Hugging Face's logo

maanasharma5
/
dialect-debiasing-gpt2-medium-translated-pnlogmse-e1-r20_eval-n1.0

PEFT
Safetensors
gpt2
Model card Files
xet
Community
maanasharma5 commited on
Commit
28e3d49
·
verified ·
1 Parent(s): 5fec4e9

Upload folder using huggingface_hub

Browse files
Files changed (21) hide show
  1. README.md +202 -0
  2. adapter_config.json +31 -0
  3. adapter_model.safetensors +3 -0
  4. checkpoint-3125/README.md +202 -0
  5. checkpoint-3125/adapter_config.json +31 -0
  6. checkpoint-3125/adapter_model.safetensors +3 -0
  7. checkpoint-3125/merges.txt +0 -0
  8. checkpoint-3125/optimizer.pt +3 -0
  9. checkpoint-3125/rng_state.pth +3 -0
  10. checkpoint-3125/scheduler.pt +3 -0
  11. checkpoint-3125/special_tokens_map.json +24 -0
  12. checkpoint-3125/tokenizer_config.json +22 -0
  13. checkpoint-3125/trainer_state.json +2217 -0
  14. checkpoint-3125/training_args.bin +3 -0
  15. checkpoint-3125/vocab.json +0 -0
  16. config.json +40 -0
  17. merges.txt +0 -0
  18. special_tokens_map.json +24 -0
  19. tokenizer_config.json +22 -0
  20. training_logs.csv +314 -0
  21. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: gpt2-medium
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 0.13.2
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "GPT2LMHeadModel",
5
+ "parent_library": "transformers.models.gpt2.modeling_gpt2"
6
+ },
7
+ "base_model_name_or_path": "gpt2-medium",
8
+ "bias": "none",
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_dropout": 0.0,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "c_attn"
27
+ ],
28
+ "task_type": null,
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44c7e725baa71408800ce9f8d8f4e019f8974dca81a77f7bc3e7b2a63ac67cf
3
+ size 6297648
checkpoint-3125/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: gpt2-medium
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 0.13.2
checkpoint-3125/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "GPT2LMHeadModel",
5
+ "parent_library": "transformers.models.gpt2.modeling_gpt2"
6
+ },
7
+ "base_model_name_or_path": "gpt2-medium",
8
+ "bias": "none",
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_dropout": 0.0,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "c_attn"
27
+ ],
28
+ "task_type": null,
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
checkpoint-3125/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44c7e725baa71408800ce9f8d8f4e019f8974dca81a77f7bc3e7b2a63ac67cf
3
+ size 6297648
checkpoint-3125/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3125/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74d390dda549b3991043d9d8286c3eb3ee76516a5c44b2e857a8aaa66364c1d5
3
+ size 12623610
checkpoint-3125/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5994634e90ce1b45d012a45568063be05fea876e791cd66b48a4efc924164b2
3
+ size 14244
checkpoint-3125/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42e57efa8b95889e87232fe6ea0805483ed6c8a2d35bb60230715b624ff5bda
3
+ size 1064
checkpoint-3125/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-3125/tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": false,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 1024,
19
+ "pad_token": "<|endoftext|>",
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
checkpoint-3125/trainer_state.json ADDED
@@ -0,0 +1,2217 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3125,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0032,
13
+ "grad_norm": 0.9999998211860657,
14
+ "learning_rate": 6.369426751592357e-06,
15
+ "loss": 22.4779,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0064,
20
+ "grad_norm": 0.9999998211860657,
21
+ "learning_rate": 1.2738853503184714e-05,
22
+ "loss": 18.8384,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0096,
27
+ "grad_norm": 0.9999999403953552,
28
+ "learning_rate": 1.910828025477707e-05,
29
+ "loss": 19.7931,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0128,
34
+ "grad_norm": 0.9999999403953552,
35
+ "learning_rate": 2.5477707006369428e-05,
36
+ "loss": 19.6268,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.016,
41
+ "grad_norm": 0.9999998807907104,
42
+ "learning_rate": 3.184713375796178e-05,
43
+ "loss": 17.6451,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.0192,
48
+ "grad_norm": 0.9999998807907104,
49
+ "learning_rate": 3.821656050955414e-05,
50
+ "loss": 18.5002,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.0224,
55
+ "grad_norm": 0.9999999403953552,
56
+ "learning_rate": 4.45859872611465e-05,
57
+ "loss": 16.7061,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.0256,
62
+ "grad_norm": 0.9999998807907104,
63
+ "learning_rate": 5.0955414012738855e-05,
64
+ "loss": 14.6224,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.0288,
69
+ "grad_norm": 0.9999999403953552,
70
+ "learning_rate": 5.732484076433121e-05,
71
+ "loss": 14.3869,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.032,
76
+ "grad_norm": 0.9999998211860657,
77
+ "learning_rate": 6.369426751592356e-05,
78
+ "loss": 13.3853,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.0352,
83
+ "grad_norm": 0.9999999403953552,
84
+ "learning_rate": 7.006369426751592e-05,
85
+ "loss": 10.5028,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.0384,
90
+ "grad_norm": 0.9999999403953552,
91
+ "learning_rate": 7.643312101910829e-05,
92
+ "loss": 11.3589,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.0416,
97
+ "grad_norm": 0.9999999403953552,
98
+ "learning_rate": 8.280254777070065e-05,
99
+ "loss": 8.8268,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.0448,
104
+ "grad_norm": 0.9999998211860657,
105
+ "learning_rate": 8.9171974522293e-05,
106
+ "loss": 8.1005,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.048,
111
+ "grad_norm": 0.9999998807907104,
112
+ "learning_rate": 9.554140127388536e-05,
113
+ "loss": 7.0647,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.0512,
118
+ "grad_norm": 0.9999999403953552,
119
+ "learning_rate": 9.989892183288411e-05,
120
+ "loss": 6.3656,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.0544,
125
+ "grad_norm": 0.9999999403953552,
126
+ "learning_rate": 9.956199460916442e-05,
127
+ "loss": 5.5873,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.0576,
132
+ "grad_norm": 0.9999998211860657,
133
+ "learning_rate": 9.922506738544474e-05,
134
+ "loss": 5.3475,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.0608,
139
+ "grad_norm": 0.9999998807907104,
140
+ "learning_rate": 9.888814016172507e-05,
141
+ "loss": 4.8772,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.064,
146
+ "grad_norm": 1.0,
147
+ "learning_rate": 9.85512129380054e-05,
148
+ "loss": 4.3908,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.0672,
153
+ "grad_norm": 0.9999999403953552,
154
+ "learning_rate": 9.821428571428572e-05,
155
+ "loss": 3.9887,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.0704,
160
+ "grad_norm": 0.9999999403953552,
161
+ "learning_rate": 9.787735849056603e-05,
162
+ "loss": 3.5629,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.0736,
167
+ "grad_norm": 0.9999998211860657,
168
+ "learning_rate": 9.754043126684636e-05,
169
+ "loss": 3.8297,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.0768,
174
+ "grad_norm": 0.9999998211860657,
175
+ "learning_rate": 9.720350404312669e-05,
176
+ "loss": 3.4697,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.08,
181
+ "grad_norm": 0.9999998211860657,
182
+ "learning_rate": 9.686657681940702e-05,
183
+ "loss": 3.4108,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.0832,
188
+ "grad_norm": 0.9999998807907104,
189
+ "learning_rate": 9.652964959568734e-05,
190
+ "loss": 3.3772,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.0864,
195
+ "grad_norm": 0.9999998211860657,
196
+ "learning_rate": 9.619272237196765e-05,
197
+ "loss": 3.3633,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.0896,
202
+ "grad_norm": 0.9999999403953552,
203
+ "learning_rate": 9.585579514824798e-05,
204
+ "loss": 3.1345,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.0928,
209
+ "grad_norm": 0.9999998211860657,
210
+ "learning_rate": 9.551886792452831e-05,
211
+ "loss": 2.9512,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.096,
216
+ "grad_norm": 0.9999999403953552,
217
+ "learning_rate": 9.518194070080863e-05,
218
+ "loss": 3.347,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.0992,
223
+ "grad_norm": 0.9999999403953552,
224
+ "learning_rate": 9.484501347708896e-05,
225
+ "loss": 3.1399,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.1024,
230
+ "grad_norm": 0.9999998807907104,
231
+ "learning_rate": 9.450808625336927e-05,
232
+ "loss": 2.9876,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.1056,
237
+ "grad_norm": 0.9999998807907104,
238
+ "learning_rate": 9.41711590296496e-05,
239
+ "loss": 2.825,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.1088,
244
+ "grad_norm": 0.9999999403953552,
245
+ "learning_rate": 9.383423180592993e-05,
246
+ "loss": 2.6934,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.112,
251
+ "grad_norm": 0.9999998807907104,
252
+ "learning_rate": 9.349730458221025e-05,
253
+ "loss": 2.6445,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.1152,
258
+ "grad_norm": 0.9999998807907104,
259
+ "learning_rate": 9.316037735849057e-05,
260
+ "loss": 2.6892,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.1184,
265
+ "grad_norm": 0.9999998807907104,
266
+ "learning_rate": 9.282345013477089e-05,
267
+ "loss": 2.5397,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.1216,
272
+ "grad_norm": 0.9999999403953552,
273
+ "learning_rate": 9.248652291105122e-05,
274
+ "loss": 2.7159,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.1248,
279
+ "grad_norm": 0.9999998807907104,
280
+ "learning_rate": 9.214959568733154e-05,
281
+ "loss": 2.5994,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.128,
286
+ "grad_norm": 0.9999998807907104,
287
+ "learning_rate": 9.181266846361186e-05,
288
+ "loss": 2.2929,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.1312,
293
+ "grad_norm": 0.9999998211860657,
294
+ "learning_rate": 9.14757412398922e-05,
295
+ "loss": 2.51,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.1344,
300
+ "grad_norm": 0.9999998807907104,
301
+ "learning_rate": 9.113881401617251e-05,
302
+ "loss": 2.2427,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.1376,
307
+ "grad_norm": 0.9999999403953552,
308
+ "learning_rate": 9.080188679245284e-05,
309
+ "loss": 2.3756,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.1408,
314
+ "grad_norm": 0.9999999403953552,
315
+ "learning_rate": 9.046495956873315e-05,
316
+ "loss": 2.2291,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.144,
321
+ "grad_norm": 0.9999999403953552,
322
+ "learning_rate": 9.012803234501348e-05,
323
+ "loss": 2.2808,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.1472,
328
+ "grad_norm": 0.9999998807907104,
329
+ "learning_rate": 8.979110512129381e-05,
330
+ "loss": 1.9267,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.1504,
335
+ "grad_norm": 0.9999999403953552,
336
+ "learning_rate": 8.945417789757413e-05,
337
+ "loss": 2.16,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.1536,
342
+ "grad_norm": 0.9999998807907104,
343
+ "learning_rate": 8.911725067385444e-05,
344
+ "loss": 1.9578,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.1568,
349
+ "grad_norm": 0.9999998211860657,
350
+ "learning_rate": 8.878032345013477e-05,
351
+ "loss": 2.0149,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.16,
356
+ "grad_norm": 0.9999997615814209,
357
+ "learning_rate": 8.84433962264151e-05,
358
+ "loss": 2.2299,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.1632,
363
+ "grad_norm": 0.9999998211860657,
364
+ "learning_rate": 8.810646900269543e-05,
365
+ "loss": 1.9608,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.1664,
370
+ "grad_norm": 0.9999998211860657,
371
+ "learning_rate": 8.776954177897575e-05,
372
+ "loss": 2.0082,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.1696,
377
+ "grad_norm": 0.9999997615814209,
378
+ "learning_rate": 8.743261455525606e-05,
379
+ "loss": 1.7805,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.1728,
384
+ "grad_norm": 0.9999999403953552,
385
+ "learning_rate": 8.709568733153639e-05,
386
+ "loss": 1.8744,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.176,
391
+ "grad_norm": 0.9999998807907104,
392
+ "learning_rate": 8.675876010781672e-05,
393
+ "loss": 1.8776,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.1792,
398
+ "grad_norm": 0.9999998807907104,
399
+ "learning_rate": 8.642183288409704e-05,
400
+ "loss": 1.8193,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.1824,
405
+ "grad_norm": 0.9999997615814209,
406
+ "learning_rate": 8.608490566037735e-05,
407
+ "loss": 1.6604,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.1856,
412
+ "grad_norm": 0.9999998211860657,
413
+ "learning_rate": 8.574797843665768e-05,
414
+ "loss": 1.8959,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.1888,
419
+ "grad_norm": 0.9999998211860657,
420
+ "learning_rate": 8.541105121293801e-05,
421
+ "loss": 1.8175,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.192,
426
+ "grad_norm": 0.9999998807907104,
427
+ "learning_rate": 8.507412398921834e-05,
428
+ "loss": 1.9855,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.1952,
433
+ "grad_norm": 0.9999998211860657,
434
+ "learning_rate": 8.473719676549866e-05,
435
+ "loss": 1.6491,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.1984,
440
+ "grad_norm": 0.9999997615814209,
441
+ "learning_rate": 8.440026954177897e-05,
442
+ "loss": 1.4581,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.2016,
447
+ "grad_norm": 1.0,
448
+ "learning_rate": 8.40633423180593e-05,
449
+ "loss": 1.6256,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.2048,
454
+ "grad_norm": 0.9999998807907104,
455
+ "learning_rate": 8.372641509433963e-05,
456
+ "loss": 1.7204,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.208,
461
+ "grad_norm": 0.9999998807907104,
462
+ "learning_rate": 8.338948787061996e-05,
463
+ "loss": 1.6769,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.2112,
468
+ "grad_norm": 0.9999997615814209,
469
+ "learning_rate": 8.305256064690027e-05,
470
+ "loss": 1.6198,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.2144,
475
+ "grad_norm": 0.9999999403953552,
476
+ "learning_rate": 8.271563342318059e-05,
477
+ "loss": 1.6906,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.2176,
482
+ "grad_norm": 0.9999998807907104,
483
+ "learning_rate": 8.237870619946092e-05,
484
+ "loss": 1.508,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.2208,
489
+ "grad_norm": 0.9999998211860657,
490
+ "learning_rate": 8.204177897574125e-05,
491
+ "loss": 1.45,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.224,
496
+ "grad_norm": 0.9999998807907104,
497
+ "learning_rate": 8.170485175202158e-05,
498
+ "loss": 1.4575,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.2272,
503
+ "grad_norm": 0.9999998807907104,
504
+ "learning_rate": 8.136792452830189e-05,
505
+ "loss": 1.5332,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.2304,
510
+ "grad_norm": 0.9999998211860657,
511
+ "learning_rate": 8.103099730458221e-05,
512
+ "loss": 1.3485,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.2336,
517
+ "grad_norm": 0.9999998807907104,
518
+ "learning_rate": 8.069407008086254e-05,
519
+ "loss": 1.3703,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.2368,
524
+ "grad_norm": 0.9999998807907104,
525
+ "learning_rate": 8.035714285714287e-05,
526
+ "loss": 1.4383,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.24,
531
+ "grad_norm": 0.9999998211860657,
532
+ "learning_rate": 8.002021563342318e-05,
533
+ "loss": 1.4196,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.2432,
538
+ "grad_norm": 0.9999998211860657,
539
+ "learning_rate": 7.968328840970351e-05,
540
+ "loss": 1.4706,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.2464,
545
+ "grad_norm": 0.9999998807907104,
546
+ "learning_rate": 7.934636118598383e-05,
547
+ "loss": 1.4038,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.2496,
552
+ "grad_norm": 0.9999998807907104,
553
+ "learning_rate": 7.900943396226416e-05,
554
+ "loss": 1.3802,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.2528,
559
+ "grad_norm": 0.9999998807907104,
560
+ "learning_rate": 7.867250673854449e-05,
561
+ "loss": 1.3093,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.256,
566
+ "grad_norm": 0.9999998211860657,
567
+ "learning_rate": 7.83355795148248e-05,
568
+ "loss": 1.2819,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.2592,
573
+ "grad_norm": 0.9999997615814209,
574
+ "learning_rate": 7.799865229110512e-05,
575
+ "loss": 1.1946,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.2624,
580
+ "grad_norm": 0.9999998211860657,
581
+ "learning_rate": 7.766172506738545e-05,
582
+ "loss": 1.4261,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.2656,
587
+ "grad_norm": 0.9999998211860657,
588
+ "learning_rate": 7.732479784366577e-05,
589
+ "loss": 1.1928,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.2688,
594
+ "grad_norm": 0.9999998211860657,
595
+ "learning_rate": 7.69878706199461e-05,
596
+ "loss": 1.2264,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.272,
601
+ "grad_norm": 0.9999997615814209,
602
+ "learning_rate": 7.665094339622642e-05,
603
+ "loss": 1.2548,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.2752,
608
+ "grad_norm": 0.9999998211860657,
609
+ "learning_rate": 7.631401617250674e-05,
610
+ "loss": 1.2714,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.2784,
615
+ "grad_norm": 0.9999997615814209,
616
+ "learning_rate": 7.597708894878706e-05,
617
+ "loss": 1.1514,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.2816,
622
+ "grad_norm": 0.9999997615814209,
623
+ "learning_rate": 7.56401617250674e-05,
624
+ "loss": 1.1413,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.2848,
629
+ "grad_norm": 0.9999998211860657,
630
+ "learning_rate": 7.530323450134771e-05,
631
+ "loss": 1.1009,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.288,
636
+ "grad_norm": 0.9999998211860657,
637
+ "learning_rate": 7.496630727762804e-05,
638
+ "loss": 1.0864,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.2912,
643
+ "grad_norm": 0.9999998807907104,
644
+ "learning_rate": 7.462938005390835e-05,
645
+ "loss": 1.1562,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.2944,
650
+ "grad_norm": 0.9999998211860657,
651
+ "learning_rate": 7.429245283018868e-05,
652
+ "loss": 1.0136,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.2976,
657
+ "grad_norm": 0.9999998211860657,
658
+ "learning_rate": 7.395552560646901e-05,
659
+ "loss": 1.0745,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.3008,
664
+ "grad_norm": 0.9999998807907104,
665
+ "learning_rate": 7.361859838274933e-05,
666
+ "loss": 1.0076,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.304,
671
+ "grad_norm": 0.9999997615814209,
672
+ "learning_rate": 7.328167115902966e-05,
673
+ "loss": 1.0461,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.3072,
678
+ "grad_norm": 0.9999998211860657,
679
+ "learning_rate": 7.294474393530997e-05,
680
+ "loss": 0.9676,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.3104,
685
+ "grad_norm": 0.9999997615814209,
686
+ "learning_rate": 7.26078167115903e-05,
687
+ "loss": 1.0348,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.3136,
692
+ "grad_norm": 0.9999998211860657,
693
+ "learning_rate": 7.227088948787062e-05,
694
+ "loss": 1.0912,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.3168,
699
+ "grad_norm": 0.9999998211860657,
700
+ "learning_rate": 7.193396226415095e-05,
701
+ "loss": 0.9251,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.32,
706
+ "grad_norm": 0.9999998211860657,
707
+ "learning_rate": 7.159703504043128e-05,
708
+ "loss": 0.9651,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.3232,
713
+ "grad_norm": 0.9999998211860657,
714
+ "learning_rate": 7.126010781671159e-05,
715
+ "loss": 0.9448,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.3264,
720
+ "grad_norm": 0.9999998807907104,
721
+ "learning_rate": 7.092318059299192e-05,
722
+ "loss": 0.9397,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.3296,
727
+ "grad_norm": 0.9999997615814209,
728
+ "learning_rate": 7.058625336927224e-05,
729
+ "loss": 0.8734,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.3328,
734
+ "grad_norm": 0.9999998211860657,
735
+ "learning_rate": 7.024932614555257e-05,
736
+ "loss": 0.883,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.336,
741
+ "grad_norm": 0.9999998211860657,
742
+ "learning_rate": 6.99123989218329e-05,
743
+ "loss": 0.9049,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.3392,
748
+ "grad_norm": 0.9999999403953552,
749
+ "learning_rate": 6.957547169811321e-05,
750
+ "loss": 0.9222,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.3424,
755
+ "grad_norm": 0.9999997615814209,
756
+ "learning_rate": 6.923854447439353e-05,
757
+ "loss": 0.9091,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.3456,
762
+ "grad_norm": 0.9999997615814209,
763
+ "learning_rate": 6.890161725067386e-05,
764
+ "loss": 0.9974,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.3488,
769
+ "grad_norm": 0.9999998807907104,
770
+ "learning_rate": 6.856469002695418e-05,
771
+ "loss": 0.9262,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.352,
776
+ "grad_norm": 0.9999998807907104,
777
+ "learning_rate": 6.822776280323451e-05,
778
+ "loss": 0.9237,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.3552,
783
+ "grad_norm": 0.9999998211860657,
784
+ "learning_rate": 6.789083557951483e-05,
785
+ "loss": 0.8918,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.3584,
790
+ "grad_norm": 0.9999999403953552,
791
+ "learning_rate": 6.755390835579514e-05,
792
+ "loss": 0.9706,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.3616,
797
+ "grad_norm": 0.9999999403953552,
798
+ "learning_rate": 6.721698113207547e-05,
799
+ "loss": 0.8162,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.3648,
804
+ "grad_norm": 0.9999998807907104,
805
+ "learning_rate": 6.68800539083558e-05,
806
+ "loss": 0.894,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.368,
811
+ "grad_norm": 0.9999998211860657,
812
+ "learning_rate": 6.654312668463612e-05,
813
+ "loss": 0.8603,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.3712,
818
+ "grad_norm": 0.9999998807907104,
819
+ "learning_rate": 6.620619946091643e-05,
820
+ "loss": 0.8208,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.3744,
825
+ "grad_norm": 0.9999998807907104,
826
+ "learning_rate": 6.586927223719676e-05,
827
+ "loss": 0.8293,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.3776,
832
+ "grad_norm": 0.9999998211860657,
833
+ "learning_rate": 6.553234501347709e-05,
834
+ "loss": 0.8365,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.3808,
839
+ "grad_norm": 0.9999998807907104,
840
+ "learning_rate": 6.519541778975742e-05,
841
+ "loss": 0.8245,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.384,
846
+ "grad_norm": 0.9999997615814209,
847
+ "learning_rate": 6.485849056603774e-05,
848
+ "loss": 0.8185,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.3872,
853
+ "grad_norm": 0.9999998807907104,
854
+ "learning_rate": 6.452156334231805e-05,
855
+ "loss": 0.8074,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.3904,
860
+ "grad_norm": 0.9999998807907104,
861
+ "learning_rate": 6.418463611859838e-05,
862
+ "loss": 0.7867,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.3936,
867
+ "grad_norm": 0.9999997615814209,
868
+ "learning_rate": 6.384770889487871e-05,
869
+ "loss": 0.7521,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.3968,
874
+ "grad_norm": 0.9999998211860657,
875
+ "learning_rate": 6.351078167115904e-05,
876
+ "loss": 0.84,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.4,
881
+ "grad_norm": 0.9999998211860657,
882
+ "learning_rate": 6.317385444743936e-05,
883
+ "loss": 0.7753,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.4032,
888
+ "grad_norm": 0.9999998211860657,
889
+ "learning_rate": 6.283692722371967e-05,
890
+ "loss": 0.7454,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.4064,
895
+ "grad_norm": 0.9999998211860657,
896
+ "learning_rate": 6.25e-05,
897
+ "loss": 0.8022,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.4096,
902
+ "grad_norm": 0.9999997615814209,
903
+ "learning_rate": 6.216307277628033e-05,
904
+ "loss": 0.8555,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.4128,
909
+ "grad_norm": 0.9999998211860657,
910
+ "learning_rate": 6.182614555256066e-05,
911
+ "loss": 0.7896,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.416,
916
+ "grad_norm": 0.9999998211860657,
917
+ "learning_rate": 6.148921832884098e-05,
918
+ "loss": 0.8118,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.4192,
923
+ "grad_norm": 0.9999999403953552,
924
+ "learning_rate": 6.115229110512129e-05,
925
+ "loss": 0.7797,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.4224,
930
+ "grad_norm": 0.9999997615814209,
931
+ "learning_rate": 6.081536388140162e-05,
932
+ "loss": 0.7525,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.4256,
937
+ "grad_norm": 0.9999997019767761,
938
+ "learning_rate": 6.047843665768195e-05,
939
+ "loss": 0.7792,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.4288,
944
+ "grad_norm": 0.9999998807907104,
945
+ "learning_rate": 6.0141509433962265e-05,
946
+ "loss": 0.7726,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 0.432,
951
+ "grad_norm": 0.9999998807907104,
952
+ "learning_rate": 5.980458221024259e-05,
953
+ "loss": 0.7568,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 0.4352,
958
+ "grad_norm": 0.9999998211860657,
959
+ "learning_rate": 5.9467654986522916e-05,
960
+ "loss": 0.7533,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 0.4384,
965
+ "grad_norm": 0.9999998211860657,
966
+ "learning_rate": 5.913072776280324e-05,
967
+ "loss": 0.6976,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 0.4416,
972
+ "grad_norm": 0.9999998807907104,
973
+ "learning_rate": 5.879380053908357e-05,
974
+ "loss": 0.7086,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 0.4448,
979
+ "grad_norm": 0.9999997615814209,
980
+ "learning_rate": 5.8456873315363884e-05,
981
+ "loss": 0.7263,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 0.448,
986
+ "grad_norm": 0.9999998211860657,
987
+ "learning_rate": 5.8119946091644206e-05,
988
+ "loss": 0.7509,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 0.4512,
993
+ "grad_norm": 0.9999997019767761,
994
+ "learning_rate": 5.7783018867924535e-05,
995
+ "loss": 0.7335,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 0.4544,
1000
+ "grad_norm": 0.9999997615814209,
1001
+ "learning_rate": 5.744609164420486e-05,
1002
+ "loss": 0.6938,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.4576,
1007
+ "grad_norm": 0.9999998807907104,
1008
+ "learning_rate": 5.710916442048517e-05,
1009
+ "loss": 0.7498,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 0.4608,
1014
+ "grad_norm": 0.9999998807907104,
1015
+ "learning_rate": 5.6772237196765496e-05,
1016
+ "loss": 0.712,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 0.464,
1021
+ "grad_norm": 0.9999998211860657,
1022
+ "learning_rate": 5.6435309973045825e-05,
1023
+ "loss": 0.7554,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 0.4672,
1028
+ "grad_norm": 0.9999998211860657,
1029
+ "learning_rate": 5.609838274932615e-05,
1030
+ "loss": 0.7097,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 0.4704,
1035
+ "grad_norm": 0.9999998807907104,
1036
+ "learning_rate": 5.5761455525606476e-05,
1037
+ "loss": 0.6609,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 0.4736,
1042
+ "grad_norm": 0.9999999403953552,
1043
+ "learning_rate": 5.542452830188679e-05,
1044
+ "loss": 0.7271,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 0.4768,
1049
+ "grad_norm": 0.9999997615814209,
1050
+ "learning_rate": 5.5087601078167114e-05,
1051
+ "loss": 0.7051,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 0.48,
1056
+ "grad_norm": 0.9999997019767761,
1057
+ "learning_rate": 5.4750673854447444e-05,
1058
+ "loss": 0.639,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 0.4832,
1063
+ "grad_norm": 0.9999999403953552,
1064
+ "learning_rate": 5.4413746630727766e-05,
1065
+ "loss": 0.6541,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 0.4864,
1070
+ "grad_norm": 0.9999998211860657,
1071
+ "learning_rate": 5.407681940700808e-05,
1072
+ "loss": 0.7052,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 0.4896,
1077
+ "grad_norm": 0.9999999403953552,
1078
+ "learning_rate": 5.373989218328841e-05,
1079
+ "loss": 0.6734,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 0.4928,
1084
+ "grad_norm": 0.9999997615814209,
1085
+ "learning_rate": 5.340296495956873e-05,
1086
+ "loss": 0.6799,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 0.496,
1091
+ "grad_norm": 0.9999998211860657,
1092
+ "learning_rate": 5.306603773584906e-05,
1093
+ "loss": 0.655,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 0.4992,
1098
+ "grad_norm": 0.9999998211860657,
1099
+ "learning_rate": 5.2729110512129385e-05,
1100
+ "loss": 0.6558,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 0.5024,
1105
+ "grad_norm": 0.9999998807907104,
1106
+ "learning_rate": 5.23921832884097e-05,
1107
+ "loss": 0.6646,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 0.5056,
1112
+ "grad_norm": 0.9999998211860657,
1113
+ "learning_rate": 5.205525606469003e-05,
1114
+ "loss": 0.6283,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 0.5088,
1119
+ "grad_norm": 0.9999997615814209,
1120
+ "learning_rate": 5.171832884097035e-05,
1121
+ "loss": 0.6036,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 0.512,
1126
+ "grad_norm": 0.9999998807907104,
1127
+ "learning_rate": 5.138140161725068e-05,
1128
+ "loss": 0.6356,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 0.5152,
1133
+ "grad_norm": 0.9999999403953552,
1134
+ "learning_rate": 5.1044474393531e-05,
1135
+ "loss": 0.6533,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 0.5184,
1140
+ "grad_norm": 0.9999998211860657,
1141
+ "learning_rate": 5.070754716981132e-05,
1142
+ "loss": 0.6502,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 0.5216,
1147
+ "grad_norm": 0.9999998211860657,
1148
+ "learning_rate": 5.037061994609165e-05,
1149
+ "loss": 0.6149,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 0.5248,
1154
+ "grad_norm": 0.9999998807907104,
1155
+ "learning_rate": 5.003369272237197e-05,
1156
+ "loss": 0.6067,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 0.528,
1161
+ "grad_norm": 0.9999998807907104,
1162
+ "learning_rate": 4.969676549865229e-05,
1163
+ "loss": 0.6391,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 0.5312,
1168
+ "grad_norm": 0.9999998807907104,
1169
+ "learning_rate": 4.9359838274932616e-05,
1170
+ "loss": 0.6326,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 0.5344,
1175
+ "grad_norm": 0.9999998211860657,
1176
+ "learning_rate": 4.902291105121294e-05,
1177
+ "loss": 0.5844,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 0.5376,
1182
+ "grad_norm": 0.9999998211860657,
1183
+ "learning_rate": 4.868598382749327e-05,
1184
+ "loss": 0.5819,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 0.5408,
1189
+ "grad_norm": 0.9999997019767761,
1190
+ "learning_rate": 4.834905660377358e-05,
1191
+ "loss": 0.5874,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 0.544,
1196
+ "grad_norm": 0.9999997019767761,
1197
+ "learning_rate": 4.801212938005391e-05,
1198
+ "loss": 0.6167,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 0.5472,
1203
+ "grad_norm": 0.9999998807907104,
1204
+ "learning_rate": 4.7675202156334234e-05,
1205
+ "loss": 0.5793,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 0.5504,
1210
+ "grad_norm": 0.9999998807907104,
1211
+ "learning_rate": 4.733827493261456e-05,
1212
+ "loss": 0.5649,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 0.5536,
1217
+ "grad_norm": 0.9999998807907104,
1218
+ "learning_rate": 4.7001347708894886e-05,
1219
+ "loss": 0.575,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 0.5568,
1224
+ "grad_norm": 0.9999997615814209,
1225
+ "learning_rate": 4.66644204851752e-05,
1226
+ "loss": 0.611,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 0.56,
1231
+ "grad_norm": 0.9999997615814209,
1232
+ "learning_rate": 4.632749326145553e-05,
1233
+ "loss": 0.5746,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 0.5632,
1238
+ "grad_norm": 0.9999998211860657,
1239
+ "learning_rate": 4.5990566037735846e-05,
1240
+ "loss": 0.6094,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 0.5664,
1245
+ "grad_norm": 0.9999997615814209,
1246
+ "learning_rate": 4.5653638814016176e-05,
1247
+ "loss": 0.5542,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 0.5696,
1252
+ "grad_norm": 0.9999997615814209,
1253
+ "learning_rate": 4.53167115902965e-05,
1254
+ "loss": 0.5652,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 0.5728,
1259
+ "grad_norm": 0.9999998807907104,
1260
+ "learning_rate": 4.497978436657682e-05,
1261
+ "loss": 0.6055,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 0.576,
1266
+ "grad_norm": 0.9999998211860657,
1267
+ "learning_rate": 4.464285714285715e-05,
1268
+ "loss": 0.5633,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 0.5792,
1273
+ "grad_norm": 0.9999999403953552,
1274
+ "learning_rate": 4.4305929919137465e-05,
1275
+ "loss": 0.5832,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 0.5824,
1280
+ "grad_norm": 0.9999998807907104,
1281
+ "learning_rate": 4.3969002695417794e-05,
1282
+ "loss": 0.5602,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 0.5856,
1287
+ "grad_norm": 0.9999998807907104,
1288
+ "learning_rate": 4.363207547169812e-05,
1289
+ "loss": 0.6509,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 0.5888,
1294
+ "grad_norm": 0.9999998807907104,
1295
+ "learning_rate": 4.329514824797844e-05,
1296
+ "loss": 0.5299,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 0.592,
1301
+ "grad_norm": 0.9999998211860657,
1302
+ "learning_rate": 4.295822102425876e-05,
1303
+ "loss": 0.5828,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 0.5952,
1308
+ "grad_norm": 0.9999998807907104,
1309
+ "learning_rate": 4.2621293800539084e-05,
1310
+ "loss": 0.5318,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 0.5984,
1315
+ "grad_norm": 0.9999998211860657,
1316
+ "learning_rate": 4.2284366576819406e-05,
1317
+ "loss": 0.5179,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 0.6016,
1322
+ "grad_norm": 0.9999997615814209,
1323
+ "learning_rate": 4.1947439353099736e-05,
1324
+ "loss": 0.5874,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 0.6048,
1329
+ "grad_norm": 0.9999998211860657,
1330
+ "learning_rate": 4.161051212938006e-05,
1331
+ "loss": 0.5543,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 0.608,
1336
+ "grad_norm": 0.9999998807907104,
1337
+ "learning_rate": 4.127358490566038e-05,
1338
+ "loss": 0.5569,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 0.6112,
1343
+ "grad_norm": 0.9999998211860657,
1344
+ "learning_rate": 4.09366576819407e-05,
1345
+ "loss": 0.4994,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 0.6144,
1350
+ "grad_norm": 1.0,
1351
+ "learning_rate": 4.0599730458221025e-05,
1352
+ "loss": 0.6358,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 0.6176,
1357
+ "grad_norm": 0.9999998211860657,
1358
+ "learning_rate": 4.026280323450135e-05,
1359
+ "loss": 0.5509,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 0.6208,
1364
+ "grad_norm": 0.9999999403953552,
1365
+ "learning_rate": 3.992587601078167e-05,
1366
+ "loss": 0.5172,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 0.624,
1371
+ "grad_norm": 0.9999998211860657,
1372
+ "learning_rate": 3.9588948787062e-05,
1373
+ "loss": 0.5299,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 0.6272,
1378
+ "grad_norm": 0.9999998211860657,
1379
+ "learning_rate": 3.9252021563342315e-05,
1380
+ "loss": 0.5489,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 0.6304,
1385
+ "grad_norm": 0.9999998211860657,
1386
+ "learning_rate": 3.8915094339622644e-05,
1387
+ "loss": 0.5682,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 0.6336,
1392
+ "grad_norm": 0.9999998211860657,
1393
+ "learning_rate": 3.8578167115902966e-05,
1394
+ "loss": 0.5102,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 0.6368,
1399
+ "grad_norm": 0.9999997615814209,
1400
+ "learning_rate": 3.824123989218329e-05,
1401
+ "loss": 0.4894,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 0.64,
1406
+ "grad_norm": 0.9999998211860657,
1407
+ "learning_rate": 3.790431266846362e-05,
1408
+ "loss": 0.5157,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 0.6432,
1413
+ "grad_norm": 0.9999998807907104,
1414
+ "learning_rate": 3.7567385444743934e-05,
1415
+ "loss": 0.5583,
1416
+ "step": 2010
1417
+ },
1418
+ {
1419
+ "epoch": 0.6464,
1420
+ "grad_norm": 1.0,
1421
+ "learning_rate": 3.723045822102426e-05,
1422
+ "loss": 0.5314,
1423
+ "step": 2020
1424
+ },
1425
+ {
1426
+ "epoch": 0.6496,
1427
+ "grad_norm": 0.9999998211860657,
1428
+ "learning_rate": 3.689353099730458e-05,
1429
+ "loss": 0.5237,
1430
+ "step": 2030
1431
+ },
1432
+ {
1433
+ "epoch": 0.6528,
1434
+ "grad_norm": 0.9999998211860657,
1435
+ "learning_rate": 3.655660377358491e-05,
1436
+ "loss": 0.5142,
1437
+ "step": 2040
1438
+ },
1439
+ {
1440
+ "epoch": 0.656,
1441
+ "grad_norm": 0.9999999403953552,
1442
+ "learning_rate": 3.621967654986524e-05,
1443
+ "loss": 0.5398,
1444
+ "step": 2050
1445
+ },
1446
+ {
1447
+ "epoch": 0.6592,
1448
+ "grad_norm": 0.9999998807907104,
1449
+ "learning_rate": 3.588274932614555e-05,
1450
+ "loss": 0.5186,
1451
+ "step": 2060
1452
+ },
1453
+ {
1454
+ "epoch": 0.6624,
1455
+ "grad_norm": 0.9999997019767761,
1456
+ "learning_rate": 3.554582210242588e-05,
1457
+ "loss": 0.474,
1458
+ "step": 2070
1459
+ },
1460
+ {
1461
+ "epoch": 0.6656,
1462
+ "grad_norm": 0.9999998807907104,
1463
+ "learning_rate": 3.52088948787062e-05,
1464
+ "loss": 0.5297,
1465
+ "step": 2080
1466
+ },
1467
+ {
1468
+ "epoch": 0.6688,
1469
+ "grad_norm": 0.9999998211860657,
1470
+ "learning_rate": 3.4871967654986526e-05,
1471
+ "loss": 0.5392,
1472
+ "step": 2090
1473
+ },
1474
+ {
1475
+ "epoch": 0.672,
1476
+ "grad_norm": 0.9999999403953552,
1477
+ "learning_rate": 3.453504043126685e-05,
1478
+ "loss": 0.4953,
1479
+ "step": 2100
1480
+ },
1481
+ {
1482
+ "epoch": 0.6752,
1483
+ "grad_norm": 0.9999998211860657,
1484
+ "learning_rate": 3.419811320754717e-05,
1485
+ "loss": 0.5161,
1486
+ "step": 2110
1487
+ },
1488
+ {
1489
+ "epoch": 0.6784,
1490
+ "grad_norm": 0.9999998211860657,
1491
+ "learning_rate": 3.3861185983827494e-05,
1492
+ "loss": 0.4658,
1493
+ "step": 2120
1494
+ },
1495
+ {
1496
+ "epoch": 0.6816,
1497
+ "grad_norm": 0.9999998211860657,
1498
+ "learning_rate": 3.3524258760107816e-05,
1499
+ "loss": 0.4874,
1500
+ "step": 2130
1501
+ },
1502
+ {
1503
+ "epoch": 0.6848,
1504
+ "grad_norm": 0.9999997615814209,
1505
+ "learning_rate": 3.3187331536388145e-05,
1506
+ "loss": 0.5508,
1507
+ "step": 2140
1508
+ },
1509
+ {
1510
+ "epoch": 0.688,
1511
+ "grad_norm": 0.9999997615814209,
1512
+ "learning_rate": 3.285040431266847e-05,
1513
+ "loss": 0.5054,
1514
+ "step": 2150
1515
+ },
1516
+ {
1517
+ "epoch": 0.6912,
1518
+ "grad_norm": 0.9999998807907104,
1519
+ "learning_rate": 3.251347708894879e-05,
1520
+ "loss": 0.444,
1521
+ "step": 2160
1522
+ },
1523
+ {
1524
+ "epoch": 0.6944,
1525
+ "grad_norm": 0.9999998211860657,
1526
+ "learning_rate": 3.217654986522911e-05,
1527
+ "loss": 0.4757,
1528
+ "step": 2170
1529
+ },
1530
+ {
1531
+ "epoch": 0.6976,
1532
+ "grad_norm": 0.9999998807907104,
1533
+ "learning_rate": 3.1839622641509435e-05,
1534
+ "loss": 0.4786,
1535
+ "step": 2180
1536
+ },
1537
+ {
1538
+ "epoch": 0.7008,
1539
+ "grad_norm": 0.9999999403953552,
1540
+ "learning_rate": 3.150269541778976e-05,
1541
+ "loss": 0.4771,
1542
+ "step": 2190
1543
+ },
1544
+ {
1545
+ "epoch": 0.704,
1546
+ "grad_norm": 0.9999997019767761,
1547
+ "learning_rate": 3.1165768194070086e-05,
1548
+ "loss": 0.4734,
1549
+ "step": 2200
1550
+ },
1551
+ {
1552
+ "epoch": 0.7072,
1553
+ "grad_norm": 0.9999998211860657,
1554
+ "learning_rate": 3.08288409703504e-05,
1555
+ "loss": 0.561,
1556
+ "step": 2210
1557
+ },
1558
+ {
1559
+ "epoch": 0.7104,
1560
+ "grad_norm": 0.9999998211860657,
1561
+ "learning_rate": 3.0491913746630728e-05,
1562
+ "loss": 0.4613,
1563
+ "step": 2220
1564
+ },
1565
+ {
1566
+ "epoch": 0.7136,
1567
+ "grad_norm": 0.9999998807907104,
1568
+ "learning_rate": 3.0154986522911054e-05,
1569
+ "loss": 0.4811,
1570
+ "step": 2230
1571
+ },
1572
+ {
1573
+ "epoch": 0.7168,
1574
+ "grad_norm": 0.9999998211860657,
1575
+ "learning_rate": 2.9818059299191376e-05,
1576
+ "loss": 0.4352,
1577
+ "step": 2240
1578
+ },
1579
+ {
1580
+ "epoch": 0.72,
1581
+ "grad_norm": 0.9999998807907104,
1582
+ "learning_rate": 2.9481132075471702e-05,
1583
+ "loss": 0.4895,
1584
+ "step": 2250
1585
+ },
1586
+ {
1587
+ "epoch": 0.7232,
1588
+ "grad_norm": 0.9999998211860657,
1589
+ "learning_rate": 2.914420485175202e-05,
1590
+ "loss": 0.4737,
1591
+ "step": 2260
1592
+ },
1593
+ {
1594
+ "epoch": 0.7264,
1595
+ "grad_norm": 0.9999998211860657,
1596
+ "learning_rate": 2.8807277628032347e-05,
1597
+ "loss": 0.4311,
1598
+ "step": 2270
1599
+ },
1600
+ {
1601
+ "epoch": 0.7296,
1602
+ "grad_norm": 0.9999997615814209,
1603
+ "learning_rate": 2.847035040431267e-05,
1604
+ "loss": 0.4281,
1605
+ "step": 2280
1606
+ },
1607
+ {
1608
+ "epoch": 0.7328,
1609
+ "grad_norm": 0.9999998211860657,
1610
+ "learning_rate": 2.8133423180592995e-05,
1611
+ "loss": 0.4837,
1612
+ "step": 2290
1613
+ },
1614
+ {
1615
+ "epoch": 0.736,
1616
+ "grad_norm": 0.9999997615814209,
1617
+ "learning_rate": 2.7796495956873314e-05,
1618
+ "loss": 0.4498,
1619
+ "step": 2300
1620
+ },
1621
+ {
1622
+ "epoch": 0.7392,
1623
+ "grad_norm": 0.9999998807907104,
1624
+ "learning_rate": 2.745956873315364e-05,
1625
+ "loss": 0.4429,
1626
+ "step": 2310
1627
+ },
1628
+ {
1629
+ "epoch": 0.7424,
1630
+ "grad_norm": 0.9999997019767761,
1631
+ "learning_rate": 2.7122641509433965e-05,
1632
+ "loss": 0.5109,
1633
+ "step": 2320
1634
+ },
1635
+ {
1636
+ "epoch": 0.7456,
1637
+ "grad_norm": 0.9999998211860657,
1638
+ "learning_rate": 2.6785714285714288e-05,
1639
+ "loss": 0.4687,
1640
+ "step": 2330
1641
+ },
1642
+ {
1643
+ "epoch": 0.7488,
1644
+ "grad_norm": 0.9999998807907104,
1645
+ "learning_rate": 2.6448787061994614e-05,
1646
+ "loss": 0.476,
1647
+ "step": 2340
1648
+ },
1649
+ {
1650
+ "epoch": 0.752,
1651
+ "grad_norm": 0.9999997615814209,
1652
+ "learning_rate": 2.6111859838274933e-05,
1653
+ "loss": 0.4682,
1654
+ "step": 2350
1655
+ },
1656
+ {
1657
+ "epoch": 0.7552,
1658
+ "grad_norm": 0.9999998211860657,
1659
+ "learning_rate": 2.577493261455526e-05,
1660
+ "loss": 0.4515,
1661
+ "step": 2360
1662
+ },
1663
+ {
1664
+ "epoch": 0.7584,
1665
+ "grad_norm": 0.9999997615814209,
1666
+ "learning_rate": 2.5438005390835577e-05,
1667
+ "loss": 0.4167,
1668
+ "step": 2370
1669
+ },
1670
+ {
1671
+ "epoch": 0.7616,
1672
+ "grad_norm": 0.9999998211860657,
1673
+ "learning_rate": 2.5101078167115903e-05,
1674
+ "loss": 0.4342,
1675
+ "step": 2380
1676
+ },
1677
+ {
1678
+ "epoch": 0.7648,
1679
+ "grad_norm": 0.9999998807907104,
1680
+ "learning_rate": 2.476415094339623e-05,
1681
+ "loss": 0.4468,
1682
+ "step": 2390
1683
+ },
1684
+ {
1685
+ "epoch": 0.768,
1686
+ "grad_norm": 0.9999998807907104,
1687
+ "learning_rate": 2.442722371967655e-05,
1688
+ "loss": 0.4465,
1689
+ "step": 2400
1690
+ },
1691
+ {
1692
+ "epoch": 0.7712,
1693
+ "grad_norm": 0.9999998807907104,
1694
+ "learning_rate": 2.4090296495956874e-05,
1695
+ "loss": 0.4008,
1696
+ "step": 2410
1697
+ },
1698
+ {
1699
+ "epoch": 0.7744,
1700
+ "grad_norm": 0.9999998807907104,
1701
+ "learning_rate": 2.3753369272237196e-05,
1702
+ "loss": 0.4513,
1703
+ "step": 2420
1704
+ },
1705
+ {
1706
+ "epoch": 0.7776,
1707
+ "grad_norm": 0.9999998211860657,
1708
+ "learning_rate": 2.341644204851752e-05,
1709
+ "loss": 0.431,
1710
+ "step": 2430
1711
+ },
1712
+ {
1713
+ "epoch": 0.7808,
1714
+ "grad_norm": 0.9999998211860657,
1715
+ "learning_rate": 2.3079514824797844e-05,
1716
+ "loss": 0.4242,
1717
+ "step": 2440
1718
+ },
1719
+ {
1720
+ "epoch": 0.784,
1721
+ "grad_norm": 0.9999997019767761,
1722
+ "learning_rate": 2.274258760107817e-05,
1723
+ "loss": 0.412,
1724
+ "step": 2450
1725
+ },
1726
+ {
1727
+ "epoch": 0.7872,
1728
+ "grad_norm": 0.9999998211860657,
1729
+ "learning_rate": 2.2405660377358493e-05,
1730
+ "loss": 0.4532,
1731
+ "step": 2460
1732
+ },
1733
+ {
1734
+ "epoch": 0.7904,
1735
+ "grad_norm": 0.9999999403953552,
1736
+ "learning_rate": 2.2068733153638815e-05,
1737
+ "loss": 0.3779,
1738
+ "step": 2470
1739
+ },
1740
+ {
1741
+ "epoch": 0.7936,
1742
+ "grad_norm": 0.9999998807907104,
1743
+ "learning_rate": 2.1731805929919137e-05,
1744
+ "loss": 0.4426,
1745
+ "step": 2480
1746
+ },
1747
+ {
1748
+ "epoch": 0.7968,
1749
+ "grad_norm": 0.9999998211860657,
1750
+ "learning_rate": 2.1394878706199463e-05,
1751
+ "loss": 0.4239,
1752
+ "step": 2490
1753
+ },
1754
+ {
1755
+ "epoch": 0.8,
1756
+ "grad_norm": 1.0,
1757
+ "learning_rate": 2.1057951482479785e-05,
1758
+ "loss": 0.3927,
1759
+ "step": 2500
1760
+ },
1761
+ {
1762
+ "epoch": 0.8032,
1763
+ "grad_norm": 0.9999998211860657,
1764
+ "learning_rate": 2.0721024258760108e-05,
1765
+ "loss": 0.4217,
1766
+ "step": 2510
1767
+ },
1768
+ {
1769
+ "epoch": 0.8064,
1770
+ "grad_norm": 0.9999998211860657,
1771
+ "learning_rate": 2.038409703504043e-05,
1772
+ "loss": 0.4215,
1773
+ "step": 2520
1774
+ },
1775
+ {
1776
+ "epoch": 0.8096,
1777
+ "grad_norm": 0.9999998807907104,
1778
+ "learning_rate": 2.0047169811320756e-05,
1779
+ "loss": 0.4556,
1780
+ "step": 2530
1781
+ },
1782
+ {
1783
+ "epoch": 0.8128,
1784
+ "grad_norm": 1.0,
1785
+ "learning_rate": 1.971024258760108e-05,
1786
+ "loss": 0.4434,
1787
+ "step": 2540
1788
+ },
1789
+ {
1790
+ "epoch": 0.816,
1791
+ "grad_norm": 0.9999998807907104,
1792
+ "learning_rate": 1.9373315363881404e-05,
1793
+ "loss": 0.4255,
1794
+ "step": 2550
1795
+ },
1796
+ {
1797
+ "epoch": 0.8192,
1798
+ "grad_norm": 0.9999997615814209,
1799
+ "learning_rate": 1.9036388140161727e-05,
1800
+ "loss": 0.4167,
1801
+ "step": 2560
1802
+ },
1803
+ {
1804
+ "epoch": 0.8224,
1805
+ "grad_norm": 0.9999998211860657,
1806
+ "learning_rate": 1.869946091644205e-05,
1807
+ "loss": 0.4525,
1808
+ "step": 2570
1809
+ },
1810
+ {
1811
+ "epoch": 0.8256,
1812
+ "grad_norm": 0.9999998211860657,
1813
+ "learning_rate": 1.836253369272237e-05,
1814
+ "loss": 0.4351,
1815
+ "step": 2580
1816
+ },
1817
+ {
1818
+ "epoch": 0.8288,
1819
+ "grad_norm": 0.9999998807907104,
1820
+ "learning_rate": 1.8025606469002694e-05,
1821
+ "loss": 0.4177,
1822
+ "step": 2590
1823
+ },
1824
+ {
1825
+ "epoch": 0.832,
1826
+ "grad_norm": 0.9999997615814209,
1827
+ "learning_rate": 1.768867924528302e-05,
1828
+ "loss": 0.4165,
1829
+ "step": 2600
1830
+ },
1831
+ {
1832
+ "epoch": 0.8352,
1833
+ "grad_norm": 0.9999998807907104,
1834
+ "learning_rate": 1.7351752021563345e-05,
1835
+ "loss": 0.364,
1836
+ "step": 2610
1837
+ },
1838
+ {
1839
+ "epoch": 0.8384,
1840
+ "grad_norm": 0.9999998807907104,
1841
+ "learning_rate": 1.7014824797843668e-05,
1842
+ "loss": 0.424,
1843
+ "step": 2620
1844
+ },
1845
+ {
1846
+ "epoch": 0.8416,
1847
+ "grad_norm": 0.9999997615814209,
1848
+ "learning_rate": 1.667789757412399e-05,
1849
+ "loss": 0.4083,
1850
+ "step": 2630
1851
+ },
1852
+ {
1853
+ "epoch": 0.8448,
1854
+ "grad_norm": 0.9999998211860657,
1855
+ "learning_rate": 1.6340970350404313e-05,
1856
+ "loss": 0.424,
1857
+ "step": 2640
1858
+ },
1859
+ {
1860
+ "epoch": 0.848,
1861
+ "grad_norm": 0.9999997615814209,
1862
+ "learning_rate": 1.600404312668464e-05,
1863
+ "loss": 0.4166,
1864
+ "step": 2650
1865
+ },
1866
+ {
1867
+ "epoch": 0.8512,
1868
+ "grad_norm": 0.9999995827674866,
1869
+ "learning_rate": 1.566711590296496e-05,
1870
+ "loss": 0.3883,
1871
+ "step": 2660
1872
+ },
1873
+ {
1874
+ "epoch": 0.8544,
1875
+ "grad_norm": 0.9999998211860657,
1876
+ "learning_rate": 1.5330188679245283e-05,
1877
+ "loss": 0.3951,
1878
+ "step": 2670
1879
+ },
1880
+ {
1881
+ "epoch": 0.8576,
1882
+ "grad_norm": 0.9999999403953552,
1883
+ "learning_rate": 1.4993261455525606e-05,
1884
+ "loss": 0.4045,
1885
+ "step": 2680
1886
+ },
1887
+ {
1888
+ "epoch": 0.8608,
1889
+ "grad_norm": 0.9999998211860657,
1890
+ "learning_rate": 1.465633423180593e-05,
1891
+ "loss": 0.3974,
1892
+ "step": 2690
1893
+ },
1894
+ {
1895
+ "epoch": 0.864,
1896
+ "grad_norm": 0.9999998211860657,
1897
+ "learning_rate": 1.4319407008086256e-05,
1898
+ "loss": 0.3847,
1899
+ "step": 2700
1900
+ },
1901
+ {
1902
+ "epoch": 0.8672,
1903
+ "grad_norm": 0.9999998211860657,
1904
+ "learning_rate": 1.3982479784366578e-05,
1905
+ "loss": 0.4168,
1906
+ "step": 2710
1907
+ },
1908
+ {
1909
+ "epoch": 0.8704,
1910
+ "grad_norm": 0.9999998211860657,
1911
+ "learning_rate": 1.3645552560646902e-05,
1912
+ "loss": 0.3736,
1913
+ "step": 2720
1914
+ },
1915
+ {
1916
+ "epoch": 0.8736,
1917
+ "grad_norm": 0.9999998807907104,
1918
+ "learning_rate": 1.3308625336927224e-05,
1919
+ "loss": 0.4252,
1920
+ "step": 2730
1921
+ },
1922
+ {
1923
+ "epoch": 0.8768,
1924
+ "grad_norm": 0.9999998211860657,
1925
+ "learning_rate": 1.2971698113207547e-05,
1926
+ "loss": 0.3873,
1927
+ "step": 2740
1928
+ },
1929
+ {
1930
+ "epoch": 0.88,
1931
+ "grad_norm": 0.9999998807907104,
1932
+ "learning_rate": 1.2634770889487871e-05,
1933
+ "loss": 0.4049,
1934
+ "step": 2750
1935
+ },
1936
+ {
1937
+ "epoch": 0.8832,
1938
+ "grad_norm": 0.9999998211860657,
1939
+ "learning_rate": 1.2297843665768195e-05,
1940
+ "loss": 0.5941,
1941
+ "step": 2760
1942
+ },
1943
+ {
1944
+ "epoch": 0.8864,
1945
+ "grad_norm": 0.9999998211860657,
1946
+ "learning_rate": 1.1960916442048519e-05,
1947
+ "loss": 0.3756,
1948
+ "step": 2770
1949
+ },
1950
+ {
1951
+ "epoch": 0.8896,
1952
+ "grad_norm": 0.9999997019767761,
1953
+ "learning_rate": 1.1623989218328842e-05,
1954
+ "loss": 0.3537,
1955
+ "step": 2780
1956
+ },
1957
+ {
1958
+ "epoch": 0.8928,
1959
+ "grad_norm": 0.9999998211860657,
1960
+ "learning_rate": 1.1287061994609164e-05,
1961
+ "loss": 0.399,
1962
+ "step": 2790
1963
+ },
1964
+ {
1965
+ "epoch": 0.896,
1966
+ "grad_norm": 0.9999998211860657,
1967
+ "learning_rate": 1.0950134770889488e-05,
1968
+ "loss": 0.4019,
1969
+ "step": 2800
1970
+ },
1971
+ {
1972
+ "epoch": 0.8992,
1973
+ "grad_norm": 0.9999998211860657,
1974
+ "learning_rate": 1.0613207547169812e-05,
1975
+ "loss": 0.4116,
1976
+ "step": 2810
1977
+ },
1978
+ {
1979
+ "epoch": 0.9024,
1980
+ "grad_norm": 0.9999999403953552,
1981
+ "learning_rate": 1.0276280323450135e-05,
1982
+ "loss": 0.3609,
1983
+ "step": 2820
1984
+ },
1985
+ {
1986
+ "epoch": 0.9056,
1987
+ "grad_norm": 0.9999997019767761,
1988
+ "learning_rate": 9.939353099730459e-06,
1989
+ "loss": 0.4178,
1990
+ "step": 2830
1991
+ },
1992
+ {
1993
+ "epoch": 0.9088,
1994
+ "grad_norm": 0.9999998211860657,
1995
+ "learning_rate": 9.602425876010781e-06,
1996
+ "loss": 0.3782,
1997
+ "step": 2840
1998
+ },
1999
+ {
2000
+ "epoch": 0.912,
2001
+ "grad_norm": 0.9999999403953552,
2002
+ "learning_rate": 9.265498652291107e-06,
2003
+ "loss": 0.3814,
2004
+ "step": 2850
2005
+ },
2006
+ {
2007
+ "epoch": 0.9152,
2008
+ "grad_norm": 0.9999998211860657,
2009
+ "learning_rate": 8.92857142857143e-06,
2010
+ "loss": 0.3763,
2011
+ "step": 2860
2012
+ },
2013
+ {
2014
+ "epoch": 0.9184,
2015
+ "grad_norm": 0.9999998211860657,
2016
+ "learning_rate": 8.591644204851752e-06,
2017
+ "loss": 0.3534,
2018
+ "step": 2870
2019
+ },
2020
+ {
2021
+ "epoch": 0.9216,
2022
+ "grad_norm": 0.9999998211860657,
2023
+ "learning_rate": 8.254716981132076e-06,
2024
+ "loss": 0.4102,
2025
+ "step": 2880
2026
+ },
2027
+ {
2028
+ "epoch": 0.9248,
2029
+ "grad_norm": 0.9999999403953552,
2030
+ "learning_rate": 7.9177897574124e-06,
2031
+ "loss": 0.3824,
2032
+ "step": 2890
2033
+ },
2034
+ {
2035
+ "epoch": 0.928,
2036
+ "grad_norm": 0.9999998211860657,
2037
+ "learning_rate": 7.580862533692723e-06,
2038
+ "loss": 0.4134,
2039
+ "step": 2900
2040
+ },
2041
+ {
2042
+ "epoch": 0.9312,
2043
+ "grad_norm": 0.9999998211860657,
2044
+ "learning_rate": 7.243935309973046e-06,
2045
+ "loss": 0.3944,
2046
+ "step": 2910
2047
+ },
2048
+ {
2049
+ "epoch": 0.9344,
2050
+ "grad_norm": 0.9999997615814209,
2051
+ "learning_rate": 6.90700808625337e-06,
2052
+ "loss": 0.3949,
2053
+ "step": 2920
2054
+ },
2055
+ {
2056
+ "epoch": 0.9376,
2057
+ "grad_norm": 0.9999998211860657,
2058
+ "learning_rate": 6.570080862533692e-06,
2059
+ "loss": 0.385,
2060
+ "step": 2930
2061
+ },
2062
+ {
2063
+ "epoch": 0.9408,
2064
+ "grad_norm": 0.9999997019767761,
2065
+ "learning_rate": 6.233153638814016e-06,
2066
+ "loss": 0.3935,
2067
+ "step": 2940
2068
+ },
2069
+ {
2070
+ "epoch": 0.944,
2071
+ "grad_norm": 0.9999998807907104,
2072
+ "learning_rate": 5.89622641509434e-06,
2073
+ "loss": 0.3674,
2074
+ "step": 2950
2075
+ },
2076
+ {
2077
+ "epoch": 0.9472,
2078
+ "grad_norm": 0.9999998807907104,
2079
+ "learning_rate": 5.5592991913746634e-06,
2080
+ "loss": 0.3692,
2081
+ "step": 2960
2082
+ },
2083
+ {
2084
+ "epoch": 0.9504,
2085
+ "grad_norm": 0.9999998211860657,
2086
+ "learning_rate": 5.222371967654987e-06,
2087
+ "loss": 0.3985,
2088
+ "step": 2970
2089
+ },
2090
+ {
2091
+ "epoch": 0.9536,
2092
+ "grad_norm": 0.9999998211860657,
2093
+ "learning_rate": 4.88544474393531e-06,
2094
+ "loss": 0.3791,
2095
+ "step": 2980
2096
+ },
2097
+ {
2098
+ "epoch": 0.9568,
2099
+ "grad_norm": 0.9999998211860657,
2100
+ "learning_rate": 4.548517520215634e-06,
2101
+ "loss": 0.3763,
2102
+ "step": 2990
2103
+ },
2104
+ {
2105
+ "epoch": 0.96,
2106
+ "grad_norm": 0.9999997615814209,
2107
+ "learning_rate": 4.211590296495957e-06,
2108
+ "loss": 0.4065,
2109
+ "step": 3000
2110
+ },
2111
+ {
2112
+ "epoch": 0.9632,
2113
+ "grad_norm": 0.9999997019767761,
2114
+ "learning_rate": 3.8746630727762805e-06,
2115
+ "loss": 0.3502,
2116
+ "step": 3010
2117
+ },
2118
+ {
2119
+ "epoch": 0.9664,
2120
+ "grad_norm": 0.9999998807907104,
2121
+ "learning_rate": 3.5377358490566038e-06,
2122
+ "loss": 0.4178,
2123
+ "step": 3020
2124
+ },
2125
+ {
2126
+ "epoch": 0.9696,
2127
+ "grad_norm": 0.9999998211860657,
2128
+ "learning_rate": 3.200808625336928e-06,
2129
+ "loss": 0.3689,
2130
+ "step": 3030
2131
+ },
2132
+ {
2133
+ "epoch": 0.9728,
2134
+ "grad_norm": 0.9999999403953552,
2135
+ "learning_rate": 2.8638814016172507e-06,
2136
+ "loss": 0.4036,
2137
+ "step": 3040
2138
+ },
2139
+ {
2140
+ "epoch": 0.976,
2141
+ "grad_norm": 0.9999998211860657,
2142
+ "learning_rate": 2.5269541778975744e-06,
2143
+ "loss": 0.3813,
2144
+ "step": 3050
2145
+ },
2146
+ {
2147
+ "epoch": 0.9792,
2148
+ "grad_norm": 0.9999997615814209,
2149
+ "learning_rate": 2.1900269541778976e-06,
2150
+ "loss": 0.4084,
2151
+ "step": 3060
2152
+ },
2153
+ {
2154
+ "epoch": 0.9824,
2155
+ "grad_norm": 0.9999997019767761,
2156
+ "learning_rate": 1.853099730458221e-06,
2157
+ "loss": 0.3416,
2158
+ "step": 3070
2159
+ },
2160
+ {
2161
+ "epoch": 0.9856,
2162
+ "grad_norm": 0.9999998211860657,
2163
+ "learning_rate": 1.5161725067385445e-06,
2164
+ "loss": 0.3627,
2165
+ "step": 3080
2166
+ },
2167
+ {
2168
+ "epoch": 0.9888,
2169
+ "grad_norm": 0.9999998211860657,
2170
+ "learning_rate": 1.179245283018868e-06,
2171
+ "loss": 0.3732,
2172
+ "step": 3090
2173
+ },
2174
+ {
2175
+ "epoch": 0.992,
2176
+ "grad_norm": 0.9999997615814209,
2177
+ "learning_rate": 8.423180592991913e-07,
2178
+ "loss": 0.3656,
2179
+ "step": 3100
2180
+ },
2181
+ {
2182
+ "epoch": 0.9952,
2183
+ "grad_norm": 0.9999998211860657,
2184
+ "learning_rate": 5.053908355795148e-07,
2185
+ "loss": 0.372,
2186
+ "step": 3110
2187
+ },
2188
+ {
2189
+ "epoch": 0.9984,
2190
+ "grad_norm": 0.9999998807907104,
2191
+ "learning_rate": 1.684636118598383e-07,
2192
+ "loss": 0.3606,
2193
+ "step": 3120
2194
+ }
2195
+ ],
2196
+ "logging_steps": 10,
2197
+ "max_steps": 3125,
2198
+ "num_input_tokens_seen": 0,
2199
+ "num_train_epochs": 1,
2200
+ "save_steps": 500,
2201
+ "stateful_callbacks": {
2202
+ "TrainerControl": {
2203
+ "args": {
2204
+ "should_epoch_stop": false,
2205
+ "should_evaluate": false,
2206
+ "should_log": false,
2207
+ "should_save": true,
2208
+ "should_training_stop": true
2209
+ },
2210
+ "attributes": {}
2211
+ }
2212
+ },
2213
+ "total_flos": 0.0,
2214
+ "train_batch_size": 32,
2215
+ "trial_name": null,
2216
+ "trial_params": null
2217
+ }
checkpoint-3125/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6fc1dc38c8da9483b4aa53468be307a1536980e013c78e9eaf8b57784394c40
3
+ size 5304
checkpoint-3125/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "transformers_version": "4.45.2",
38
+ "use_cache": true,
39
+ "vocab_size": 50257
40
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": false,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 1024,
19
+ "pad_token": "<|endoftext|>",
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
training_logs.csv ADDED
@@ -0,0 +1,314 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ step,training_loss,grad_norm
2
+ 10,22.4779,0.9999998211860657
3
+ 20,18.8384,0.9999998211860657
4
+ 30,19.7931,0.9999999403953552
5
+ 40,19.6268,0.9999999403953552
6
+ 50,17.6451,0.9999998807907104
7
+ 60,18.5002,0.9999998807907104
8
+ 70,16.7061,0.9999999403953552
9
+ 80,14.6224,0.9999998807907104
10
+ 90,14.3869,0.9999999403953552
11
+ 100,13.3853,0.9999998211860657
12
+ 110,10.5028,0.9999999403953552
13
+ 120,11.3589,0.9999999403953552
14
+ 130,8.8268,0.9999999403953552
15
+ 140,8.1005,0.9999998211860657
16
+ 150,7.0647,0.9999998807907104
17
+ 160,6.3656,0.9999999403953552
18
+ 170,5.5873,0.9999999403953552
19
+ 180,5.3475,0.9999998211860657
20
+ 190,4.8772,0.9999998807907104
21
+ 200,4.3908,1.0
22
+ 210,3.9887,0.9999999403953552
23
+ 220,3.5629,0.9999999403953552
24
+ 230,3.8297,0.9999998211860657
25
+ 240,3.4697,0.9999998211860657
26
+ 250,3.4108,0.9999998211860657
27
+ 260,3.3772,0.9999998807907104
28
+ 270,3.3633,0.9999998211860657
29
+ 280,3.1345,0.9999999403953552
30
+ 290,2.9512,0.9999998211860657
31
+ 300,3.347,0.9999999403953552
32
+ 310,3.1399,0.9999999403953552
33
+ 320,2.9876,0.9999998807907104
34
+ 330,2.825,0.9999998807907104
35
+ 340,2.6934,0.9999999403953552
36
+ 350,2.6445,0.9999998807907104
37
+ 360,2.6892,0.9999998807907104
38
+ 370,2.5397,0.9999998807907104
39
+ 380,2.7159,0.9999999403953552
40
+ 390,2.5994,0.9999998807907104
41
+ 400,2.2929,0.9999998807907104
42
+ 410,2.51,0.9999998211860657
43
+ 420,2.2427,0.9999998807907104
44
+ 430,2.3756,0.9999999403953552
45
+ 440,2.2291,0.9999999403953552
46
+ 450,2.2808,0.9999999403953552
47
+ 460,1.9267,0.9999998807907104
48
+ 470,2.16,0.9999999403953552
49
+ 480,1.9578,0.9999998807907104
50
+ 490,2.0149,0.9999998211860657
51
+ 500,2.2299,0.9999997615814209
52
+ 510,1.9608,0.9999998211860657
53
+ 520,2.0082,0.9999998211860657
54
+ 530,1.7805,0.9999997615814209
55
+ 540,1.8744,0.9999999403953552
56
+ 550,1.8776,0.9999998807907104
57
+ 560,1.8193,0.9999998807907104
58
+ 570,1.6604,0.9999997615814209
59
+ 580,1.8959,0.9999998211860657
60
+ 590,1.8175,0.9999998211860657
61
+ 600,1.9855,0.9999998807907104
62
+ 610,1.6491,0.9999998211860657
63
+ 620,1.4581,0.9999997615814209
64
+ 630,1.6256,1.0
65
+ 640,1.7204,0.9999998807907104
66
+ 650,1.6769,0.9999998807907104
67
+ 660,1.6198,0.9999997615814209
68
+ 670,1.6906,0.9999999403953552
69
+ 680,1.508,0.9999998807907104
70
+ 690,1.45,0.9999998211860657
71
+ 700,1.4575,0.9999998807907104
72
+ 710,1.5332,0.9999998807907104
73
+ 720,1.3485,0.9999998211860657
74
+ 730,1.3703,0.9999998807907104
75
+ 740,1.4383,0.9999998807907104
76
+ 750,1.4196,0.9999998211860657
77
+ 760,1.4706,0.9999998211860657
78
+ 770,1.4038,0.9999998807907104
79
+ 780,1.3802,0.9999998807907104
80
+ 790,1.3093,0.9999998807907104
81
+ 800,1.2819,0.9999998211860657
82
+ 810,1.1946,0.9999997615814209
83
+ 820,1.4261,0.9999998211860657
84
+ 830,1.1928,0.9999998211860657
85
+ 840,1.2264,0.9999998211860657
86
+ 850,1.2548,0.9999997615814209
87
+ 860,1.2714,0.9999998211860657
88
+ 870,1.1514,0.9999997615814209
89
+ 880,1.1413,0.9999997615814209
90
+ 890,1.1009,0.9999998211860657
91
+ 900,1.0864,0.9999998211860657
92
+ 910,1.1562,0.9999998807907104
93
+ 920,1.0136,0.9999998211860657
94
+ 930,1.0745,0.9999998211860657
95
+ 940,1.0076,0.9999998807907104
96
+ 950,1.0461,0.9999997615814209
97
+ 960,0.9676,0.9999998211860657
98
+ 970,1.0348,0.9999997615814209
99
+ 980,1.0912,0.9999998211860657
100
+ 990,0.9251,0.9999998211860657
101
+ 1000,0.9651,0.9999998211860657
102
+ 1010,0.9448,0.9999998211860657
103
+ 1020,0.9397,0.9999998807907104
104
+ 1030,0.8734,0.9999997615814209
105
+ 1040,0.883,0.9999998211860657
106
+ 1050,0.9049,0.9999998211860657
107
+ 1060,0.9222,0.9999999403953552
108
+ 1070,0.9091,0.9999997615814209
109
+ 1080,0.9974,0.9999997615814209
110
+ 1090,0.9262,0.9999998807907104
111
+ 1100,0.9237,0.9999998807907104
112
+ 1110,0.8918,0.9999998211860657
113
+ 1120,0.9706,0.9999999403953552
114
+ 1130,0.8162,0.9999999403953552
115
+ 1140,0.894,0.9999998807907104
116
+ 1150,0.8603,0.9999998211860657
117
+ 1160,0.8208,0.9999998807907104
118
+ 1170,0.8293,0.9999998807907104
119
+ 1180,0.8365,0.9999998211860657
120
+ 1190,0.8245,0.9999998807907104
121
+ 1200,0.8185,0.9999997615814209
122
+ 1210,0.8074,0.9999998807907104
123
+ 1220,0.7867,0.9999998807907104
124
+ 1230,0.7521,0.9999997615814209
125
+ 1240,0.84,0.9999998211860657
126
+ 1250,0.7753,0.9999998211860657
127
+ 1260,0.7454,0.9999998211860657
128
+ 1270,0.8022,0.9999998211860657
129
+ 1280,0.8555,0.9999997615814209
130
+ 1290,0.7896,0.9999998211860657
131
+ 1300,0.8118,0.9999998211860657
132
+ 1310,0.7797,0.9999999403953552
133
+ 1320,0.7525,0.9999997615814209
134
+ 1330,0.7792,0.9999997019767761
135
+ 1340,0.7726,0.9999998807907104
136
+ 1350,0.7568,0.9999998807907104
137
+ 1360,0.7533,0.9999998211860657
138
+ 1370,0.6976,0.9999998211860657
139
+ 1380,0.7086,0.9999998807907104
140
+ 1390,0.7263,0.9999997615814209
141
+ 1400,0.7509,0.9999998211860657
142
+ 1410,0.7335,0.9999997019767761
143
+ 1420,0.6938,0.9999997615814209
144
+ 1430,0.7498,0.9999998807907104
145
+ 1440,0.712,0.9999998807907104
146
+ 1450,0.7554,0.9999998211860657
147
+ 1460,0.7097,0.9999998211860657
148
+ 1470,0.6609,0.9999998807907104
149
+ 1480,0.7271,0.9999999403953552
150
+ 1490,0.7051,0.9999997615814209
151
+ 1500,0.639,0.9999997019767761
152
+ 1510,0.6541,0.9999999403953552
153
+ 1520,0.7052,0.9999998211860657
154
+ 1530,0.6734,0.9999999403953552
155
+ 1540,0.6799,0.9999997615814209
156
+ 1550,0.655,0.9999998211860657
157
+ 1560,0.6558,0.9999998211860657
158
+ 1570,0.6646,0.9999998807907104
159
+ 1580,0.6283,0.9999998211860657
160
+ 1590,0.6036,0.9999997615814209
161
+ 1600,0.6356,0.9999998807907104
162
+ 1610,0.6533,0.9999999403953552
163
+ 1620,0.6502,0.9999998211860657
164
+ 1630,0.6149,0.9999998211860657
165
+ 1640,0.6067,0.9999998807907104
166
+ 1650,0.6391,0.9999998807907104
167
+ 1660,0.6326,0.9999998807907104
168
+ 1670,0.5844,0.9999998211860657
169
+ 1680,0.5819,0.9999998211860657
170
+ 1690,0.5874,0.9999997019767761
171
+ 1700,0.6167,0.9999997019767761
172
+ 1710,0.5793,0.9999998807907104
173
+ 1720,0.5649,0.9999998807907104
174
+ 1730,0.575,0.9999998807907104
175
+ 1740,0.611,0.9999997615814209
176
+ 1750,0.5746,0.9999997615814209
177
+ 1760,0.6094,0.9999998211860657
178
+ 1770,0.5542,0.9999997615814209
179
+ 1780,0.5652,0.9999997615814209
180
+ 1790,0.6055,0.9999998807907104
181
+ 1800,0.5633,0.9999998211860657
182
+ 1810,0.5832,0.9999999403953552
183
+ 1820,0.5602,0.9999998807907104
184
+ 1830,0.6509,0.9999998807907104
185
+ 1840,0.5299,0.9999998807907104
186
+ 1850,0.5828,0.9999998211860657
187
+ 1860,0.5318,0.9999998807907104
188
+ 1870,0.5179,0.9999998211860657
189
+ 1880,0.5874,0.9999997615814209
190
+ 1890,0.5543,0.9999998211860657
191
+ 1900,0.5569,0.9999998807907104
192
+ 1910,0.4994,0.9999998211860657
193
+ 1920,0.6358,1.0
194
+ 1930,0.5509,0.9999998211860657
195
+ 1940,0.5172,0.9999999403953552
196
+ 1950,0.5299,0.9999998211860657
197
+ 1960,0.5489,0.9999998211860657
198
+ 1970,0.5682,0.9999998211860657
199
+ 1980,0.5102,0.9999998211860657
200
+ 1990,0.4894,0.9999997615814209
201
+ 2000,0.5157,0.9999998211860657
202
+ 2010,0.5583,0.9999998807907104
203
+ 2020,0.5314,1.0
204
+ 2030,0.5237,0.9999998211860657
205
+ 2040,0.5142,0.9999998211860657
206
+ 2050,0.5398,0.9999999403953552
207
+ 2060,0.5186,0.9999998807907104
208
+ 2070,0.474,0.9999997019767761
209
+ 2080,0.5297,0.9999998807907104
210
+ 2090,0.5392,0.9999998211860657
211
+ 2100,0.4953,0.9999999403953552
212
+ 2110,0.5161,0.9999998211860657
213
+ 2120,0.4658,0.9999998211860657
214
+ 2130,0.4874,0.9999998211860657
215
+ 2140,0.5508,0.9999997615814209
216
+ 2150,0.5054,0.9999997615814209
217
+ 2160,0.444,0.9999998807907104
218
+ 2170,0.4757,0.9999998211860657
219
+ 2180,0.4786,0.9999998807907104
220
+ 2190,0.4771,0.9999999403953552
221
+ 2200,0.4734,0.9999997019767761
222
+ 2210,0.561,0.9999998211860657
223
+ 2220,0.4613,0.9999998211860657
224
+ 2230,0.4811,0.9999998807907104
225
+ 2240,0.4352,0.9999998211860657
226
+ 2250,0.4895,0.9999998807907104
227
+ 2260,0.4737,0.9999998211860657
228
+ 2270,0.4311,0.9999998211860657
229
+ 2280,0.4281,0.9999997615814209
230
+ 2290,0.4837,0.9999998211860657
231
+ 2300,0.4498,0.9999997615814209
232
+ 2310,0.4429,0.9999998807907104
233
+ 2320,0.5109,0.9999997019767761
234
+ 2330,0.4687,0.9999998211860657
235
+ 2340,0.476,0.9999998807907104
236
+ 2350,0.4682,0.9999997615814209
237
+ 2360,0.4515,0.9999998211860657
238
+ 2370,0.4167,0.9999997615814209
239
+ 2380,0.4342,0.9999998211860657
240
+ 2390,0.4468,0.9999998807907104
241
+ 2400,0.4465,0.9999998807907104
242
+ 2410,0.4008,0.9999998807907104
243
+ 2420,0.4513,0.9999998807907104
244
+ 2430,0.431,0.9999998211860657
245
+ 2440,0.4242,0.9999998211860657
246
+ 2450,0.412,0.9999997019767761
247
+ 2460,0.4532,0.9999998211860657
248
+ 2470,0.3779,0.9999999403953552
249
+ 2480,0.4426,0.9999998807907104
250
+ 2490,0.4239,0.9999998211860657
251
+ 2500,0.3927,1.0
252
+ 2510,0.4217,0.9999998211860657
253
+ 2520,0.4215,0.9999998211860657
254
+ 2530,0.4556,0.9999998807907104
255
+ 2540,0.4434,1.0
256
+ 2550,0.4255,0.9999998807907104
257
+ 2560,0.4167,0.9999997615814209
258
+ 2570,0.4525,0.9999998211860657
259
+ 2580,0.4351,0.9999998211860657
260
+ 2590,0.4177,0.9999998807907104
261
+ 2600,0.4165,0.9999997615814209
262
+ 2610,0.364,0.9999998807907104
263
+ 2620,0.424,0.9999998807907104
264
+ 2630,0.4083,0.9999997615814209
265
+ 2640,0.424,0.9999998211860657
266
+ 2650,0.4166,0.9999997615814209
267
+ 2660,0.3883,0.9999995827674866
268
+ 2670,0.3951,0.9999998211860657
269
+ 2680,0.4045,0.9999999403953552
270
+ 2690,0.3974,0.9999998211860657
271
+ 2700,0.3847,0.9999998211860657
272
+ 2710,0.4168,0.9999998211860657
273
+ 2720,0.3736,0.9999998211860657
274
+ 2730,0.4252,0.9999998807907104
275
+ 2740,0.3873,0.9999998211860657
276
+ 2750,0.4049,0.9999998807907104
277
+ 2760,0.5941,0.9999998211860657
278
+ 2770,0.3756,0.9999998211860657
279
+ 2780,0.3537,0.9999997019767761
280
+ 2790,0.399,0.9999998211860657
281
+ 2800,0.4019,0.9999998211860657
282
+ 2810,0.4116,0.9999998211860657
283
+ 2820,0.3609,0.9999999403953552
284
+ 2830,0.4178,0.9999997019767761
285
+ 2840,0.3782,0.9999998211860657
286
+ 2850,0.3814,0.9999999403953552
287
+ 2860,0.3763,0.9999998211860657
288
+ 2870,0.3534,0.9999998211860657
289
+ 2880,0.4102,0.9999998211860657
290
+ 2890,0.3824,0.9999999403953552
291
+ 2900,0.4134,0.9999998211860657
292
+ 2910,0.3944,0.9999998211860657
293
+ 2920,0.3949,0.9999997615814209
294
+ 2930,0.385,0.9999998211860657
295
+ 2940,0.3935,0.9999997019767761
296
+ 2950,0.3674,0.9999998807907104
297
+ 2960,0.3692,0.9999998807907104
298
+ 2970,0.3985,0.9999998211860657
299
+ 2980,0.3791,0.9999998211860657
300
+ 2990,0.3763,0.9999998211860657
301
+ 3000,0.4065,0.9999997615814209
302
+ 3010,0.3502,0.9999997019767761
303
+ 3020,0.4178,0.9999998807907104
304
+ 3030,0.3689,0.9999998211860657
305
+ 3040,0.4036,0.9999999403953552
306
+ 3050,0.3813,0.9999998211860657
307
+ 3060,0.4084,0.9999997615814209
308
+ 3070,0.3416,0.9999997019767761
309
+ 3080,0.3627,0.9999998211860657
310
+ 3090,0.3732,0.9999998211860657
311
+ 3100,0.3656,0.9999997615814209
312
+ 3110,0.372,0.9999998211860657
313
+ 3120,0.3606,0.9999998807907104
314
+ 3125,nan,nan
vocab.json ADDED
The diff for this file is too large to render. See raw diff