556263367,
1828
+ "loss": 0.0006,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.2208939434012166,
1833
+ "grad_norm": 0.11100467294454575,
1834
+ "learning_rate": 0.00017820701807435584,
1835
+ "loss": 0.0003,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.221740280349114,
1840
+ "grad_norm": 0.43430548906326294,
1841
+ "learning_rate": 0.0001780396886460237,
1842
+ "loss": 0.0005,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.22258661729701137,
1847
+ "grad_norm": 0.370032399892807,
1848
+ "learning_rate": 0.00017787179847994757,
1849
+ "loss": 0.0007,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.22343295424490875,
1854
+ "grad_norm": 0.8565439581871033,
1855
+ "learning_rate": 0.00017770334878246686,
1856
+ "loss": 0.0012,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.22427929119280612,
1861
+ "grad_norm": 0.31265321373939514,
1862
+ "learning_rate": 0.00017753434076394142,
1863
+ "loss": 0.0005,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.22512562814070353,
1868
+ "grad_norm": 0.4533150792121887,
1869
+ "learning_rate": 0.00017736477563874275,
1870
+ "loss": 0.0006,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.2259719650886009,
1875
+ "grad_norm": 0.3379235565662384,
1876
+ "learning_rate": 0.00017719465462524533,
1877
+ "loss": 0.0008,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.22681830203649828,
1882
+ "grad_norm": 0.5092006921768188,
1883
+ "learning_rate": 0.00017702397894581788,
1884
+ "loss": 0.0005,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.22766463898439565,
1889
+ "grad_norm": 0.4077492654323578,
1890
+ "learning_rate": 0.00017685274982681454,
1891
+ "loss": 0.0007,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.22851097593229305,
1896
+ "grad_norm": 0.5492392778396606,
1897
+ "learning_rate": 0.0001766809684985661,
1898
+ "loss": 0.0004,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.22935731288019043,
1903
+ "grad_norm": 0.5803564786911011,
1904
+ "learning_rate": 0.00017650863619537107,
1905
+ "loss": 0.0007,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.2302036498280878,
1910
+ "grad_norm": 0.15004323422908783,
1911
+ "learning_rate": 0.00017633575415548693,
1912
+ "loss": 0.0003,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.23104998677598518,
1917
+ "grad_norm": 0.2035101354122162,
1918
+ "learning_rate": 0.00017616232362112116,
1919
+ "loss": 0.0004,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.23189632372388258,
1924
+ "grad_norm": 0.08870142698287964,
1925
+ "learning_rate": 0.00017598834583842235,
1926
+ "loss": 0.0003,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.23274266067177996,
1931
+ "grad_norm": 0.09822133928537369,
1932
+ "learning_rate": 0.00017581382205747117,
1933
+ "loss": 0.0003,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.23358899761967733,
1938
+ "grad_norm": 0.10656624287366867,
1939
+ "learning_rate": 0.00017563875353227153,
1940
+ "loss": 0.0003,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.2344353345675747,
1945
+ "grad_norm": 0.09961220622062683,
1946
+ "learning_rate": 0.00017546314152074138,
1947
+ "loss": 0.0002,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.2352816715154721,
1952
+ "grad_norm": 0.9810962080955505,
1953
+ "learning_rate": 0.00017528698728470392,
1954
+ "loss": 0.0007,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.23612800846336948,
1959
+ "grad_norm": 0.19340015947818756,
1960
+ "learning_rate": 0.00017511029208987824,
1961
+ "loss": 0.0004,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.23697434541126686,
1966
+ "grad_norm": 0.1273375153541565,
1967
+ "learning_rate": 0.00017493305720587047,
1968
+ "loss": 0.0004,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.23782068235916423,
1973
+ "grad_norm": 0.12967373430728912,
1974
