akkky02 commited on
Commit
8123f19
1 Parent(s): 8149b8e

Upload folder using huggingface_hub

Browse files
Files changed (33) hide show
  1. llama2_7b_base_adapter/.gitattributes +35 -0
  2. llama2_7b_base_adapter/README.md +204 -0
  3. llama2_7b_base_adapter/adapter_config.json +27 -0
  4. llama2_7b_base_adapter/adapter_model.safetensors +3 -0
  5. llama2_7b_base_adapter/all_results.json +7 -0
  6. llama2_7b_base_adapter/bnb_config.json +6 -0
  7. llama2_7b_base_adapter/checkpoint-350/README.md +204 -0
  8. llama2_7b_base_adapter/checkpoint-350/adapter_config.json +27 -0
  9. llama2_7b_base_adapter/checkpoint-350/adapter_model.safetensors +3 -0
  10. llama2_7b_base_adapter/checkpoint-350/optimizer.pt +3 -0
  11. llama2_7b_base_adapter/checkpoint-350/rng_state.pth +3 -0
  12. llama2_7b_base_adapter/checkpoint-350/scheduler.pt +3 -0
  13. llama2_7b_base_adapter/checkpoint-350/trainer_state.json +2121 -0
  14. llama2_7b_base_adapter/checkpoint-350/training_args.bin +3 -0
  15. llama2_7b_base_adapter/checkpoint-375/README.md +204 -0
  16. llama2_7b_base_adapter/checkpoint-375/adapter_config.json +27 -0
  17. llama2_7b_base_adapter/checkpoint-375/adapter_model.safetensors +3 -0
  18. llama2_7b_base_adapter/checkpoint-375/optimizer.pt +3 -0
  19. llama2_7b_base_adapter/checkpoint-375/rng_state.pth +3 -0
  20. llama2_7b_base_adapter/checkpoint-375/scheduler.pt +3 -0
  21. llama2_7b_base_adapter/checkpoint-375/trainer_state.json +2271 -0
  22. llama2_7b_base_adapter/checkpoint-375/training_args.bin +3 -0
  23. llama2_7b_base_adapter/checkpoint-400/README.md +204 -0
  24. llama2_7b_base_adapter/checkpoint-400/adapter_config.json +27 -0
  25. llama2_7b_base_adapter/checkpoint-400/adapter_model.safetensors +3 -0
  26. llama2_7b_base_adapter/checkpoint-400/optimizer.pt +3 -0
  27. llama2_7b_base_adapter/checkpoint-400/rng_state.pth +3 -0
  28. llama2_7b_base_adapter/checkpoint-400/scheduler.pt +3 -0
  29. llama2_7b_base_adapter/checkpoint-400/trainer_state.json +2421 -0
  30. llama2_7b_base_adapter/checkpoint-400/training_args.bin +3 -0
  31. llama2_7b_base_adapter/train_results.json +7 -0
  32. llama2_7b_base_adapter/trainer_state.json +2454 -0
  33. llama2_7b_base_adapter/training_args.bin +3 -0
llama2_7b_base_adapter/.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
llama2_7b_base_adapter/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Llama-2-7b-hf
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
llama2_7b_base_adapter/adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16.0,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj,",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
llama2_7b_base_adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fef8323423be8b15b5e4e6be21051e12d58122a4b08216f475b96979cdff35a
3
+ size 8397056
llama2_7b_base_adapter/all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.8384708828560197,
4
+ "train_runtime": 16978.7398,
5
+ "train_samples_per_second": 3.049,
6
+ "train_steps_per_second": 0.024
7
+ }
llama2_7b_base_adapter/bnb_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "load_in_4bit": false,
3
+ "bnb_4bit_quant_type" : "fp4",
4
+ "bnb_4bit_use_double_quant" : false,
5
+ "bnb_4bit_compute_dtype" : "float32"
6
+ }
llama2_7b_base_adapter/checkpoint-350/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Llama-2-7b-hf
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
llama2_7b_base_adapter/checkpoint-350/adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16.0,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj,",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
llama2_7b_base_adapter/checkpoint-350/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668382ecdd5335b4114944a06a5b1f3b6e7f3e3bde60e4892d7d9541dce67af2
3
+ size 8397056
llama2_7b_base_adapter/checkpoint-350/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b2b62dc10131653000f452105f497b5e6dc13b8ea6cc073eca8d09a14da7b11
3
+ size 16831290
llama2_7b_base_adapter/checkpoint-350/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fad764dc4fdad5d5711c95cabb670515d289d8f504219305df3572500a90d7f
3
+ size 14244
llama2_7b_base_adapter/checkpoint-350/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb8667a83950be0c98f02598cd77edba87c3860dfb23232169d020ae72feaa8
3
+ size 1064
llama2_7b_base_adapter/checkpoint-350/trainer_state.json ADDED
@@ -0,0 +1,2121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.865533230293663,
5
+ "eval_steps": 500,
6
+ "global_step": 350,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.0003,
14
+ "loss": 1.717,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 0.0003,
20
+ "loss": 1.5844,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.0003,
26
+ "loss": 1.6147,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 0.0003,
32
+ "loss": 1.6272,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 0.0003,
38
+ "loss": 1.4652,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 0.0003,
44
+ "loss": 1.3925,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 0.0003,
50
+ "loss": 1.2981,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 0.0003,
56
+ "loss": 1.2549,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.02,
61
+ "learning_rate": 0.0003,
62
+ "loss": 1.1734,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.02,
67
+ "learning_rate": 0.0003,
68
+ "loss": 1.0787,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.03,
73
+ "learning_rate": 0.0003,
74
+ "loss": 1.0597,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.03,
79
+ "learning_rate": 0.0003,
80
+ "loss": 1.0002,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.03,
85
+ "learning_rate": 0.0003,
86
+ "loss": 0.9364,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.03,
91
+ "learning_rate": 0.0003,
92
+ "loss": 0.931,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.04,
97
+ "learning_rate": 0.0003,
98
+ "loss": 0.9021,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.04,
103
+ "learning_rate": 0.0003,
104
+ "loss": 0.9024,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.04,
109
+ "learning_rate": 0.0003,
110
+ "loss": 0.8829,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.04,
115
+ "learning_rate": 0.0003,
116
+ "loss": 0.881,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.05,
121
+ "learning_rate": 0.0003,
122
+ "loss": 0.907,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.05,
127
+ "learning_rate": 0.0003,
128
+ "loss": 0.908,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.05,
133
+ "learning_rate": 0.0003,
134
+ "loss": 0.8973,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.05,
139
+ "learning_rate": 0.0003,
140
+ "loss": 0.927,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.06,
145
+ "learning_rate": 0.0003,
146
+ "loss": 0.9174,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.06,
151
+ "learning_rate": 0.0003,
152
+ "loss": 0.85,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.06,
157
+ "learning_rate": 0.0003,
158
+ "loss": 0.8331,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.06,
163
+ "learning_rate": 0.0003,
164
+ "loss": 0.8393,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.07,
169
+ "learning_rate": 0.0003,
170
+ "loss": 0.9184,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.07,
175
+ "learning_rate": 0.0003,
176
+ "loss": 0.8506,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.07,
181
+ "learning_rate": 0.0003,
182
+ "loss": 0.8487,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.07,
187
+ "learning_rate": 0.0003,
188
+ "loss": 0.8352,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.08,
193
+ "learning_rate": 0.0003,
194
+ "loss": 0.8581,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.08,
199
+ "learning_rate": 0.0003,
200
+ "loss": 0.8843,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.08,
205
+ "learning_rate": 0.0003,
206
+ "loss": 0.858,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.08,
211
+ "learning_rate": 0.0003,
212
+ "loss": 0.8927,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.09,
217
+ "learning_rate": 0.0003,
218
+ "loss": 0.8385,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.09,
223
+ "learning_rate": 0.0003,
224
+ "loss": 0.8775,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.09,
229
+ "learning_rate": 0.0003,
230
+ "loss": 0.8506,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.09,
235
+ "learning_rate": 0.0003,
236
+ "loss": 0.846,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.1,
241
+ "learning_rate": 0.0003,
242
+ "loss": 0.8599,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.1,
247
+ "learning_rate": 0.0003,
248
+ "loss": 0.8277,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.1,
253
+ "learning_rate": 0.0003,
254
+ "loss": 0.8776,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.1,
259
+ "learning_rate": 0.0003,
260
+ "loss": 0.8536,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.11,
265
+ "learning_rate": 0.0003,
266
+ "loss": 0.8411,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.11,
271
+ "learning_rate": 0.0003,
272
+ "loss": 0.8515,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.11,
277
+ "learning_rate": 0.0003,
278
+ "loss": 0.8253,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.11,
283
+ "learning_rate": 0.0003,
284
+ "loss": 0.8666,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.12,
289
+ "learning_rate": 0.0003,
290
+ "loss": 0.8353,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.12,
295
+ "learning_rate": 0.0003,
296
+ "loss": 0.841,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.12,
301
+ "learning_rate": 0.0003,
302
+ "loss": 0.8512,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.12,
307
+ "learning_rate": 0.0003,
308
+ "loss": 0.8768,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.13,
313
+ "learning_rate": 0.0003,
314
+ "loss": 0.8201,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.13,
319
+ "learning_rate": 0.0003,
320
+ "loss": 0.8264,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.13,
325
+ "learning_rate": 0.0003,
326
+ "loss": 0.8303,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.13,
331
+ "learning_rate": 0.0003,
332
+ "loss": 0.8334,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.14,
337
+ "learning_rate": 0.0003,
338
+ "loss": 0.8514,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.14,
343
+ "learning_rate": 0.0003,
344
+ "loss": 0.8443,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.14,
349
+ "learning_rate": 0.0003,
350
+ "loss": 0.8866,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.14,
355
+ "learning_rate": 0.0003,
356
+ "loss": 0.8196,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.15,
361
+ "learning_rate": 0.0003,
362
+ "loss": 0.8133,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.15,
367
+ "learning_rate": 0.0003,
368
+ "loss": 0.8366,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.15,
373
+ "learning_rate": 0.0003,
374
+ "loss": 0.8313,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.15,
379
+ "learning_rate": 0.0003,
380
+ "loss": 0.8401,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.16,
385
+ "learning_rate": 0.0003,
386
+ "loss": 0.8324,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.16,
391
+ "learning_rate": 0.0003,
392
+ "loss": 0.8395,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.16,
397
+ "learning_rate": 0.0003,
398
+ "loss": 0.8468,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.16,
403
+ "learning_rate": 0.0003,
404
+ "loss": 0.8332,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.17,
409
+ "learning_rate": 0.0003,
410
+ "loss": 0.8415,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.17,
415
+ "learning_rate": 0.0003,
416
+ "loss": 0.8882,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.17,
421
+ "learning_rate": 0.0003,
422
+ "loss": 0.8104,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.17,
427
+ "learning_rate": 0.0003,
428
+ "loss": 0.8485,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.18,
433
+ "learning_rate": 0.0003,
434
+ "loss": 0.8475,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.18,
439
+ "learning_rate": 0.0003,
440
+ "loss": 0.7839,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.18,
445
+ "learning_rate": 0.0003,
446
+ "loss": 0.841,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.18,
451
+ "learning_rate": 0.0003,
452
+ "loss": 0.8401,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.19,
457
+ "learning_rate": 0.0003,
458
+ "loss": 0.8442,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.19,
463
+ "learning_rate": 0.0003,
464
+ "loss": 0.8336,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.19,
469
+ "learning_rate": 0.0003,
470
+ "loss": 0.8371,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.19,
475
+ "learning_rate": 0.0003,
476
+ "loss": 0.8391,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.2,
481
+ "learning_rate": 0.0003,
482
+ "loss": 0.8245,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.2,
487
+ "learning_rate": 0.0003,
488
+ "loss": 0.8196,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.2,
493
+ "learning_rate": 0.0003,
494
+ "loss": 0.7927,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.2,
499
+ "learning_rate": 0.0003,
500
+ "loss": 0.8374,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.21,
505
+ "learning_rate": 0.0003,
506
+ "loss": 0.8349,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.21,
511
+ "learning_rate": 0.0003,
512
+ "loss": 0.8271,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.21,
517
+ "learning_rate": 0.0003,
518
+ "loss": 0.8134,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.21,
523
+ "learning_rate": 0.0003,
524
+ "loss": 0.8481,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.22,
529
+ "learning_rate": 0.0003,
530
+ "loss": 0.8259,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.22,
535
+ "learning_rate": 0.0003,
536
+ "loss": 0.8447,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.22,
541
+ "learning_rate": 0.0003,
542
+ "loss": 0.839,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.22,
547
+ "learning_rate": 0.0003,
548
+ "loss": 0.8413,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.23,
553
+ "learning_rate": 0.0003,
554
+ "loss": 0.8168,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.23,
559
+ "learning_rate": 0.0003,
560
+ "loss": 0.8362,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.23,
565
+ "learning_rate": 0.0003,
566
+ "loss": 0.8595,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.23,
571
+ "learning_rate": 0.0003,
572
+ "loss": 0.8247,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.23,
577
+ "learning_rate": 0.0003,
578
+ "loss": 0.8122,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.24,
583
+ "learning_rate": 0.0003,
584
+ "loss": 0.8282,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.24,
589
+ "learning_rate": 0.0003,
590
+ "loss": 0.8326,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.24,
595
+ "learning_rate": 0.0003,
596
+ "loss": 0.8086,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.24,
601
+ "learning_rate": 0.0003,
602
+ "loss": 0.8564,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.25,
607
+ "learning_rate": 0.0003,
608
+ "loss": 0.8377,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.25,
613
+ "learning_rate": 0.0003,
614
+ "loss": 0.8456,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.25,
619
+ "learning_rate": 0.0003,
620
+ "loss": 0.7863,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.25,
625
+ "learning_rate": 0.0003,
626
+ "loss": 0.8117,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.26,
631
+ "learning_rate": 0.0003,
632
+ "loss": 0.8347,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.26,
637
+ "learning_rate": 0.0003,
638
+ "loss": 0.8155,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.26,
643
+ "learning_rate": 0.0003,
644
+ "loss": 0.8434,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.26,
649
+ "learning_rate": 0.0003,
650
+ "loss": 0.835,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.27,
655
+ "learning_rate": 0.0003,
656
+ "loss": 0.8437,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.27,
661
+ "learning_rate": 0.0003,
662
+ "loss": 0.8051,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.27,
667
+ "learning_rate": 0.0003,
668
+ "loss": 0.8197,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.27,
673
+ "learning_rate": 0.0003,
674
+ "loss": 0.8337,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.28,
679
+ "learning_rate": 0.0003,
680
+ "loss": 0.8442,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.28,
685
+ "learning_rate": 0.0003,
686
+ "loss": 0.8277,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.28,
691
+ "learning_rate": 0.0003,
692
+ "loss": 0.7963,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.28,
697
+ "learning_rate": 0.0003,
698
+ "loss": 0.7699,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.29,
703
+ "learning_rate": 0.0003,
704
+ "loss": 0.8266,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.29,
709
+ "learning_rate": 0.0003,
710
+ "loss": 0.7808,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.29,
715
+ "learning_rate": 0.0003,
716
+ "loss": 0.8247,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.29,
721
+ "learning_rate": 0.0003,
722
+ "loss": 0.8174,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.3,
727
+ "learning_rate": 0.0003,
728
+ "loss": 0.8338,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.3,
733
+ "learning_rate": 0.0003,
734
+ "loss": 0.8273,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.3,
739
+ "learning_rate": 0.0003,
740
+ "loss": 0.8258,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.3,
745
+ "learning_rate": 0.0003,
746
+ "loss": 0.8368,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.31,
751
+ "learning_rate": 0.0003,
752
+ "loss": 0.8133,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.31,
757
+ "learning_rate": 0.0003,
758
+ "loss": 0.8457,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.31,
763
+ "learning_rate": 0.0003,
764
+ "loss": 0.8479,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.31,
769
+ "learning_rate": 0.0003,
770
+ "loss": 0.8141,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.32,
775
+ "learning_rate": 0.0003,
776
+ "loss": 0.8147,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.32,
781
+ "learning_rate": 0.0003,
782
+ "loss": 0.8125,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.32,
787
+ "learning_rate": 0.0003,
788
+ "loss": 0.8066,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.32,
793
+ "learning_rate": 0.0003,
794
+ "loss": 0.8781,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.33,
799
+ "learning_rate": 0.0003,
800
+ "loss": 0.858,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.33,
805
+ "learning_rate": 0.0003,
806
+ "loss": 0.7778,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.33,
811
+ "learning_rate": 0.0003,
812
+ "loss": 0.7964,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.33,
817
+ "learning_rate": 0.0003,
818
+ "loss": 0.836,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.34,
823
+ "learning_rate": 0.0003,
824
+ "loss": 0.8205,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.34,
829
+ "learning_rate": 0.0003,
830
+ "loss": 0.7889,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.34,
835
+ "learning_rate": 0.0003,
836
+ "loss": 0.8597,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.34,
841
+ "learning_rate": 0.0003,
842
+ "loss": 0.8203,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.35,
847
+ "learning_rate": 0.0003,
848
+ "loss": 0.8256,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.35,
853
+ "learning_rate": 0.0003,
854
+ "loss": 0.8284,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.35,
859
+ "learning_rate": 0.0003,
860
+ "loss": 0.8457,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.35,
865
+ "learning_rate": 0.0003,
866
+ "loss": 0.7978,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.36,
871
+ "learning_rate": 0.0003,
872
+ "loss": 0.7882,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.36,
877
+ "learning_rate": 0.0003,
878
+ "loss": 0.8211,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.36,
883
+ "learning_rate": 0.0003,
884
+ "loss": 0.8464,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.36,
889
+ "learning_rate": 0.0003,
890
+ "loss": 0.8007,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.37,
895
+ "learning_rate": 0.0003,
896
+ "loss": 0.8526,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.37,
901
+ "learning_rate": 0.0003,
902
+ "loss": 0.7931,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.37,
907
+ "learning_rate": 0.0003,
908
+ "loss": 0.8185,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.37,
913
+ "learning_rate": 0.0003,
914
+ "loss": 0.802,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.38,
919
+ "learning_rate": 0.0003,
920
+ "loss": 0.8354,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.38,
925
+ "learning_rate": 0.0003,
926
+ "loss": 0.8124,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.38,
931
+ "learning_rate": 0.0003,
932
+ "loss": 0.8436,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.38,
937
+ "learning_rate": 0.0003,
938
+ "loss": 0.8159,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.39,
943
+ "learning_rate": 0.0003,
944
+ "loss": 0.8255,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.39,
949
+ "learning_rate": 0.0003,
950
+ "loss": 0.7855,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.39,
955
+ "learning_rate": 0.0003,
956
+ "loss": 0.802,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.39,
961
+ "learning_rate": 0.0003,
962
+ "loss": 0.8207,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.4,
967
+ "learning_rate": 0.0003,
968
+ "loss": 0.7981,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.4,
973
+ "learning_rate": 0.0003,
974
+ "loss": 0.818,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.4,
979
+ "learning_rate": 0.0003,
980
+ "loss": 0.8684,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.4,
985
+ "learning_rate": 0.0003,
986
+ "loss": 0.7987,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.41,
991
+ "learning_rate": 0.0003,
992
+ "loss": 0.8009,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.41,
997
+ "learning_rate": 0.0003,
998
+ "loss": 0.7902,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.41,
1003
+ "learning_rate": 0.0003,
1004
+ "loss": 0.8244,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.41,
1009
+ "learning_rate": 0.0003,
1010
+ "loss": 0.8476,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.42,
1015
+ "learning_rate": 0.0003,
1016
+ "loss": 0.8506,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.42,
1021
+ "learning_rate": 0.0003,
1022
+ "loss": 0.8357,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.42,
1027
+ "learning_rate": 0.0003,
1028
+ "loss": 0.8073,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.42,
1033
+ "learning_rate": 0.0003,
1034
+ "loss": 0.8377,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.43,
1039
+ "learning_rate": 0.0003,
1040
+ "loss": 0.7911,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.43,
1045
+ "learning_rate": 0.0003,
1046
+ "loss": 0.8392,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.43,
1051
+ "learning_rate": 0.0003,
1052
+ "loss": 0.8261,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.43,
1057
+ "learning_rate": 0.0003,
1058
+ "loss": 0.8175,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.44,
1063
+ "learning_rate": 0.0003,
1064
+ "loss": 0.82,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.44,
1069
+ "learning_rate": 0.0003,
1070
+ "loss": 0.8448,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.44,
1075
+ "learning_rate": 0.0003,
1076
+ "loss": 0.8449,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.44,
1081
+ "learning_rate": 0.0003,
1082
+ "loss": 0.8176,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.45,
1087
+ "learning_rate": 0.0003,
1088
+ "loss": 0.8211,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.45,
1093
+ "learning_rate": 0.0003,
1094
+ "loss": 0.7787,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.45,
1099
+ "learning_rate": 0.0003,
1100
+ "loss": 0.8119,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.45,
1105
+ "learning_rate": 0.0003,
1106
+ "loss": 0.8361,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.46,
1111
+ "learning_rate": 0.0003,
1112
+ "loss": 0.8496,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.46,
1117
+ "learning_rate": 0.0003,
1118
+ "loss": 0.8501,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.46,
1123
+ "learning_rate": 0.0003,
1124
+ "loss": 0.834,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.46,
1129
+ "learning_rate": 0.0003,
1130
+ "loss": 0.8189,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.46,
1135
+ "learning_rate": 0.0003,
1136
+ "loss": 0.8241,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.47,
1141
+ "learning_rate": 0.0003,
1142
+ "loss": 0.8458,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.47,
1147
+ "learning_rate": 0.0003,
1148
+ "loss": 0.8439,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.47,
1153
+ "learning_rate": 0.0003,
1154
+ "loss": 0.7946,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.47,
1159
+ "learning_rate": 0.0003,
1160
+ "loss": 0.8297,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.48,
1165
+ "learning_rate": 0.0003,
1166
+ "loss": 0.8388,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.48,
1171
+ "learning_rate": 0.0003,
1172
+ "loss": 0.842,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.48,
1177
+ "learning_rate": 0.0003,
1178
+ "loss": 0.8286,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.48,
1183
+ "learning_rate": 0.0003,
1184
+ "loss": 0.8126,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.49,
1189
+ "learning_rate": 0.0003,
1190
+ "loss": 0.8392,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.49,
1195
+ "learning_rate": 0.0003,
1196
+ "loss": 0.779,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.49,
1201
+ "learning_rate": 0.0003,
1202
+ "loss": 0.8178,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.49,
1207
+ "learning_rate": 0.0003,
1208
+ "loss": 0.7796,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.5,
1213
+ "learning_rate": 0.0003,
1214
+ "loss": 0.8119,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.5,
1219
+ "learning_rate": 0.0003,
1220
+ "loss": 0.7988,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.5,
1225
+ "learning_rate": 0.0003,
1226
+ "loss": 0.8195,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.5,
1231
+ "learning_rate": 0.0003,
1232
+ "loss": 0.8413,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.51,
1237
+ "learning_rate": 0.0003,
1238
+ "loss": 0.849,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.51,
1243
+ "learning_rate": 0.0003,
1244
+ "loss": 0.8184,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.51,
1249
+ "learning_rate": 0.0003,
1250
+ "loss": 0.8572,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.51,
1255
+ "learning_rate": 0.0003,
1256
+ "loss": 0.8146,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.52,
1261
+ "learning_rate": 0.0003,
1262
+ "loss": 0.8045,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.52,
1267
+ "learning_rate": 0.0003,
1268
+ "loss": 0.8128,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.52,
1273
+ "learning_rate": 0.0003,
1274
+ "loss": 0.7768,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.52,
1279
+ "learning_rate": 0.0003,
1280
+ "loss": 0.8289,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.53,
1285
+ "learning_rate": 0.0003,
1286
+ "loss": 0.8173,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.53,
1291
+ "learning_rate": 0.0003,
1292
+ "loss": 0.8749,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.53,
1297
+ "learning_rate": 0.0003,
1298
+ "loss": 0.8143,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.53,
1303
+ "learning_rate": 0.0003,
1304
+ "loss": 0.8287,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.54,
1309
+ "learning_rate": 0.0003,
1310
+ "loss": 0.804,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.54,
1315
+ "learning_rate": 0.0003,
1316
+ "loss": 0.8153,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.54,
1321
+ "learning_rate": 0.0003,
1322
+ "loss": 0.7883,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.54,
1327
+ "learning_rate": 0.0003,
1328
+ "loss": 0.8065,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.55,
1333
+ "learning_rate": 0.0003,
1334
+ "loss": 0.8538,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.55,
1339
+ "learning_rate": 0.0003,
1340
+ "loss": 0.8239,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.55,
1345
+ "learning_rate": 0.0003,
1346
+ "loss": 0.8615,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.55,
1351
+ "learning_rate": 0.0003,
1352
+ "loss": 0.8097,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.56,
1357
+ "learning_rate": 0.0003,
1358
+ "loss": 0.8191,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.56,
1363
+ "learning_rate": 0.0003,
1364
+ "loss": 0.8105,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.56,
1369
+ "learning_rate": 0.0003,
1370
+ "loss": 0.8228,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.56,
1375
+ "learning_rate": 0.0003,
1376
+ "loss": 0.7983,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.57,
1381
+ "learning_rate": 0.0003,
1382
+ "loss": 0.8382,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.57,
1387
+ "learning_rate": 0.0003,
1388
+ "loss": 0.8134,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.57,
1393
+ "learning_rate": 0.0003,
1394
+ "loss": 0.8338,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.57,
1399
+ "learning_rate": 0.0003,
1400
+ "loss": 0.826,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.58,
1405
+ "learning_rate": 0.0003,
1406
+ "loss": 0.8145,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.58,
1411
+ "learning_rate": 0.0003,
1412
+ "loss": 0.8139,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.58,
1417
+ "learning_rate": 0.0003,
1418
+ "loss": 0.7867,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.58,
1423
+ "learning_rate": 0.0003,
1424
+ "loss": 0.8064,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.59,
1429
+ "learning_rate": 0.0003,
1430
+ "loss": 0.8282,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.59,
1435
+ "learning_rate": 0.0003,
1436
+ "loss": 0.8448,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.59,
1441
+ "learning_rate": 0.0003,
1442
+ "loss": 0.8281,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.59,
1447
+ "learning_rate": 0.0003,
1448
+ "loss": 0.8608,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.6,
1453
+ "learning_rate": 0.0003,
1454
+ "loss": 0.8041,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.6,
1459
+ "learning_rate": 0.0003,
1460
+ "loss": 0.8092,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.6,
1465
+ "learning_rate": 0.0003,
1466
+ "loss": 0.8166,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.6,
1471
+ "learning_rate": 0.0003,
1472
+ "loss": 0.8047,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.61,
1477
+ "learning_rate": 0.0003,
1478
+ "loss": 0.8236,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.61,
1483
+ "learning_rate": 0.0003,
1484
+ "loss": 0.821,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.61,
1489
+ "learning_rate": 0.0003,
1490
+ "loss": 0.8409,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.61,
1495
+ "learning_rate": 0.0003,
1496
+ "loss": 0.8129,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.62,
1501
+ "learning_rate": 0.0003,
1502
+ "loss": 0.806,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.62,
1507
+ "learning_rate": 0.0003,
1508
+ "loss": 0.7602,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.62,
1513
+ "learning_rate": 0.0003,
1514
+ "loss": 0.8244,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.62,
1519
+ "learning_rate": 0.0003,
1520
+ "loss": 0.8279,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.63,
1525
+ "learning_rate": 0.0003,
1526
+ "loss": 0.8273,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.63,
1531
+ "learning_rate": 0.0003,
1532
+ "loss": 0.8229,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.63,
1537
+ "learning_rate": 0.0003,
1538
+ "loss": 0.816,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.63,
1543
+ "learning_rate": 0.0003,
1544
+ "loss": 0.8284,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.64,
1549
+ "learning_rate": 0.0003,
1550
+ "loss": 0.7923,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.64,
1555
+ "learning_rate": 0.0003,
1556
+ "loss": 0.8008,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.64,
1561
+ "learning_rate": 0.0003,
1562
+ "loss": 0.825,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.64,
1567
+ "learning_rate": 0.0003,
1568
+ "loss": 0.7781,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.65,
1573
+ "learning_rate": 0.0003,
1574
+ "loss": 0.7963,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.65,
1579
+ "learning_rate": 0.0003,
1580
+ "loss": 0.8652,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.65,
1585
+ "learning_rate": 0.0003,
1586
+ "loss": 0.8112,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.65,
1591
+ "learning_rate": 0.0003,
1592
+ "loss": 0.8307,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.66,
1597
+ "learning_rate": 0.0003,
1598
+ "loss": 0.7696,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.66,
1603
+ "learning_rate": 0.0003,
1604
+ "loss": 0.804,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.66,
1609
+ "learning_rate": 0.0003,
1610
+ "loss": 0.7744,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.66,
1615
+ "learning_rate": 0.0003,
1616
+ "loss": 0.806,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.67,
1621
+ "learning_rate": 0.0003,
1622
+ "loss": 0.8223,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.67,
1627
+ "learning_rate": 0.0003,
1628
+ "loss": 0.8517,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.67,
1633
+ "learning_rate": 0.0003,
1634
+ "loss": 0.7775,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.67,
1639
+ "learning_rate": 0.0003,
1640
+ "loss": 0.7867,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.68,
1645
+ "learning_rate": 0.0003,
1646
+ "loss": 0.7762,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.68,
1651
+ "learning_rate": 0.0003,
1652
+ "loss": 0.8187,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.68,
1657
+ "learning_rate": 0.0003,
1658
+ "loss": 0.814,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.68,
1663
+ "learning_rate": 0.0003,
1664
+ "loss": 0.8146,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.69,
1669
+ "learning_rate": 0.0003,
1670
+ "loss": 0.7844,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.69,
1675
+ "learning_rate": 0.0003,
1676
+ "loss": 0.8237,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.69,
1681
+ "learning_rate": 0.0003,
1682
+ "loss": 0.8364,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.69,
1687
+ "learning_rate": 0.0003,
1688
+ "loss": 0.8035,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.69,
1693
+ "learning_rate": 0.0003,
1694
+ "loss": 0.807,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.7,
1699
+ "learning_rate": 0.0003,
1700
+ "loss": 0.8138,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.7,
1705
+ "learning_rate": 0.0003,
1706
+ "loss": 0.8015,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.7,
1711
+ "learning_rate": 0.0003,
1712
+ "loss": 0.7838,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.7,
1717
+ "learning_rate": 0.0003,
1718
+ "loss": 0.8062,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.71,
1723
+ "learning_rate": 0.0003,
1724
+ "loss": 0.803,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.71,
1729
+ "learning_rate": 0.0003,
1730
+ "loss": 0.8124,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.71,
1735
+ "learning_rate": 0.0003,
1736
+ "loss": 0.8318,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.71,
1741
+ "learning_rate": 0.0003,
1742
+ "loss": 0.7836,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.72,
1747
+ "learning_rate": 0.0003,
1748
+ "loss": 0.8017,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.72,
1753
+ "learning_rate": 0.0003,
1754
+ "loss": 0.7574,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.72,
1759
+ "learning_rate": 0.0003,
1760
+ "loss": 0.7959,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.72,
1765
+ "learning_rate": 0.0003,
1766
+ "loss": 0.8077,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.73,
1771
+ "learning_rate": 0.0003,
1772
+ "loss": 0.7988,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.73,
1777
+ "learning_rate": 0.0003,
1778
+ "loss": 0.8183,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.73,
1783
+ "learning_rate": 0.0003,
1784
+ "loss": 0.7909,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.73,
1789
+ "learning_rate": 0.0003,
1790
+ "loss": 0.8241,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.74,
1795
+ "learning_rate": 0.0003,
1796
+ "loss": 0.7927,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.74,
1801
+ "learning_rate": 0.0003,
1802
+ "loss": 0.8215,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.74,
1807
+ "learning_rate": 0.0003,
1808
+ "loss": 0.8243,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 0.74,
1813
+ "learning_rate": 0.0003,
1814
+ "loss": 0.7996,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 0.75,
1819
+ "learning_rate": 0.0003,
1820
+ "loss": 0.7886,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 0.75,
1825
+ "learning_rate": 0.0003,
1826
+ "loss": 0.8271,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 0.75,
1831
+ "learning_rate": 0.0003,
1832
+ "loss": 0.7985,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 0.75,
1837
+ "learning_rate": 0.0003,
1838
+ "loss": 0.7996,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 0.76,
1843
+ "learning_rate": 0.0003,
1844
+ "loss": 0.8274,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 0.76,
1849
+ "learning_rate": 0.0003,
1850
+ "loss": 0.8091,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 0.76,
1855
+ "learning_rate": 0.0003,
1856
+ "loss": 0.8352,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 0.76,
1861
+ "learning_rate": 0.0003,
1862
+ "loss": 0.8365,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 0.77,
1867
+ "learning_rate": 0.0003,
1868
+ "loss": 0.8241,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 0.77,
1873
+ "learning_rate": 0.0003,
1874
+ "loss": 0.8125,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 0.77,
1879
+ "learning_rate": 0.0003,
1880
+ "loss": 0.7694,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 0.77,
1885
+ "learning_rate": 0.0003,
1886
+ "loss": 0.8051,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 0.78,
1891
+ "learning_rate": 0.0003,
1892
+ "loss": 0.825,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 0.78,
1897
+ "learning_rate": 0.0003,
1898
+ "loss": 0.8051,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 0.78,
1903
+ "learning_rate": 0.0003,
1904
+ "loss": 0.8149,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 0.78,
1909
+ "learning_rate": 0.0003,
1910
+ "loss": 0.8483,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 0.79,
1915
+ "learning_rate": 0.0003,
1916
+ "loss": 0.8013,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 0.79,
1921
+ "learning_rate": 0.0003,
1922
+ "loss": 0.7661,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 0.79,
1927
+ "learning_rate": 0.0003,
1928
+ "loss": 0.7741,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 0.79,
1933
+ "learning_rate": 0.0003,
1934
+ "loss": 0.8237,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 0.8,
1939
+ "learning_rate": 0.0003,
1940
+ "loss": 0.8298,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 0.8,
1945
+ "learning_rate": 0.0003,
1946
+ "loss": 0.8414,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 0.8,
1951
+ "learning_rate": 0.0003,
1952
+ "loss": 0.8061,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 0.8,
1957
+ "learning_rate": 0.0003,
1958
+ "loss": 0.8104,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 0.81,
1963
+ "learning_rate": 0.0003,
1964
+ "loss": 0.8064,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 0.81,
1969
+ "learning_rate": 0.0003,
1970
+ "loss": 0.8202,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 0.81,
1975
+ "learning_rate": 0.0003,
1976
+ "loss": 0.7952,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 0.81,
1981
+ "learning_rate": 0.0003,
1982
+ "loss": 0.7901,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 0.82,
1987
+ "learning_rate": 0.0003,
1988
+ "loss": 0.7949,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 0.82,
1993
+ "learning_rate": 0.0003,
1994
+ "loss": 0.7887,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 0.82,
1999
+ "learning_rate": 0.0003,
2000
+ "loss": 0.8413,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 0.82,
2005
+ "learning_rate": 0.0003,
2006
+ "loss": 0.7949,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 0.83,
2011
+ "learning_rate": 0.0003,
2012
+ "loss": 0.8184,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 0.83,
2017
+ "learning_rate": 0.0003,
2018
+ "loss": 0.7874,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 0.83,
2023
+ "learning_rate": 0.0003,
2024
+ "loss": 0.8264,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 0.83,
2029
+ "learning_rate": 0.0003,
2030
+ "loss": 0.7812,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 0.84,
2035
+ "learning_rate": 0.0003,
2036
+ "loss": 0.8128,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 0.84,
2041
+ "learning_rate": 0.0003,
2042
+ "loss": 0.8061,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 0.84,
2047
+ "learning_rate": 0.0003,
2048
+ "loss": 0.831,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 0.84,
2053
+ "learning_rate": 0.0003,
2054
+ "loss": 0.797,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 0.85,
2059
+ "learning_rate": 0.0003,
2060
+ "loss": 0.8133,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 0.85,
2065
+ "learning_rate": 0.0003,
2066
+ "loss": 0.8221,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 0.85,
2071
+ "learning_rate": 0.0003,
2072
+ "loss": 0.8287,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 0.85,
2077
+ "learning_rate": 0.0003,
2078
+ "loss": 0.811,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 0.86,
2083
+ "learning_rate": 0.0003,
2084
+ "loss": 0.8321,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 0.86,
2089
+ "learning_rate": 0.0003,
2090
+ "loss": 0.8095,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 0.86,
2095
+ "learning_rate": 0.0003,
2096
+ "loss": 0.8114,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 0.86,
2101
+ "learning_rate": 0.0003,
2102
+ "loss": 0.8042,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 0.87,
2107
+ "learning_rate": 0.0003,
2108
+ "loss": 0.8012,
2109
+ "step": 350
2110
+ }
2111
+ ],
2112
+ "logging_steps": 1,
2113
+ "max_steps": 404,
2114
+ "num_input_tokens_seen": 0,
2115
+ "num_train_epochs": 1,
2116
+ "save_steps": 25,
2117
+ "total_flos": 3.9310521413861376e+17,
2118
+ "train_batch_size": 1,
2119
+ "trial_name": null,
2120
+ "trial_params": null
2121
+ }
llama2_7b_base_adapter/checkpoint-350/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1247dc269d0fa8df18e8e48dc478e4daaf7fd88110fd82993765140de4f97c83
3
+ size 4984
llama2_7b_base_adapter/checkpoint-375/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Llama-2-7b-hf
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
llama2_7b_base_adapter/checkpoint-375/adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16.0,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj,",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
llama2_7b_base_adapter/checkpoint-375/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b38d4638bdaf600e4cd28bafe4d0f1dc28514b733513cfb0533d7254255429a
3
+ size 8397056
llama2_7b_base_adapter/checkpoint-375/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66df62ccc7fd7bc9d40017e5e22b10d1083935cbc004135bdd60ed2f88c3e2fc
3
+ size 16831290
llama2_7b_base_adapter/checkpoint-375/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb0adbd8cb675c06ea37e7b8cd0f727aff6d64b6b54dcaa30377206597e8a085
3
+ size 14244
llama2_7b_base_adapter/checkpoint-375/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14cea28c471a1fa6c9ff7b3f2af69adfdf6d7188fce36d402b7c4283553cbae4
3
+ size 1064
llama2_7b_base_adapter/checkpoint-375/trainer_state.json ADDED
@@ -0,0 +1,2271 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9273570324574961,
5
+ "eval_steps": 500,
6
+ "global_step": 375,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.0003,
14
+ "loss": 1.717,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 0.0003,
20
+ "loss": 1.5844,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.0003,
26
+ "loss": 1.6147,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 0.0003,
32
+ "loss": 1.6272,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 0.0003,
38
+ "loss": 1.4652,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 0.0003,
44
+ "loss": 1.3925,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 0.0003,
50
+ "loss": 1.2981,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 0.0003,
56
+ "loss": 1.2549,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.02,
61
+ "learning_rate": 0.0003,
62
+ "loss": 1.1734,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.02,
67
+ "learning_rate": 0.0003,
68
+ "loss": 1.0787,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.03,
73
+ "learning_rate": 0.0003,
74
+ "loss": 1.0597,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.03,
79
+ "learning_rate": 0.0003,
80
+ "loss": 1.0002,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.03,
85
+ "learning_rate": 0.0003,
86
+ "loss": 0.9364,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.03,
91
+ "learning_rate": 0.0003,
92
+ "loss": 0.931,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.04,
97
+ "learning_rate": 0.0003,
98
+ "loss": 0.9021,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.04,
103
+ "learning_rate": 0.0003,
104
+ "loss": 0.9024,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.04,
109
+ "learning_rate": 0.0003,
110
+ "loss": 0.8829,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.04,
115
+ "learning_rate": 0.0003,
116
+ "loss": 0.881,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.05,
121
+ "learning_rate": 0.0003,
122
+ "loss": 0.907,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.05,
127
+ "learning_rate": 0.0003,
128
+ "loss": 0.908,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.05,
133
+ "learning_rate": 0.0003,
134
+ "loss": 0.8973,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.05,
139
+ "learning_rate": 0.0003,
140
+ "loss": 0.927,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.06,
145
+ "learning_rate": 0.0003,
146
+ "loss": 0.9174,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.06,
151
+ "learning_rate": 0.0003,
152
+ "loss": 0.85,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.06,
157
+ "learning_rate": 0.0003,
158
+ "loss": 0.8331,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.06,
163
+ "learning_rate": 0.0003,
164
+ "loss": 0.8393,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.07,
169
+ "learning_rate": 0.0003,
170
+ "loss": 0.9184,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.07,
175
+ "learning_rate": 0.0003,
176
+ "loss": 0.8506,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.07,
181
+ "learning_rate": 0.0003,
182
+ "loss": 0.8487,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.07,
187
+ "learning_rate": 0.0003,
188
+ "loss": 0.8352,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.08,
193
+ "learning_rate": 0.0003,
194
+ "loss": 0.8581,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.08,
199
+ "learning_rate": 0.0003,
200
+ "loss": 0.8843,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.08,
205
+ "learning_rate": 0.0003,
206
+ "loss": 0.858,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.08,
211
+ "learning_rate": 0.0003,
212
+ "loss": 0.8927,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.09,
217
+ "learning_rate": 0.0003,
218
+ "loss": 0.8385,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.09,
223
+ "learning_rate": 0.0003,
224
+ "loss": 0.8775,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.09,
229
+ "learning_rate": 0.0003,
230
+ "loss": 0.8506,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.09,
235
+ "learning_rate": 0.0003,
236
+ "loss": 0.846,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.1,
241
+ "learning_rate": 0.0003,
242
+ "loss": 0.8599,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.1,
247
+ "learning_rate": 0.0003,
248
+ "loss": 0.8277,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.1,
253
+ "learning_rate": 0.0003,
254
+ "loss": 0.8776,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.1,
259
+ "learning_rate": 0.0003,
260
+ "loss": 0.8536,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.11,
265
+ "learning_rate": 0.0003,
266
+ "loss": 0.8411,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.11,
271
+ "learning_rate": 0.0003,
272
+ "loss": 0.8515,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.11,
277
+ "learning_rate": 0.0003,
278
+ "loss": 0.8253,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.11,
283
+ "learning_rate": 0.0003,
284
+ "loss": 0.8666,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.12,
289
+ "learning_rate": 0.0003,
290
+ "loss": 0.8353,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.12,
295
+ "learning_rate": 0.0003,
296
+ "loss": 0.841,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.12,
301
+ "learning_rate": 0.0003,
302
+ "loss": 0.8512,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.12,
307
+ "learning_rate": 0.0003,
308
+ "loss": 0.8768,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.13,
313
+ "learning_rate": 0.0003,
314
+ "loss": 0.8201,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.13,
319
+ "learning_rate": 0.0003,
320
+ "loss": 0.8264,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.13,
325
+ "learning_rate": 0.0003,
326
+ "loss": 0.8303,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.13,
331
+ "learning_rate": 0.0003,
332
+ "loss": 0.8334,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.14,
337
+ "learning_rate": 0.0003,
338
+ "loss": 0.8514,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.14,
343
+ "learning_rate": 0.0003,
344
+ "loss": 0.8443,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.14,
349
+ "learning_rate": 0.0003,
350
+ "loss": 0.8866,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.14,
355
+ "learning_rate": 0.0003,
356
+ "loss": 0.8196,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.15,
361
+ "learning_rate": 0.0003,
362
+ "loss": 0.8133,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.15,
367
+ "learning_rate": 0.0003,
368
+ "loss": 0.8366,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.15,
373
+ "learning_rate": 0.0003,
374
+ "loss": 0.8313,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.15,
379
+ "learning_rate": 0.0003,
380
+ "loss": 0.8401,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.16,
385
+ "learning_rate": 0.0003,
386
+ "loss": 0.8324,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.16,
391
+ "learning_rate": 0.0003,
392
+ "loss": 0.8395,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.16,
397
+ "learning_rate": 0.0003,
398
+ "loss": 0.8468,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.16,
403
+ "learning_rate": 0.0003,
404
+ "loss": 0.8332,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.17,
409
+ "learning_rate": 0.0003,
410
+ "loss": 0.8415,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.17,
415
+ "learning_rate": 0.0003,
416
+ "loss": 0.8882,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.17,
421
+ "learning_rate": 0.0003,
422
+ "loss": 0.8104,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.17,
427
+ "learning_rate": 0.0003,
428
+ "loss": 0.8485,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.18,
433
+ "learning_rate": 0.0003,
434
+ "loss": 0.8475,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.18,
439
+ "learning_rate": 0.0003,
440
+ "loss": 0.7839,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.18,
445
+ "learning_rate": 0.0003,
446
+ "loss": 0.841,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.18,
451
+ "learning_rate": 0.0003,
452
+ "loss": 0.8401,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.19,
457
+ "learning_rate": 0.0003,
458
+ "loss": 0.8442,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.19,
463
+ "learning_rate": 0.0003,
464
+ "loss": 0.8336,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.19,
469
+ "learning_rate": 0.0003,
470
+ "loss": 0.8371,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.19,
475
+ "learning_rate": 0.0003,
476
+ "loss": 0.8391,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.2,
481
+ "learning_rate": 0.0003,
482
+ "loss": 0.8245,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.2,
487
+ "learning_rate": 0.0003,
488
+ "loss": 0.8196,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.2,
493
+ "learning_rate": 0.0003,
494
+ "loss": 0.7927,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.2,
499
+ "learning_rate": 0.0003,
500
+ "loss": 0.8374,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.21,
505
+ "learning_rate": 0.0003,
506
+ "loss": 0.8349,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.21,
511
+ "learning_rate": 0.0003,
512
+ "loss": 0.8271,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.21,
517
+ "learning_rate": 0.0003,
518
+ "loss": 0.8134,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.21,
523
+ "learning_rate": 0.0003,
524
+ "loss": 0.8481,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.22,
529
+ "learning_rate": 0.0003,
530
+ "loss": 0.8259,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.22,
535
+ "learning_rate": 0.0003,
536
+ "loss": 0.8447,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.22,
541
+ "learning_rate": 0.0003,
542
+ "loss": 0.839,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.22,
547
+ "learning_rate": 0.0003,
548
+ "loss": 0.8413,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.23,
553
+ "learning_rate": 0.0003,
554
+ "loss": 0.8168,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.23,
559
+ "learning_rate": 0.0003,
560
+ "loss": 0.8362,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.23,
565
+ "learning_rate": 0.0003,
566
+ "loss": 0.8595,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.23,
571
+ "learning_rate": 0.0003,
572
+ "loss": 0.8247,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.23,
577
+ "learning_rate": 0.0003,
578
+ "loss": 0.8122,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.24,
583
+ "learning_rate": 0.0003,
584
+ "loss": 0.8282,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.24,
589
+ "learning_rate": 0.0003,
590
+ "loss": 0.8326,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.24,
595
+ "learning_rate": 0.0003,
596
+ "loss": 0.8086,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.24,
601
+ "learning_rate": 0.0003,
602
+ "loss": 0.8564,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.25,
607
+ "learning_rate": 0.0003,
608
+ "loss": 0.8377,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.25,
613
+ "learning_rate": 0.0003,
614
+ "loss": 0.8456,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.25,
619
+ "learning_rate": 0.0003,
620
+ "loss": 0.7863,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.25,
625
+ "learning_rate": 0.0003,
626
+ "loss": 0.8117,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.26,
631
+ "learning_rate": 0.0003,
632
+ "loss": 0.8347,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.26,
637
+ "learning_rate": 0.0003,
638
+ "loss": 0.8155,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.26,
643
+ "learning_rate": 0.0003,
644
+ "loss": 0.8434,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.26,
649
+ "learning_rate": 0.0003,
650
+ "loss": 0.835,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.27,
655
+ "learning_rate": 0.0003,
656
+ "loss": 0.8437,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.27,
661
+ "learning_rate": 0.0003,
662
+ "loss": 0.8051,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.27,
667
+ "learning_rate": 0.0003,
668
+ "loss": 0.8197,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.27,
673
+ "learning_rate": 0.0003,
674
+ "loss": 0.8337,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.28,
679
+ "learning_rate": 0.0003,
680
+ "loss": 0.8442,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.28,
685
+ "learning_rate": 0.0003,
686
+ "loss": 0.8277,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.28,
691
+ "learning_rate": 0.0003,
692
+ "loss": 0.7963,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.28,
697
+ "learning_rate": 0.0003,
698
+ "loss": 0.7699,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.29,
703
+ "learning_rate": 0.0003,
704
+ "loss": 0.8266,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.29,
709
+ "learning_rate": 0.0003,
710
+ "loss": 0.7808,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.29,
715
+ "learning_rate": 0.0003,
716
+ "loss": 0.8247,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.29,
721
+ "learning_rate": 0.0003,
722
+ "loss": 0.8174,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.3,
727
+ "learning_rate": 0.0003,
728
+ "loss": 0.8338,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.3,
733
+ "learning_rate": 0.0003,
734
+ "loss": 0.8273,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.3,
739
+ "learning_rate": 0.0003,
740
+ "loss": 0.8258,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.3,
745
+ "learning_rate": 0.0003,
746
+ "loss": 0.8368,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.31,
751
+ "learning_rate": 0.0003,
752
+ "loss": 0.8133,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.31,
757
+ "learning_rate": 0.0003,
758
+ "loss": 0.8457,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.31,
763
+ "learning_rate": 0.0003,
764
+ "loss": 0.8479,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.31,
769
+ "learning_rate": 0.0003,
770
+ "loss": 0.8141,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.32,
775
+ "learning_rate": 0.0003,
776
+ "loss": 0.8147,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.32,
781
+ "learning_rate": 0.0003,
782
+ "loss": 0.8125,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.32,
787
+ "learning_rate": 0.0003,
788
+ "loss": 0.8066,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.32,
793
+ "learning_rate": 0.0003,
794
+ "loss": 0.8781,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.33,
799
+ "learning_rate": 0.0003,
800
+ "loss": 0.858,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.33,
805
+ "learning_rate": 0.0003,
806
+ "loss": 0.7778,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.33,
811
+ "learning_rate": 0.0003,
812
+ "loss": 0.7964,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.33,
817
+ "learning_rate": 0.0003,
818
+ "loss": 0.836,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.34,
823
+ "learning_rate": 0.0003,
824
+ "loss": 0.8205,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.34,
829
+ "learning_rate": 0.0003,
830
+ "loss": 0.7889,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.34,
835
+ "learning_rate": 0.0003,
836
+ "loss": 0.8597,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.34,
841
+ "learning_rate": 0.0003,
842
+ "loss": 0.8203,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.35,
847
+ "learning_rate": 0.0003,
848
+ "loss": 0.8256,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.35,
853
+ "learning_rate": 0.0003,
854
+ "loss": 0.8284,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.35,
859
+ "learning_rate": 0.0003,
860
+ "loss": 0.8457,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.35,
865
+ "learning_rate": 0.0003,
866
+ "loss": 0.7978,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.36,
871
+ "learning_rate": 0.0003,
872
+ "loss": 0.7882,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.36,
877
+ "learning_rate": 0.0003,
878
+ "loss": 0.8211,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.36,
883
+ "learning_rate": 0.0003,
884
+ "loss": 0.8464,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.36,
889
+ "learning_rate": 0.0003,
890
+ "loss": 0.8007,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.37,
895
+ "learning_rate": 0.0003,
896
+ "loss": 0.8526,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.37,
901
+ "learning_rate": 0.0003,
902
+ "loss": 0.7931,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.37,
907
+ "learning_rate": 0.0003,
908
+ "loss": 0.8185,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.37,
913
+ "learning_rate": 0.0003,
914
+ "loss": 0.802,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.38,
919
+ "learning_rate": 0.0003,
920
+ "loss": 0.8354,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.38,
925
+ "learning_rate": 0.0003,
926
+ "loss": 0.8124,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.38,
931
+ "learning_rate": 0.0003,
932
+ "loss": 0.8436,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.38,
937
+ "learning_rate": 0.0003,
938
+ "loss": 0.8159,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.39,
943
+ "learning_rate": 0.0003,
944
+ "loss": 0.8255,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.39,
949
+ "learning_rate": 0.0003,
950
+ "loss": 0.7855,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.39,
955
+ "learning_rate": 0.0003,
956
+ "loss": 0.802,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.39,
961
+ "learning_rate": 0.0003,
962
+ "loss": 0.8207,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.4,
967
+ "learning_rate": 0.0003,
968
+ "loss": 0.7981,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.4,
973
+ "learning_rate": 0.0003,
974
+ "loss": 0.818,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.4,
979
+ "learning_rate": 0.0003,
980
+ "loss": 0.8684,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.4,
985
+ "learning_rate": 0.0003,
986
+ "loss": 0.7987,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.41,
991
+ "learning_rate": 0.0003,
992
+ "loss": 0.8009,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.41,
997
+ "learning_rate": 0.0003,
998
+ "loss": 0.7902,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.41,
1003
+ "learning_rate": 0.0003,
1004
+ "loss": 0.8244,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.41,
1009
+ "learning_rate": 0.0003,
1010
+ "loss": 0.8476,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.42,
1015
+ "learning_rate": 0.0003,
1016
+ "loss": 0.8506,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.42,
1021
+ "learning_rate": 0.0003,
1022
+ "loss": 0.8357,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.42,
1027
+ "learning_rate": 0.0003,
1028
+ "loss": 0.8073,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.42,
1033
+ "learning_rate": 0.0003,
1034
+ "loss": 0.8377,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.43,
1039
+ "learning_rate": 0.0003,
1040
+ "loss": 0.7911,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.43,
1045
+ "learning_rate": 0.0003,
1046
+ "loss": 0.8392,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.43,
1051
+ "learning_rate": 0.0003,
1052
+ "loss": 0.8261,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.43,
1057
+ "learning_rate": 0.0003,
1058
+ "loss": 0.8175,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.44,
1063
+ "learning_rate": 0.0003,
1064
+ "loss": 0.82,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.44,
1069
+ "learning_rate": 0.0003,
1070
+ "loss": 0.8448,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.44,
1075
+ "learning_rate": 0.0003,
1076
+ "loss": 0.8449,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.44,
1081
+ "learning_rate": 0.0003,
1082
+ "loss": 0.8176,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.45,
1087
+ "learning_rate": 0.0003,
1088
+ "loss": 0.8211,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.45,
1093
+ "learning_rate": 0.0003,
1094
+ "loss": 0.7787,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.45,
1099
+ "learning_rate": 0.0003,
1100
+ "loss": 0.8119,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.45,
1105
+ "learning_rate": 0.0003,
1106
+ "loss": 0.8361,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.46,
1111
+ "learning_rate": 0.0003,
1112
+ "loss": 0.8496,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.46,
1117
+ "learning_rate": 0.0003,
1118
+ "loss": 0.8501,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.46,
1123
+ "learning_rate": 0.0003,
1124
+ "loss": 0.834,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.46,
1129
+ "learning_rate": 0.0003,
1130
+ "loss": 0.8189,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.46,
1135
+ "learning_rate": 0.0003,
1136
+ "loss": 0.8241,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.47,
1141
+ "learning_rate": 0.0003,
1142
+ "loss": 0.8458,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.47,
1147
+ "learning_rate": 0.0003,
1148
+ "loss": 0.8439,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.47,
1153
+ "learning_rate": 0.0003,
1154
+ "loss": 0.7946,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.47,
1159
+ "learning_rate": 0.0003,
1160
+ "loss": 0.8297,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.48,
1165
+ "learning_rate": 0.0003,
1166
+ "loss": 0.8388,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.48,
1171
+ "learning_rate": 0.0003,
1172
+ "loss": 0.842,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.48,
1177
+ "learning_rate": 0.0003,
1178
+ "loss": 0.8286,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.48,
1183
+ "learning_rate": 0.0003,
1184
+ "loss": 0.8126,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.49,
1189
+ "learning_rate": 0.0003,
1190
+ "loss": 0.8392,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.49,
1195
+ "learning_rate": 0.0003,
1196
+ "loss": 0.779,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.49,
1201
+ "learning_rate": 0.0003,
1202
+ "loss": 0.8178,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.49,
1207
+ "learning_rate": 0.0003,
1208
+ "loss": 0.7796,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.5,
1213
+ "learning_rate": 0.0003,
1214
+ "loss": 0.8119,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.5,
1219
+ "learning_rate": 0.0003,
1220
+ "loss": 0.7988,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.5,
1225
+ "learning_rate": 0.0003,
1226
+ "loss": 0.8195,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.5,
1231
+ "learning_rate": 0.0003,
1232
+ "loss": 0.8413,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.51,
1237
+ "learning_rate": 0.0003,
1238
+ "loss": 0.849,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.51,
1243
+ "learning_rate": 0.0003,
1244
+ "loss": 0.8184,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.51,
1249
+ "learning_rate": 0.0003,
1250
+ "loss": 0.8572,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.51,
1255
+ "learning_rate": 0.0003,
1256
+ "loss": 0.8146,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.52,
1261
+ "learning_rate": 0.0003,
1262
+ "loss": 0.8045,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.52,
1267
+ "learning_rate": 0.0003,
1268
+ "loss": 0.8128,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.52,
1273
+ "learning_rate": 0.0003,
1274
+ "loss": 0.7768,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.52,
1279
+ "learning_rate": 0.0003,
1280
+ "loss": 0.8289,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.53,
1285
+ "learning_rate": 0.0003,
1286
+ "loss": 0.8173,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.53,
1291
+ "learning_rate": 0.0003,
1292
+ "loss": 0.8749,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.53,
1297
+ "learning_rate": 0.0003,
1298
+ "loss": 0.8143,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.53,
1303
+ "learning_rate": 0.0003,
1304
+ "loss": 0.8287,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.54,
1309
+ "learning_rate": 0.0003,
1310
+ "loss": 0.804,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.54,
1315
+ "learning_rate": 0.0003,
1316
+ "loss": 0.8153,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.54,
1321
+ "learning_rate": 0.0003,
1322
+ "loss": 0.7883,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.54,
1327
+ "learning_rate": 0.0003,
1328
+ "loss": 0.8065,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.55,
1333
+ "learning_rate": 0.0003,
1334
+ "loss": 0.8538,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.55,
1339
+ "learning_rate": 0.0003,
1340
+ "loss": 0.8239,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.55,
1345
+ "learning_rate": 0.0003,
1346
+ "loss": 0.8615,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.55,
1351
+ "learning_rate": 0.0003,
1352
+ "loss": 0.8097,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.56,
1357
+ "learning_rate": 0.0003,
1358
+ "loss": 0.8191,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.56,
1363
+ "learning_rate": 0.0003,
1364
+ "loss": 0.8105,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.56,
1369
+ "learning_rate": 0.0003,
1370
+ "loss": 0.8228,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.56,
1375
+ "learning_rate": 0.0003,
1376
+ "loss": 0.7983,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.57,
1381
+ "learning_rate": 0.0003,
1382
+ "loss": 0.8382,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.57,
1387
+ "learning_rate": 0.0003,
1388
+ "loss": 0.8134,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.57,
1393
+ "learning_rate": 0.0003,
1394
+ "loss": 0.8338,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.57,
1399
+ "learning_rate": 0.0003,
1400
+ "loss": 0.826,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.58,
1405
+ "learning_rate": 0.0003,
1406
+ "loss": 0.8145,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.58,
1411
+ "learning_rate": 0.0003,
1412
+ "loss": 0.8139,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.58,
1417
+ "learning_rate": 0.0003,
1418
+ "loss": 0.7867,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.58,
1423
+ "learning_rate": 0.0003,
1424
+ "loss": 0.8064,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.59,
1429
+ "learning_rate": 0.0003,
1430
+ "loss": 0.8282,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.59,
1435
+ "learning_rate": 0.0003,
1436
+ "loss": 0.8448,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.59,
1441
+ "learning_rate": 0.0003,
1442
+ "loss": 0.8281,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.59,
1447
+ "learning_rate": 0.0003,
1448
+ "loss": 0.8608,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.6,
1453
+ "learning_rate": 0.0003,
1454
+ "loss": 0.8041,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.6,
1459
+ "learning_rate": 0.0003,
1460
+ "loss": 0.8092,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.6,
1465
+ "learning_rate": 0.0003,
1466
+ "loss": 0.8166,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.6,
1471
+ "learning_rate": 0.0003,
1472
+ "loss": 0.8047,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.61,
1477
+ "learning_rate": 0.0003,
1478
+ "loss": 0.8236,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.61,
1483
+ "learning_rate": 0.0003,
1484
+ "loss": 0.821,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.61,
1489
+ "learning_rate": 0.0003,
1490
+ "loss": 0.8409,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.61,
1495
+ "learning_rate": 0.0003,
1496
+ "loss": 0.8129,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.62,
1501
+ "learning_rate": 0.0003,
1502
+ "loss": 0.806,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.62,
1507
+ "learning_rate": 0.0003,
1508
+ "loss": 0.7602,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.62,
1513
+ "learning_rate": 0.0003,
1514
+ "loss": 0.8244,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.62,
1519
+ "learning_rate": 0.0003,
1520
+ "loss": 0.8279,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.63,
1525
+ "learning_rate": 0.0003,
1526
+ "loss": 0.8273,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.63,
1531
+ "learning_rate": 0.0003,
1532
+ "loss": 0.8229,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.63,
1537
+ "learning_rate": 0.0003,
1538
+ "loss": 0.816,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.63,
1543
+ "learning_rate": 0.0003,
1544
+ "loss": 0.8284,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.64,
1549
+ "learning_rate": 0.0003,
1550
+ "loss": 0.7923,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.64,
1555
+ "learning_rate": 0.0003,
1556
+ "loss": 0.8008,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.64,
1561
+ "learning_rate": 0.0003,
1562
+ "loss": 0.825,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.64,
1567
+ "learning_rate": 0.0003,
1568
+ "loss": 0.7781,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.65,
1573
+ "learning_rate": 0.0003,
1574
+ "loss": 0.7963,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.65,
1579
+ "learning_rate": 0.0003,
1580
+ "loss": 0.8652,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.65,
1585
+ "learning_rate": 0.0003,
1586
+ "loss": 0.8112,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.65,
1591
+ "learning_rate": 0.0003,
1592
+ "loss": 0.8307,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.66,
1597
+ "learning_rate": 0.0003,
1598
+ "loss": 0.7696,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.66,
1603
+ "learning_rate": 0.0003,
1604
+ "loss": 0.804,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.66,
1609
+ "learning_rate": 0.0003,
1610
+ "loss": 0.7744,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.66,
1615
+ "learning_rate": 0.0003,
1616
+ "loss": 0.806,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.67,
1621
+ "learning_rate": 0.0003,
1622
+ "loss": 0.8223,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.67,
1627
+ "learning_rate": 0.0003,
1628
+ "loss": 0.8517,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.67,
1633
+ "learning_rate": 0.0003,
1634
+ "loss": 0.7775,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.67,
1639
+ "learning_rate": 0.0003,
1640
+ "loss": 0.7867,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.68,
1645
+ "learning_rate": 0.0003,
1646
+ "loss": 0.7762,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.68,
1651
+ "learning_rate": 0.0003,
1652
+ "loss": 0.8187,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.68,
1657
+ "learning_rate": 0.0003,
1658
+ "loss": 0.814,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.68,
1663
+ "learning_rate": 0.0003,
1664
+ "loss": 0.8146,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.69,
1669
+ "learning_rate": 0.0003,
1670
+ "loss": 0.7844,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.69,
1675
+ "learning_rate": 0.0003,
1676
+ "loss": 0.8237,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.69,
1681
+ "learning_rate": 0.0003,
1682
+ "loss": 0.8364,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.69,
1687
+ "learning_rate": 0.0003,
1688
+ "loss": 0.8035,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.69,
1693
+ "learning_rate": 0.0003,
1694
+ "loss": 0.807,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.7,
1699
+ "learning_rate": 0.0003,
1700
+ "loss": 0.8138,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.7,
1705
+ "learning_rate": 0.0003,
1706
+ "loss": 0.8015,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.7,
1711
+ "learning_rate": 0.0003,
1712
+ "loss": 0.7838,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.7,
1717
+ "learning_rate": 0.0003,
1718
+ "loss": 0.8062,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.71,
1723
+ "learning_rate": 0.0003,
1724
+ "loss": 0.803,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.71,
1729
+ "learning_rate": 0.0003,
1730
+ "loss": 0.8124,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.71,
1735
+ "learning_rate": 0.0003,
1736
+ "loss": 0.8318,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.71,
1741
+ "learning_rate": 0.0003,
1742
+ "loss": 0.7836,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.72,
1747
+ "learning_rate": 0.0003,
1748
+ "loss": 0.8017,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.72,
1753
+ "learning_rate": 0.0003,
1754
+ "loss": 0.7574,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.72,
1759
+ "learning_rate": 0.0003,
1760
+ "loss": 0.7959,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.72,
1765
+ "learning_rate": 0.0003,
1766
+ "loss": 0.8077,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.73,
1771
+ "learning_rate": 0.0003,
1772
+ "loss": 0.7988,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.73,
1777
+ "learning_rate": 0.0003,
1778
+ "loss": 0.8183,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.73,
1783
+ "learning_rate": 0.0003,
1784
+ "loss": 0.7909,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.73,
1789
+ "learning_rate": 0.0003,
1790
+ "loss": 0.8241,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.74,
1795
+ "learning_rate": 0.0003,
1796
+ "loss": 0.7927,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.74,
1801
+ "learning_rate": 0.0003,
1802
+ "loss": 0.8215,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.74,
1807
+ "learning_rate": 0.0003,
1808
+ "loss": 0.8243,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 0.74,
1813
+ "learning_rate": 0.0003,
1814
+ "loss": 0.7996,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 0.75,
1819
+ "learning_rate": 0.0003,
1820
+ "loss": 0.7886,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 0.75,
1825
+ "learning_rate": 0.0003,
1826
+ "loss": 0.8271,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 0.75,
1831
+ "learning_rate": 0.0003,
1832
+ "loss": 0.7985,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 0.75,
1837
+ "learning_rate": 0.0003,
1838
+ "loss": 0.7996,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 0.76,
1843
+ "learning_rate": 0.0003,
1844
+ "loss": 0.8274,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 0.76,
1849
+ "learning_rate": 0.0003,
1850
+ "loss": 0.8091,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 0.76,
1855
+ "learning_rate": 0.0003,
1856
+ "loss": 0.8352,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 0.76,
1861
+ "learning_rate": 0.0003,
1862
+ "loss": 0.8365,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 0.77,
1867
+ "learning_rate": 0.0003,
1868
+ "loss": 0.8241,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 0.77,
1873
+ "learning_rate": 0.0003,
1874
+ "loss": 0.8125,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 0.77,
1879
+ "learning_rate": 0.0003,
1880
+ "loss": 0.7694,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 0.77,
1885
+ "learning_rate": 0.0003,
1886
+ "loss": 0.8051,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 0.78,
1891
+ "learning_rate": 0.0003,
1892
+ "loss": 0.825,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 0.78,
1897
+ "learning_rate": 0.0003,
1898
+ "loss": 0.8051,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 0.78,
1903
+ "learning_rate": 0.0003,
1904
+ "loss": 0.8149,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 0.78,
1909
+ "learning_rate": 0.0003,
1910
+ "loss": 0.8483,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 0.79,
1915
+ "learning_rate": 0.0003,
1916
+ "loss": 0.8013,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 0.79,
1921
+ "learning_rate": 0.0003,
1922
+ "loss": 0.7661,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 0.79,
1927
+ "learning_rate": 0.0003,
1928
+ "loss": 0.7741,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 0.79,
1933
+ "learning_rate": 0.0003,
1934
+ "loss": 0.8237,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 0.8,
1939
+ "learning_rate": 0.0003,
1940
+ "loss": 0.8298,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 0.8,
1945
+ "learning_rate": 0.0003,
1946
+ "loss": 0.8414,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 0.8,
1951
+ "learning_rate": 0.0003,
1952
+ "loss": 0.8061,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 0.8,
1957
+ "learning_rate": 0.0003,
1958
+ "loss": 0.8104,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 0.81,
1963
+ "learning_rate": 0.0003,
1964
+ "loss": 0.8064,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 0.81,
1969
+ "learning_rate": 0.0003,
1970
+ "loss": 0.8202,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 0.81,
1975
+ "learning_rate": 0.0003,
1976
+ "loss": 0.7952,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 0.81,
1981
+ "learning_rate": 0.0003,
1982
+ "loss": 0.7901,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 0.82,
1987
+ "learning_rate": 0.0003,
1988
+ "loss": 0.7949,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 0.82,
1993
+ "learning_rate": 0.0003,
1994
+ "loss": 0.7887,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 0.82,
1999
+ "learning_rate": 0.0003,
2000
+ "loss": 0.8413,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 0.82,
2005
+ "learning_rate": 0.0003,
2006
+ "loss": 0.7949,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 0.83,
2011
+ "learning_rate": 0.0003,
2012
+ "loss": 0.8184,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 0.83,
2017
+ "learning_rate": 0.0003,
2018
+ "loss": 0.7874,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 0.83,
2023
+ "learning_rate": 0.0003,
2024
+ "loss": 0.8264,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 0.83,
2029
+ "learning_rate": 0.0003,
2030
+ "loss": 0.7812,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 0.84,
2035
+ "learning_rate": 0.0003,
2036
+ "loss": 0.8128,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 0.84,
2041
+ "learning_rate": 0.0003,
2042
+ "loss": 0.8061,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 0.84,
2047
+ "learning_rate": 0.0003,
2048
+ "loss": 0.831,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 0.84,
2053
+ "learning_rate": 0.0003,
2054
+ "loss": 0.797,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 0.85,
2059
+ "learning_rate": 0.0003,
2060
+ "loss": 0.8133,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 0.85,
2065
+ "learning_rate": 0.0003,
2066
+ "loss": 0.8221,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 0.85,
2071
+ "learning_rate": 0.0003,
2072
+ "loss": 0.8287,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 0.85,
2077
+ "learning_rate": 0.0003,
2078
+ "loss": 0.811,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 0.86,
2083
+ "learning_rate": 0.0003,
2084
+ "loss": 0.8321,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 0.86,
2089
+ "learning_rate": 0.0003,
2090
+ "loss": 0.8095,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 0.86,
2095
+ "learning_rate": 0.0003,
2096
+ "loss": 0.8114,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 0.86,
2101
+ "learning_rate": 0.0003,
2102
+ "loss": 0.8042,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 0.87,
2107
+ "learning_rate": 0.0003,
2108
+ "loss": 0.8012,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 0.87,
2113
+ "learning_rate": 0.0003,
2114
+ "loss": 0.8012,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 0.87,
2119
+ "learning_rate": 0.0003,
2120
+ "loss": 0.7844,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 0.87,
2125
+ "learning_rate": 0.0003,
2126
+ "loss": 0.8078,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 0.88,
2131
+ "learning_rate": 0.0003,
2132
+ "loss": 0.8141,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 0.88,
2137
+ "learning_rate": 0.0003,
2138
+ "loss": 0.8235,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 0.88,
2143
+ "learning_rate": 0.0003,
2144
+ "loss": 0.8159,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 0.88,
2149
+ "learning_rate": 0.0003,
2150
+ "loss": 0.8536,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 0.89,
2155
+ "learning_rate": 0.0003,
2156
+ "loss": 0.7994,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 0.89,
2161
+ "learning_rate": 0.0003,
2162
+ "loss": 0.7894,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 0.89,
2167
+ "learning_rate": 0.0003,
2168
+ "loss": 0.7861,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 0.89,
2173
+ "learning_rate": 0.0003,
2174
+ "loss": 0.8554,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 0.9,
2179
+ "learning_rate": 0.0003,
2180
+ "loss": 0.8001,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 0.9,
2185
+ "learning_rate": 0.0003,
2186
+ "loss": 0.773,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 0.9,
2191
+ "learning_rate": 0.0003,
2192
+ "loss": 0.7982,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 0.9,
2197
+ "learning_rate": 0.0003,
2198
+ "loss": 0.819,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 0.91,
2203
+ "learning_rate": 0.0003,
2204
+ "loss": 0.8085,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 0.91,
2209
+ "learning_rate": 0.0003,
2210
+ "loss": 0.805,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 0.91,
2215
+ "learning_rate": 0.0003,
2216
+ "loss": 0.8258,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 0.91,
2221
+ "learning_rate": 0.0003,
2222
+ "loss": 0.8438,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 0.91,
2227
+ "learning_rate": 0.0003,
2228
+ "loss": 0.8152,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 0.92,
2233
+ "learning_rate": 0.0003,
2234
+ "loss": 0.8093,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 0.92,
2239
+ "learning_rate": 0.0003,
2240
+ "loss": 0.7816,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 0.92,
2245
+ "learning_rate": 0.0003,
2246
+ "loss": 0.7958,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 0.92,
2251
+ "learning_rate": 0.0003,
2252
+ "loss": 0.8041,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 0.93,
2257
+ "learning_rate": 0.0003,
2258
+ "loss": 0.7954,
2259
+ "step": 375
2260
+ }
2261
+ ],
2262
+ "logging_steps": 1,
2263
+ "max_steps": 404,
2264
+ "num_input_tokens_seen": 0,
2265
+ "num_train_epochs": 1,
2266
+ "save_steps": 25,
2267
+ "total_flos": 4.214459938342994e+17,
2268
+ "train_batch_size": 1,
2269
+ "trial_name": null,
2270
+ "trial_params": null
2271
+ }
llama2_7b_base_adapter/checkpoint-375/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1247dc269d0fa8df18e8e48dc478e4daaf7fd88110fd82993765140de4f97c83
3
+ size 4984
llama2_7b_base_adapter/checkpoint-400/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Llama-2-7b-hf
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
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
llama2_7b_base_adapter/checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16.0,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "q_proj,",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
llama2_7b_base_adapter/checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fc2505f99883e647ec6ec5d4cbc41d94d1ca510c0755282b2e145c12a24d71c
3
+ size 8397056
llama2_7b_base_adapter/checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a4b9ecabd04b3017365ebdeb9562d7dbe400055d7e900be962ec0518d822c0
3
+ size 16831290
llama2_7b_base_adapter/checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a8e2639340d8644780a15f83dd523fe71a787435d9e2f2e948fbb1aba1f410
3
+ size 14244
llama2_7b_base_adapter/checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b97723dff35b080a119aa0ed1d20263fbea0a5b26831bf27653458b28c680d1
3
+ size 1064
llama2_7b_base_adapter/checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,2421 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9891808346213292,
5
+ "eval_steps": 500,
6
+ "global_step": 400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.0003,
14
+ "loss": 1.717,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 0.0003,
20
+ "loss": 1.5844,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.0003,
26
+ "loss": 1.6147,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 0.0003,
32
+ "loss": 1.6272,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 0.0003,
38
+ "loss": 1.4652,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 0.0003,
44
+ "loss": 1.3925,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 0.0003,
50
+ "loss": 1.2981,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 0.0003,
56
+ "loss": 1.2549,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.02,
61
+ "learning_rate": 0.0003,
62
+ "loss": 1.1734,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.02,
67
+ "learning_rate": 0.0003,
68
+ "loss": 1.0787,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.03,
73
+ "learning_rate": 0.0003,
74
+ "loss": 1.0597,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.03,
79
+ "learning_rate": 0.0003,
80
+ "loss": 1.0002,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.03,
85
+ "learning_rate": 0.0003,
86
+ "loss": 0.9364,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.03,
91
+ "learning_rate": 0.0003,
92
+ "loss": 0.931,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.04,
97
+ "learning_rate": 0.0003,
98
+ "loss": 0.9021,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.04,
103
+ "learning_rate": 0.0003,
104
+ "loss": 0.9024,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.04,
109
+ "learning_rate": 0.0003,
110
+ "loss": 0.8829,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.04,
115
+ "learning_rate": 0.0003,
116
+ "loss": 0.881,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.05,
121
+ "learning_rate": 0.0003,
122
+ "loss": 0.907,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.05,
127
+ "learning_rate": 0.0003,
128
+ "loss": 0.908,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.05,
133
+ "learning_rate": 0.0003,
134
+ "loss": 0.8973,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.05,
139
+ "learning_rate": 0.0003,
140
+ "loss": 0.927,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.06,
145
+ "learning_rate": 0.0003,
146
+ "loss": 0.9174,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.06,
151
+ "learning_rate": 0.0003,
152
+ "loss": 0.85,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.06,
157
+ "learning_rate": 0.0003,
158
+ "loss": 0.8331,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.06,
163
+ "learning_rate": 0.0003,
164
+ "loss": 0.8393,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.07,
169
+ "learning_rate": 0.0003,
170
+ "loss": 0.9184,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.07,
175
+ "learning_rate": 0.0003,
176
+ "loss": 0.8506,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.07,
181
+ "learning_rate": 0.0003,
182
+ "loss": 0.8487,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.07,
187
+ "learning_rate": 0.0003,
188
+ "loss": 0.8352,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.08,
193
+ "learning_rate": 0.0003,
194
+ "loss": 0.8581,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.08,
199
+ "learning_rate": 0.0003,
200
+ "loss": 0.8843,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.08,
205
+ "learning_rate": 0.0003,
206
+ "loss": 0.858,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.08,
211
+ "learning_rate": 0.0003,
212
+ "loss": 0.8927,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.09,
217
+ "learning_rate": 0.0003,
218
+ "loss": 0.8385,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.09,
223
+ "learning_rate": 0.0003,
224
+ "loss": 0.8775,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.09,
229
+ "learning_rate": 0.0003,
230
+ "loss": 0.8506,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.09,
235
+ "learning_rate": 0.0003,
236
+ "loss": 0.846,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.1,
241
+ "learning_rate": 0.0003,
242
+ "loss": 0.8599,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.1,
247
+ "learning_rate": 0.0003,
248
+ "loss": 0.8277,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.1,
253
+ "learning_rate": 0.0003,
254
+ "loss": 0.8776,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.1,
259
+ "learning_rate": 0.0003,
260
+ "loss": 0.8536,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.11,
265
+ "learning_rate": 0.0003,
266
+ "loss": 0.8411,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.11,
271
+ "learning_rate": 0.0003,
272
+ "loss": 0.8515,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.11,
277
+ "learning_rate": 0.0003,
278
+ "loss": 0.8253,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.11,
283
+ "learning_rate": 0.0003,
284
+ "loss": 0.8666,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.12,
289
+ "learning_rate": 0.0003,
290
+ "loss": 0.8353,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.12,
295
+ "learning_rate": 0.0003,
296
+ "loss": 0.841,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.12,
301
+ "learning_rate": 0.0003,
302
+ "loss": 0.8512,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.12,
307
+ "learning_rate": 0.0003,
308
+ "loss": 0.8768,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.13,
313
+ "learning_rate": 0.0003,
314
+ "loss": 0.8201,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.13,
319
+ "learning_rate": 0.0003,
320
+ "loss": 0.8264,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.13,
325
+ "learning_rate": 0.0003,
326
+ "loss": 0.8303,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.13,
331
+ "learning_rate": 0.0003,
332
+ "loss": 0.8334,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.14,
337
+ "learning_rate": 0.0003,
338
+ "loss": 0.8514,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.14,
343
+ "learning_rate": 0.0003,
344
+ "loss": 0.8443,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.14,
349
+ "learning_rate": 0.0003,
350
+ "loss": 0.8866,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.14,
355
+ "learning_rate": 0.0003,
356
+ "loss": 0.8196,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.15,
361
+ "learning_rate": 0.0003,
362
+ "loss": 0.8133,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.15,
367
+ "learning_rate": 0.0003,
368
+ "loss": 0.8366,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.15,
373
+ "learning_rate": 0.0003,
374
+ "loss": 0.8313,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.15,
379
+ "learning_rate": 0.0003,
380
+ "loss": 0.8401,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.16,
385
+ "learning_rate": 0.0003,
386
+ "loss": 0.8324,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.16,
391
+ "learning_rate": 0.0003,
392
+ "loss": 0.8395,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.16,
397
+ "learning_rate": 0.0003,
398
+ "loss": 0.8468,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.16,
403
+ "learning_rate": 0.0003,
404
+ "loss": 0.8332,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.17,
409
+ "learning_rate": 0.0003,
410
+ "loss": 0.8415,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.17,
415
+ "learning_rate": 0.0003,
416
+ "loss": 0.8882,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.17,
421
+ "learning_rate": 0.0003,
422
+ "loss": 0.8104,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.17,
427
+ "learning_rate": 0.0003,
428
+ "loss": 0.8485,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.18,
433
+ "learning_rate": 0.0003,
434
+ "loss": 0.8475,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.18,
439
+ "learning_rate": 0.0003,
440
+ "loss": 0.7839,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.18,
445
+ "learning_rate": 0.0003,
446
+ "loss": 0.841,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.18,
451
+ "learning_rate": 0.0003,
452
+ "loss": 0.8401,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.19,
457
+ "learning_rate": 0.0003,
458
+ "loss": 0.8442,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.19,
463
+ "learning_rate": 0.0003,
464
+ "loss": 0.8336,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.19,
469
+ "learning_rate": 0.0003,
470
+ "loss": 0.8371,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.19,
475
+ "learning_rate": 0.0003,
476
+ "loss": 0.8391,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.2,
481
+ "learning_rate": 0.0003,
482
+ "loss": 0.8245,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.2,
487
+ "learning_rate": 0.0003,
488
+ "loss": 0.8196,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.2,
493
+ "learning_rate": 0.0003,
494
+ "loss": 0.7927,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.2,
499
+ "learning_rate": 0.0003,
500
+ "loss": 0.8374,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.21,
505
+ "learning_rate": 0.0003,
506
+ "loss": 0.8349,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.21,
511
+ "learning_rate": 0.0003,
512
+ "loss": 0.8271,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.21,
517
+ "learning_rate": 0.0003,
518
+ "loss": 0.8134,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.21,
523
+ "learning_rate": 0.0003,
524
+ "loss": 0.8481,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.22,
529
+ "learning_rate": 0.0003,
530
+ "loss": 0.8259,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.22,
535
+ "learning_rate": 0.0003,
536
+ "loss": 0.8447,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.22,
541
+ "learning_rate": 0.0003,
542
+ "loss": 0.839,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.22,
547
+ "learning_rate": 0.0003,
548
+ "loss": 0.8413,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.23,
553
+ "learning_rate": 0.0003,
554
+ "loss": 0.8168,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.23,
559
+ "learning_rate": 0.0003,
560
+ "loss": 0.8362,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.23,
565
+ "learning_rate": 0.0003,
566
+ "loss": 0.8595,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.23,
571
+ "learning_rate": 0.0003,
572
+ "loss": 0.8247,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.23,
577
+ "learning_rate": 0.0003,
578
+ "loss": 0.8122,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.24,
583
+ "learning_rate": 0.0003,
584
+ "loss": 0.8282,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.24,
589
+ "learning_rate": 0.0003,
590
+ "loss": 0.8326,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.24,
595
+ "learning_rate": 0.0003,
596
+ "loss": 0.8086,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.24,
601
+ "learning_rate": 0.0003,
602
+ "loss": 0.8564,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.25,
607
+ "learning_rate": 0.0003,
608
+ "loss": 0.8377,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.25,
613
+ "learning_rate": 0.0003,
614
+ "loss": 0.8456,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.25,
619
+ "learning_rate": 0.0003,
620
+ "loss": 0.7863,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.25,
625
+ "learning_rate": 0.0003,
626
+ "loss": 0.8117,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.26,
631
+ "learning_rate": 0.0003,
632
+ "loss": 0.8347,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.26,
637
+ "learning_rate": 0.0003,
638
+ "loss": 0.8155,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.26,
643
+ "learning_rate": 0.0003,
644
+ "loss": 0.8434,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.26,
649
+ "learning_rate": 0.0003,
650
+ "loss": 0.835,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.27,
655
+ "learning_rate": 0.0003,
656
+ "loss": 0.8437,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.27,
661
+ "learning_rate": 0.0003,
662
+ "loss": 0.8051,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.27,
667
+ "learning_rate": 0.0003,
668
+ "loss": 0.8197,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.27,
673
+ "learning_rate": 0.0003,
674
+ "loss": 0.8337,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.28,
679
+ "learning_rate": 0.0003,
680
+ "loss": 0.8442,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.28,
685
+ "learning_rate": 0.0003,
686
+ "loss": 0.8277,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.28,
691
+ "learning_rate": 0.0003,
692
+ "loss": 0.7963,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.28,
697
+ "learning_rate": 0.0003,
698
+ "loss": 0.7699,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.29,
703
+ "learning_rate": 0.0003,
704
+ "loss": 0.8266,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.29,
709
+ "learning_rate": 0.0003,
710
+ "loss": 0.7808,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.29,
715
+ "learning_rate": 0.0003,
716
+ "loss": 0.8247,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.29,
721
+ "learning_rate": 0.0003,
722
+ "loss": 0.8174,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.3,
727
+ "learning_rate": 0.0003,
728
+ "loss": 0.8338,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.3,
733
+ "learning_rate": 0.0003,
734
+ "loss": 0.8273,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.3,
739
+ "learning_rate": 0.0003,
740
+ "loss": 0.8258,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.3,
745
+ "learning_rate": 0.0003,
746
+ "loss": 0.8368,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.31,
751
+ "learning_rate": 0.0003,
752
+ "loss": 0.8133,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.31,
757
+ "learning_rate": 0.0003,
758
+ "loss": 0.8457,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.31,
763
+ "learning_rate": 0.0003,
764
+ "loss": 0.8479,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.31,
769
+ "learning_rate": 0.0003,
770
+ "loss": 0.8141,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.32,
775
+ "learning_rate": 0.0003,
776
+ "loss": 0.8147,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.32,
781
+ "learning_rate": 0.0003,
782
+ "loss": 0.8125,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.32,
787
+ "learning_rate": 0.0003,
788
+ "loss": 0.8066,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.32,
793
+ "learning_rate": 0.0003,
794
+ "loss": 0.8781,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.33,
799
+ "learning_rate": 0.0003,
800
+ "loss": 0.858,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.33,
805
+ "learning_rate": 0.0003,
806
+ "loss": 0.7778,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.33,
811
+ "learning_rate": 0.0003,
812
+ "loss": 0.7964,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.33,
817
+ "learning_rate": 0.0003,
818
+ "loss": 0.836,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.34,
823
+ "learning_rate": 0.0003,
824
+ "loss": 0.8205,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.34,
829
+ "learning_rate": 0.0003,
830
+ "loss": 0.7889,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.34,
835
+ "learning_rate": 0.0003,
836
+ "loss": 0.8597,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.34,
841
+ "learning_rate": 0.0003,
842
+ "loss": 0.8203,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.35,
847
+ "learning_rate": 0.0003,
848
+ "loss": 0.8256,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.35,
853
+ "learning_rate": 0.0003,
854
+ "loss": 0.8284,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.35,
859
+ "learning_rate": 0.0003,
860
+ "loss": 0.8457,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.35,
865
+ "learning_rate": 0.0003,
866
+ "loss": 0.7978,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.36,
871
+ "learning_rate": 0.0003,
872
+ "loss": 0.7882,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.36,
877
+ "learning_rate": 0.0003,
878
+ "loss": 0.8211,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.36,
883
+ "learning_rate": 0.0003,
884
+ "loss": 0.8464,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.36,
889
+ "learning_rate": 0.0003,
890
+ "loss": 0.8007,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.37,
895
+ "learning_rate": 0.0003,
896
+ "loss": 0.8526,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.37,
901
+ "learning_rate": 0.0003,
902
+ "loss": 0.7931,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.37,
907
+ "learning_rate": 0.0003,
908
+ "loss": 0.8185,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.37,
913
+ "learning_rate": 0.0003,
914
+ "loss": 0.802,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.38,
919
+ "learning_rate": 0.0003,
920
+ "loss": 0.8354,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.38,
925
+ "learning_rate": 0.0003,
926
+ "loss": 0.8124,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.38,
931
+ "learning_rate": 0.0003,
932
+ "loss": 0.8436,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.38,
937
+ "learning_rate": 0.0003,
938
+ "loss": 0.8159,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.39,
943
+ "learning_rate": 0.0003,
944
+ "loss": 0.8255,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.39,
949
+ "learning_rate": 0.0003,
950
+ "loss": 0.7855,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.39,
955
+ "learning_rate": 0.0003,
956
+ "loss": 0.802,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.39,
961
+ "learning_rate": 0.0003,
962
+ "loss": 0.8207,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.4,
967
+ "learning_rate": 0.0003,
968
+ "loss": 0.7981,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.4,
973
+ "learning_rate": 0.0003,
974
+ "loss": 0.818,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.4,
979
+ "learning_rate": 0.0003,
980
+ "loss": 0.8684,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.4,
985
+ "learning_rate": 0.0003,
986
+ "loss": 0.7987,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.41,
991
+ "learning_rate": 0.0003,
992
+ "loss": 0.8009,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.41,
997
+ "learning_rate": 0.0003,
998
+ "loss": 0.7902,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.41,
1003
+ "learning_rate": 0.0003,
1004
+ "loss": 0.8244,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.41,
1009
+ "learning_rate": 0.0003,
1010
+ "loss": 0.8476,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.42,
1015
+ "learning_rate": 0.0003,
1016
+ "loss": 0.8506,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.42,
1021
+ "learning_rate": 0.0003,
1022
+ "loss": 0.8357,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.42,
1027
+ "learning_rate": 0.0003,
1028
+ "loss": 0.8073,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.42,
1033
+ "learning_rate": 0.0003,
1034
+ "loss": 0.8377,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.43,
1039
+ "learning_rate": 0.0003,
1040
+ "loss": 0.7911,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.43,
1045
+ "learning_rate": 0.0003,
1046
+ "loss": 0.8392,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.43,
1051
+ "learning_rate": 0.0003,
1052
+ "loss": 0.8261,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.43,
1057
+ "learning_rate": 0.0003,
1058
+ "loss": 0.8175,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.44,
1063
+ "learning_rate": 0.0003,
1064
+ "loss": 0.82,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.44,
1069
+ "learning_rate": 0.0003,
1070
+ "loss": 0.8448,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.44,
1075
+ "learning_rate": 0.0003,
1076
+ "loss": 0.8449,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.44,
1081
+ "learning_rate": 0.0003,
1082
+ "loss": 0.8176,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.45,
1087
+ "learning_rate": 0.0003,
1088
+ "loss": 0.8211,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.45,
1093
+ "learning_rate": 0.0003,
1094
+ "loss": 0.7787,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.45,
1099
+ "learning_rate": 0.0003,
1100
+ "loss": 0.8119,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.45,
1105
+ "learning_rate": 0.0003,
1106
+ "loss": 0.8361,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.46,
1111
+ "learning_rate": 0.0003,
1112
+ "loss": 0.8496,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.46,
1117
+ "learning_rate": 0.0003,
1118
+ "loss": 0.8501,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.46,
1123
+ "learning_rate": 0.0003,
1124
+ "loss": 0.834,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.46,
1129
+ "learning_rate": 0.0003,
1130
+ "loss": 0.8189,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.46,
1135
+ "learning_rate": 0.0003,
1136
+ "loss": 0.8241,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.47,
1141
+ "learning_rate": 0.0003,
1142
+ "loss": 0.8458,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.47,
1147
+ "learning_rate": 0.0003,
1148
+ "loss": 0.8439,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.47,
1153
+ "learning_rate": 0.0003,
1154
+ "loss": 0.7946,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.47,
1159
+ "learning_rate": 0.0003,
1160
+ "loss": 0.8297,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.48,
1165
+ "learning_rate": 0.0003,
1166
+ "loss": 0.8388,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.48,
1171
+ "learning_rate": 0.0003,
1172
+ "loss": 0.842,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.48,
1177
+ "learning_rate": 0.0003,
1178
+ "loss": 0.8286,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.48,
1183
+ "learning_rate": 0.0003,
1184
+ "loss": 0.8126,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.49,
1189
+ "learning_rate": 0.0003,
1190
+ "loss": 0.8392,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.49,
1195
+ "learning_rate": 0.0003,
1196
+ "loss": 0.779,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.49,
1201
+ "learning_rate": 0.0003,
1202
+ "loss": 0.8178,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.49,
1207
+ "learning_rate": 0.0003,
1208
+ "loss": 0.7796,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.5,
1213
+ "learning_rate": 0.0003,
1214
+ "loss": 0.8119,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.5,
1219
+ "learning_rate": 0.0003,
1220
+ "loss": 0.7988,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.5,
1225
+ "learning_rate": 0.0003,
1226
+ "loss": 0.8195,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.5,
1231
+ "learning_rate": 0.0003,
1232
+ "loss": 0.8413,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.51,
1237
+ "learning_rate": 0.0003,
1238
+ "loss": 0.849,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.51,
1243
+ "learning_rate": 0.0003,
1244
+ "loss": 0.8184,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.51,
1249
+ "learning_rate": 0.0003,
1250
+ "loss": 0.8572,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.51,
1255
+ "learning_rate": 0.0003,
1256
+ "loss": 0.8146,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.52,
1261
+ "learning_rate": 0.0003,
1262
+ "loss": 0.8045,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.52,
1267
+ "learning_rate": 0.0003,
1268
+ "loss": 0.8128,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.52,
1273
+ "learning_rate": 0.0003,
1274
+ "loss": 0.7768,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.52,
1279
+ "learning_rate": 0.0003,
1280
+ "loss": 0.8289,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.53,
1285
+ "learning_rate": 0.0003,
1286
+ "loss": 0.8173,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.53,
1291
+ "learning_rate": 0.0003,
1292
+ "loss": 0.8749,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.53,
1297
+ "learning_rate": 0.0003,
1298
+ "loss": 0.8143,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.53,
1303
+ "learning_rate": 0.0003,
1304
+ "loss": 0.8287,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.54,
1309
+ "learning_rate": 0.0003,
1310
+ "loss": 0.804,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.54,
1315
+ "learning_rate": 0.0003,
1316
+ "loss": 0.8153,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.54,
1321
+ "learning_rate": 0.0003,
1322
+ "loss": 0.7883,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.54,
1327
+ "learning_rate": 0.0003,
1328
+ "loss": 0.8065,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.55,
1333
+ "learning_rate": 0.0003,
1334
+ "loss": 0.8538,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.55,
1339
+ "learning_rate": 0.0003,
1340
+ "loss": 0.8239,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.55,
1345
+ "learning_rate": 0.0003,
1346
+ "loss": 0.8615,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.55,
1351
+ "learning_rate": 0.0003,
1352
+ "loss": 0.8097,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.56,
1357
+ "learning_rate": 0.0003,
1358
+ "loss": 0.8191,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.56,
1363
+ "learning_rate": 0.0003,
1364
+ "loss": 0.8105,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.56,
1369
+ "learning_rate": 0.0003,
1370
+ "loss": 0.8228,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.56,
1375
+ "learning_rate": 0.0003,
1376
+ "loss": 0.7983,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.57,
1381
+ "learning_rate": 0.0003,
1382
+ "loss": 0.8382,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.57,
1387
+ "learning_rate": 0.0003,
1388
+ "loss": 0.8134,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.57,
1393
+ "learning_rate": 0.0003,
1394
+ "loss": 0.8338,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.57,
1399
+ "learning_rate": 0.0003,
1400
+ "loss": 0.826,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.58,
1405
+ "learning_rate": 0.0003,
1406
+ "loss": 0.8145,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.58,
1411
+ "learning_rate": 0.0003,
1412
+ "loss": 0.8139,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.58,
1417
+ "learning_rate": 0.0003,
1418
+ "loss": 0.7867,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.58,
1423
+ "learning_rate": 0.0003,
1424
+ "loss": 0.8064,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.59,
1429
+ "learning_rate": 0.0003,
1430
+ "loss": 0.8282,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.59,
1435
+ "learning_rate": 0.0003,
1436
+ "loss": 0.8448,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.59,
1441
+ "learning_rate": 0.0003,
1442
+ "loss": 0.8281,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.59,
1447
+ "learning_rate": 0.0003,
1448
+ "loss": 0.8608,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.6,
1453
+ "learning_rate": 0.0003,
1454
+ "loss": 0.8041,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.6,
1459
+ "learning_rate": 0.0003,
1460
+ "loss": 0.8092,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.6,
1465
+ "learning_rate": 0.0003,
1466
+ "loss": 0.8166,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.6,
1471
+ "learning_rate": 0.0003,
1472
+ "loss": 0.8047,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.61,
1477
+ "learning_rate": 0.0003,
1478
+ "loss": 0.8236,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.61,
1483
+ "learning_rate": 0.0003,
1484
+ "loss": 0.821,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.61,
1489
+ "learning_rate": 0.0003,
1490
+ "loss": 0.8409,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.61,
1495
+ "learning_rate": 0.0003,
1496
+ "loss": 0.8129,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.62,
1501
+ "learning_rate": 0.0003,
1502
+ "loss": 0.806,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.62,
1507
+ "learning_rate": 0.0003,
1508
+ "loss": 0.7602,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.62,
1513
+ "learning_rate": 0.0003,
1514
+ "loss": 0.8244,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.62,
1519
+ "learning_rate": 0.0003,
1520
+ "loss": 0.8279,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.63,
1525
+ "learning_rate": 0.0003,
1526
+ "loss": 0.8273,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.63,
1531
+ "learning_rate": 0.0003,
1532
+ "loss": 0.8229,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.63,
1537
+ "learning_rate": 0.0003,
1538
+ "loss": 0.816,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.63,
1543
+ "learning_rate": 0.0003,
1544
+ "loss": 0.8284,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.64,
1549
+ "learning_rate": 0.0003,
1550
+ "loss": 0.7923,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.64,
1555
+ "learning_rate": 0.0003,
1556
+ "loss": 0.8008,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.64,
1561
+ "learning_rate": 0.0003,
1562
+ "loss": 0.825,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.64,
1567
+ "learning_rate": 0.0003,
1568
+ "loss": 0.7781,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.65,
1573
+ "learning_rate": 0.0003,
1574
+ "loss": 0.7963,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.65,
1579
+ "learning_rate": 0.0003,
1580
+ "loss": 0.8652,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.65,
1585
+ "learning_rate": 0.0003,
1586
+ "loss": 0.8112,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.65,
1591
+ "learning_rate": 0.0003,
1592
+ "loss": 0.8307,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.66,
1597
+ "learning_rate": 0.0003,
1598
+ "loss": 0.7696,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.66,
1603
+ "learning_rate": 0.0003,
1604
+ "loss": 0.804,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.66,
1609
+ "learning_rate": 0.0003,
1610
+ "loss": 0.7744,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.66,
1615
+ "learning_rate": 0.0003,
1616
+ "loss": 0.806,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.67,
1621
+ "learning_rate": 0.0003,
1622
+ "loss": 0.8223,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.67,
1627
+ "learning_rate": 0.0003,
1628
+ "loss": 0.8517,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.67,
1633
+ "learning_rate": 0.0003,
1634
+ "loss": 0.7775,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.67,
1639
+ "learning_rate": 0.0003,
1640
+ "loss": 0.7867,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.68,
1645
+ "learning_rate": 0.0003,
1646
+ "loss": 0.7762,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.68,
1651
+ "learning_rate": 0.0003,
1652
+ "loss": 0.8187,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.68,
1657
+ "learning_rate": 0.0003,
1658
+ "loss": 0.814,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.68,
1663
+ "learning_rate": 0.0003,
1664
+ "loss": 0.8146,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.69,
1669
+ "learning_rate": 0.0003,
1670
+ "loss": 0.7844,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.69,
1675
+ "learning_rate": 0.0003,
1676
+ "loss": 0.8237,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.69,
1681
+ "learning_rate": 0.0003,
1682
+ "loss": 0.8364,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.69,
1687
+ "learning_rate": 0.0003,
1688
+ "loss": 0.8035,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.69,
1693
+ "learning_rate": 0.0003,
1694
+ "loss": 0.807,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.7,
1699
+ "learning_rate": 0.0003,
1700
+ "loss": 0.8138,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.7,
1705
+ "learning_rate": 0.0003,
1706
+ "loss": 0.8015,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.7,
1711
+ "learning_rate": 0.0003,
1712
+ "loss": 0.7838,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.7,
1717
+ "learning_rate": 0.0003,
1718
+ "loss": 0.8062,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.71,
1723
+ "learning_rate": 0.0003,
1724
+ "loss": 0.803,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.71,
1729
+ "learning_rate": 0.0003,
1730
+ "loss": 0.8124,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.71,
1735
+ "learning_rate": 0.0003,
1736
+ "loss": 0.8318,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.71,
1741
+ "learning_rate": 0.0003,
1742
+ "loss": 0.7836,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.72,
1747
+ "learning_rate": 0.0003,
1748
+ "loss": 0.8017,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.72,
1753
+ "learning_rate": 0.0003,
1754
+ "loss": 0.7574,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.72,
1759
+ "learning_rate": 0.0003,
1760
+ "loss": 0.7959,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.72,
1765
+ "learning_rate": 0.0003,
1766
+ "loss": 0.8077,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.73,
1771
+ "learning_rate": 0.0003,
1772
+ "loss": 0.7988,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.73,
1777
+ "learning_rate": 0.0003,
1778
+ "loss": 0.8183,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.73,
1783
+ "learning_rate": 0.0003,
1784
+ "loss": 0.7909,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.73,
1789
+ "learning_rate": 0.0003,
1790
+ "loss": 0.8241,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.74,
1795
+ "learning_rate": 0.0003,
1796
+ "loss": 0.7927,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.74,
1801
+ "learning_rate": 0.0003,
1802
+ "loss": 0.8215,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.74,
1807
+ "learning_rate": 0.0003,
1808
+ "loss": 0.8243,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 0.74,
1813
+ "learning_rate": 0.0003,
1814
+ "loss": 0.7996,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 0.75,
1819
+ "learning_rate": 0.0003,
1820
+ "loss": 0.7886,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 0.75,
1825
+ "learning_rate": 0.0003,
1826
+ "loss": 0.8271,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 0.75,
1831
+ "learning_rate": 0.0003,
1832
+ "loss": 0.7985,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 0.75,
1837
+ "learning_rate": 0.0003,
1838
+ "loss": 0.7996,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 0.76,
1843
+ "learning_rate": 0.0003,
1844
+ "loss": 0.8274,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 0.76,
1849
+ "learning_rate": 0.0003,
1850
+ "loss": 0.8091,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 0.76,
1855
+ "learning_rate": 0.0003,
1856
+ "loss": 0.8352,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 0.76,
1861
+ "learning_rate": 0.0003,
1862
+ "loss": 0.8365,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 0.77,
1867
+ "learning_rate": 0.0003,
1868
+ "loss": 0.8241,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 0.77,
1873
+ "learning_rate": 0.0003,
1874
+ "loss": 0.8125,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 0.77,
1879
+ "learning_rate": 0.0003,
1880
+ "loss": 0.7694,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 0.77,
1885
+ "learning_rate": 0.0003,
1886
+ "loss": 0.8051,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 0.78,
1891
+ "learning_rate": 0.0003,
1892
+ "loss": 0.825,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 0.78,
1897
+ "learning_rate": 0.0003,
1898
+ "loss": 0.8051,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 0.78,
1903
+ "learning_rate": 0.0003,
1904
+ "loss": 0.8149,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 0.78,
1909
+ "learning_rate": 0.0003,
1910
+ "loss": 0.8483,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 0.79,
1915
+ "learning_rate": 0.0003,
1916
+ "loss": 0.8013,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 0.79,
1921
+ "learning_rate": 0.0003,
1922
+ "loss": 0.7661,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 0.79,
1927
+ "learning_rate": 0.0003,
1928
+ "loss": 0.7741,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 0.79,
1933
+ "learning_rate": 0.0003,
1934
+ "loss": 0.8237,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 0.8,
1939
+ "learning_rate": 0.0003,
1940
+ "loss": 0.8298,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 0.8,
1945
+ "learning_rate": 0.0003,
1946
+ "loss": 0.8414,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 0.8,
1951
+ "learning_rate": 0.0003,
1952
+ "loss": 0.8061,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 0.8,
1957
+ "learning_rate": 0.0003,
1958
+ "loss": 0.8104,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 0.81,
1963
+ "learning_rate": 0.0003,
1964
+ "loss": 0.8064,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 0.81,
1969
+ "learning_rate": 0.0003,
1970
+ "loss": 0.8202,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 0.81,
1975
+ "learning_rate": 0.0003,
1976
+ "loss": 0.7952,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 0.81,
1981
+ "learning_rate": 0.0003,
1982
+ "loss": 0.7901,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 0.82,
1987
+ "learning_rate": 0.0003,
1988
+ "loss": 0.7949,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 0.82,
1993
+ "learning_rate": 0.0003,
1994
+ "loss": 0.7887,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 0.82,
1999
+ "learning_rate": 0.0003,
2000
+ "loss": 0.8413,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 0.82,
2005
+ "learning_rate": 0.0003,
2006
+ "loss": 0.7949,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 0.83,
2011
+ "learning_rate": 0.0003,
2012
+ "loss": 0.8184,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 0.83,
2017
+ "learning_rate": 0.0003,
2018
+ "loss": 0.7874,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 0.83,
2023
+ "learning_rate": 0.0003,
2024
+ "loss": 0.8264,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 0.83,
2029
+ "learning_rate": 0.0003,
2030
+ "loss": 0.7812,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 0.84,
2035
+ "learning_rate": 0.0003,
2036
+ "loss": 0.8128,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 0.84,
2041
+ "learning_rate": 0.0003,
2042
+ "loss": 0.8061,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 0.84,
2047
+ "learning_rate": 0.0003,
2048
+ "loss": 0.831,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 0.84,
2053
+ "learning_rate": 0.0003,
2054
+ "loss": 0.797,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 0.85,
2059
+ "learning_rate": 0.0003,
2060
+ "loss": 0.8133,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 0.85,
2065
+ "learning_rate": 0.0003,
2066
+ "loss": 0.8221,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 0.85,
2071
+ "learning_rate": 0.0003,
2072
+ "loss": 0.8287,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 0.85,
2077
+ "learning_rate": 0.0003,
2078
+ "loss": 0.811,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 0.86,
2083
+ "learning_rate": 0.0003,
2084
+ "loss": 0.8321,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 0.86,
2089
+ "learning_rate": 0.0003,
2090
+ "loss": 0.8095,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 0.86,
2095
+ "learning_rate": 0.0003,
2096
+ "loss": 0.8114,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 0.86,
2101
+ "learning_rate": 0.0003,
2102
+ "loss": 0.8042,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 0.87,
2107
+ "learning_rate": 0.0003,
2108
+ "loss": 0.8012,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 0.87,
2113
+ "learning_rate": 0.0003,
2114
+ "loss": 0.8012,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 0.87,
2119
+ "learning_rate": 0.0003,
2120
+ "loss": 0.7844,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 0.87,
2125
+ "learning_rate": 0.0003,
2126
+ "loss": 0.8078,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 0.88,
2131
+ "learning_rate": 0.0003,
2132
+ "loss": 0.8141,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 0.88,
2137
+ "learning_rate": 0.0003,
2138
+ "loss": 0.8235,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 0.88,
2143
+ "learning_rate": 0.0003,
2144
+ "loss": 0.8159,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 0.88,
2149
+ "learning_rate": 0.0003,
2150
+ "loss": 0.8536,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 0.89,
2155
+ "learning_rate": 0.0003,
2156
+ "loss": 0.7994,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 0.89,
2161
+ "learning_rate": 0.0003,
2162
+ "loss": 0.7894,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 0.89,
2167
+ "learning_rate": 0.0003,
2168
+ "loss": 0.7861,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 0.89,
2173
+ "learning_rate": 0.0003,
2174
+ "loss": 0.8554,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 0.9,
2179
+ "learning_rate": 0.0003,
2180
+ "loss": 0.8001,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 0.9,
2185
+ "learning_rate": 0.0003,
2186
+ "loss": 0.773,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 0.9,
2191
+ "learning_rate": 0.0003,
2192
+ "loss": 0.7982,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 0.9,
2197
+ "learning_rate": 0.0003,
2198
+ "loss": 0.819,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 0.91,
2203
+ "learning_rate": 0.0003,
2204
+ "loss": 0.8085,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 0.91,
2209
+ "learning_rate": 0.0003,
2210
+ "loss": 0.805,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 0.91,
2215
+ "learning_rate": 0.0003,
2216
+ "loss": 0.8258,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 0.91,
2221
+ "learning_rate": 0.0003,
2222
+ "loss": 0.8438,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 0.91,
2227
+ "learning_rate": 0.0003,
2228
+ "loss": 0.8152,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 0.92,
2233
+ "learning_rate": 0.0003,
2234
+ "loss": 0.8093,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 0.92,
2239
+ "learning_rate": 0.0003,
2240
+ "loss": 0.7816,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 0.92,
2245
+ "learning_rate": 0.0003,
2246
+ "loss": 0.7958,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 0.92,
2251
+ "learning_rate": 0.0003,
2252
+ "loss": 0.8041,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 0.93,
2257
+ "learning_rate": 0.0003,
2258
+ "loss": 0.7954,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 0.93,
2263
+ "learning_rate": 0.0003,
2264
+ "loss": 0.8015,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 0.93,
2269
+ "learning_rate": 0.0003,
2270
+ "loss": 0.8445,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 0.93,
2275
+ "learning_rate": 0.0003,
2276
+ "loss": 0.778,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 0.94,
2281
+ "learning_rate": 0.0003,
2282
+ "loss": 0.7999,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 0.94,
2287
+ "learning_rate": 0.0003,
2288
+ "loss": 0.8195,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 0.94,
2293
+ "learning_rate": 0.0003,
2294
+ "loss": 0.8193,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 0.94,
2299
+ "learning_rate": 0.0003,
2300
+ "loss": 0.8213,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 0.95,
2305
+ "learning_rate": 0.0003,
2306
+ "loss": 0.8164,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 0.95,
2311
+ "learning_rate": 0.0003,
2312
+ "loss": 0.8143,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 0.95,
2317
+ "learning_rate": 0.0003,
2318
+ "loss": 0.8051,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 0.95,
2323
+ "learning_rate": 0.0003,
2324
+ "loss": 0.8187,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 0.96,
2329
+ "learning_rate": 0.0003,
2330
+ "loss": 0.7838,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 0.96,
2335
+ "learning_rate": 0.0003,
2336
+ "loss": 0.7702,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 0.96,
2341
+ "learning_rate": 0.0003,
2342
+ "loss": 0.7866,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 0.96,
2347
+ "learning_rate": 0.0003,
2348
+ "loss": 0.8483,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 0.97,
2353
+ "learning_rate": 0.0003,
2354
+ "loss": 0.8023,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 0.97,
2359
+ "learning_rate": 0.0003,
2360
+ "loss": 0.8304,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 0.97,
2365
+ "learning_rate": 0.0003,
2366
+ "loss": 0.7956,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 0.97,
2371
+ "learning_rate": 0.0003,
2372
+ "loss": 0.8194,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 0.98,
2377
+ "learning_rate": 0.0003,
2378
+ "loss": 0.785,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 0.98,
2383
+ "learning_rate": 0.0003,
2384
+ "loss": 0.8153,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 0.98,
2389
+ "learning_rate": 0.0003,
2390
+ "loss": 0.8193,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 0.98,
2395
+ "learning_rate": 0.0003,
2396
+ "loss": 0.8125,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 0.99,
2401
+ "learning_rate": 0.0003,
2402
+ "loss": 0.8176,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 0.99,
2407
+ "learning_rate": 0.0003,
2408
+ "loss": 0.7885,
2409
+ "step": 400
2410
+ }
2411
+ ],
2412
+ "logging_steps": 1,
2413
+ "max_steps": 404,
2414
+ "num_input_tokens_seen": 0,
2415
+ "num_train_epochs": 1,
2416
+ "save_steps": 25,
2417
+ "total_flos": 4.495223430237389e+17,
2418
+ "train_batch_size": 1,
2419
+ "trial_name": null,
2420
+ "trial_params": null
2421
+ }
llama2_7b_base_adapter/checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1247dc269d0fa8df18e8e48dc478e4daaf7fd88110fd82993765140de4f97c83
3
+ size 4984
llama2_7b_base_adapter/train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.8384708828560197,
4
+ "train_runtime": 16978.7398,
5
+ "train_samples_per_second": 3.049,
6
+ "train_steps_per_second": 0.024
7
+ }
llama2_7b_base_adapter/trainer_state.json ADDED
@@ -0,0 +1,2454 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9990726429675425,
5
+ "eval_steps": 500,
6
+ "global_step": 404,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.0003,
14
+ "loss": 1.717,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 0.0003,
20
+ "loss": 1.5844,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.0003,
26
+ "loss": 1.6147,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 0.0003,
32
+ "loss": 1.6272,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 0.0003,
38
+ "loss": 1.4652,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 0.0003,
44
+ "loss": 1.3925,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 0.0003,
50
+ "loss": 1.2981,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 0.0003,
56
+ "loss": 1.2549,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.02,
61
+ "learning_rate": 0.0003,
62
+ "loss": 1.1734,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.02,
67
+ "learning_rate": 0.0003,
68
+ "loss": 1.0787,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.03,
73
+ "learning_rate": 0.0003,
74
+ "loss": 1.0597,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.03,
79
+ "learning_rate": 0.0003,
80
+ "loss": 1.0002,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.03,
85
+ "learning_rate": 0.0003,
86
+ "loss": 0.9364,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.03,
91
+ "learning_rate": 0.0003,
92
+ "loss": 0.931,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.04,
97
+ "learning_rate": 0.0003,
98
+ "loss": 0.9021,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.04,
103
+ "learning_rate": 0.0003,
104
+ "loss": 0.9024,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.04,
109
+ "learning_rate": 0.0003,
110
+ "loss": 0.8829,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.04,
115
+ "learning_rate": 0.0003,
116
+ "loss": 0.881,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.05,
121
+ "learning_rate": 0.0003,
122
+ "loss": 0.907,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.05,
127
+ "learning_rate": 0.0003,
128
+ "loss": 0.908,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.05,
133
+ "learning_rate": 0.0003,
134
+ "loss": 0.8973,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.05,
139
+ "learning_rate": 0.0003,
140
+ "loss": 0.927,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.06,
145
+ "learning_rate": 0.0003,
146
+ "loss": 0.9174,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.06,
151
+ "learning_rate": 0.0003,
152
+ "loss": 0.85,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.06,
157
+ "learning_rate": 0.0003,
158
+ "loss": 0.8331,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.06,
163
+ "learning_rate": 0.0003,
164
+ "loss": 0.8393,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.07,
169
+ "learning_rate": 0.0003,
170
+ "loss": 0.9184,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.07,
175
+ "learning_rate": 0.0003,
176
+ "loss": 0.8506,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.07,
181
+ "learning_rate": 0.0003,
182
+ "loss": 0.8487,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.07,
187
+ "learning_rate": 0.0003,
188
+ "loss": 0.8352,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.08,
193
+ "learning_rate": 0.0003,
194
+ "loss": 0.8581,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.08,
199
+ "learning_rate": 0.0003,
200
+ "loss": 0.8843,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.08,
205
+ "learning_rate": 0.0003,
206
+ "loss": 0.858,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.08,
211
+ "learning_rate": 0.0003,
212
+ "loss": 0.8927,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.09,
217
+ "learning_rate": 0.0003,
218
+ "loss": 0.8385,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.09,
223
+ "learning_rate": 0.0003,
224
+ "loss": 0.8775,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.09,
229
+ "learning_rate": 0.0003,
230
+ "loss": 0.8506,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.09,
235
+ "learning_rate": 0.0003,
236
+ "loss": 0.846,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.1,
241
+ "learning_rate": 0.0003,
242
+ "loss": 0.8599,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.1,
247
+ "learning_rate": 0.0003,
248
+ "loss": 0.8277,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.1,
253
+ "learning_rate": 0.0003,
254
+ "loss": 0.8776,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.1,
259
+ "learning_rate": 0.0003,
260
+ "loss": 0.8536,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.11,
265
+ "learning_rate": 0.0003,
266
+ "loss": 0.8411,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.11,
271
+ "learning_rate": 0.0003,
272
+ "loss": 0.8515,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.11,
277
+ "learning_rate": 0.0003,
278
+ "loss": 0.8253,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.11,
283
+ "learning_rate": 0.0003,
284
+ "loss": 0.8666,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.12,
289
+ "learning_rate": 0.0003,
290
+ "loss": 0.8353,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.12,
295
+ "learning_rate": 0.0003,
296
+ "loss": 0.841,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.12,
301
+ "learning_rate": 0.0003,
302
+ "loss": 0.8512,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.12,
307
+ "learning_rate": 0.0003,
308
+ "loss": 0.8768,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.13,
313
+ "learning_rate": 0.0003,
314
+ "loss": 0.8201,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.13,
319
+ "learning_rate": 0.0003,
320
+ "loss": 0.8264,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.13,
325
+ "learning_rate": 0.0003,
326
+ "loss": 0.8303,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.13,
331
+ "learning_rate": 0.0003,
332
+ "loss": 0.8334,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.14,
337
+ "learning_rate": 0.0003,
338
+ "loss": 0.8514,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.14,
343
+ "learning_rate": 0.0003,
344
+ "loss": 0.8443,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.14,
349
+ "learning_rate": 0.0003,
350
+ "loss": 0.8866,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.14,
355
+ "learning_rate": 0.0003,
356
+ "loss": 0.8196,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.15,
361
+ "learning_rate": 0.0003,
362
+ "loss": 0.8133,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.15,
367
+ "learning_rate": 0.0003,
368
+ "loss": 0.8366,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.15,
373
+ "learning_rate": 0.0003,
374
+ "loss": 0.8313,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.15,
379
+ "learning_rate": 0.0003,
380
+ "loss": 0.8401,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.16,
385
+ "learning_rate": 0.0003,
386
+ "loss": 0.8324,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.16,
391
+ "learning_rate": 0.0003,
392
+ "loss": 0.8395,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.16,
397
+ "learning_rate": 0.0003,
398
+ "loss": 0.8468,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.16,
403
+ "learning_rate": 0.0003,
404
+ "loss": 0.8332,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.17,
409
+ "learning_rate": 0.0003,
410
+ "loss": 0.8415,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.17,
415
+ "learning_rate": 0.0003,
416
+ "loss": 0.8882,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.17,
421
+ "learning_rate": 0.0003,
422
+ "loss": 0.8104,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.17,
427
+ "learning_rate": 0.0003,
428
+ "loss": 0.8485,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.18,
433
+ "learning_rate": 0.0003,
434
+ "loss": 0.8475,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.18,
439
+ "learning_rate": 0.0003,
440
+ "loss": 0.7839,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.18,
445
+ "learning_rate": 0.0003,
446
+ "loss": 0.841,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.18,
451
+ "learning_rate": 0.0003,
452
+ "loss": 0.8401,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.19,
457
+ "learning_rate": 0.0003,
458
+ "loss": 0.8442,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.19,
463
+ "learning_rate": 0.0003,
464
+ "loss": 0.8336,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.19,
469
+ "learning_rate": 0.0003,
470
+ "loss": 0.8371,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.19,
475
+ "learning_rate": 0.0003,
476
+ "loss": 0.8391,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.2,
481
+ "learning_rate": 0.0003,
482
+ "loss": 0.8245,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.2,
487
+ "learning_rate": 0.0003,
488
+ "loss": 0.8196,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.2,
493
+ "learning_rate": 0.0003,
494
+ "loss": 0.7927,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.2,
499
+ "learning_rate": 0.0003,
500
+ "loss": 0.8374,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.21,
505
+ "learning_rate": 0.0003,
506
+ "loss": 0.8349,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.21,
511
+ "learning_rate": 0.0003,
512
+ "loss": 0.8271,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.21,
517
+ "learning_rate": 0.0003,
518
+ "loss": 0.8134,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.21,
523
+ "learning_rate": 0.0003,
524
+ "loss": 0.8481,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.22,
529
+ "learning_rate": 0.0003,
530
+ "loss": 0.8259,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.22,
535
+ "learning_rate": 0.0003,
536
+ "loss": 0.8447,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.22,
541
+ "learning_rate": 0.0003,
542
+ "loss": 0.839,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.22,
547
+ "learning_rate": 0.0003,
548
+ "loss": 0.8413,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.23,
553
+ "learning_rate": 0.0003,
554
+ "loss": 0.8168,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.23,
559
+ "learning_rate": 0.0003,
560
+ "loss": 0.8362,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.23,
565
+ "learning_rate": 0.0003,
566
+ "loss": 0.8595,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.23,
571
+ "learning_rate": 0.0003,
572
+ "loss": 0.8247,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.23,
577
+ "learning_rate": 0.0003,
578
+ "loss": 0.8122,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.24,
583
+ "learning_rate": 0.0003,
584
+ "loss": 0.8282,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.24,
589
+ "learning_rate": 0.0003,
590
+ "loss": 0.8326,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.24,
595
+ "learning_rate": 0.0003,
596
+ "loss": 0.8086,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.24,
601
+ "learning_rate": 0.0003,
602
+ "loss": 0.8564,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.25,
607
+ "learning_rate": 0.0003,
608
+ "loss": 0.8377,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.25,
613
+ "learning_rate": 0.0003,
614
+ "loss": 0.8456,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.25,
619
+ "learning_rate": 0.0003,
620
+ "loss": 0.7863,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.25,
625
+ "learning_rate": 0.0003,
626
+ "loss": 0.8117,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.26,
631
+ "learning_rate": 0.0003,
632
+ "loss": 0.8347,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.26,
637
+ "learning_rate": 0.0003,
638
+ "loss": 0.8155,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.26,
643
+ "learning_rate": 0.0003,
644
+ "loss": 0.8434,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.26,
649
+ "learning_rate": 0.0003,
650
+ "loss": 0.835,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.27,
655
+ "learning_rate": 0.0003,
656
+ "loss": 0.8437,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.27,
661
+ "learning_rate": 0.0003,
662
+ "loss": 0.8051,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.27,
667
+ "learning_rate": 0.0003,
668
+ "loss": 0.8197,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.27,
673
+ "learning_rate": 0.0003,
674
+ "loss": 0.8337,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.28,
679
+ "learning_rate": 0.0003,
680
+ "loss": 0.8442,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.28,
685
+ "learning_rate": 0.0003,
686
+ "loss": 0.8277,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.28,
691
+ "learning_rate": 0.0003,
692
+ "loss": 0.7963,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.28,
697
+ "learning_rate": 0.0003,
698
+ "loss": 0.7699,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.29,
703
+ "learning_rate": 0.0003,
704
+ "loss": 0.8266,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.29,
709
+ "learning_rate": 0.0003,
710
+ "loss": 0.7808,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.29,
715
+ "learning_rate": 0.0003,
716
+ "loss": 0.8247,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.29,
721
+ "learning_rate": 0.0003,
722
+ "loss": 0.8174,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.3,
727
+ "learning_rate": 0.0003,
728
+ "loss": 0.8338,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.3,
733
+ "learning_rate": 0.0003,
734
+ "loss": 0.8273,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.3,
739
+ "learning_rate": 0.0003,
740
+ "loss": 0.8258,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.3,
745
+ "learning_rate": 0.0003,
746
+ "loss": 0.8368,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.31,
751
+ "learning_rate": 0.0003,
752
+ "loss": 0.8133,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.31,
757
+ "learning_rate": 0.0003,
758
+ "loss": 0.8457,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.31,
763
+ "learning_rate": 0.0003,
764
+ "loss": 0.8479,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.31,
769
+ "learning_rate": 0.0003,
770
+ "loss": 0.8141,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.32,
775
+ "learning_rate": 0.0003,
776
+ "loss": 0.8147,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.32,
781
+ "learning_rate": 0.0003,
782
+ "loss": 0.8125,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.32,
787
+ "learning_rate": 0.0003,
788
+ "loss": 0.8066,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.32,
793
+ "learning_rate": 0.0003,
794
+ "loss": 0.8781,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.33,
799
+ "learning_rate": 0.0003,
800
+ "loss": 0.858,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.33,
805
+ "learning_rate": 0.0003,
806
+ "loss": 0.7778,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.33,
811
+ "learning_rate": 0.0003,
812
+ "loss": 0.7964,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.33,
817
+ "learning_rate": 0.0003,
818
+ "loss": 0.836,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.34,
823
+ "learning_rate": 0.0003,
824
+ "loss": 0.8205,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.34,
829
+ "learning_rate": 0.0003,
830
+ "loss": 0.7889,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.34,
835
+ "learning_rate": 0.0003,
836
+ "loss": 0.8597,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.34,
841
+ "learning_rate": 0.0003,
842
+ "loss": 0.8203,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.35,
847
+ "learning_rate": 0.0003,
848
+ "loss": 0.8256,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.35,
853
+ "learning_rate": 0.0003,
854
+ "loss": 0.8284,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.35,
859
+ "learning_rate": 0.0003,
860
+ "loss": 0.8457,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.35,
865
+ "learning_rate": 0.0003,
866
+ "loss": 0.7978,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.36,
871
+ "learning_rate": 0.0003,
872
+ "loss": 0.7882,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.36,
877
+ "learning_rate": 0.0003,
878
+ "loss": 0.8211,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.36,
883
+ "learning_rate": 0.0003,
884
+ "loss": 0.8464,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.36,
889
+ "learning_rate": 0.0003,
890
+ "loss": 0.8007,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.37,
895
+ "learning_rate": 0.0003,
896
+ "loss": 0.8526,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.37,
901
+ "learning_rate": 0.0003,
902
+ "loss": 0.7931,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.37,
907
+ "learning_rate": 0.0003,
908
+ "loss": 0.8185,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.37,
913
+ "learning_rate": 0.0003,
914
+ "loss": 0.802,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.38,
919
+ "learning_rate": 0.0003,
920
+ "loss": 0.8354,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.38,
925
+ "learning_rate": 0.0003,
926
+ "loss": 0.8124,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.38,
931
+ "learning_rate": 0.0003,
932
+ "loss": 0.8436,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.38,
937
+ "learning_rate": 0.0003,
938
+ "loss": 0.8159,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.39,
943
+ "learning_rate": 0.0003,
944
+ "loss": 0.8255,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.39,
949
+ "learning_rate": 0.0003,
950
+ "loss": 0.7855,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.39,
955
+ "learning_rate": 0.0003,
956
+ "loss": 0.802,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.39,
961
+ "learning_rate": 0.0003,
962
+ "loss": 0.8207,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.4,
967
+ "learning_rate": 0.0003,
968
+ "loss": 0.7981,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.4,
973
+ "learning_rate": 0.0003,
974
+ "loss": 0.818,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.4,
979
+ "learning_rate": 0.0003,
980
+ "loss": 0.8684,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.4,
985
+ "learning_rate": 0.0003,
986
+ "loss": 0.7987,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.41,
991
+ "learning_rate": 0.0003,
992
+ "loss": 0.8009,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.41,
997
+ "learning_rate": 0.0003,
998
+ "loss": 0.7902,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.41,
1003
+ "learning_rate": 0.0003,
1004
+ "loss": 0.8244,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.41,
1009
+ "learning_rate": 0.0003,
1010
+ "loss": 0.8476,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.42,
1015
+ "learning_rate": 0.0003,
1016
+ "loss": 0.8506,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.42,
1021
+ "learning_rate": 0.0003,
1022
+ "loss": 0.8357,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.42,
1027
+ "learning_rate": 0.0003,
1028
+ "loss": 0.8073,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.42,
1033
+ "learning_rate": 0.0003,
1034
+ "loss": 0.8377,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.43,
1039
+ "learning_rate": 0.0003,
1040
+ "loss": 0.7911,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.43,
1045
+ "learning_rate": 0.0003,
1046
+ "loss": 0.8392,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.43,
1051
+ "learning_rate": 0.0003,
1052
+ "loss": 0.8261,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.43,
1057
+ "learning_rate": 0.0003,
1058
+ "loss": 0.8175,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.44,
1063
+ "learning_rate": 0.0003,
1064
+ "loss": 0.82,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.44,
1069
+ "learning_rate": 0.0003,
1070
+ "loss": 0.8448,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.44,
1075
+ "learning_rate": 0.0003,
1076
+ "loss": 0.8449,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.44,
1081
+ "learning_rate": 0.0003,
1082
+ "loss": 0.8176,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.45,
1087
+ "learning_rate": 0.0003,
1088
+ "loss": 0.8211,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.45,
1093
+ "learning_rate": 0.0003,
1094
+ "loss": 0.7787,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.45,
1099
+ "learning_rate": 0.0003,
1100
+ "loss": 0.8119,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.45,
1105
+ "learning_rate": 0.0003,
1106
+ "loss": 0.8361,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.46,
1111
+ "learning_rate": 0.0003,
1112
+ "loss": 0.8496,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.46,
1117
+ "learning_rate": 0.0003,
1118
+ "loss": 0.8501,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.46,
1123
+ "learning_rate": 0.0003,
1124
+ "loss": 0.834,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.46,
1129
+ "learning_rate": 0.0003,
1130
+ "loss": 0.8189,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.46,
1135
+ "learning_rate": 0.0003,
1136
+ "loss": 0.8241,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.47,
1141
+ "learning_rate": 0.0003,
1142
+ "loss": 0.8458,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.47,
1147
+ "learning_rate": 0.0003,
1148
+ "loss": 0.8439,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.47,
1153
+ "learning_rate": 0.0003,
1154
+ "loss": 0.7946,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.47,
1159
+ "learning_rate": 0.0003,
1160
+ "loss": 0.8297,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.48,
1165
+ "learning_rate": 0.0003,
1166
+ "loss": 0.8388,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.48,
1171
+ "learning_rate": 0.0003,
1172
+ "loss": 0.842,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.48,
1177
+ "learning_rate": 0.0003,
1178
+ "loss": 0.8286,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.48,
1183
+ "learning_rate": 0.0003,
1184
+ "loss": 0.8126,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.49,
1189
+ "learning_rate": 0.0003,
1190
+ "loss": 0.8392,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.49,
1195
+ "learning_rate": 0.0003,
1196
+ "loss": 0.779,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.49,
1201
+ "learning_rate": 0.0003,
1202
+ "loss": 0.8178,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.49,
1207
+ "learning_rate": 0.0003,
1208
+ "loss": 0.7796,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.5,
1213
+ "learning_rate": 0.0003,
1214
+ "loss": 0.8119,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.5,
1219
+ "learning_rate": 0.0003,
1220
+ "loss": 0.7988,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.5,
1225
+ "learning_rate": 0.0003,
1226
+ "loss": 0.8195,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.5,
1231
+ "learning_rate": 0.0003,
1232
+ "loss": 0.8413,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.51,
1237
+ "learning_rate": 0.0003,
1238
+ "loss": 0.849,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.51,
1243
+ "learning_rate": 0.0003,
1244
+ "loss": 0.8184,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.51,
1249
+ "learning_rate": 0.0003,
1250
+ "loss": 0.8572,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.51,
1255
+ "learning_rate": 0.0003,
1256
+ "loss": 0.8146,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.52,
1261
+ "learning_rate": 0.0003,
1262
+ "loss": 0.8045,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.52,
1267
+ "learning_rate": 0.0003,
1268
+ "loss": 0.8128,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.52,
1273
+ "learning_rate": 0.0003,
1274
+ "loss": 0.7768,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.52,
1279
+ "learning_rate": 0.0003,
1280
+ "loss": 0.8289,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.53,
1285
+ "learning_rate": 0.0003,
1286
+ "loss": 0.8173,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.53,
1291
+ "learning_rate": 0.0003,
1292
+ "loss": 0.8749,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.53,
1297
+ "learning_rate": 0.0003,
1298
+ "loss": 0.8143,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.53,
1303
+ "learning_rate": 0.0003,
1304
+ "loss": 0.8287,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.54,
1309
+ "learning_rate": 0.0003,
1310
+ "loss": 0.804,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.54,
1315
+ "learning_rate": 0.0003,
1316
+ "loss": 0.8153,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.54,
1321
+ "learning_rate": 0.0003,
1322
+ "loss": 0.7883,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.54,
1327
+ "learning_rate": 0.0003,
1328
+ "loss": 0.8065,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.55,
1333
+ "learning_rate": 0.0003,
1334
+ "loss": 0.8538,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.55,
1339
+ "learning_rate": 0.0003,
1340
+ "loss": 0.8239,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.55,
1345
+ "learning_rate": 0.0003,
1346
+ "loss": 0.8615,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.55,
1351
+ "learning_rate": 0.0003,
1352
+ "loss": 0.8097,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.56,
1357
+ "learning_rate": 0.0003,
1358
+ "loss": 0.8191,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.56,
1363
+ "learning_rate": 0.0003,
1364
+ "loss": 0.8105,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.56,
1369
+ "learning_rate": 0.0003,
1370
+ "loss": 0.8228,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.56,
1375
+ "learning_rate": 0.0003,
1376
+ "loss": 0.7983,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.57,
1381
+ "learning_rate": 0.0003,
1382
+ "loss": 0.8382,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.57,
1387
+ "learning_rate": 0.0003,
1388
+ "loss": 0.8134,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.57,
1393
+ "learning_rate": 0.0003,
1394
+ "loss": 0.8338,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.57,
1399
+ "learning_rate": 0.0003,
1400
+ "loss": 0.826,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.58,
1405
+ "learning_rate": 0.0003,
1406
+ "loss": 0.8145,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.58,
1411
+ "learning_rate": 0.0003,
1412
+ "loss": 0.8139,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.58,
1417
+ "learning_rate": 0.0003,
1418
+ "loss": 0.7867,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.58,
1423
+ "learning_rate": 0.0003,
1424
+ "loss": 0.8064,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.59,
1429
+ "learning_rate": 0.0003,
1430
+ "loss": 0.8282,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.59,
1435
+ "learning_rate": 0.0003,
1436
+ "loss": 0.8448,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.59,
1441
+ "learning_rate": 0.0003,
1442
+ "loss": 0.8281,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.59,
1447
+ "learning_rate": 0.0003,
1448
+ "loss": 0.8608,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.6,
1453
+ "learning_rate": 0.0003,
1454
+ "loss": 0.8041,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.6,
1459
+ "learning_rate": 0.0003,
1460
+ "loss": 0.8092,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.6,
1465
+ "learning_rate": 0.0003,
1466
+ "loss": 0.8166,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.6,
1471
+ "learning_rate": 0.0003,
1472
+ "loss": 0.8047,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.61,
1477
+ "learning_rate": 0.0003,
1478
+ "loss": 0.8236,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.61,
1483
+ "learning_rate": 0.0003,
1484
+ "loss": 0.821,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.61,
1489
+ "learning_rate": 0.0003,
1490
+ "loss": 0.8409,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.61,
1495
+ "learning_rate": 0.0003,
1496
+ "loss": 0.8129,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.62,
1501
+ "learning_rate": 0.0003,
1502
+ "loss": 0.806,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.62,
1507
+ "learning_rate": 0.0003,
1508
+ "loss": 0.7602,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.62,
1513
+ "learning_rate": 0.0003,
1514
+ "loss": 0.8244,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.62,
1519
+ "learning_rate": 0.0003,
1520
+ "loss": 0.8279,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.63,
1525
+ "learning_rate": 0.0003,
1526
+ "loss": 0.8273,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.63,
1531
+ "learning_rate": 0.0003,
1532
+ "loss": 0.8229,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.63,
1537
+ "learning_rate": 0.0003,
1538
+ "loss": 0.816,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.63,
1543
+ "learning_rate": 0.0003,
1544
+ "loss": 0.8284,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.64,
1549
+ "learning_rate": 0.0003,
1550
+ "loss": 0.7923,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.64,
1555
+ "learning_rate": 0.0003,
1556
+ "loss": 0.8008,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.64,
1561
+ "learning_rate": 0.0003,
1562
+ "loss": 0.825,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.64,
1567
+ "learning_rate": 0.0003,
1568
+ "loss": 0.7781,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.65,
1573
+ "learning_rate": 0.0003,
1574
+ "loss": 0.7963,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.65,
1579
+ "learning_rate": 0.0003,
1580
+ "loss": 0.8652,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.65,
1585
+ "learning_rate": 0.0003,
1586
+ "loss": 0.8112,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.65,
1591
+ "learning_rate": 0.0003,
1592
+ "loss": 0.8307,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.66,
1597
+ "learning_rate": 0.0003,
1598
+ "loss": 0.7696,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.66,
1603
+ "learning_rate": 0.0003,
1604
+ "loss": 0.804,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.66,
1609
+ "learning_rate": 0.0003,
1610
+ "loss": 0.7744,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.66,
1615
+ "learning_rate": 0.0003,
1616
+ "loss": 0.806,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.67,
1621
+ "learning_rate": 0.0003,
1622
+ "loss": 0.8223,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.67,
1627
+ "learning_rate": 0.0003,
1628
+ "loss": 0.8517,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.67,
1633
+ "learning_rate": 0.0003,
1634
+ "loss": 0.7775,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.67,
1639
+ "learning_rate": 0.0003,
1640
+ "loss": 0.7867,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.68,
1645
+ "learning_rate": 0.0003,
1646
+ "loss": 0.7762,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.68,
1651
+ "learning_rate": 0.0003,
1652
+ "loss": 0.8187,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.68,
1657
+ "learning_rate": 0.0003,
1658
+ "loss": 0.814,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.68,
1663
+ "learning_rate": 0.0003,
1664
+ "loss": 0.8146,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.69,
1669
+ "learning_rate": 0.0003,
1670
+ "loss": 0.7844,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.69,
1675
+ "learning_rate": 0.0003,
1676
+ "loss": 0.8237,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.69,
1681
+ "learning_rate": 0.0003,
1682
+ "loss": 0.8364,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.69,
1687
+ "learning_rate": 0.0003,
1688
+ "loss": 0.8035,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.69,
1693
+ "learning_rate": 0.0003,
1694
+ "loss": 0.807,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.7,
1699
+ "learning_rate": 0.0003,
1700
+ "loss": 0.8138,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.7,
1705
+ "learning_rate": 0.0003,
1706
+ "loss": 0.8015,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.7,
1711
+ "learning_rate": 0.0003,
1712
+ "loss": 0.7838,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.7,
1717
+ "learning_rate": 0.0003,
1718
+ "loss": 0.8062,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.71,
1723
+ "learning_rate": 0.0003,
1724
+ "loss": 0.803,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.71,
1729
+ "learning_rate": 0.0003,
1730
+ "loss": 0.8124,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.71,
1735
+ "learning_rate": 0.0003,
1736
+ "loss": 0.8318,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.71,
1741
+ "learning_rate": 0.0003,
1742
+ "loss": 0.7836,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.72,
1747
+ "learning_rate": 0.0003,
1748
+ "loss": 0.8017,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.72,
1753
+ "learning_rate": 0.0003,
1754
+ "loss": 0.7574,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.72,
1759
+ "learning_rate": 0.0003,
1760
+ "loss": 0.7959,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.72,
1765
+ "learning_rate": 0.0003,
1766
+ "loss": 0.8077,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.73,
1771
+ "learning_rate": 0.0003,
1772
+ "loss": 0.7988,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.73,
1777
+ "learning_rate": 0.0003,
1778
+ "loss": 0.8183,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.73,
1783
+ "learning_rate": 0.0003,
1784
+ "loss": 0.7909,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.73,
1789
+ "learning_rate": 0.0003,
1790
+ "loss": 0.8241,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.74,
1795
+ "learning_rate": 0.0003,
1796
+ "loss": 0.7927,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.74,
1801
+ "learning_rate": 0.0003,
1802
+ "loss": 0.8215,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.74,
1807
+ "learning_rate": 0.0003,
1808
+ "loss": 0.8243,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 0.74,
1813
+ "learning_rate": 0.0003,
1814
+ "loss": 0.7996,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 0.75,
1819
+ "learning_rate": 0.0003,
1820
+ "loss": 0.7886,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 0.75,
1825
+ "learning_rate": 0.0003,
1826
+ "loss": 0.8271,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 0.75,
1831
+ "learning_rate": 0.0003,
1832
+ "loss": 0.7985,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 0.75,
1837
+ "learning_rate": 0.0003,
1838
+ "loss": 0.7996,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 0.76,
1843
+ "learning_rate": 0.0003,
1844
+ "loss": 0.8274,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 0.76,
1849
+ "learning_rate": 0.0003,
1850
+ "loss": 0.8091,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 0.76,
1855
+ "learning_rate": 0.0003,
1856
+ "loss": 0.8352,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 0.76,
1861
+ "learning_rate": 0.0003,
1862
+ "loss": 0.8365,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 0.77,
1867
+ "learning_rate": 0.0003,
1868
+ "loss": 0.8241,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 0.77,
1873
+ "learning_rate": 0.0003,
1874
+ "loss": 0.8125,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 0.77,
1879
+ "learning_rate": 0.0003,
1880
+ "loss": 0.7694,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 0.77,
1885
+ "learning_rate": 0.0003,
1886
+ "loss": 0.8051,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 0.78,
1891
+ "learning_rate": 0.0003,
1892
+ "loss": 0.825,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 0.78,
1897
+ "learning_rate": 0.0003,
1898
+ "loss": 0.8051,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 0.78,
1903
+ "learning_rate": 0.0003,
1904
+ "loss": 0.8149,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 0.78,
1909
+ "learning_rate": 0.0003,
1910
+ "loss": 0.8483,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 0.79,
1915
+ "learning_rate": 0.0003,
1916
+ "loss": 0.8013,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 0.79,
1921
+ "learning_rate": 0.0003,
1922
+ "loss": 0.7661,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 0.79,
1927
+ "learning_rate": 0.0003,
1928
+ "loss": 0.7741,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 0.79,
1933
+ "learning_rate": 0.0003,
1934
+ "loss": 0.8237,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 0.8,
1939
+ "learning_rate": 0.0003,
1940
+ "loss": 0.8298,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 0.8,
1945
+ "learning_rate": 0.0003,
1946
+ "loss": 0.8414,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 0.8,
1951
+ "learning_rate": 0.0003,
1952
+ "loss": 0.8061,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 0.8,
1957
+ "learning_rate": 0.0003,
1958
+ "loss": 0.8104,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 0.81,
1963
+ "learning_rate": 0.0003,
1964
+ "loss": 0.8064,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 0.81,
1969
+ "learning_rate": 0.0003,
1970
+ "loss": 0.8202,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 0.81,
1975
+ "learning_rate": 0.0003,
1976
+ "loss": 0.7952,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 0.81,
1981
+ "learning_rate": 0.0003,
1982
+ "loss": 0.7901,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 0.82,
1987
+ "learning_rate": 0.0003,
1988
+ "loss": 0.7949,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 0.82,
1993
+ "learning_rate": 0.0003,
1994
+ "loss": 0.7887,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 0.82,
1999
+ "learning_rate": 0.0003,
2000
+ "loss": 0.8413,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 0.82,
2005
+ "learning_rate": 0.0003,
2006
+ "loss": 0.7949,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 0.83,
2011
+ "learning_rate": 0.0003,
2012
+ "loss": 0.8184,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 0.83,
2017
+ "learning_rate": 0.0003,
2018
+ "loss": 0.7874,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 0.83,
2023
+ "learning_rate": 0.0003,
2024
+ "loss": 0.8264,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 0.83,
2029
+ "learning_rate": 0.0003,
2030
+ "loss": 0.7812,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 0.84,
2035
+ "learning_rate": 0.0003,
2036
+ "loss": 0.8128,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 0.84,
2041
+ "learning_rate": 0.0003,
2042
+ "loss": 0.8061,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 0.84,
2047
+ "learning_rate": 0.0003,
2048
+ "loss": 0.831,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 0.84,
2053
+ "learning_rate": 0.0003,
2054
+ "loss": 0.797,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 0.85,
2059
+ "learning_rate": 0.0003,
2060
+ "loss": 0.8133,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 0.85,
2065
+ "learning_rate": 0.0003,
2066
+ "loss": 0.8221,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 0.85,
2071
+ "learning_rate": 0.0003,
2072
+ "loss": 0.8287,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 0.85,
2077
+ "learning_rate": 0.0003,
2078
+ "loss": 0.811,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 0.86,
2083
+ "learning_rate": 0.0003,
2084
+ "loss": 0.8321,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 0.86,
2089
+ "learning_rate": 0.0003,
2090
+ "loss": 0.8095,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 0.86,
2095
+ "learning_rate": 0.0003,
2096
+ "loss": 0.8114,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 0.86,
2101
+ "learning_rate": 0.0003,
2102
+ "loss": 0.8042,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 0.87,
2107
+ "learning_rate": 0.0003,
2108
+ "loss": 0.8012,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 0.87,
2113
+ "learning_rate": 0.0003,
2114
+ "loss": 0.8012,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 0.87,
2119
+ "learning_rate": 0.0003,
2120
+ "loss": 0.7844,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 0.87,
2125
+ "learning_rate": 0.0003,
2126
+ "loss": 0.8078,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 0.88,
2131
+ "learning_rate": 0.0003,
2132
+ "loss": 0.8141,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 0.88,
2137
+ "learning_rate": 0.0003,
2138
+ "loss": 0.8235,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 0.88,
2143
+ "learning_rate": 0.0003,
2144
+ "loss": 0.8159,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 0.88,
2149
+ "learning_rate": 0.0003,
2150
+ "loss": 0.8536,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 0.89,
2155
+ "learning_rate": 0.0003,
2156
+ "loss": 0.7994,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 0.89,
2161
+ "learning_rate": 0.0003,
2162
+ "loss": 0.7894,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 0.89,
2167
+ "learning_rate": 0.0003,
2168
+ "loss": 0.7861,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 0.89,
2173
+ "learning_rate": 0.0003,
2174
+ "loss": 0.8554,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 0.9,
2179
+ "learning_rate": 0.0003,
2180
+ "loss": 0.8001,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 0.9,
2185
+ "learning_rate": 0.0003,
2186
+ "loss": 0.773,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 0.9,
2191
+ "learning_rate": 0.0003,
2192
+ "loss": 0.7982,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 0.9,
2197
+ "learning_rate": 0.0003,
2198
+ "loss": 0.819,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 0.91,
2203
+ "learning_rate": 0.0003,
2204
+ "loss": 0.8085,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 0.91,
2209
+ "learning_rate": 0.0003,
2210
+ "loss": 0.805,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 0.91,
2215
+ "learning_rate": 0.0003,
2216
+ "loss": 0.8258,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 0.91,
2221
+ "learning_rate": 0.0003,
2222
+ "loss": 0.8438,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 0.91,
2227
+ "learning_rate": 0.0003,
2228
+ "loss": 0.8152,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 0.92,
2233
+ "learning_rate": 0.0003,
2234
+ "loss": 0.8093,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 0.92,
2239
+ "learning_rate": 0.0003,
2240
+ "loss": 0.7816,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 0.92,
2245
+ "learning_rate": 0.0003,
2246
+ "loss": 0.7958,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 0.92,
2251
+ "learning_rate": 0.0003,
2252
+ "loss": 0.8041,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 0.93,
2257
+ "learning_rate": 0.0003,
2258
+ "loss": 0.7954,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 0.93,
2263
+ "learning_rate": 0.0003,
2264
+ "loss": 0.8015,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 0.93,
2269
+ "learning_rate": 0.0003,
2270
+ "loss": 0.8445,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 0.93,
2275
+ "learning_rate": 0.0003,
2276
+ "loss": 0.778,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 0.94,
2281
+ "learning_rate": 0.0003,
2282
+ "loss": 0.7999,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 0.94,
2287
+ "learning_rate": 0.0003,
2288
+ "loss": 0.8195,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 0.94,
2293
+ "learning_rate": 0.0003,
2294
+ "loss": 0.8193,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 0.94,
2299
+ "learning_rate": 0.0003,
2300
+ "loss": 0.8213,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 0.95,
2305
+ "learning_rate": 0.0003,
2306
+ "loss": 0.8164,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 0.95,
2311
+ "learning_rate": 0.0003,
2312
+ "loss": 0.8143,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 0.95,
2317
+ "learning_rate": 0.0003,
2318
+ "loss": 0.8051,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 0.95,
2323
+ "learning_rate": 0.0003,
2324
+ "loss": 0.8187,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 0.96,
2329
+ "learning_rate": 0.0003,
2330
+ "loss": 0.7838,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 0.96,
2335
+ "learning_rate": 0.0003,
2336
+ "loss": 0.7702,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 0.96,
2341
+ "learning_rate": 0.0003,
2342
+ "loss": 0.7866,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 0.96,
2347
+ "learning_rate": 0.0003,
2348
+ "loss": 0.8483,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 0.97,
2353
+ "learning_rate": 0.0003,
2354
+ "loss": 0.8023,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 0.97,
2359
+ "learning_rate": 0.0003,
2360
+ "loss": 0.8304,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 0.97,
2365
+ "learning_rate": 0.0003,
2366
+ "loss": 0.7956,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 0.97,
2371
+ "learning_rate": 0.0003,
2372
+ "loss": 0.8194,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 0.98,
2377
+ "learning_rate": 0.0003,
2378
+ "loss": 0.785,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 0.98,
2383
+ "learning_rate": 0.0003,
2384
+ "loss": 0.8153,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 0.98,
2389
+ "learning_rate": 0.0003,
2390
+ "loss": 0.8193,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 0.98,
2395
+ "learning_rate": 0.0003,
2396
+ "loss": 0.8125,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 0.99,
2401
+ "learning_rate": 0.0003,
2402
+ "loss": 0.8176,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 0.99,
2407
+ "learning_rate": 0.0003,
2408
+ "loss": 0.7885,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 0.99,
2413
+ "learning_rate": 0.0003,
2414
+ "loss": 0.8021,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 0.99,
2419
+ "learning_rate": 0.0003,
2420
+ "loss": 0.7945,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 1.0,
2425
+ "learning_rate": 0.0003,
2426
+ "loss": 0.8175,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 1.0,
2431
+ "learning_rate": 0.0003,
2432
+ "loss": 0.8007,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 1.0,
2437
+ "step": 404,
2438
+ "total_flos": 4.5406536857338675e+17,
2439
+ "train_loss": 0.8384708828560197,
2440
+ "train_runtime": 16978.7398,
2441
+ "train_samples_per_second": 3.049,
2442
+ "train_steps_per_second": 0.024
2443
+ }
2444
+ ],
2445
+ "logging_steps": 1,
2446
+ "max_steps": 404,
2447
+ "num_input_tokens_seen": 0,
2448
+ "num_train_epochs": 1,
2449
+ "save_steps": 25,
2450
+ "total_flos": 4.5406536857338675e+17,
2451
+ "train_batch_size": 1,
2452
+ "trial_name": null,
2453
+ "trial_params": null
2454
+ }
llama2_7b_base_adapter/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1247dc269d0fa8df18e8e48dc478e4daaf7fd88110fd82993765140de4f97c83
3
+ size 4984