+ "learning_rate": 0.00017475528390616452,
1975
+ "loss": 0.0003,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.23866701930706163,
1980
+ "grad_norm": 0.6166614294052124,
1981
+ "learning_rate": 0.000174576973468113,
1982
+ "loss": 0.0008,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.239513356254959,
1987
+ "grad_norm": 0.6157065629959106,
1988
+ "learning_rate": 0.00017439812717292798,
1989
+ "loss": 0.0008,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.24035969320285638,
1994
+ "grad_norm": 0.10683294385671616,
1995
+ "learning_rate": 0.00017421874630567188,
1996
+ "loss": 0.0003,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.24120603015075376,
2001
+ "grad_norm": 1.4939329624176025,
2002
+ "learning_rate": 0.00017403883215524811,
2003
+ "loss": 0.0008,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.24205236709865116,
2008
+ "grad_norm": 1.0055180788040161,
2009
+ "learning_rate": 0.0001738583860143919,
2010
+ "loss": 0.0009,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.24289870404654854,
2015
+ "grad_norm": 0.12554600834846497,
2016
+ "learning_rate": 0.000173677409179661,
2017
+ "loss": 0.0003,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.2437450409944459,
2022
+ "grad_norm": 0.23707199096679688,
2023
+ "learning_rate": 0.00017349590295142635,
2024
+ "loss": 0.0003,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.24459137794234329,
2029
+ "grad_norm": 3.2323226928710938,
2030
+ "learning_rate": 0.00017331386863386262,
2031
+ "loss": 0.0031,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.2454377148902407,
2036
+ "grad_norm": 0.4041217863559723,
2037
+ "learning_rate": 0.00017313130753493917,
2038
+ "loss": 0.0006,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.24628405183813806,
2043
+ "grad_norm": 0.4350222647190094,
2044
+ "learning_rate": 0.00017294822096641032,
2045
+ "loss": 0.0006,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.24713038878603544,
2050
+ "grad_norm": 0.3703482449054718,
2051
+ "learning_rate": 0.00017276461024380596,
2052
+ "loss": 0.0006,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.2479767257339328,
2057
+ "grad_norm": 0.16974994540214539,
2058
+ "learning_rate": 0.00017258047668642225,
2059
+ "loss": 0.0003,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.24882306268183021,
2064
+ "grad_norm": 0.06141228228807449,
2065
+ "learning_rate": 0.00017239582161731218,
2066
+ "loss": 0.0002,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.2496693996297276,
2071
+ "grad_norm": 0.09231980890035629,
2072
+ "learning_rate": 0.0001722106463632758,
2073
+ "loss": 0.0003,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.250515736577625,
2078
+ "grad_norm": 0.1844186633825302,
2079
+ "learning_rate": 0.00017202495225485088,
2080
+ "loss": 0.0005,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.250515736577625,
2085
+ "eval_loss": 0.0016514281742274761,
2086
+ "eval_runtime": 22.4693,
2087
+ "eval_samples_per_second": 88.565,
2088
+ "eval_steps_per_second": 44.283,
2089
+ "step": 296
2090
+ }
2091
+ ],
2092
+ "logging_steps": 1,
2093
+ "max_steps": 1182,
2094
+ "num_input_tokens_seen": 0,
2095
+ "num_train_epochs": 2,
2096
+ "save_steps": 296,
2097
+ "stateful_callbacks": {
2098
+ "TrainerControl": {
2099
+ "args": {
2100
+ "should_epoch_stop": false,
2101
+ "should_evaluate": false,
2102
+ "should_log": false,
2103
+ "should_save": true,
2104
+ "should_training_stop": false
2105
+ },
2106
+ "attributes": {}
2107
+ }
2108
+ },
2109
+ "total_flos": 8067098779582464.0,
2110
+ "train_batch_size": 2,
2111
+ "trial_name": null,
2112
+ "trial_params": null
2113
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4db4212ff4f954c350823554dbb77647dc8c99aabee58c6924529e6dadb1a14
3
+ size 6840
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff