Hugging Face's logo

Doctor-Shotgun
/
Norobara-ZLoss-8x7b-qlora

PEFT
Safetensors
mixtral
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files
Doctor-Shotgun commited on
Commit
b8d1913
·
1 Parent(s): e18c9ba

Upload folder using huggingface_hub

Browse files
Files changed (31) hide show
  1. README.md +187 -0
  2. adapter_config.json +29 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-175/README.md +220 -0
  5. checkpoint-175/adapter_config.json +29 -0
  6. checkpoint-175/adapter_model.safetensors +3 -0
  7. checkpoint-175/optimizer.pt +3 -0
  8. checkpoint-175/rng_state.pth +3 -0
  9. checkpoint-175/scheduler.pt +3 -0
  10. checkpoint-175/trainer_state.json +1071 -0
  11. checkpoint-175/training_args.bin +3 -0
  12. checkpoint-350/README.md +220 -0
  13. checkpoint-350/adapter_config.json +29 -0
  14. checkpoint-350/adapter_model.safetensors +3 -0
  15. checkpoint-350/optimizer.pt +3 -0
  16. checkpoint-350/rng_state.pth +3 -0
  17. checkpoint-350/scheduler.pt +3 -0
  18. checkpoint-350/trainer_state.json +2121 -0
  19. checkpoint-350/training_args.bin +3 -0
  20. checkpoint-525/README.md +220 -0
  21. checkpoint-525/adapter_config.json +29 -0
  22. checkpoint-525/adapter_model.safetensors +3 -0
  23. checkpoint-525/optimizer.pt +3 -0
  24. checkpoint-525/rng_state.pth +3 -0
  25. checkpoint-525/scheduler.pt +3 -0
  26. checkpoint-525/trainer_state.json +3171 -0
  27. checkpoint-525/training_args.bin +3 -0
  28. config.json +43 -0
  29. special_tokens_map.json +24 -0
  30. tokenizer.model +3 -0
  31. tokenizer_config.json +44 -0
README.md ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - generated_from_trainer
5
+ base_model: mistralai/Mixtral-8x7B-v0.1
6
+ model-index:
7
+ - name: mixtral-norobara-qlora-out
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
15
+ <details><summary>See axolotl config</summary>
16
+
17
+ axolotl version: `0.3.0`
18
+ ```yaml
19
+ base_model: mistralai/Mixtral-8x7B-v0.1
20
+ model_type: AutoModelForCausalLM
21
+ tokenizer_type: LlamaTokenizer
22
+ trust_remote_code: true
23
+
24
+ model_config:
25
+ output_router_logits: true
26
+ router_aux_loss_coef: 0.02
27
+ router_z_loss_coef: 0.001
28
+
29
+ load_in_8bit: false
30
+ load_in_4bit: true
31
+ strict: false
32
+
33
+ datasets:
34
+ - path: capybara-sharegpt.jsonl
35
+ type: sharegpt
36
+ conversation: alpaca_multiturn
37
+ - path: no-robots-sharegpt-fixed.jsonl
38
+ type: sharegpt
39
+ conversation: alpaca_multiturn
40
+ - path: toxicsharegpt-NoWarning.jsonl
41
+ type: sharegpt
42
+ conversation: alpaca_multiturn
43
+ - path: camel-verified-sharegpt.jsonl
44
+ type: sharegpt
45
+ conversation: alpaca_multiturn
46
+ dataset_prepared_path: last_run_prepared
47
+ val_set_size: 0.0
48
+ output_dir: mixtral-norobara-qlora-out
49
+
50
+ ## You can optionally freeze the entire model and unfreeze a subset of parameters
51
+ #unfrozen_parameters:
52
+ # - lm_head.*
53
+ # - model.embed_tokens.*
54
+ # - model.layers.2[0-9]+.block_sparse_moe.gate.*
55
+ # - model.layers.2[0-9]+.block_sparse_moe.experts.*
56
+ # - model.layers.3[0-9]+.block_sparse_moe.gate.*
57
+ # - model.layers.3[0-9]+.block_sparse_moe.experts.*
58
+
59
+ adapter: qlora
60
+ lora_model_dir:
61
+
62
+ sequence_len: 8192
63
+ sample_packing: true
64
+ pad_to_sequence_len: true
65
+
66
+ lora_r: 32
67
+ lora_alpha: 16
68
+ lora_dropout: 0.05
69
+ lora_target_linear: true
70
+ lora_fan_in_fan_out:
71
+ #lora_target_modules:
72
+ # - gate
73
+ # - q_proj
74
+ # - k_proj
75
+ # - v_proj
76
+ # - o_proj
77
+ # - w1
78
+ # - w2
79
+ # - w3
80
+
81
+ wandb_project: mixtral-lora
82
+ wandb_entity:
83
+ wandb_watch:
84
+ wandb_name:
85
+ wandb_log_model:
86
+
87
+ gradient_accumulation_steps: 16
88
+ micro_batch_size: 1
89
+ num_epochs: 3
90
+ optimizer: adamw_bnb_8bit
91
+ lr_scheduler: cosine
92
+ learning_rate: 0.0001
93
+
94
+ train_on_inputs: false
95
+ group_by_length: false
96
+ bf16: true
97
+ fp16: false
98
+ tf32: true
99
+
100
+ gradient_checkpointing: true
101
+ early_stopping_patience:
102
+ resume_from_checkpoint:
103
+ local_rank:
104
+ logging_steps: 1
105
+ xformers_attention:
106
+ flash_attention: true
107
+
108
+ loss_watchdog_threshold:
109
+ loss_watchdog_patience:
110
+
111
+ warmup_steps: 10
112
+ evals_per_epoch:
113
+ eval_table_size:
114
+ eval_table_max_new_tokens:
115
+ saves_per_epoch: 1
116
+ debug:
117
+ deepspeed:
118
+ weight_decay: 0.0
119
+ fsdp:
120
+ fsdp_config:
121
+ special_tokens:
122
+
123
+ ```
124
+
125
+ </details><br>
126
+
127
+ # mixtral-norobara-qlora-out
128
+
129
+ This model was trained from scratch on the None dataset.
130
+
131
+ ## Model description
132
+
133
+ More information needed
134
+
135
+ ## Intended uses & limitations
136
+
137
+ More information needed
138
+
139
+ ## Training and evaluation data
140
+
141
+ More information needed
142
+
143
+ ## Training procedure
144
+
145
+ ### Training hyperparameters
146
+
147
+ The following hyperparameters were used during training:
148
+ - learning_rate: 0.0001
149
+ - train_batch_size: 1
150
+ - eval_batch_size: 1
151
+ - seed: 42
152
+ - gradient_accumulation_steps: 16
153
+ - total_train_batch_size: 16
154
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
155
+ - lr_scheduler_type: cosine
156
+ - lr_scheduler_warmup_steps: 10
157
+ - num_epochs: 3
158
+
159
+ ### Training results
160
+
161
+
162
+
163
+ ### Framework versions
164
+
165
+ - Transformers 4.37.0.dev0
166
+ - Pytorch 2.1.2+cu121
167
+ - Datasets 2.16.1
168
+ - Tokenizers 0.15.0
169
+ ## Training procedure
170
+
171
+
172
+ The following `bitsandbytes` quantization config was used during training:
173
+ - quant_method: bitsandbytes
174
+ - load_in_8bit: False
175
+ - load_in_4bit: True
176
+ - llm_int8_threshold: 6.0
177
+ - llm_int8_skip_modules: None
178
+ - llm_int8_enable_fp32_cpu_offload: False
179
+ - llm_int8_has_fp16_weight: False
180
+ - bnb_4bit_quant_type: nf4
181
+ - bnb_4bit_use_double_quant: True
182
+ - bnb_4bit_compute_dtype: bfloat16
183
+
184
+ ### Framework versions
185
+
186
+
187
+ - PEFT 0.6.0
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "models/Mixtral-8x7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 32,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "k_proj",
20
+ "w1",
21
+ "w2",
22
+ "q_proj",
23
+ "gate",
24
+ "w3",
25
+ "o_proj",
26
+ "v_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM"
29
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1da60c9f9d1083adea8d85a87e18641a77f047d39e01dd844b07c81c1d8bb436
3
+ size 1938497058
checkpoint-175/README.md ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: models/Mixtral-8x7B-v0.1
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
+ ## Training procedure
203
+
204
+
205
+ The following `bitsandbytes` quantization config was used during training:
206
+ - quant_method: bitsandbytes
207
+ - load_in_8bit: False
208
+ - load_in_4bit: True
209
+ - llm_int8_threshold: 6.0
210
+ - llm_int8_skip_modules: None
211
+ - llm_int8_enable_fp32_cpu_offload: False
212
+ - llm_int8_has_fp16_weight: False
213
+ - bnb_4bit_quant_type: nf4
214
+ - bnb_4bit_use_double_quant: True
215
+ - bnb_4bit_compute_dtype: bfloat16
216
+
217
+ ### Framework versions
218
+
219
+
220
+ - PEFT 0.6.0
checkpoint-175/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "models/Mixtral-8x7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 32,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "k_proj",
20
+ "w1",
21
+ "w2",
22
+ "q_proj",
23
+ "gate",
24
+ "w3",
25
+ "o_proj",
26
+ "v_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM"
29
+ }
checkpoint-175/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b831dba0a74eb7786cd4447d814946e9e40fbc1e5503b6e34cd99515d96f26f
3
+ size 1938077512
checkpoint-175/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20f5dc843a95c86b7778888d7b06e880f0b5dd9c4d4d21bed06087f8d7d735a
3
+ size 972997268
checkpoint-175/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0839a435748227a1b2dac208fc8f7852b79e353c7210496231fce32a4c0ccc80
3
+ size 14244
checkpoint-175/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:450669ef9cad283a563a5f7596bbeefd03e147f964194e7c4c3e990fc01edfcd
3
+ size 1064
checkpoint-175/trainer_state.json ADDED
@@ -0,0 +1,1071 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.99644128113879,
5
+ "eval_steps": 500,
6
+ "global_step": 175,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 1e-05,
14
+ "loss": 0.9314,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2e-05,
20
+ "loss": 1.0801,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 3e-05,
26
+ "loss": 1.0054,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 4e-05,
32
+ "loss": 0.9802,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 5e-05,
38
+ "loss": 1.0545,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 6e-05,
44
+ "loss": 1.0273,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 7e-05,
50
+ "loss": 0.9404,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 8e-05,
56
+ "loss": 1.0031,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 9e-05,
62
+ "loss": 1.0347,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 0.0001,
68
+ "loss": 1.045,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "learning_rate": 9.999906969801157e-05,
74
+ "loss": 0.9026,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 9.999627882666473e-05,
80
+ "loss": 1.0206,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.07,
85
+ "learning_rate": 9.999162748981361e-05,
86
+ "loss": 0.9519,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 9.998511586054414e-05,
92
+ "loss": 1.0259,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "learning_rate": 9.997674418116758e-05,
98
+ "loss": 1.0508,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.09,
103
+ "learning_rate": 9.996651276321153e-05,
104
+ "loss": 0.9679,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.1,
109
+ "learning_rate": 9.995442198740833e-05,
110
+ "loss": 0.9564,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.1,
115
+ "learning_rate": 9.994047230368086e-05,
116
+ "loss": 1.0159,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 9.99246642311259e-05,
122
+ "loss": 0.9157,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.11,
127
+ "learning_rate": 9.990699835799469e-05,
128
+ "loss": 1.0788,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.12,
133
+ "learning_rate": 9.988747534167111e-05,
134
+ "loss": 0.957,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "learning_rate": 9.986609590864719e-05,
140
+ "loss": 1.022,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.13,
145
+ "learning_rate": 9.98428608544961e-05,
146
+ "loss": 0.9874,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.14,
151
+ "learning_rate": 9.981777104384251e-05,
152
+ "loss": 1.1594,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.14,
157
+ "learning_rate": 9.979082741033047e-05,
158
+ "loss": 0.9913,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "learning_rate": 9.97620309565886e-05,
164
+ "loss": 0.9641,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.15,
169
+ "learning_rate": 9.97313827541928e-05,
170
+ "loss": 0.9905,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.16,
175
+ "learning_rate": 9.969888394362647e-05,
176
+ "loss": 0.9986,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.17,
181
+ "learning_rate": 9.966453573423791e-05,
182
+ "loss": 1.0096,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.17,
187
+ "learning_rate": 9.96283394041954e-05,
188
+ "loss": 0.962,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.18,
193
+ "learning_rate": 9.959029630043968e-05,
194
+ "loss": 1.0025,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.18,
199
+ "learning_rate": 9.955040783863374e-05,
200
+ "loss": 0.896,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.19,
205
+ "learning_rate": 9.950867550311018e-05,
206
+ "loss": 0.9042,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.19,
211
+ "learning_rate": 9.946510084681602e-05,
212
+ "loss": 0.9408,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.2,
217
+ "learning_rate": 9.941968549125481e-05,
218
+ "loss": 0.9185,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "learning_rate": 9.937243112642638e-05,
224
+ "loss": 0.8821,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.21,
229
+ "learning_rate": 9.932333951076394e-05,
230
+ "loss": 1.0143,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.22,
235
+ "learning_rate": 9.927241247106855e-05,
236
+ "loss": 0.9814,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.22,
241
+ "learning_rate": 9.921965190244129e-05,
242
+ "loss": 0.8808,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.23,
247
+ "learning_rate": 9.916505976821263e-05,
248
+ "loss": 0.9583,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.23,
253
+ "learning_rate": 9.910863809986941e-05,
254
+ "loss": 0.9627,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.24,
259
+ "learning_rate": 9.905038899697924e-05,
260
+ "loss": 0.9287,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.24,
265
+ "learning_rate": 9.899031462711237e-05,
266
+ "loss": 0.9075,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.25,
271
+ "learning_rate": 9.892841722576103e-05,
272
+ "loss": 0.9912,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.26,
277
+ "learning_rate": 9.886469909625625e-05,
278
+ "loss": 0.8891,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.26,
283
+ "learning_rate": 9.879916260968212e-05,
284
+ "loss": 0.9577,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.27,
289
+ "learning_rate": 9.87318102047876e-05,
290
+ "loss": 0.8791,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.27,
295
+ "learning_rate": 9.866264438789573e-05,
296
+ "loss": 0.9926,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.28,
301
+ "learning_rate": 9.85916677328104e-05,
302
+ "loss": 0.9273,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.28,
307
+ "learning_rate": 9.851888288072053e-05,
308
+ "loss": 0.9066,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.29,
313
+ "learning_rate": 9.844429254010185e-05,
314
+ "loss": 0.9806,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.3,
319
+ "learning_rate": 9.836789948661602e-05,
320
+ "loss": 0.91,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.3,
325
+ "learning_rate": 9.828970656300744e-05,
326
+ "loss": 0.9746,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.31,
331
+ "learning_rate": 9.820971667899739e-05,
332
+ "loss": 0.967,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.31,
337
+ "learning_rate": 9.81279328111758e-05,
338
+ "loss": 0.9605,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.32,
343
+ "learning_rate": 9.804435800289047e-05,
344
+ "loss": 0.8964,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.32,
349
+ "learning_rate": 9.795899536413382e-05,
350
+ "loss": 0.9759,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.33,
355
+ "learning_rate": 9.787184807142713e-05,
356
+ "loss": 0.9432,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.34,
361
+ "learning_rate": 9.77829193677024e-05,
362
+ "loss": 0.9003,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.34,
367
+ "learning_rate": 9.769221256218164e-05,
368
+ "loss": 0.9446,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.35,
373
+ "learning_rate": 9.759973103025368e-05,
374
+ "loss": 0.9903,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.35,
379
+ "learning_rate": 9.750547821334868e-05,
380
+ "loss": 0.9553,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.36,
385
+ "learning_rate": 9.740945761880993e-05,
386
+ "loss": 0.9117,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.36,
391
+ "learning_rate": 9.731167281976345e-05,
392
+ "loss": 0.8618,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.37,
397
+ "learning_rate": 9.721212745498494e-05,
398
+ "loss": 0.9687,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.38,
403
+ "learning_rate": 9.711082522876444e-05,
404
+ "loss": 0.8913,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.38,
409
+ "learning_rate": 9.700776991076845e-05,
410
+ "loss": 0.9567,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.39,
415
+ "learning_rate": 9.690296533589968e-05,
416
+ "loss": 0.8572,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.39,
421
+ "learning_rate": 9.679641540415427e-05,
422
+ "loss": 0.943,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.4,
427
+ "learning_rate": 9.668812408047679e-05,
428
+ "loss": 0.951,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.4,
433
+ "learning_rate": 9.657809539461256e-05,
434
+ "loss": 0.9608,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.41,
439
+ "learning_rate": 9.64663334409578e-05,
440
+ "loss": 0.8861,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.42,
445
+ "learning_rate": 9.635284237840721e-05,
446
+ "loss": 0.9538,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.42,
451
+ "learning_rate": 9.623762643019926e-05,
452
+ "loss": 0.9816,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.43,
457
+ "learning_rate": 9.612068988375897e-05,
458
+ "loss": 0.9205,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.43,
463
+ "learning_rate": 9.60020370905384e-05,
464
+ "loss": 0.9999,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.44,
469
+ "learning_rate": 9.588167246585473e-05,
470
+ "loss": 0.9324,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.44,
475
+ "learning_rate": 9.575960048872594e-05,
476
+ "loss": 0.9301,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.45,
481
+ "learning_rate": 9.563582570170417e-05,
482
+ "loss": 0.9512,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.46,
487
+ "learning_rate": 9.551035271070664e-05,
488
+ "loss": 0.9418,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.46,
493
+ "learning_rate": 9.538318618484425e-05,
494
+ "loss": 0.9221,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.47,
499
+ "learning_rate": 9.525433085624788e-05,
500
+ "loss": 0.905,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.47,
505
+ "learning_rate": 9.512379151989229e-05,
506
+ "loss": 0.9487,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.48,
511
+ "learning_rate": 9.499157303341762e-05,
512
+ "loss": 0.9569,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.48,
517
+ "learning_rate": 9.485768031694872e-05,
518
+ "loss": 0.933,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.49,
523
+ "learning_rate": 9.472211835291199e-05,
524
+ "loss": 0.9122,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.5,
529
+ "learning_rate": 9.458489218585002e-05,
530
+ "loss": 0.9518,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.5,
535
+ "learning_rate": 9.444600692223389e-05,
536
+ "loss": 0.8929,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.51,
541
+ "learning_rate": 9.430546773027302e-05,
542
+ "loss": 0.9438,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.51,
547
+ "learning_rate": 9.416327983972304e-05,
548
+ "loss": 0.9683,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.52,
553
+ "learning_rate": 9.401944854169102e-05,
554
+ "loss": 0.8427,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.52,
559
+ "learning_rate": 9.38739791884387e-05,
560
+ "loss": 0.9222,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.53,
565
+ "learning_rate": 9.372687719318317e-05,
566
+ "loss": 0.8887,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.54,
571
+ "learning_rate": 9.35781480298956e-05,
572
+ "loss": 0.9668,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.54,
577
+ "learning_rate": 9.342779723309745e-05,
578
+ "loss": 0.904,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.55,
583
+ "learning_rate": 9.327583039765453e-05,
584
+ "loss": 1.004,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.55,
589
+ "learning_rate": 9.31222531785688e-05,
590
+ "loss": 0.9759,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.56,
595
+ "learning_rate": 9.296707129076793e-05,
596
+ "loss": 0.9768,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.56,
601
+ "learning_rate": 9.281029050889274e-05,
602
+ "loss": 0.9175,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.57,
607
+ "learning_rate": 9.265191666708209e-05,
608
+ "loss": 0.9464,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.58,
613
+ "learning_rate": 9.2491955658756e-05,
614
+ "loss": 0.9382,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.58,
619
+ "learning_rate": 9.233041343639622e-05,
620
+ "loss": 0.9593,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.59,
625
+ "learning_rate": 9.216729601132481e-05,
626
+ "loss": 0.9245,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.59,
631
+ "learning_rate": 9.200260945348034e-05,
632
+ "loss": 0.9738,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.6,
637
+ "learning_rate": 9.18363598911921e-05,
638
+ "loss": 1.0077,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.6,
643
+ "learning_rate": 9.166855351095204e-05,
644
+ "loss": 0.9239,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.61,
649
+ "learning_rate": 9.149919655718454e-05,
650
+ "loss": 0.9601,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.61,
655
+ "learning_rate": 9.132829533201397e-05,
656
+ "loss": 0.9079,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.62,
661
+ "learning_rate": 9.115585619503039e-05,
662
+ "loss": 0.9859,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.63,
667
+ "learning_rate": 9.098188556305263e-05,
668
+ "loss": 0.9909,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.63,
673
+ "learning_rate": 9.08063899098897e-05,
674
+ "loss": 1.0114,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.64,
679
+ "learning_rate": 9.062937576609982e-05,
680
+ "loss": 0.9271,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.64,
685
+ "learning_rate": 9.045084971874738e-05,
686
+ "loss": 1.1316,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.65,
691
+ "learning_rate": 9.027081841115783e-05,
692
+ "loss": 0.9439,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.65,
697
+ "learning_rate": 9.008928854267054e-05,
698
+ "loss": 0.9477,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.66,
703
+ "learning_rate": 8.990626686838938e-05,
704
+ "loss": 0.9807,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.67,
709
+ "learning_rate": 8.972176019893149e-05,
710
+ "loss": 0.9543,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.67,
715
+ "learning_rate": 8.95357754001737e-05,
716
+ "loss": 0.96,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.68,
721
+ "learning_rate": 8.934831939299714e-05,
722
+ "loss": 0.9741,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.68,
727
+ "learning_rate": 8.915939915302968e-05,
728
+ "loss": 0.8402,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.69,
733
+ "learning_rate": 8.896902171038628e-05,
734
+ "loss": 0.8757,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.69,
739
+ "learning_rate": 8.877719414940751e-05,
740
+ "loss": 0.8724,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.7,
745
+ "learning_rate": 8.858392360839581e-05,
746
+ "loss": 0.8953,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.71,
751
+ "learning_rate": 8.838921727934992e-05,
752
+ "loss": 1.0174,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.71,
757
+ "learning_rate": 8.819308240769724e-05,
758
+ "loss": 0.9908,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.72,
763
+ "learning_rate": 8.799552629202424e-05,
764
+ "loss": 0.8448,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.72,
769
+ "learning_rate": 8.779655628380478e-05,
770
+ "loss": 0.9708,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.73,
775
+ "learning_rate": 8.759617978712667e-05,
776
+ "loss": 0.9518,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.73,
781
+ "learning_rate": 8.739440425841599e-05,
782
+ "loss": 1.088,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.74,
787
+ "learning_rate": 8.71912372061598e-05,
788
+ "loss": 0.9201,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.75,
793
+ "learning_rate": 8.69866861906266e-05,
794
+ "loss": 0.9452,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.75,
799
+ "learning_rate": 8.678075882358506e-05,
800
+ "loss": 0.9759,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.76,
805
+ "learning_rate": 8.657346276802071e-05,
806
+ "loss": 0.9172,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.76,
811
+ "learning_rate": 8.636480573785089e-05,
812
+ "loss": 0.9034,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.77,
817
+ "learning_rate": 8.615479549763756e-05,
818
+ "loss": 0.897,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.77,
823
+ "learning_rate": 8.594343986229854e-05,
824
+ "loss": 0.8837,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.78,
829
+ "learning_rate": 8.573074669681649e-05,
830
+ "loss": 0.8814,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.79,
835
+ "learning_rate": 8.551672391594645e-05,
836
+ "loss": 0.9168,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.79,
841
+ "learning_rate": 8.530137948392112e-05,
842
+ "loss": 0.9591,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.8,
847
+ "learning_rate": 8.508472141415467e-05,
848
+ "loss": 0.9279,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.8,
853
+ "learning_rate": 8.486675776894439e-05,
854
+ "loss": 0.8967,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.81,
859
+ "learning_rate": 8.464749665917081e-05,
860
+ "loss": 0.963,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.81,
865
+ "learning_rate": 8.442694624399576e-05,
866
+ "loss": 0.8653,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.82,
871
+ "learning_rate": 8.420511473055886e-05,
872
+ "loss": 0.9247,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.83,
877
+ "learning_rate": 8.398201037367201e-05,
878
+ "loss": 0.9432,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.83,
883
+ "learning_rate": 8.375764147551231e-05,
884
+ "loss": 0.9025,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.84,
889
+ "learning_rate": 8.3532016385313e-05,
890
+ "loss": 0.9395,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.84,
895
+ "learning_rate": 8.330514349905293e-05,
896
+ "loss": 0.88,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.85,
901
+ "learning_rate": 8.307703125914397e-05,
902
+ "loss": 0.8917,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.85,
907
+ "learning_rate": 8.284768815411692e-05,
908
+ "loss": 0.9516,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.86,
913
+ "learning_rate": 8.261712271830564e-05,
914
+ "loss": 0.9678,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.87,
919
+ "learning_rate": 8.238534353152951e-05,
920
+ "loss": 0.9055,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.87,
925
+ "learning_rate": 8.215235921877404e-05,
926
+ "loss": 0.91,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.88,
931
+ "learning_rate": 8.191817844986998e-05,
932
+ "loss": 0.9115,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.88,
937
+ "learning_rate": 8.168280993917077e-05,
938
+ "loss": 0.9546,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.89,
943
+ "learning_rate": 8.144626244522813e-05,
944
+ "loss": 0.868,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.89,
949
+ "learning_rate": 8.12085447704662e-05,
950
+ "loss": 0.91,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.9,
955
+ "learning_rate": 8.096966576085406e-05,
956
+ "loss": 0.9302,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.91,
961
+ "learning_rate": 8.072963430557636e-05,
962
+ "loss": 0.8818,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.91,
967
+ "learning_rate": 8.048845933670273e-05,
968
+ "loss": 0.9061,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.92,
973
+ "learning_rate": 8.024614982885527e-05,
974
+ "loss": 0.9108,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.92,
979
+ "learning_rate": 8.000271479887468e-05,
980
+ "loss": 0.8746,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.93,
985
+ "learning_rate": 7.975816330548467e-05,
986
+ "loss": 1.023,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.93,
991
+ "learning_rate": 7.951250444895484e-05,
992
+ "loss": 0.8844,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.94,
997
+ "learning_rate": 7.926574737076211e-05,
998
+ "loss": 0.9637,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.95,
1003
+ "learning_rate": 7.901790125325047e-05,
1004
+ "loss": 0.9124,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.95,
1009
+ "learning_rate": 7.876897531928943e-05,
1010
+ "loss": 0.9414,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.96,
1015
+ "learning_rate": 7.851897883193057e-05,
1016
+ "loss": 0.8677,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.96,
1021
+ "learning_rate": 7.826792109406308e-05,
1022
+ "loss": 0.9703,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.97,
1027
+ "learning_rate": 7.801581144806752e-05,
1028
+ "loss": 0.9004,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.97,
1033
+ "learning_rate": 7.776265927546799e-05,
1034
+ "loss": 0.8913,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.98,
1039
+ "learning_rate": 7.750847399658336e-05,
1040
+ "loss": 0.9349,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.99,
1045
+ "learning_rate": 7.725326507017643e-05,
1046
+ "loss": 0.9964,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.99,
1051
+ "learning_rate": 7.699704199310204e-05,
1052
+ "loss": 0.8782,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.0,
1057
+ "learning_rate": 7.673981429995372e-05,
1058
+ "loss": 0.895,
1059
+ "step": 175
1060
+ }
1061
+ ],
1062
+ "logging_steps": 1,
1063
+ "max_steps": 525,
1064
+ "num_input_tokens_seen": 0,
1065
+ "num_train_epochs": 3,
1066
+ "save_steps": 175,
1067
+ "total_flos": 6.476133768678605e+18,
1068
+ "train_batch_size": 1,
1069
+ "trial_name": null,
1070
+ "trial_params": null
1071
+ }
checkpoint-175/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:862899d2d90e28bcdb2d7301eb97d6ede02950401db2351f4f6591f98d8e42bd
3
+ size 5240
checkpoint-350/README.md ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: models/Mixtral-8x7B-v0.1
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
+ ## Training procedure
203
+
204
+
205
+ The following `bitsandbytes` quantization config was used during training:
206
+ - quant_method: bitsandbytes
207
+ - load_in_8bit: False
208
+ - load_in_4bit: True
209
+ - llm_int8_threshold: 6.0
210
+ - llm_int8_skip_modules: None
211
+ - llm_int8_enable_fp32_cpu_offload: False
212
+ - llm_int8_has_fp16_weight: False
213
+ - bnb_4bit_quant_type: nf4
214
+ - bnb_4bit_use_double_quant: True
215
+ - bnb_4bit_compute_dtype: bfloat16
216
+
217
+ ### Framework versions
218
+
219
+
220
+ - PEFT 0.6.0
checkpoint-350/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "models/Mixtral-8x7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 32,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "k_proj",
20
+ "w1",
21
+ "w2",
22
+ "q_proj",
23
+ "gate",
24
+ "w3",
25
+ "o_proj",
26
+ "v_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM"
29
+ }
checkpoint-350/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85634b8be29e96eda2b59b1ac87358561414c11d43873123601a456d8e4d9b7c
3
+ size 1938077512
checkpoint-350/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e6fcac4a36515ea238eee42b373285077d1f3f35836e0cbc23cc775d964c14
3
+ size 972999124
checkpoint-350/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5d412c765c9eec5a8e5b9ea2eeefe7952ed4652d609713083022d2ad31605d
3
+ size 14244
checkpoint-350/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb130abb9794459391d7cc6a275e4f10ae5b773c392a69ef0cb4c62c7f197f1
3
+ size 1064
checkpoint-350/trainer_state.json ADDED
@@ -0,0 +1,2121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9793594306049822,
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": 0.01,
13
+ "learning_rate": 1e-05,
14
+ "loss": 0.9314,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2e-05,
20
+ "loss": 1.0801,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 3e-05,
26
+ "loss": 1.0054,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 4e-05,
32
+ "loss": 0.9802,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 5e-05,
38
+ "loss": 1.0545,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 6e-05,
44
+ "loss": 1.0273,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 7e-05,
50
+ "loss": 0.9404,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 8e-05,
56
+ "loss": 1.0031,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 9e-05,
62
+ "loss": 1.0347,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 0.0001,
68
+ "loss": 1.045,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "learning_rate": 9.999906969801157e-05,
74
+ "loss": 0.9026,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 9.999627882666473e-05,
80
+ "loss": 1.0206,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.07,
85
+ "learning_rate": 9.999162748981361e-05,
86
+ "loss": 0.9519,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 9.998511586054414e-05,
92
+ "loss": 1.0259,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "learning_rate": 9.997674418116758e-05,
98
+ "loss": 1.0508,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.09,
103
+ "learning_rate": 9.996651276321153e-05,
104
+ "loss": 0.9679,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.1,
109
+ "learning_rate": 9.995442198740833e-05,
110
+ "loss": 0.9564,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.1,
115
+ "learning_rate": 9.994047230368086e-05,
116
+ "loss": 1.0159,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 9.99246642311259e-05,
122
+ "loss": 0.9157,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.11,
127
+ "learning_rate": 9.990699835799469e-05,
128
+ "loss": 1.0788,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.12,
133
+ "learning_rate": 9.988747534167111e-05,
134
+ "loss": 0.957,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "learning_rate": 9.986609590864719e-05,
140
+ "loss": 1.022,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.13,
145
+ "learning_rate": 9.98428608544961e-05,
146
+ "loss": 0.9874,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.14,
151
+ "learning_rate": 9.981777104384251e-05,
152
+ "loss": 1.1594,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.14,
157
+ "learning_rate": 9.979082741033047e-05,
158
+ "loss": 0.9913,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "learning_rate": 9.97620309565886e-05,
164
+ "loss": 0.9641,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.15,
169
+ "learning_rate": 9.97313827541928e-05,
170
+ "loss": 0.9905,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.16,
175
+ "learning_rate": 9.969888394362647e-05,
176
+ "loss": 0.9986,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.17,
181
+ "learning_rate": 9.966453573423791e-05,
182
+ "loss": 1.0096,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.17,
187
+ "learning_rate": 9.96283394041954e-05,
188
+ "loss": 0.962,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.18,
193
+ "learning_rate": 9.959029630043968e-05,
194
+ "loss": 1.0025,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.18,
199
+ "learning_rate": 9.955040783863374e-05,
200
+ "loss": 0.896,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.19,
205
+ "learning_rate": 9.950867550311018e-05,
206
+ "loss": 0.9042,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.19,
211
+ "learning_rate": 9.946510084681602e-05,
212
+ "loss": 0.9408,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.2,
217
+ "learning_rate": 9.941968549125481e-05,
218
+ "loss": 0.9185,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "learning_rate": 9.937243112642638e-05,
224
+ "loss": 0.8821,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.21,
229
+ "learning_rate": 9.932333951076394e-05,
230
+ "loss": 1.0143,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.22,
235
+ "learning_rate": 9.927241247106855e-05,
236
+ "loss": 0.9814,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.22,
241
+ "learning_rate": 9.921965190244129e-05,
242
+ "loss": 0.8808,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.23,
247
+ "learning_rate": 9.916505976821263e-05,
248
+ "loss": 0.9583,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.23,
253
+ "learning_rate": 9.910863809986941e-05,
254
+ "loss": 0.9627,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.24,
259
+ "learning_rate": 9.905038899697924e-05,
260
+ "loss": 0.9287,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.24,
265
+ "learning_rate": 9.899031462711237e-05,
266
+ "loss": 0.9075,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.25,
271
+ "learning_rate": 9.892841722576103e-05,
272
+ "loss": 0.9912,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.26,
277
+ "learning_rate": 9.886469909625625e-05,
278
+ "loss": 0.8891,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.26,
283
+ "learning_rate": 9.879916260968212e-05,
284
+ "loss": 0.9577,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.27,
289
+ "learning_rate": 9.87318102047876e-05,
290
+ "loss": 0.8791,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.27,
295
+ "learning_rate": 9.866264438789573e-05,
296
+ "loss": 0.9926,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.28,
301
+ "learning_rate": 9.85916677328104e-05,
302
+ "loss": 0.9273,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.28,
307
+ "learning_rate": 9.851888288072053e-05,
308
+ "loss": 0.9066,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.29,
313
+ "learning_rate": 9.844429254010185e-05,
314
+ "loss": 0.9806,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.3,
319
+ "learning_rate": 9.836789948661602e-05,
320
+ "loss": 0.91,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.3,
325
+ "learning_rate": 9.828970656300744e-05,
326
+ "loss": 0.9746,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.31,
331
+ "learning_rate": 9.820971667899739e-05,
332
+ "loss": 0.967,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.31,
337
+ "learning_rate": 9.81279328111758e-05,
338
+ "loss": 0.9605,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.32,
343
+ "learning_rate": 9.804435800289047e-05,
344
+ "loss": 0.8964,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.32,
349
+ "learning_rate": 9.795899536413382e-05,
350
+ "loss": 0.9759,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.33,
355
+ "learning_rate": 9.787184807142713e-05,
356
+ "loss": 0.9432,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.34,
361
+ "learning_rate": 9.77829193677024e-05,
362
+ "loss": 0.9003,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.34,
367
+ "learning_rate": 9.769221256218164e-05,
368
+ "loss": 0.9446,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.35,
373
+ "learning_rate": 9.759973103025368e-05,
374
+ "loss": 0.9903,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.35,
379
+ "learning_rate": 9.750547821334868e-05,
380
+ "loss": 0.9553,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.36,
385
+ "learning_rate": 9.740945761880993e-05,
386
+ "loss": 0.9117,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.36,
391
+ "learning_rate": 9.731167281976345e-05,
392
+ "loss": 0.8618,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.37,
397
+ "learning_rate": 9.721212745498494e-05,
398
+ "loss": 0.9687,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.38,
403
+ "learning_rate": 9.711082522876444e-05,
404
+ "loss": 0.8913,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.38,
409
+ "learning_rate": 9.700776991076845e-05,
410
+ "loss": 0.9567,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.39,
415
+ "learning_rate": 9.690296533589968e-05,
416
+ "loss": 0.8572,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.39,
421
+ "learning_rate": 9.679641540415427e-05,
422
+ "loss": 0.943,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.4,
427
+ "learning_rate": 9.668812408047679e-05,
428
+ "loss": 0.951,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.4,
433
+ "learning_rate": 9.657809539461256e-05,
434
+ "loss": 0.9608,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.41,
439
+ "learning_rate": 9.64663334409578e-05,
440
+ "loss": 0.8861,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.42,
445
+ "learning_rate": 9.635284237840721e-05,
446
+ "loss": 0.9538,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.42,
451
+ "learning_rate": 9.623762643019926e-05,
452
+ "loss": 0.9816,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.43,
457
+ "learning_rate": 9.612068988375897e-05,
458
+ "loss": 0.9205,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.43,
463
+ "learning_rate": 9.60020370905384e-05,
464
+ "loss": 0.9999,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.44,
469
+ "learning_rate": 9.588167246585473e-05,
470
+ "loss": 0.9324,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.44,
475
+ "learning_rate": 9.575960048872594e-05,
476
+ "loss": 0.9301,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.45,
481
+ "learning_rate": 9.563582570170417e-05,
482
+ "loss": 0.9512,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.46,
487
+ "learning_rate": 9.551035271070664e-05,
488
+ "loss": 0.9418,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.46,
493
+ "learning_rate": 9.538318618484425e-05,
494
+ "loss": 0.9221,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.47,
499
+ "learning_rate": 9.525433085624788e-05,
500
+ "loss": 0.905,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.47,
505
+ "learning_rate": 9.512379151989229e-05,
506
+ "loss": 0.9487,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.48,
511
+ "learning_rate": 9.499157303341762e-05,
512
+ "loss": 0.9569,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.48,
517
+ "learning_rate": 9.485768031694872e-05,
518
+ "loss": 0.933,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.49,
523
+ "learning_rate": 9.472211835291199e-05,
524
+ "loss": 0.9122,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.5,
529
+ "learning_rate": 9.458489218585002e-05,
530
+ "loss": 0.9518,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.5,
535
+ "learning_rate": 9.444600692223389e-05,
536
+ "loss": 0.8929,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.51,
541
+ "learning_rate": 9.430546773027302e-05,
542
+ "loss": 0.9438,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.51,
547
+ "learning_rate": 9.416327983972304e-05,
548
+ "loss": 0.9683,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.52,
553
+ "learning_rate": 9.401944854169102e-05,
554
+ "loss": 0.8427,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.52,
559
+ "learning_rate": 9.38739791884387e-05,
560
+ "loss": 0.9222,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.53,
565
+ "learning_rate": 9.372687719318317e-05,
566
+ "loss": 0.8887,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.54,
571
+ "learning_rate": 9.35781480298956e-05,
572
+ "loss": 0.9668,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.54,
577
+ "learning_rate": 9.342779723309745e-05,
578
+ "loss": 0.904,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.55,
583
+ "learning_rate": 9.327583039765453e-05,
584
+ "loss": 1.004,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.55,
589
+ "learning_rate": 9.31222531785688e-05,
590
+ "loss": 0.9759,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.56,
595
+ "learning_rate": 9.296707129076793e-05,
596
+ "loss": 0.9768,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.56,
601
+ "learning_rate": 9.281029050889274e-05,
602
+ "loss": 0.9175,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.57,
607
+ "learning_rate": 9.265191666708209e-05,
608
+ "loss": 0.9464,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.58,
613
+ "learning_rate": 9.2491955658756e-05,
614
+ "loss": 0.9382,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.58,
619
+ "learning_rate": 9.233041343639622e-05,
620
+ "loss": 0.9593,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.59,
625
+ "learning_rate": 9.216729601132481e-05,
626
+ "loss": 0.9245,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.59,
631
+ "learning_rate": 9.200260945348034e-05,
632
+ "loss": 0.9738,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.6,
637
+ "learning_rate": 9.18363598911921e-05,
638
+ "loss": 1.0077,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.6,
643
+ "learning_rate": 9.166855351095204e-05,
644
+ "loss": 0.9239,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.61,
649
+ "learning_rate": 9.149919655718454e-05,
650
+ "loss": 0.9601,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.61,
655
+ "learning_rate": 9.132829533201397e-05,
656
+ "loss": 0.9079,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.62,
661
+ "learning_rate": 9.115585619503039e-05,
662
+ "loss": 0.9859,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.63,
667
+ "learning_rate": 9.098188556305263e-05,
668
+ "loss": 0.9909,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.63,
673
+ "learning_rate": 9.08063899098897e-05,
674
+ "loss": 1.0114,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.64,
679
+ "learning_rate": 9.062937576609982e-05,
680
+ "loss": 0.9271,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.64,
685
+ "learning_rate": 9.045084971874738e-05,
686
+ "loss": 1.1316,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.65,
691
+ "learning_rate": 9.027081841115783e-05,
692
+ "loss": 0.9439,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.65,
697
+ "learning_rate": 9.008928854267054e-05,
698
+ "loss": 0.9477,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.66,
703
+ "learning_rate": 8.990626686838938e-05,
704
+ "loss": 0.9807,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.67,
709
+ "learning_rate": 8.972176019893149e-05,
710
+ "loss": 0.9543,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.67,
715
+ "learning_rate": 8.95357754001737e-05,
716
+ "loss": 0.96,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.68,
721
+ "learning_rate": 8.934831939299714e-05,
722
+ "loss": 0.9741,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.68,
727
+ "learning_rate": 8.915939915302968e-05,
728
+ "loss": 0.8402,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.69,
733
+ "learning_rate": 8.896902171038628e-05,
734
+ "loss": 0.8757,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.69,
739
+ "learning_rate": 8.877719414940751e-05,
740
+ "loss": 0.8724,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.7,
745
+ "learning_rate": 8.858392360839581e-05,
746
+ "loss": 0.8953,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.71,
751
+ "learning_rate": 8.838921727934992e-05,
752
+ "loss": 1.0174,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.71,
757
+ "learning_rate": 8.819308240769724e-05,
758
+ "loss": 0.9908,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.72,
763
+ "learning_rate": 8.799552629202424e-05,
764
+ "loss": 0.8448,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.72,
769
+ "learning_rate": 8.779655628380478e-05,
770
+ "loss": 0.9708,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.73,
775
+ "learning_rate": 8.759617978712667e-05,
776
+ "loss": 0.9518,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.73,
781
+ "learning_rate": 8.739440425841599e-05,
782
+ "loss": 1.088,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.74,
787
+ "learning_rate": 8.71912372061598e-05,
788
+ "loss": 0.9201,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.75,
793
+ "learning_rate": 8.69866861906266e-05,
794
+ "loss": 0.9452,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.75,
799
+ "learning_rate": 8.678075882358506e-05,
800
+ "loss": 0.9759,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.76,
805
+ "learning_rate": 8.657346276802071e-05,
806
+ "loss": 0.9172,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.76,
811
+ "learning_rate": 8.636480573785089e-05,
812
+ "loss": 0.9034,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.77,
817
+ "learning_rate": 8.615479549763756e-05,
818
+ "loss": 0.897,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.77,
823
+ "learning_rate": 8.594343986229854e-05,
824
+ "loss": 0.8837,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.78,
829
+ "learning_rate": 8.573074669681649e-05,
830
+ "loss": 0.8814,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.79,
835
+ "learning_rate": 8.551672391594645e-05,
836
+ "loss": 0.9168,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.79,
841
+ "learning_rate": 8.530137948392112e-05,
842
+ "loss": 0.9591,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.8,
847
+ "learning_rate": 8.508472141415467e-05,
848
+ "loss": 0.9279,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.8,
853
+ "learning_rate": 8.486675776894439e-05,
854
+ "loss": 0.8967,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.81,
859
+ "learning_rate": 8.464749665917081e-05,
860
+ "loss": 0.963,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.81,
865
+ "learning_rate": 8.442694624399576e-05,
866
+ "loss": 0.8653,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.82,
871
+ "learning_rate": 8.420511473055886e-05,
872
+ "loss": 0.9247,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.83,
877
+ "learning_rate": 8.398201037367201e-05,
878
+ "loss": 0.9432,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.83,
883
+ "learning_rate": 8.375764147551231e-05,
884
+ "loss": 0.9025,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.84,
889
+ "learning_rate": 8.3532016385313e-05,
890
+ "loss": 0.9395,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.84,
895
+ "learning_rate": 8.330514349905293e-05,
896
+ "loss": 0.88,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.85,
901
+ "learning_rate": 8.307703125914397e-05,
902
+ "loss": 0.8917,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.85,
907
+ "learning_rate": 8.284768815411692e-05,
908
+ "loss": 0.9516,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.86,
913
+ "learning_rate": 8.261712271830564e-05,
914
+ "loss": 0.9678,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.87,
919
+ "learning_rate": 8.238534353152951e-05,
920
+ "loss": 0.9055,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.87,
925
+ "learning_rate": 8.215235921877404e-05,
926
+ "loss": 0.91,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.88,
931
+ "learning_rate": 8.191817844986998e-05,
932
+ "loss": 0.9115,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.88,
937
+ "learning_rate": 8.168280993917077e-05,
938
+ "loss": 0.9546,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.89,
943
+ "learning_rate": 8.144626244522813e-05,
944
+ "loss": 0.868,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.89,
949
+ "learning_rate": 8.12085447704662e-05,
950
+ "loss": 0.91,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.9,
955
+ "learning_rate": 8.096966576085406e-05,
956
+ "loss": 0.9302,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.91,
961
+ "learning_rate": 8.072963430557636e-05,
962
+ "loss": 0.8818,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.91,
967
+ "learning_rate": 8.048845933670273e-05,
968
+ "loss": 0.9061,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.92,
973
+ "learning_rate": 8.024614982885527e-05,
974
+ "loss": 0.9108,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.92,
979
+ "learning_rate": 8.000271479887468e-05,
980
+ "loss": 0.8746,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.93,
985
+ "learning_rate": 7.975816330548467e-05,
986
+ "loss": 1.023,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.93,
991
+ "learning_rate": 7.951250444895484e-05,
992
+ "loss": 0.8844,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.94,
997
+ "learning_rate": 7.926574737076211e-05,
998
+ "loss": 0.9637,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.95,
1003
+ "learning_rate": 7.901790125325047e-05,
1004
+ "loss": 0.9124,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.95,
1009
+ "learning_rate": 7.876897531928943e-05,
1010
+ "loss": 0.9414,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.96,
1015
+ "learning_rate": 7.851897883193057e-05,
1016
+ "loss": 0.8677,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.96,
1021
+ "learning_rate": 7.826792109406308e-05,
1022
+ "loss": 0.9703,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.97,
1027
+ "learning_rate": 7.801581144806752e-05,
1028
+ "loss": 0.9004,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.97,
1033
+ "learning_rate": 7.776265927546799e-05,
1034
+ "loss": 0.8913,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.98,
1039
+ "learning_rate": 7.750847399658336e-05,
1040
+ "loss": 0.9349,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.99,
1045
+ "learning_rate": 7.725326507017643e-05,
1046
+ "loss": 0.9964,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.99,
1051
+ "learning_rate": 7.699704199310204e-05,
1052
+ "loss": 0.8782,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.0,
1057
+ "learning_rate": 7.673981429995372e-05,
1058
+ "loss": 0.895,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 1.0,
1063
+ "learning_rate": 7.648159156270884e-05,
1064
+ "loss": 0.8863,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 1.01,
1069
+ "learning_rate": 7.622238339037247e-05,
1070
+ "loss": 0.9581,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 1.01,
1075
+ "learning_rate": 7.596219942861971e-05,
1076
+ "loss": 0.9352,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.01,
1081
+ "learning_rate": 7.570104935943685e-05,
1082
+ "loss": 0.9421,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.01,
1087
+ "learning_rate": 7.543894290076103e-05,
1088
+ "loss": 0.8694,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.02,
1093
+ "learning_rate": 7.517588980611864e-05,
1094
+ "loss": 0.9163,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.02,
1099
+ "learning_rate": 7.491189986426236e-05,
1100
+ "loss": 0.899,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.03,
1105
+ "learning_rate": 7.464698289880688e-05,
1106
+ "loss": 0.9265,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.03,
1111
+ "learning_rate": 7.438114876786344e-05,
1112
+ "loss": 0.8788,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.04,
1117
+ "learning_rate": 7.411440736367281e-05,
1118
+ "loss": 0.8877,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.05,
1123
+ "learning_rate": 7.384676861223738e-05,
1124
+ "loss": 0.9121,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.05,
1129
+ "learning_rate": 7.357824247295164e-05,
1130
+ "loss": 1.0015,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.06,
1135
+ "learning_rate": 7.330883893823164e-05,
1136
+ "loss": 0.9399,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.06,
1141
+ "learning_rate": 7.303856803314313e-05,
1142
+ "loss": 0.8831,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.07,
1147
+ "learning_rate": 7.276743981502856e-05,
1148
+ "loss": 0.9024,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.07,
1153
+ "learning_rate": 7.249546437313272e-05,
1154
+ "loss": 0.8964,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.08,
1159
+ "learning_rate": 7.22226518282274e-05,
1160
+ "loss": 0.8697,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.09,
1165
+ "learning_rate": 7.19490123322347e-05,
1166
+ "loss": 0.8843,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.09,
1171
+ "learning_rate": 7.167455606784935e-05,
1172
+ "loss": 0.8963,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.1,
1177
+ "learning_rate": 7.139929324815965e-05,
1178
+ "loss": 0.8953,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.1,
1183
+ "learning_rate": 7.112323411626755e-05,
1184
+ "loss": 0.925,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.11,
1189
+ "learning_rate": 7.084638894490744e-05,
1190
+ "loss": 0.9184,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 1.11,
1195
+ "learning_rate": 7.056876803606383e-05,
1196
+ "loss": 0.8417,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 1.12,
1201
+ "learning_rate": 7.029038172058809e-05,
1202
+ "loss": 0.8966,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 1.13,
1207
+ "learning_rate": 7.00112403578139e-05,
1208
+ "loss": 0.8744,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 1.13,
1213
+ "learning_rate": 6.973135433517188e-05,
1214
+ "loss": 0.8529,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 1.14,
1219
+ "learning_rate": 6.945073406780296e-05,
1220
+ "loss": 0.8688,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 1.14,
1225
+ "learning_rate": 6.916938999817084e-05,
1226
+ "loss": 0.8688,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 1.15,
1231
+ "learning_rate": 6.888733259567342e-05,
1232
+ "loss": 0.8993,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 1.15,
1237
+ "learning_rate": 6.860457235625322e-05,
1238
+ "loss": 0.8926,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 1.16,
1243
+ "learning_rate": 6.832111980200672e-05,
1244
+ "loss": 0.8671,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 1.17,
1249
+ "learning_rate": 6.803698548079294e-05,
1250
+ "loss": 0.882,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 1.17,
1255
+ "learning_rate": 6.775217996584083e-05,
1256
+ "loss": 0.8683,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 1.18,
1261
+ "learning_rate": 6.746671385535586e-05,
1262
+ "loss": 0.878,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 1.18,
1267
+ "learning_rate": 6.718059777212567e-05,
1268
+ "loss": 0.8762,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 1.19,
1273
+ "learning_rate": 6.689384236312465e-05,
1274
+ "loss": 0.8458,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 1.19,
1279
+ "learning_rate": 6.660645829911794e-05,
1280
+ "loss": 0.8972,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 1.2,
1285
+ "learning_rate": 6.631845627426418e-05,
1286
+ "loss": 0.893,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 1.2,
1291
+ "learning_rate": 6.602984700571759e-05,
1292
+ "loss": 0.9272,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 1.21,
1297
+ "learning_rate": 6.574064123322925e-05,
1298
+ "loss": 0.9314,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 1.22,
1303
+ "learning_rate": 6.545084971874738e-05,
1304
+ "loss": 0.8403,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 1.22,
1309
+ "learning_rate": 6.516048324601684e-05,
1310
+ "loss": 0.8569,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 1.23,
1315
+ "learning_rate": 6.486955262017795e-05,
1316
+ "loss": 0.8338,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 1.23,
1321
+ "learning_rate": 6.457806866736424e-05,
1322
+ "loss": 0.9008,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 1.24,
1327
+ "learning_rate": 6.42860422342998e-05,
1328
+ "loss": 0.8683,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 1.24,
1333
+ "learning_rate": 6.399348418789545e-05,
1334
+ "loss": 0.8597,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 1.25,
1339
+ "learning_rate": 6.37004054148445e-05,
1340
+ "loss": 0.8676,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 1.26,
1345
+ "learning_rate": 6.340681682121755e-05,
1346
+ "loss": 0.8812,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 1.26,
1351
+ "learning_rate": 6.311272933205672e-05,
1352
+ "loss": 0.8568,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 1.27,
1357
+ "learning_rate": 6.281815389096903e-05,
1358
+ "loss": 0.8944,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 1.27,
1363
+ "learning_rate": 6.25231014597192e-05,
1364
+ "loss": 0.9142,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 1.28,
1369
+ "learning_rate": 6.222758301782182e-05,
1370
+ "loss": 0.8703,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 1.28,
1375
+ "learning_rate": 6.193160956213262e-05,
1376
+ "loss": 0.8331,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 1.29,
1381
+ "learning_rate": 6.163519210643939e-05,
1382
+ "loss": 0.8967,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 1.3,
1387
+ "learning_rate": 6.133834168105206e-05,
1388
+ "loss": 0.8734,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 1.3,
1393
+ "learning_rate": 6.104106933239226e-05,
1394
+ "loss": 0.877,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 1.31,
1399
+ "learning_rate": 6.0743386122582303e-05,
1400
+ "loss": 0.9077,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 1.31,
1405
+ "learning_rate": 6.0445303129033425e-05,
1406
+ "loss": 0.8835,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 1.32,
1411
+ "learning_rate": 6.014683144403375e-05,
1412
+ "loss": 0.9374,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 1.32,
1417
+ "learning_rate": 5.9847982174335316e-05,
1418
+ "loss": 0.9047,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 1.33,
1423
+ "learning_rate": 5.954876644074091e-05,
1424
+ "loss": 0.8978,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 1.34,
1429
+ "learning_rate": 5.9249195377690244e-05,
1430
+ "loss": 0.8503,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 1.34,
1435
+ "learning_rate": 5.894928013284551e-05,
1436
+ "loss": 0.8853,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 1.35,
1441
+ "learning_rate": 5.864903186667668e-05,
1442
+ "loss": 0.823,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 1.35,
1447
+ "learning_rate": 5.8348461752046116e-05,
1448
+ "loss": 0.8709,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 1.36,
1453
+ "learning_rate": 5.8047580973792805e-05,
1454
+ "loss": 0.8111,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 1.36,
1459
+ "learning_rate": 5.774640072831622e-05,
1460
+ "loss": 0.9085,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 1.37,
1465
+ "learning_rate": 5.7444932223159595e-05,
1466
+ "loss": 0.8922,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 1.38,
1471
+ "learning_rate": 5.7143186676592944e-05,
1472
+ "loss": 0.891,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 1.38,
1477
+ "learning_rate": 5.6841175317195515e-05,
1478
+ "loss": 0.867,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 1.39,
1483
+ "learning_rate": 5.653890938343805e-05,
1484
+ "loss": 0.8766,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 1.39,
1489
+ "learning_rate": 5.623640012326454e-05,
1490
+ "loss": 0.8989,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 1.4,
1495
+ "learning_rate": 5.5933658793673607e-05,
1496
+ "loss": 0.8801,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 1.4,
1501
+ "learning_rate": 5.5630696660299694e-05,
1502
+ "loss": 0.9586,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 1.41,
1507
+ "learning_rate": 5.532752499699381e-05,
1508
+ "loss": 0.8611,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 1.42,
1513
+ "learning_rate": 5.5024155085404005e-05,
1514
+ "loss": 0.9546,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 1.42,
1519
+ "learning_rate": 5.472059821455554e-05,
1520
+ "loss": 0.8471,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 1.43,
1525
+ "learning_rate": 5.4416865680430865e-05,
1526
+ "loss": 0.8532,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 1.43,
1531
+ "learning_rate": 5.411296878554918e-05,
1532
+ "loss": 0.9023,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 1.44,
1537
+ "learning_rate": 5.380891883854591e-05,
1538
+ "loss": 0.857,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 1.44,
1543
+ "learning_rate": 5.3504727153751865e-05,
1544
+ "loss": 0.8606,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 1.45,
1549
+ "learning_rate": 5.320040505077222e-05,
1550
+ "loss": 0.8525,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 1.46,
1555
+ "learning_rate": 5.289596385406527e-05,
1556
+ "loss": 0.8913,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 1.46,
1561
+ "learning_rate": 5.259141489252104e-05,
1562
+ "loss": 0.9965,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 1.47,
1567
+ "learning_rate": 5.228676949903973e-05,
1568
+ "loss": 0.8183,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 1.47,
1573
+ "learning_rate": 5.1982039010109926e-05,
1574
+ "loss": 0.8555,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 1.48,
1579
+ "learning_rate": 5.1677234765386825e-05,
1580
+ "loss": 0.9554,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 1.48,
1585
+ "learning_rate": 5.1372368107270254e-05,
1586
+ "loss": 0.8845,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 1.49,
1591
+ "learning_rate": 5.1067450380482506e-05,
1592
+ "loss": 0.9409,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 1.5,
1597
+ "learning_rate": 5.07624929316463e-05,
1598
+ "loss": 0.8255,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 1.5,
1603
+ "learning_rate": 5.045750710886248e-05,
1604
+ "loss": 0.7877,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 1.51,
1609
+ "learning_rate": 5.0152504261287725e-05,
1610
+ "loss": 0.8155,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 1.51,
1615
+ "learning_rate": 4.984749573871227e-05,
1616
+ "loss": 0.8943,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 1.52,
1621
+ "learning_rate": 4.9542492891137526e-05,
1622
+ "loss": 0.869,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 1.52,
1627
+ "learning_rate": 4.923750706835371e-05,
1628
+ "loss": 0.8187,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 1.53,
1633
+ "learning_rate": 4.893254961951751e-05,
1634
+ "loss": 0.8437,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 1.54,
1639
+ "learning_rate": 4.862763189272976e-05,
1640
+ "loss": 0.8497,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 1.54,
1645
+ "learning_rate": 4.832276523461317e-05,
1646
+ "loss": 0.856,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 1.55,
1651
+ "learning_rate": 4.8017960989890086e-05,
1652
+ "loss": 0.887,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 1.55,
1657
+ "learning_rate": 4.771323050096028e-05,
1658
+ "loss": 0.8928,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 1.56,
1663
+ "learning_rate": 4.740858510747897e-05,
1664
+ "loss": 0.8488,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 1.56,
1669
+ "learning_rate": 4.710403614593475e-05,
1670
+ "loss": 0.841,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 1.57,
1675
+ "learning_rate": 4.6799594949227786e-05,
1676
+ "loss": 0.8514,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 1.58,
1681
+ "learning_rate": 4.6495272846248146e-05,
1682
+ "loss": 0.8739,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 1.58,
1687
+ "learning_rate": 4.619108116145411e-05,
1688
+ "loss": 0.8315,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 1.59,
1693
+ "learning_rate": 4.588703121445084e-05,
1694
+ "loss": 0.8449,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 1.59,
1699
+ "learning_rate": 4.558313431956914e-05,
1700
+ "loss": 0.8413,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 1.6,
1705
+ "learning_rate": 4.527940178544446e-05,
1706
+ "loss": 0.9332,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 1.6,
1711
+ "learning_rate": 4.497584491459601e-05,
1712
+ "loss": 0.8418,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 1.61,
1717
+ "learning_rate": 4.46724750030062e-05,
1718
+ "loss": 0.9357,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 1.61,
1723
+ "learning_rate": 4.4369303339700324e-05,
1724
+ "loss": 0.9192,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 1.62,
1729
+ "learning_rate": 4.406634120632639e-05,
1730
+ "loss": 0.8618,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 1.63,
1735
+ "learning_rate": 4.3763599876735465e-05,
1736
+ "loss": 0.8305,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 1.63,
1741
+ "learning_rate": 4.346109061656195e-05,
1742
+ "loss": 0.835,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 1.64,
1747
+ "learning_rate": 4.31588246828045e-05,
1748
+ "loss": 0.8527,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 1.64,
1753
+ "learning_rate": 4.285681332340708e-05,
1754
+ "loss": 0.8881,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 1.65,
1759
+ "learning_rate": 4.255506777684041e-05,
1760
+ "loss": 0.8483,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 1.65,
1765
+ "learning_rate": 4.2253599271683794e-05,
1766
+ "loss": 0.925,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 1.66,
1771
+ "learning_rate": 4.1952419026207207e-05,
1772
+ "loss": 0.8195,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 1.67,
1777
+ "learning_rate": 4.16515382479539e-05,
1778
+ "loss": 0.8842,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 1.67,
1783
+ "learning_rate": 4.135096813332333e-05,
1784
+ "loss": 0.8351,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 1.68,
1789
+ "learning_rate": 4.105071986715449e-05,
1790
+ "loss": 0.8409,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 1.68,
1795
+ "learning_rate": 4.075080462230977e-05,
1796
+ "loss": 0.8672,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 1.69,
1801
+ "learning_rate": 4.04512335592591e-05,
1802
+ "loss": 0.9678,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 1.69,
1807
+ "learning_rate": 4.015201782566471e-05,
1808
+ "loss": 0.9089,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 1.7,
1813
+ "learning_rate": 3.985316855596626e-05,
1814
+ "loss": 0.7991,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 1.71,
1819
+ "learning_rate": 3.9554696870966566e-05,
1820
+ "loss": 0.9373,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 1.71,
1825
+ "learning_rate": 3.9256613877417715e-05,
1826
+ "loss": 0.9394,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 1.72,
1831
+ "learning_rate": 3.895893066760774e-05,
1832
+ "loss": 0.9578,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 1.72,
1837
+ "learning_rate": 3.866165831894796e-05,
1838
+ "loss": 0.8791,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 1.73,
1843
+ "learning_rate": 3.836480789356063e-05,
1844
+ "loss": 0.8872,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 1.73,
1849
+ "learning_rate": 3.806839043786738e-05,
1850
+ "loss": 0.8737,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 1.74,
1855
+ "learning_rate": 3.777241698217819e-05,
1856
+ "loss": 0.915,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 1.75,
1861
+ "learning_rate": 3.747689854028081e-05,
1862
+ "loss": 0.8755,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 1.75,
1867
+ "learning_rate": 3.7181846109031005e-05,
1868
+ "loss": 0.902,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 1.76,
1873
+ "learning_rate": 3.688727066794329e-05,
1874
+ "loss": 0.8428,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 1.76,
1879
+ "learning_rate": 3.659318317878245e-05,
1880
+ "loss": 0.8767,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 1.77,
1885
+ "learning_rate": 3.629959458515551e-05,
1886
+ "loss": 0.8413,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 1.77,
1891
+ "learning_rate": 3.600651581210457e-05,
1892
+ "loss": 0.8919,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 1.78,
1897
+ "learning_rate": 3.571395776570023e-05,
1898
+ "loss": 0.9458,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 1.79,
1903
+ "learning_rate": 3.542193133263576e-05,
1904
+ "loss": 0.9182,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 1.79,
1909
+ "learning_rate": 3.5130447379822076e-05,
1910
+ "loss": 0.7931,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 1.8,
1915
+ "learning_rate": 3.483951675398316e-05,
1916
+ "loss": 0.9585,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 1.8,
1921
+ "learning_rate": 3.4549150281252636e-05,
1922
+ "loss": 0.8682,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 1.81,
1927
+ "learning_rate": 3.4259358766770766e-05,
1928
+ "loss": 0.9327,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 1.81,
1933
+ "learning_rate": 3.397015299428242e-05,
1934
+ "loss": 0.8413,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 1.82,
1939
+ "learning_rate": 3.368154372573584e-05,
1940
+ "loss": 0.9072,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 1.83,
1945
+ "learning_rate": 3.339354170088207e-05,
1946
+ "loss": 0.8593,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 1.83,
1951
+ "learning_rate": 3.310615763687536e-05,
1952
+ "loss": 0.8536,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 1.84,
1957
+ "learning_rate": 3.2819402227874365e-05,
1958
+ "loss": 0.8735,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 1.84,
1963
+ "learning_rate": 3.2533286144644134e-05,
1964
+ "loss": 0.8723,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 1.85,
1969
+ "learning_rate": 3.224782003415918e-05,
1970
+ "loss": 0.8902,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 1.85,
1975
+ "learning_rate": 3.196301451920708e-05,
1976
+ "loss": 0.9597,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 1.86,
1981
+ "learning_rate": 3.16788801979933e-05,
1982
+ "loss": 0.8313,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 1.87,
1987
+ "learning_rate": 3.1395427643746796e-05,
1988
+ "loss": 0.877,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 1.87,
1993
+ "learning_rate": 3.111266740432658e-05,
1994
+ "loss": 0.8529,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 1.88,
1999
+ "learning_rate": 3.0830610001829174e-05,
2000
+ "loss": 0.9046,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 1.88,
2005
+ "learning_rate": 3.0549265932197055e-05,
2006
+ "loss": 0.9228,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 1.89,
2011
+ "learning_rate": 3.0268645664828134e-05,
2012
+ "loss": 0.8223,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 1.89,
2017
+ "learning_rate": 2.9988759642186097e-05,
2018
+ "loss": 0.9517,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 1.9,
2023
+ "learning_rate": 2.970961827941192e-05,
2024
+ "loss": 0.8656,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 1.91,
2029
+ "learning_rate": 2.9431231963936174e-05,
2030
+ "loss": 0.9232,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 1.91,
2035
+ "learning_rate": 2.9153611055092583e-05,
2036
+ "loss": 0.8573,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 1.92,
2041
+ "learning_rate": 2.8876765883732447e-05,
2042
+ "loss": 0.9124,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 1.92,
2047
+ "learning_rate": 2.860070675184036e-05,
2048
+ "loss": 0.8618,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 1.93,
2053
+ "learning_rate": 2.8325443932150647e-05,
2054
+ "loss": 0.8767,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 1.93,
2059
+ "learning_rate": 2.805098766776529e-05,
2060
+ "loss": 0.946,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 1.94,
2065
+ "learning_rate": 2.7777348171772604e-05,
2066
+ "loss": 0.8468,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 1.95,
2071
+ "learning_rate": 2.7504535626867288e-05,
2072
+ "loss": 0.8405,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 1.95,
2077
+ "learning_rate": 2.7232560184971434e-05,
2078
+ "loss": 0.8885,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 1.96,
2083
+ "learning_rate": 2.6961431966856864e-05,
2084
+ "loss": 0.9253,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 1.96,
2089
+ "learning_rate": 2.6691161061768376e-05,
2090
+ "loss": 0.918,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 1.97,
2095
+ "learning_rate": 2.6421757527048373e-05,
2096
+ "loss": 0.9028,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 1.97,
2101
+ "learning_rate": 2.6153231387762637e-05,
2102
+ "loss": 0.8916,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 1.98,
2107
+ "learning_rate": 2.588559263632719e-05,
2108
+ "loss": 0.9061,
2109
+ "step": 350
2110
+ }
2111
+ ],
2112
+ "logging_steps": 1,
2113
+ "max_steps": 525,
2114
+ "num_input_tokens_seen": 0,
2115
+ "num_train_epochs": 3,
2116
+ "save_steps": 175,
2117
+ "total_flos": 1.295226753735721e+19,
2118
+ "train_batch_size": 1,
2119
+ "trial_name": null,
2120
+ "trial_params": null
2121
+ }
checkpoint-350/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:862899d2d90e28bcdb2d7301eb97d6ede02950401db2351f4f6591f98d8e42bd
3
+ size 5240
checkpoint-525/README.md ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: models/Mixtral-8x7B-v0.1
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
+ ## Training procedure
203
+
204
+
205
+ The following `bitsandbytes` quantization config was used during training:
206
+ - quant_method: bitsandbytes
207
+ - load_in_8bit: False
208
+ - load_in_4bit: True
209
+ - llm_int8_threshold: 6.0
210
+ - llm_int8_skip_modules: None
211
+ - llm_int8_enable_fp32_cpu_offload: False
212
+ - llm_int8_has_fp16_weight: False
213
+ - bnb_4bit_quant_type: nf4
214
+ - bnb_4bit_use_double_quant: True
215
+ - bnb_4bit_compute_dtype: bfloat16
216
+
217
+ ### Framework versions
218
+
219
+
220
+ - PEFT 0.6.0
checkpoint-525/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "models/Mixtral-8x7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 32,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "k_proj",
20
+ "w1",
21
+ "w2",
22
+ "q_proj",
23
+ "gate",
24
+ "w3",
25
+ "o_proj",
26
+ "v_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM"
29
+ }
checkpoint-525/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5c22afcf56d95cce2020d82d9f3ed0344846a0a59ff16b9815363cb2a35b705
3
+ size 1938077512
checkpoint-525/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b57ed929edffbb047ed6f39b82033d6b062d90d818a94193cd9c0ec0ece702ef
3
+ size 972999124
checkpoint-525/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0205bc8728bceb60806fb4fc182956752f9acdd8f20fe15157a3bf8caf400d26
3
+ size 14244
checkpoint-525/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d1f327cf5a396113e7dc103b1b05a52b94616fc1a17294b6027f119947f1aee
3
+ size 1064
checkpoint-525/trainer_state.json ADDED
@@ -0,0 +1,3171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.965124555160142,
5
+ "eval_steps": 500,
6
+ "global_step": 525,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 1e-05,
14
+ "loss": 0.9314,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2e-05,
20
+ "loss": 1.0801,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 3e-05,
26
+ "loss": 1.0054,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 4e-05,
32
+ "loss": 0.9802,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 5e-05,
38
+ "loss": 1.0545,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 6e-05,
44
+ "loss": 1.0273,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 7e-05,
50
+ "loss": 0.9404,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 8e-05,
56
+ "loss": 1.0031,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 9e-05,
62
+ "loss": 1.0347,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 0.0001,
68
+ "loss": 1.045,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.06,
73
+ "learning_rate": 9.999906969801157e-05,
74
+ "loss": 0.9026,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 9.999627882666473e-05,
80
+ "loss": 1.0206,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.07,
85
+ "learning_rate": 9.999162748981361e-05,
86
+ "loss": 0.9519,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 9.998511586054414e-05,
92
+ "loss": 1.0259,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "learning_rate": 9.997674418116758e-05,
98
+ "loss": 1.0508,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.09,
103
+ "learning_rate": 9.996651276321153e-05,
104
+ "loss": 0.9679,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.1,
109
+ "learning_rate": 9.995442198740833e-05,
110
+ "loss": 0.9564,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.1,
115
+ "learning_rate": 9.994047230368086e-05,
116
+ "loss": 1.0159,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 9.99246642311259e-05,
122
+ "loss": 0.9157,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.11,
127
+ "learning_rate": 9.990699835799469e-05,
128
+ "loss": 1.0788,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.12,
133
+ "learning_rate": 9.988747534167111e-05,
134
+ "loss": 0.957,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "learning_rate": 9.986609590864719e-05,
140
+ "loss": 1.022,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.13,
145
+ "learning_rate": 9.98428608544961e-05,
146
+ "loss": 0.9874,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.14,
151
+ "learning_rate": 9.981777104384251e-05,
152
+ "loss": 1.1594,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.14,
157
+ "learning_rate": 9.979082741033047e-05,
158
+ "loss": 0.9913,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "learning_rate": 9.97620309565886e-05,
164
+ "loss": 0.9641,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.15,
169
+ "learning_rate": 9.97313827541928e-05,
170
+ "loss": 0.9905,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.16,
175
+ "learning_rate": 9.969888394362647e-05,
176
+ "loss": 0.9986,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.17,
181
+ "learning_rate": 9.966453573423791e-05,
182
+ "loss": 1.0096,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.17,
187
+ "learning_rate": 9.96283394041954e-05,
188
+ "loss": 0.962,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.18,
193
+ "learning_rate": 9.959029630043968e-05,
194
+ "loss": 1.0025,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.18,
199
+ "learning_rate": 9.955040783863374e-05,
200
+ "loss": 0.896,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.19,
205
+ "learning_rate": 9.950867550311018e-05,
206
+ "loss": 0.9042,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.19,
211
+ "learning_rate": 9.946510084681602e-05,
212
+ "loss": 0.9408,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.2,
217
+ "learning_rate": 9.941968549125481e-05,
218
+ "loss": 0.9185,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "learning_rate": 9.937243112642638e-05,
224
+ "loss": 0.8821,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.21,
229
+ "learning_rate": 9.932333951076394e-05,
230
+ "loss": 1.0143,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.22,
235
+ "learning_rate": 9.927241247106855e-05,
236
+ "loss": 0.9814,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.22,
241
+ "learning_rate": 9.921965190244129e-05,
242
+ "loss": 0.8808,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.23,
247
+ "learning_rate": 9.916505976821263e-05,
248
+ "loss": 0.9583,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.23,
253
+ "learning_rate": 9.910863809986941e-05,
254
+ "loss": 0.9627,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.24,
259
+ "learning_rate": 9.905038899697924e-05,
260
+ "loss": 0.9287,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.24,
265
+ "learning_rate": 9.899031462711237e-05,
266
+ "loss": 0.9075,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.25,
271
+ "learning_rate": 9.892841722576103e-05,
272
+ "loss": 0.9912,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.26,
277
+ "learning_rate": 9.886469909625625e-05,
278
+ "loss": 0.8891,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.26,
283
+ "learning_rate": 9.879916260968212e-05,
284
+ "loss": 0.9577,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.27,
289
+ "learning_rate": 9.87318102047876e-05,
290
+ "loss": 0.8791,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.27,
295
+ "learning_rate": 9.866264438789573e-05,
296
+ "loss": 0.9926,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.28,
301
+ "learning_rate": 9.85916677328104e-05,
302
+ "loss": 0.9273,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.28,
307
+ "learning_rate": 9.851888288072053e-05,
308
+ "loss": 0.9066,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.29,
313
+ "learning_rate": 9.844429254010185e-05,
314
+ "loss": 0.9806,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.3,
319
+ "learning_rate": 9.836789948661602e-05,
320
+ "loss": 0.91,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.3,
325
+ "learning_rate": 9.828970656300744e-05,
326
+ "loss": 0.9746,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.31,
331
+ "learning_rate": 9.820971667899739e-05,
332
+ "loss": 0.967,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.31,
337
+ "learning_rate": 9.81279328111758e-05,
338
+ "loss": 0.9605,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.32,
343
+ "learning_rate": 9.804435800289047e-05,
344
+ "loss": 0.8964,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.32,
349
+ "learning_rate": 9.795899536413382e-05,
350
+ "loss": 0.9759,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.33,
355
+ "learning_rate": 9.787184807142713e-05,
356
+ "loss": 0.9432,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.34,
361
+ "learning_rate": 9.77829193677024e-05,
362
+ "loss": 0.9003,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.34,
367
+ "learning_rate": 9.769221256218164e-05,
368
+ "loss": 0.9446,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.35,
373
+ "learning_rate": 9.759973103025368e-05,
374
+ "loss": 0.9903,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.35,
379
+ "learning_rate": 9.750547821334868e-05,
380
+ "loss": 0.9553,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.36,
385
+ "learning_rate": 9.740945761880993e-05,
386
+ "loss": 0.9117,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.36,
391
+ "learning_rate": 9.731167281976345e-05,
392
+ "loss": 0.8618,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.37,
397
+ "learning_rate": 9.721212745498494e-05,
398
+ "loss": 0.9687,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.38,
403
+ "learning_rate": 9.711082522876444e-05,
404
+ "loss": 0.8913,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.38,
409
+ "learning_rate": 9.700776991076845e-05,
410
+ "loss": 0.9567,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.39,
415
+ "learning_rate": 9.690296533589968e-05,
416
+ "loss": 0.8572,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.39,
421
+ "learning_rate": 9.679641540415427e-05,
422
+ "loss": 0.943,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.4,
427
+ "learning_rate": 9.668812408047679e-05,
428
+ "loss": 0.951,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.4,
433
+ "learning_rate": 9.657809539461256e-05,
434
+ "loss": 0.9608,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.41,
439
+ "learning_rate": 9.64663334409578e-05,
440
+ "loss": 0.8861,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.42,
445
+ "learning_rate": 9.635284237840721e-05,
446
+ "loss": 0.9538,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.42,
451
+ "learning_rate": 9.623762643019926e-05,
452
+ "loss": 0.9816,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.43,
457
+ "learning_rate": 9.612068988375897e-05,
458
+ "loss": 0.9205,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.43,
463
+ "learning_rate": 9.60020370905384e-05,
464
+ "loss": 0.9999,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.44,
469
+ "learning_rate": 9.588167246585473e-05,
470
+ "loss": 0.9324,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.44,
475
+ "learning_rate": 9.575960048872594e-05,
476
+ "loss": 0.9301,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.45,
481
+ "learning_rate": 9.563582570170417e-05,
482
+ "loss": 0.9512,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.46,
487
+ "learning_rate": 9.551035271070664e-05,
488
+ "loss": 0.9418,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.46,
493
+ "learning_rate": 9.538318618484425e-05,
494
+ "loss": 0.9221,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.47,
499
+ "learning_rate": 9.525433085624788e-05,
500
+ "loss": 0.905,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.47,
505
+ "learning_rate": 9.512379151989229e-05,
506
+ "loss": 0.9487,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.48,
511
+ "learning_rate": 9.499157303341762e-05,
512
+ "loss": 0.9569,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.48,
517
+ "learning_rate": 9.485768031694872e-05,
518
+ "loss": 0.933,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.49,
523
+ "learning_rate": 9.472211835291199e-05,
524
+ "loss": 0.9122,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.5,
529
+ "learning_rate": 9.458489218585002e-05,
530
+ "loss": 0.9518,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.5,
535
+ "learning_rate": 9.444600692223389e-05,
536
+ "loss": 0.8929,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.51,
541
+ "learning_rate": 9.430546773027302e-05,
542
+ "loss": 0.9438,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.51,
547
+ "learning_rate": 9.416327983972304e-05,
548
+ "loss": 0.9683,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.52,
553
+ "learning_rate": 9.401944854169102e-05,
554
+ "loss": 0.8427,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.52,
559
+ "learning_rate": 9.38739791884387e-05,
560
+ "loss": 0.9222,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.53,
565
+ "learning_rate": 9.372687719318317e-05,
566
+ "loss": 0.8887,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.54,
571
+ "learning_rate": 9.35781480298956e-05,
572
+ "loss": 0.9668,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.54,
577
+ "learning_rate": 9.342779723309745e-05,
578
+ "loss": 0.904,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.55,
583
+ "learning_rate": 9.327583039765453e-05,
584
+ "loss": 1.004,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.55,
589
+ "learning_rate": 9.31222531785688e-05,
590
+ "loss": 0.9759,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.56,
595
+ "learning_rate": 9.296707129076793e-05,
596
+ "loss": 0.9768,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.56,
601
+ "learning_rate": 9.281029050889274e-05,
602
+ "loss": 0.9175,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.57,
607
+ "learning_rate": 9.265191666708209e-05,
608
+ "loss": 0.9464,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.58,
613
+ "learning_rate": 9.2491955658756e-05,
614
+ "loss": 0.9382,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.58,
619
+ "learning_rate": 9.233041343639622e-05,
620
+ "loss": 0.9593,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.59,
625
+ "learning_rate": 9.216729601132481e-05,
626
+ "loss": 0.9245,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.59,
631
+ "learning_rate": 9.200260945348034e-05,
632
+ "loss": 0.9738,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.6,
637
+ "learning_rate": 9.18363598911921e-05,
638
+ "loss": 1.0077,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.6,
643
+ "learning_rate": 9.166855351095204e-05,
644
+ "loss": 0.9239,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.61,
649
+ "learning_rate": 9.149919655718454e-05,
650
+ "loss": 0.9601,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.61,
655
+ "learning_rate": 9.132829533201397e-05,
656
+ "loss": 0.9079,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.62,
661
+ "learning_rate": 9.115585619503039e-05,
662
+ "loss": 0.9859,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.63,
667
+ "learning_rate": 9.098188556305263e-05,
668
+ "loss": 0.9909,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.63,
673
+ "learning_rate": 9.08063899098897e-05,
674
+ "loss": 1.0114,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.64,
679
+ "learning_rate": 9.062937576609982e-05,
680
+ "loss": 0.9271,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.64,
685
+ "learning_rate": 9.045084971874738e-05,
686
+ "loss": 1.1316,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.65,
691
+ "learning_rate": 9.027081841115783e-05,
692
+ "loss": 0.9439,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.65,
697
+ "learning_rate": 9.008928854267054e-05,
698
+ "loss": 0.9477,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.66,
703
+ "learning_rate": 8.990626686838938e-05,
704
+ "loss": 0.9807,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.67,
709
+ "learning_rate": 8.972176019893149e-05,
710
+ "loss": 0.9543,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.67,
715
+ "learning_rate": 8.95357754001737e-05,
716
+ "loss": 0.96,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.68,
721
+ "learning_rate": 8.934831939299714e-05,
722
+ "loss": 0.9741,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.68,
727
+ "learning_rate": 8.915939915302968e-05,
728
+ "loss": 0.8402,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.69,
733
+ "learning_rate": 8.896902171038628e-05,
734
+ "loss": 0.8757,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.69,
739
+ "learning_rate": 8.877719414940751e-05,
740
+ "loss": 0.8724,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.7,
745
+ "learning_rate": 8.858392360839581e-05,
746
+ "loss": 0.8953,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.71,
751
+ "learning_rate": 8.838921727934992e-05,
752
+ "loss": 1.0174,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.71,
757
+ "learning_rate": 8.819308240769724e-05,
758
+ "loss": 0.9908,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.72,
763
+ "learning_rate": 8.799552629202424e-05,
764
+ "loss": 0.8448,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.72,
769
+ "learning_rate": 8.779655628380478e-05,
770
+ "loss": 0.9708,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.73,
775
+ "learning_rate": 8.759617978712667e-05,
776
+ "loss": 0.9518,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.73,
781
+ "learning_rate": 8.739440425841599e-05,
782
+ "loss": 1.088,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.74,
787
+ "learning_rate": 8.71912372061598e-05,
788
+ "loss": 0.9201,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.75,
793
+ "learning_rate": 8.69866861906266e-05,
794
+ "loss": 0.9452,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.75,
799
+ "learning_rate": 8.678075882358506e-05,
800
+ "loss": 0.9759,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.76,
805
+ "learning_rate": 8.657346276802071e-05,
806
+ "loss": 0.9172,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.76,
811
+ "learning_rate": 8.636480573785089e-05,
812
+ "loss": 0.9034,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.77,
817
+ "learning_rate": 8.615479549763756e-05,
818
+ "loss": 0.897,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.77,
823
+ "learning_rate": 8.594343986229854e-05,
824
+ "loss": 0.8837,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.78,
829
+ "learning_rate": 8.573074669681649e-05,
830
+ "loss": 0.8814,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.79,
835
+ "learning_rate": 8.551672391594645e-05,
836
+ "loss": 0.9168,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.79,
841
+ "learning_rate": 8.530137948392112e-05,
842
+ "loss": 0.9591,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.8,
847
+ "learning_rate": 8.508472141415467e-05,
848
+ "loss": 0.9279,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.8,
853
+ "learning_rate": 8.486675776894439e-05,
854
+ "loss": 0.8967,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.81,
859
+ "learning_rate": 8.464749665917081e-05,
860
+ "loss": 0.963,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.81,
865
+ "learning_rate": 8.442694624399576e-05,
866
+ "loss": 0.8653,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.82,
871
+ "learning_rate": 8.420511473055886e-05,
872
+ "loss": 0.9247,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.83,
877
+ "learning_rate": 8.398201037367201e-05,
878
+ "loss": 0.9432,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.83,
883
+ "learning_rate": 8.375764147551231e-05,
884
+ "loss": 0.9025,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.84,
889
+ "learning_rate": 8.3532016385313e-05,
890
+ "loss": 0.9395,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.84,
895
+ "learning_rate": 8.330514349905293e-05,
896
+ "loss": 0.88,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.85,
901
+ "learning_rate": 8.307703125914397e-05,
902
+ "loss": 0.8917,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.85,
907
+ "learning_rate": 8.284768815411692e-05,
908
+ "loss": 0.9516,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.86,
913
+ "learning_rate": 8.261712271830564e-05,
914
+ "loss": 0.9678,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.87,
919
+ "learning_rate": 8.238534353152951e-05,
920
+ "loss": 0.9055,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.87,
925
+ "learning_rate": 8.215235921877404e-05,
926
+ "loss": 0.91,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.88,
931
+ "learning_rate": 8.191817844986998e-05,
932
+ "loss": 0.9115,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.88,
937
+ "learning_rate": 8.168280993917077e-05,
938
+ "loss": 0.9546,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.89,
943
+ "learning_rate": 8.144626244522813e-05,
944
+ "loss": 0.868,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.89,
949
+ "learning_rate": 8.12085447704662e-05,
950
+ "loss": 0.91,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.9,
955
+ "learning_rate": 8.096966576085406e-05,
956
+ "loss": 0.9302,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.91,
961
+ "learning_rate": 8.072963430557636e-05,
962
+ "loss": 0.8818,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.91,
967
+ "learning_rate": 8.048845933670273e-05,
968
+ "loss": 0.9061,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.92,
973
+ "learning_rate": 8.024614982885527e-05,
974
+ "loss": 0.9108,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.92,
979
+ "learning_rate": 8.000271479887468e-05,
980
+ "loss": 0.8746,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.93,
985
+ "learning_rate": 7.975816330548467e-05,
986
+ "loss": 1.023,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.93,
991
+ "learning_rate": 7.951250444895484e-05,
992
+ "loss": 0.8844,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.94,
997
+ "learning_rate": 7.926574737076211e-05,
998
+ "loss": 0.9637,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.95,
1003
+ "learning_rate": 7.901790125325047e-05,
1004
+ "loss": 0.9124,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.95,
1009
+ "learning_rate": 7.876897531928943e-05,
1010
+ "loss": 0.9414,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.96,
1015
+ "learning_rate": 7.851897883193057e-05,
1016
+ "loss": 0.8677,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.96,
1021
+ "learning_rate": 7.826792109406308e-05,
1022
+ "loss": 0.9703,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.97,
1027
+ "learning_rate": 7.801581144806752e-05,
1028
+ "loss": 0.9004,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.97,
1033
+ "learning_rate": 7.776265927546799e-05,
1034
+ "loss": 0.8913,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.98,
1039
+ "learning_rate": 7.750847399658336e-05,
1040
+ "loss": 0.9349,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.99,
1045
+ "learning_rate": 7.725326507017643e-05,
1046
+ "loss": 0.9964,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.99,
1051
+ "learning_rate": 7.699704199310204e-05,
1052
+ "loss": 0.8782,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.0,
1057
+ "learning_rate": 7.673981429995372e-05,
1058
+ "loss": 0.895,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 1.0,
1063
+ "learning_rate": 7.648159156270884e-05,
1064
+ "loss": 0.8863,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 1.01,
1069
+ "learning_rate": 7.622238339037247e-05,
1070
+ "loss": 0.9581,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 1.01,
1075
+ "learning_rate": 7.596219942861971e-05,
1076
+ "loss": 0.9352,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.01,
1081
+ "learning_rate": 7.570104935943685e-05,
1082
+ "loss": 0.9421,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.01,
1087
+ "learning_rate": 7.543894290076103e-05,
1088
+ "loss": 0.8694,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.02,
1093
+ "learning_rate": 7.517588980611864e-05,
1094
+ "loss": 0.9163,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.02,
1099
+ "learning_rate": 7.491189986426236e-05,
1100
+ "loss": 0.899,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.03,
1105
+ "learning_rate": 7.464698289880688e-05,
1106
+ "loss": 0.9265,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.03,
1111
+ "learning_rate": 7.438114876786344e-05,
1112
+ "loss": 0.8788,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.04,
1117
+ "learning_rate": 7.411440736367281e-05,
1118
+ "loss": 0.8877,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.05,
1123
+ "learning_rate": 7.384676861223738e-05,
1124
+ "loss": 0.9121,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.05,
1129
+ "learning_rate": 7.357824247295164e-05,
1130
+ "loss": 1.0015,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.06,
1135
+ "learning_rate": 7.330883893823164e-05,
1136
+ "loss": 0.9399,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.06,
1141
+ "learning_rate": 7.303856803314313e-05,
1142
+ "loss": 0.8831,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.07,
1147
+ "learning_rate": 7.276743981502856e-05,
1148
+ "loss": 0.9024,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.07,
1153
+ "learning_rate": 7.249546437313272e-05,
1154
+ "loss": 0.8964,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.08,
1159
+ "learning_rate": 7.22226518282274e-05,
1160
+ "loss": 0.8697,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.09,
1165
+ "learning_rate": 7.19490123322347e-05,
1166
+ "loss": 0.8843,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.09,
1171
+ "learning_rate": 7.167455606784935e-05,
1172
+ "loss": 0.8963,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.1,
1177
+ "learning_rate": 7.139929324815965e-05,
1178
+ "loss": 0.8953,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.1,
1183
+ "learning_rate": 7.112323411626755e-05,
1184
+ "loss": 0.925,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.11,
1189
+ "learning_rate": 7.084638894490744e-05,
1190
+ "loss": 0.9184,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 1.11,
1195
+ "learning_rate": 7.056876803606383e-05,
1196
+ "loss": 0.8417,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 1.12,
1201
+ "learning_rate": 7.029038172058809e-05,
1202
+ "loss": 0.8966,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 1.13,
1207
+ "learning_rate": 7.00112403578139e-05,
1208
+ "loss": 0.8744,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 1.13,
1213
+ "learning_rate": 6.973135433517188e-05,
1214
+ "loss": 0.8529,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 1.14,
1219
+ "learning_rate": 6.945073406780296e-05,
1220
+ "loss": 0.8688,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 1.14,
1225
+ "learning_rate": 6.916938999817084e-05,
1226
+ "loss": 0.8688,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 1.15,
1231
+ "learning_rate": 6.888733259567342e-05,
1232
+ "loss": 0.8993,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 1.15,
1237
+ "learning_rate": 6.860457235625322e-05,
1238
+ "loss": 0.8926,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 1.16,
1243
+ "learning_rate": 6.832111980200672e-05,
1244
+ "loss": 0.8671,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 1.17,
1249
+ "learning_rate": 6.803698548079294e-05,
1250
+ "loss": 0.882,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 1.17,
1255
+ "learning_rate": 6.775217996584083e-05,
1256
+ "loss": 0.8683,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 1.18,
1261
+ "learning_rate": 6.746671385535586e-05,
1262
+ "loss": 0.878,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 1.18,
1267
+ "learning_rate": 6.718059777212567e-05,
1268
+ "loss": 0.8762,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 1.19,
1273
+ "learning_rate": 6.689384236312465e-05,
1274
+ "loss": 0.8458,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 1.19,
1279
+ "learning_rate": 6.660645829911794e-05,
1280
+ "loss": 0.8972,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 1.2,
1285
+ "learning_rate": 6.631845627426418e-05,
1286
+ "loss": 0.893,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 1.2,
1291
+ "learning_rate": 6.602984700571759e-05,
1292
+ "loss": 0.9272,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 1.21,
1297
+ "learning_rate": 6.574064123322925e-05,
1298
+ "loss": 0.9314,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 1.22,
1303
+ "learning_rate": 6.545084971874738e-05,
1304
+ "loss": 0.8403,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 1.22,
1309
+ "learning_rate": 6.516048324601684e-05,
1310
+ "loss": 0.8569,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 1.23,
1315
+ "learning_rate": 6.486955262017795e-05,
1316
+ "loss": 0.8338,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 1.23,
1321
+ "learning_rate": 6.457806866736424e-05,
1322
+ "loss": 0.9008,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 1.24,
1327
+ "learning_rate": 6.42860422342998e-05,
1328
+ "loss": 0.8683,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 1.24,
1333
+ "learning_rate": 6.399348418789545e-05,
1334
+ "loss": 0.8597,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 1.25,
1339
+ "learning_rate": 6.37004054148445e-05,
1340
+ "loss": 0.8676,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 1.26,
1345
+ "learning_rate": 6.340681682121755e-05,
1346
+ "loss": 0.8812,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 1.26,
1351
+ "learning_rate": 6.311272933205672e-05,
1352
+ "loss": 0.8568,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 1.27,
1357
+ "learning_rate": 6.281815389096903e-05,
1358
+ "loss": 0.8944,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 1.27,
1363
+ "learning_rate": 6.25231014597192e-05,
1364
+ "loss": 0.9142,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 1.28,
1369
+ "learning_rate": 6.222758301782182e-05,
1370
+ "loss": 0.8703,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 1.28,
1375
+ "learning_rate": 6.193160956213262e-05,
1376
+ "loss": 0.8331,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 1.29,
1381
+ "learning_rate": 6.163519210643939e-05,
1382
+ "loss": 0.8967,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 1.3,
1387
+ "learning_rate": 6.133834168105206e-05,
1388
+ "loss": 0.8734,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 1.3,
1393
+ "learning_rate": 6.104106933239226e-05,
1394
+ "loss": 0.877,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 1.31,
1399
+ "learning_rate": 6.0743386122582303e-05,
1400
+ "loss": 0.9077,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 1.31,
1405
+ "learning_rate": 6.0445303129033425e-05,
1406
+ "loss": 0.8835,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 1.32,
1411
+ "learning_rate": 6.014683144403375e-05,
1412
+ "loss": 0.9374,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 1.32,
1417
+ "learning_rate": 5.9847982174335316e-05,
1418
+ "loss": 0.9047,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 1.33,
1423
+ "learning_rate": 5.954876644074091e-05,
1424
+ "loss": 0.8978,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 1.34,
1429
+ "learning_rate": 5.9249195377690244e-05,
1430
+ "loss": 0.8503,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 1.34,
1435
+ "learning_rate": 5.894928013284551e-05,
1436
+ "loss": 0.8853,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 1.35,
1441
+ "learning_rate": 5.864903186667668e-05,
1442
+ "loss": 0.823,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 1.35,
1447
+ "learning_rate": 5.8348461752046116e-05,
1448
+ "loss": 0.8709,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 1.36,
1453
+ "learning_rate": 5.8047580973792805e-05,
1454
+ "loss": 0.8111,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 1.36,
1459
+ "learning_rate": 5.774640072831622e-05,
1460
+ "loss": 0.9085,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 1.37,
1465
+ "learning_rate": 5.7444932223159595e-05,
1466
+ "loss": 0.8922,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 1.38,
1471
+ "learning_rate": 5.7143186676592944e-05,
1472
+ "loss": 0.891,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 1.38,
1477
+ "learning_rate": 5.6841175317195515e-05,
1478
+ "loss": 0.867,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 1.39,
1483
+ "learning_rate": 5.653890938343805e-05,
1484
+ "loss": 0.8766,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 1.39,
1489
+ "learning_rate": 5.623640012326454e-05,
1490
+ "loss": 0.8989,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 1.4,
1495
+ "learning_rate": 5.5933658793673607e-05,
1496
+ "loss": 0.8801,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 1.4,
1501
+ "learning_rate": 5.5630696660299694e-05,
1502
+ "loss": 0.9586,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 1.41,
1507
+ "learning_rate": 5.532752499699381e-05,
1508
+ "loss": 0.8611,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 1.42,
1513
+ "learning_rate": 5.5024155085404005e-05,
1514
+ "loss": 0.9546,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 1.42,
1519
+ "learning_rate": 5.472059821455554e-05,
1520
+ "loss": 0.8471,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 1.43,
1525
+ "learning_rate": 5.4416865680430865e-05,
1526
+ "loss": 0.8532,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 1.43,
1531
+ "learning_rate": 5.411296878554918e-05,
1532
+ "loss": 0.9023,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 1.44,
1537
+ "learning_rate": 5.380891883854591e-05,
1538
+ "loss": 0.857,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 1.44,
1543
+ "learning_rate": 5.3504727153751865e-05,
1544
+ "loss": 0.8606,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 1.45,
1549
+ "learning_rate": 5.320040505077222e-05,
1550
+ "loss": 0.8525,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 1.46,
1555
+ "learning_rate": 5.289596385406527e-05,
1556
+ "loss": 0.8913,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 1.46,
1561
+ "learning_rate": 5.259141489252104e-05,
1562
+ "loss": 0.9965,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 1.47,
1567
+ "learning_rate": 5.228676949903973e-05,
1568
+ "loss": 0.8183,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 1.47,
1573
+ "learning_rate": 5.1982039010109926e-05,
1574
+ "loss": 0.8555,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 1.48,
1579
+ "learning_rate": 5.1677234765386825e-05,
1580
+ "loss": 0.9554,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 1.48,
1585
+ "learning_rate": 5.1372368107270254e-05,
1586
+ "loss": 0.8845,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 1.49,
1591
+ "learning_rate": 5.1067450380482506e-05,
1592
+ "loss": 0.9409,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 1.5,
1597
+ "learning_rate": 5.07624929316463e-05,
1598
+ "loss": 0.8255,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 1.5,
1603
+ "learning_rate": 5.045750710886248e-05,
1604
+ "loss": 0.7877,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 1.51,
1609
+ "learning_rate": 5.0152504261287725e-05,
1610
+ "loss": 0.8155,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 1.51,
1615
+ "learning_rate": 4.984749573871227e-05,
1616
+ "loss": 0.8943,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 1.52,
1621
+ "learning_rate": 4.9542492891137526e-05,
1622
+ "loss": 0.869,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 1.52,
1627
+ "learning_rate": 4.923750706835371e-05,
1628
+ "loss": 0.8187,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 1.53,
1633
+ "learning_rate": 4.893254961951751e-05,
1634
+ "loss": 0.8437,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 1.54,
1639
+ "learning_rate": 4.862763189272976e-05,
1640
+ "loss": 0.8497,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 1.54,
1645
+ "learning_rate": 4.832276523461317e-05,
1646
+ "loss": 0.856,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 1.55,
1651
+ "learning_rate": 4.8017960989890086e-05,
1652
+ "loss": 0.887,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 1.55,
1657
+ "learning_rate": 4.771323050096028e-05,
1658
+ "loss": 0.8928,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 1.56,
1663
+ "learning_rate": 4.740858510747897e-05,
1664
+ "loss": 0.8488,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 1.56,
1669
+ "learning_rate": 4.710403614593475e-05,
1670
+ "loss": 0.841,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 1.57,
1675
+ "learning_rate": 4.6799594949227786e-05,
1676
+ "loss": 0.8514,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 1.58,
1681
+ "learning_rate": 4.6495272846248146e-05,
1682
+ "loss": 0.8739,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 1.58,
1687
+ "learning_rate": 4.619108116145411e-05,
1688
+ "loss": 0.8315,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 1.59,
1693
+ "learning_rate": 4.588703121445084e-05,
1694
+ "loss": 0.8449,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 1.59,
1699
+ "learning_rate": 4.558313431956914e-05,
1700
+ "loss": 0.8413,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 1.6,
1705
+ "learning_rate": 4.527940178544446e-05,
1706
+ "loss": 0.9332,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 1.6,
1711
+ "learning_rate": 4.497584491459601e-05,
1712
+ "loss": 0.8418,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 1.61,
1717
+ "learning_rate": 4.46724750030062e-05,
1718
+ "loss": 0.9357,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 1.61,
1723
+ "learning_rate": 4.4369303339700324e-05,
1724
+ "loss": 0.9192,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 1.62,
1729
+ "learning_rate": 4.406634120632639e-05,
1730
+ "loss": 0.8618,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 1.63,
1735
+ "learning_rate": 4.3763599876735465e-05,
1736
+ "loss": 0.8305,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 1.63,
1741
+ "learning_rate": 4.346109061656195e-05,
1742
+ "loss": 0.835,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 1.64,
1747
+ "learning_rate": 4.31588246828045e-05,
1748
+ "loss": 0.8527,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 1.64,
1753
+ "learning_rate": 4.285681332340708e-05,
1754
+ "loss": 0.8881,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 1.65,
1759
+ "learning_rate": 4.255506777684041e-05,
1760
+ "loss": 0.8483,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 1.65,
1765
+ "learning_rate": 4.2253599271683794e-05,
1766
+ "loss": 0.925,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 1.66,
1771
+ "learning_rate": 4.1952419026207207e-05,
1772
+ "loss": 0.8195,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 1.67,
1777
+ "learning_rate": 4.16515382479539e-05,
1778
+ "loss": 0.8842,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 1.67,
1783
+ "learning_rate": 4.135096813332333e-05,
1784
+ "loss": 0.8351,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 1.68,
1789
+ "learning_rate": 4.105071986715449e-05,
1790
+ "loss": 0.8409,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 1.68,
1795
+ "learning_rate": 4.075080462230977e-05,
1796
+ "loss": 0.8672,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 1.69,
1801
+ "learning_rate": 4.04512335592591e-05,
1802
+ "loss": 0.9678,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 1.69,
1807
+ "learning_rate": 4.015201782566471e-05,
1808
+ "loss": 0.9089,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 1.7,
1813
+ "learning_rate": 3.985316855596626e-05,
1814
+ "loss": 0.7991,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 1.71,
1819
+ "learning_rate": 3.9554696870966566e-05,
1820
+ "loss": 0.9373,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 1.71,
1825
+ "learning_rate": 3.9256613877417715e-05,
1826
+ "loss": 0.9394,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 1.72,
1831
+ "learning_rate": 3.895893066760774e-05,
1832
+ "loss": 0.9578,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 1.72,
1837
+ "learning_rate": 3.866165831894796e-05,
1838
+ "loss": 0.8791,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 1.73,
1843
+ "learning_rate": 3.836480789356063e-05,
1844
+ "loss": 0.8872,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 1.73,
1849
+ "learning_rate": 3.806839043786738e-05,
1850
+ "loss": 0.8737,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 1.74,
1855
+ "learning_rate": 3.777241698217819e-05,
1856
+ "loss": 0.915,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 1.75,
1861
+ "learning_rate": 3.747689854028081e-05,
1862
+ "loss": 0.8755,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 1.75,
1867
+ "learning_rate": 3.7181846109031005e-05,
1868
+ "loss": 0.902,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 1.76,
1873
+ "learning_rate": 3.688727066794329e-05,
1874
+ "loss": 0.8428,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 1.76,
1879
+ "learning_rate": 3.659318317878245e-05,
1880
+ "loss": 0.8767,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 1.77,
1885
+ "learning_rate": 3.629959458515551e-05,
1886
+ "loss": 0.8413,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 1.77,
1891
+ "learning_rate": 3.600651581210457e-05,
1892
+ "loss": 0.8919,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 1.78,
1897
+ "learning_rate": 3.571395776570023e-05,
1898
+ "loss": 0.9458,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 1.79,
1903
+ "learning_rate": 3.542193133263576e-05,
1904
+ "loss": 0.9182,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 1.79,
1909
+ "learning_rate": 3.5130447379822076e-05,
1910
+ "loss": 0.7931,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 1.8,
1915
+ "learning_rate": 3.483951675398316e-05,
1916
+ "loss": 0.9585,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 1.8,
1921
+ "learning_rate": 3.4549150281252636e-05,
1922
+ "loss": 0.8682,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 1.81,
1927
+ "learning_rate": 3.4259358766770766e-05,
1928
+ "loss": 0.9327,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 1.81,
1933
+ "learning_rate": 3.397015299428242e-05,
1934
+ "loss": 0.8413,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 1.82,
1939
+ "learning_rate": 3.368154372573584e-05,
1940
+ "loss": 0.9072,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 1.83,
1945
+ "learning_rate": 3.339354170088207e-05,
1946
+ "loss": 0.8593,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 1.83,
1951
+ "learning_rate": 3.310615763687536e-05,
1952
+ "loss": 0.8536,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 1.84,
1957
+ "learning_rate": 3.2819402227874365e-05,
1958
+ "loss": 0.8735,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 1.84,
1963
+ "learning_rate": 3.2533286144644134e-05,
1964
+ "loss": 0.8723,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 1.85,
1969
+ "learning_rate": 3.224782003415918e-05,
1970
+ "loss": 0.8902,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 1.85,
1975
+ "learning_rate": 3.196301451920708e-05,
1976
+ "loss": 0.9597,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 1.86,
1981
+ "learning_rate": 3.16788801979933e-05,
1982
+ "loss": 0.8313,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 1.87,
1987
+ "learning_rate": 3.1395427643746796e-05,
1988
+ "loss": 0.877,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 1.87,
1993
+ "learning_rate": 3.111266740432658e-05,
1994
+ "loss": 0.8529,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 1.88,
1999
+ "learning_rate": 3.0830610001829174e-05,
2000
+ "loss": 0.9046,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 1.88,
2005
+ "learning_rate": 3.0549265932197055e-05,
2006
+ "loss": 0.9228,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 1.89,
2011
+ "learning_rate": 3.0268645664828134e-05,
2012
+ "loss": 0.8223,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 1.89,
2017
+ "learning_rate": 2.9988759642186097e-05,
2018
+ "loss": 0.9517,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 1.9,
2023
+ "learning_rate": 2.970961827941192e-05,
2024
+ "loss": 0.8656,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 1.91,
2029
+ "learning_rate": 2.9431231963936174e-05,
2030
+ "loss": 0.9232,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 1.91,
2035
+ "learning_rate": 2.9153611055092583e-05,
2036
+ "loss": 0.8573,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 1.92,
2041
+ "learning_rate": 2.8876765883732447e-05,
2042
+ "loss": 0.9124,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 1.92,
2047
+ "learning_rate": 2.860070675184036e-05,
2048
+ "loss": 0.8618,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 1.93,
2053
+ "learning_rate": 2.8325443932150647e-05,
2054
+ "loss": 0.8767,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 1.93,
2059
+ "learning_rate": 2.805098766776529e-05,
2060
+ "loss": 0.946,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 1.94,
2065
+ "learning_rate": 2.7777348171772604e-05,
2066
+ "loss": 0.8468,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 1.95,
2071
+ "learning_rate": 2.7504535626867288e-05,
2072
+ "loss": 0.8405,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 1.95,
2077
+ "learning_rate": 2.7232560184971434e-05,
2078
+ "loss": 0.8885,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 1.96,
2083
+ "learning_rate": 2.6961431966856864e-05,
2084
+ "loss": 0.9253,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 1.96,
2089
+ "learning_rate": 2.6691161061768376e-05,
2090
+ "loss": 0.918,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 1.97,
2095
+ "learning_rate": 2.6421757527048373e-05,
2096
+ "loss": 0.9028,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 1.97,
2101
+ "learning_rate": 2.6153231387762637e-05,
2102
+ "loss": 0.8916,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 1.98,
2107
+ "learning_rate": 2.588559263632719e-05,
2108
+ "loss": 0.9061,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 1.99,
2113
+ "learning_rate": 2.5618851232136574e-05,
2114
+ "loss": 0.8574,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 1.99,
2119
+ "learning_rate": 2.535301710119312e-05,
2120
+ "loss": 0.8754,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 2.0,
2125
+ "learning_rate": 2.5088100135737668e-05,
2126
+ "loss": 0.815,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 2.0,
2131
+ "learning_rate": 2.4824110193881382e-05,
2132
+ "loss": 0.9369,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 2.01,
2137
+ "learning_rate": 2.456105709923897e-05,
2138
+ "loss": 0.8403,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 2.0,
2143
+ "learning_rate": 2.4298950640563156e-05,
2144
+ "loss": 0.9195,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 2.01,
2149
+ "learning_rate": 2.4037800571380297e-05,
2150
+ "loss": 0.8264,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 2.01,
2155
+ "learning_rate": 2.377761660962754e-05,
2156
+ "loss": 0.835,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 2.02,
2161
+ "learning_rate": 2.3518408437291157e-05,
2162
+ "loss": 0.8643,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 2.03,
2167
+ "learning_rate": 2.3260185700046294e-05,
2168
+ "loss": 0.9159,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 2.03,
2173
+ "learning_rate": 2.3002958006897984e-05,
2174
+ "loss": 0.862,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 2.04,
2179
+ "learning_rate": 2.2746734929823594e-05,
2180
+ "loss": 0.8736,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 2.04,
2185
+ "learning_rate": 2.249152600341665e-05,
2186
+ "loss": 0.8712,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 2.05,
2191
+ "learning_rate": 2.2237340724532007e-05,
2192
+ "loss": 0.8134,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 2.05,
2197
+ "learning_rate": 2.1984188551932512e-05,
2198
+ "loss": 0.839,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 2.06,
2203
+ "learning_rate": 2.1732078905936924e-05,
2204
+ "loss": 0.8637,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 2.07,
2209
+ "learning_rate": 2.1481021168069437e-05,
2210
+ "loss": 0.8083,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 2.07,
2215
+ "learning_rate": 2.123102468071058e-05,
2216
+ "loss": 0.8719,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 2.08,
2221
+ "learning_rate": 2.0982098746749523e-05,
2222
+ "loss": 0.7897,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 2.08,
2227
+ "learning_rate": 2.0734252629237894e-05,
2228
+ "loss": 0.8811,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 2.09,
2233
+ "learning_rate": 2.048749555104516e-05,
2234
+ "loss": 0.8262,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 2.09,
2239
+ "learning_rate": 2.0241836694515336e-05,
2240
+ "loss": 0.7671,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 2.1,
2245
+ "learning_rate": 1.9997285201125325e-05,
2246
+ "loss": 0.9032,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 2.11,
2251
+ "learning_rate": 1.975385017114473e-05,
2252
+ "loss": 0.9135,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 2.11,
2257
+ "learning_rate": 1.9511540663297285e-05,
2258
+ "loss": 0.8288,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 2.12,
2263
+ "learning_rate": 1.9270365694423653e-05,
2264
+ "loss": 0.7842,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 2.12,
2269
+ "learning_rate": 1.903033423914596e-05,
2270
+ "loss": 0.8083,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 2.13,
2275
+ "learning_rate": 1.8791455229533804e-05,
2276
+ "loss": 0.8182,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 2.13,
2281
+ "learning_rate": 1.8553737554771882e-05,
2282
+ "loss": 0.83,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 2.14,
2287
+ "learning_rate": 1.831719006082924e-05,
2288
+ "loss": 0.832,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 2.15,
2293
+ "learning_rate": 1.8081821550130028e-05,
2294
+ "loss": 0.8105,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 2.15,
2299
+ "learning_rate": 1.7847640781225983e-05,
2300
+ "loss": 0.9172,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 2.16,
2305
+ "learning_rate": 1.761465646847051e-05,
2306
+ "loss": 0.8529,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 2.16,
2311
+ "learning_rate": 1.7382877281694355e-05,
2312
+ "loss": 0.7537,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 2.17,
2317
+ "learning_rate": 1.7152311845883095e-05,
2318
+ "loss": 0.8702,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 2.17,
2323
+ "learning_rate": 1.692296874085605e-05,
2324
+ "loss": 0.8275,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 2.18,
2329
+ "learning_rate": 1.669485650094708e-05,
2330
+ "loss": 0.8079,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 2.19,
2335
+ "learning_rate": 1.6467983614686994e-05,
2336
+ "loss": 0.9227,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 2.19,
2341
+ "learning_rate": 1.62423585244877e-05,
2342
+ "loss": 0.8527,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 2.2,
2347
+ "learning_rate": 1.601798962632799e-05,
2348
+ "loss": 0.8303,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 2.2,
2353
+ "learning_rate": 1.5794885269441153e-05,
2354
+ "loss": 0.825,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 2.21,
2359
+ "learning_rate": 1.557305375600425e-05,
2360
+ "loss": 0.8522,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 2.21,
2365
+ "learning_rate": 1.53525033408292e-05,
2366
+ "loss": 0.8318,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 2.22,
2371
+ "learning_rate": 1.5133242231055622e-05,
2372
+ "loss": 1.0174,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 2.22,
2377
+ "learning_rate": 1.491527858584535e-05,
2378
+ "loss": 0.8449,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 2.23,
2383
+ "learning_rate": 1.4698620516078882e-05,
2384
+ "loss": 0.8134,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 2.24,
2389
+ "learning_rate": 1.4483276084053565e-05,
2390
+ "loss": 0.869,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 2.24,
2395
+ "learning_rate": 1.4269253303183516e-05,
2396
+ "loss": 0.8603,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 2.25,
2401
+ "learning_rate": 1.405656013770147e-05,
2402
+ "loss": 0.7749,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 2.25,
2407
+ "learning_rate": 1.384520450236244e-05,
2408
+ "loss": 0.813,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 2.26,
2413
+ "learning_rate": 1.3635194262149131e-05,
2414
+ "loss": 0.8392,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 2.26,
2419
+ "learning_rate": 1.3426537231979307e-05,
2420
+ "loss": 0.86,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 2.27,
2425
+ "learning_rate": 1.3219241176414948e-05,
2426
+ "loss": 0.8317,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 2.28,
2431
+ "learning_rate": 1.3013313809373395e-05,
2432
+ "loss": 0.9097,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 2.28,
2437
+ "learning_rate": 1.2808762793840201e-05,
2438
+ "loss": 0.8102,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 2.29,
2443
+ "learning_rate": 1.2605595741584015e-05,
2444
+ "loss": 0.852,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 2.29,
2449
+ "learning_rate": 1.2403820212873347e-05,
2450
+ "loss": 0.7385,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 2.3,
2455
+ "learning_rate": 1.2203443716195212e-05,
2456
+ "loss": 0.8461,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 2.3,
2461
+ "learning_rate": 1.2004473707975761e-05,
2462
+ "loss": 0.8323,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 2.31,
2467
+ "learning_rate": 1.1806917592302762e-05,
2468
+ "loss": 0.8098,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 2.32,
2473
+ "learning_rate": 1.1610782720650098e-05,
2474
+ "loss": 0.8603,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 2.32,
2479
+ "learning_rate": 1.1416076391604197e-05,
2480
+ "loss": 0.8478,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 2.33,
2485
+ "learning_rate": 1.1222805850592499e-05,
2486
+ "loss": 0.8358,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 2.33,
2491
+ "learning_rate": 1.1030978289613726e-05,
2492
+ "loss": 0.8083,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 2.34,
2497
+ "learning_rate": 1.0840600846970334e-05,
2498
+ "loss": 0.8197,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 2.34,
2503
+ "learning_rate": 1.0651680607002862e-05,
2504
+ "loss": 0.8329,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 2.35,
2509
+ "learning_rate": 1.04642245998263e-05,
2510
+ "loss": 0.8906,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 2.36,
2515
+ "learning_rate": 1.0278239801068517e-05,
2516
+ "loss": 0.8385,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 2.36,
2521
+ "learning_rate": 1.0093733131610622e-05,
2522
+ "loss": 0.8374,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 2.37,
2527
+ "learning_rate": 9.91071145732948e-06,
2528
+ "loss": 0.8399,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 2.37,
2533
+ "learning_rate": 9.729181588842185e-06,
2534
+ "loss": 0.8642,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 2.38,
2539
+ "learning_rate": 9.549150281252633e-06,
2540
+ "loss": 0.8702,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 2.38,
2545
+ "learning_rate": 9.370624233900183e-06,
2546
+ "loss": 0.8315,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 2.39,
2551
+ "learning_rate": 9.193610090110304e-06,
2552
+ "loss": 0.8304,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 2.4,
2557
+ "learning_rate": 9.018114436947373e-06,
2558
+ "loss": 0.8504,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 2.4,
2563
+ "learning_rate": 8.844143804969623e-06,
2564
+ "loss": 0.863,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 2.41,
2569
+ "learning_rate": 8.671704667986037e-06,
2570
+ "loss": 0.7834,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 2.41,
2575
+ "learning_rate": 8.500803442815475e-06,
2576
+ "loss": 0.8626,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 2.42,
2581
+ "learning_rate": 8.331446489047956e-06,
2582
+ "loss": 0.7614,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 2.42,
2587
+ "learning_rate": 8.163640108807896e-06,
2588
+ "loss": 0.8403,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 2.43,
2593
+ "learning_rate": 7.997390546519668e-06,
2594
+ "loss": 0.8264,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 2.44,
2599
+ "learning_rate": 7.832703988675195e-06,
2600
+ "loss": 0.8678,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 2.44,
2605
+ "learning_rate": 7.669586563603782e-06,
2606
+ "loss": 0.826,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 2.45,
2611
+ "learning_rate": 7.508044341244014e-06,
2612
+ "loss": 0.816,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 2.45,
2617
+ "learning_rate": 7.348083332917926e-06,
2618
+ "loss": 0.8868,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 2.46,
2623
+ "learning_rate": 7.189709491107271e-06,
2624
+ "loss": 0.7778,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 2.46,
2629
+ "learning_rate": 7.0329287092320615e-06,
2630
+ "loss": 0.886,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 2.47,
2635
+ "learning_rate": 6.877746821431219e-06,
2636
+ "loss": 0.8443,
2637
+ "step": 438
2638
+ },
2639
+ {
2640
+ "epoch": 2.48,
2641
+ "learning_rate": 6.724169602345487e-06,
2642
+ "loss": 0.8011,
2643
+ "step": 439
2644
+ },
2645
+ {
2646
+ "epoch": 2.48,
2647
+ "learning_rate": 6.572202766902569e-06,
2648
+ "loss": 0.8417,
2649
+ "step": 440
2650
+ },
2651
+ {
2652
+ "epoch": 2.49,
2653
+ "learning_rate": 6.421851970104409e-06,
2654
+ "loss": 0.8508,
2655
+ "step": 441
2656
+ },
2657
+ {
2658
+ "epoch": 2.49,
2659
+ "learning_rate": 6.273122806816845e-06,
2660
+ "loss": 0.8186,
2661
+ "step": 442
2662
+ },
2663
+ {
2664
+ "epoch": 2.5,
2665
+ "learning_rate": 6.1260208115613225e-06,
2666
+ "loss": 0.8853,
2667
+ "step": 443
2668
+ },
2669
+ {
2670
+ "epoch": 2.5,
2671
+ "learning_rate": 5.9805514583089805e-06,
2672
+ "loss": 0.8937,
2673
+ "step": 444
2674
+ },
2675
+ {
2676
+ "epoch": 2.51,
2677
+ "learning_rate": 5.83672016027697e-06,
2678
+ "loss": 0.8463,
2679
+ "step": 445
2680
+ },
2681
+ {
2682
+ "epoch": 2.52,
2683
+ "learning_rate": 5.6945322697269765e-06,
2684
+ "loss": 0.8497,
2685
+ "step": 446
2686
+ },
2687
+ {
2688
+ "epoch": 2.52,
2689
+ "learning_rate": 5.553993077766123e-06,
2690
+ "loss": 0.842,
2691
+ "step": 447
2692
+ },
2693
+ {
2694
+ "epoch": 2.53,
2695
+ "learning_rate": 5.415107814149978e-06,
2696
+ "loss": 0.823,
2697
+ "step": 448
2698
+ },
2699
+ {
2700
+ "epoch": 2.53,
2701
+ "learning_rate": 5.277881647088024e-06,
2702
+ "loss": 0.8383,
2703
+ "step": 449
2704
+ },
2705
+ {
2706
+ "epoch": 2.54,
2707
+ "learning_rate": 5.1423196830513e-06,
2708
+ "loss": 0.8076,
2709
+ "step": 450
2710
+ },
2711
+ {
2712
+ "epoch": 2.54,
2713
+ "learning_rate": 5.008426966582386e-06,
2714
+ "loss": 0.8737,
2715
+ "step": 451
2716
+ },
2717
+ {
2718
+ "epoch": 2.55,
2719
+ "learning_rate": 4.876208480107719e-06,
2720
+ "loss": 0.8191,
2721
+ "step": 452
2722
+ },
2723
+ {
2724
+ "epoch": 2.56,
2725
+ "learning_rate": 4.745669143752124e-06,
2726
+ "loss": 0.8222,
2727
+ "step": 453
2728
+ },
2729
+ {
2730
+ "epoch": 2.56,
2731
+ "learning_rate": 4.616813815155752e-06,
2732
+ "loss": 0.8842,
2733
+ "step": 454
2734
+ },
2735
+ {
2736
+ "epoch": 2.57,
2737
+ "learning_rate": 4.489647289293369e-06,
2738
+ "loss": 0.8472,
2739
+ "step": 455
2740
+ },
2741
+ {
2742
+ "epoch": 2.57,
2743
+ "learning_rate": 4.36417429829582e-06,
2744
+ "loss": 0.7504,
2745
+ "step": 456
2746
+ },
2747
+ {
2748
+ "epoch": 2.58,
2749
+ "learning_rate": 4.240399511274057e-06,
2750
+ "loss": 0.8233,
2751
+ "step": 457
2752
+ },
2753
+ {
2754
+ "epoch": 2.58,
2755
+ "learning_rate": 4.118327534145277e-06,
2756
+ "loss": 0.8909,
2757
+ "step": 458
2758
+ },
2759
+ {
2760
+ "epoch": 2.59,
2761
+ "learning_rate": 3.9979629094616115e-06,
2762
+ "loss": 0.8407,
2763
+ "step": 459
2764
+ },
2765
+ {
2766
+ "epoch": 2.6,
2767
+ "learning_rate": 3.879310116241042e-06,
2768
+ "loss": 0.8017,
2769
+ "step": 460
2770
+ },
2771
+ {
2772
+ "epoch": 2.6,
2773
+ "learning_rate": 3.7623735698007366e-06,
2774
+ "loss": 0.8326,
2775
+ "step": 461
2776
+ },
2777
+ {
2778
+ "epoch": 2.61,
2779
+ "learning_rate": 3.6471576215927896e-06,
2780
+ "loss": 0.8581,
2781
+ "step": 462
2782
+ },
2783
+ {
2784
+ "epoch": 2.61,
2785
+ "learning_rate": 3.5336665590422145e-06,
2786
+ "loss": 0.7771,
2787
+ "step": 463
2788
+ },
2789
+ {
2790
+ "epoch": 2.62,
2791
+ "learning_rate": 3.4219046053874603e-06,
2792
+ "loss": 0.8504,
2793
+ "step": 464
2794
+ },
2795
+ {
2796
+ "epoch": 2.62,
2797
+ "learning_rate": 3.3118759195232275e-06,
2798
+ "loss": 0.8017,
2799
+ "step": 465
2800
+ },
2801
+ {
2802
+ "epoch": 2.63,
2803
+ "learning_rate": 3.203584595845732e-06,
2804
+ "loss": 0.8317,
2805
+ "step": 466
2806
+ },
2807
+ {
2808
+ "epoch": 2.63,
2809
+ "learning_rate": 3.0970346641003346e-06,
2810
+ "loss": 0.8053,
2811
+ "step": 467
2812
+ },
2813
+ {
2814
+ "epoch": 2.64,
2815
+ "learning_rate": 2.9922300892315514e-06,
2816
+ "loss": 0.8666,
2817
+ "step": 468
2818
+ },
2819
+ {
2820
+ "epoch": 2.65,
2821
+ "learning_rate": 2.88917477123557e-06,
2822
+ "loss": 0.809,
2823
+ "step": 469
2824
+ },
2825
+ {
2826
+ "epoch": 2.65,
2827
+ "learning_rate": 2.787872545015069e-06,
2828
+ "loss": 0.8189,
2829
+ "step": 470
2830
+ },
2831
+ {
2832
+ "epoch": 2.66,
2833
+ "learning_rate": 2.6883271802365607e-06,
2834
+ "loss": 0.7692,
2835
+ "step": 471
2836
+ },
2837
+ {
2838
+ "epoch": 2.66,
2839
+ "learning_rate": 2.5905423811900754e-06,
2840
+ "loss": 0.7939,
2841
+ "step": 472
2842
+ },
2843
+ {
2844
+ "epoch": 2.67,
2845
+ "learning_rate": 2.494521786651327e-06,
2846
+ "loss": 0.8569,
2847
+ "step": 473
2848
+ },
2849
+ {
2850
+ "epoch": 2.67,
2851
+ "learning_rate": 2.400268969746322e-06,
2852
+ "loss": 0.8236,
2853
+ "step": 474
2854
+ },
2855
+ {
2856
+ "epoch": 2.68,
2857
+ "learning_rate": 2.307787437818365e-06,
2858
+ "loss": 0.7563,
2859
+ "step": 475
2860
+ },
2861
+ {
2862
+ "epoch": 2.69,
2863
+ "learning_rate": 2.2170806322976024e-06,
2864
+ "loss": 0.804,
2865
+ "step": 476
2866
+ },
2867
+ {
2868
+ "epoch": 2.69,
2869
+ "learning_rate": 2.12815192857288e-06,
2870
+ "loss": 0.7779,
2871
+ "step": 477
2872
+ },
2873
+ {
2874
+ "epoch": 2.7,
2875
+ "learning_rate": 2.041004635866195e-06,
2876
+ "loss": 0.8429,
2877
+ "step": 478
2878
+ },
2879
+ {
2880
+ "epoch": 2.7,
2881
+ "learning_rate": 1.9556419971095363e-06,
2882
+ "loss": 0.7445,
2883
+ "step": 479
2884
+ },
2885
+ {
2886
+ "epoch": 2.71,
2887
+ "learning_rate": 1.8720671888242059e-06,
2888
+ "loss": 0.7985,
2889
+ "step": 480
2890
+ },
2891
+ {
2892
+ "epoch": 2.71,
2893
+ "learning_rate": 1.7902833210026226e-06,
2894
+ "loss": 0.8194,
2895
+ "step": 481
2896
+ },
2897
+ {
2898
+ "epoch": 2.72,
2899
+ "learning_rate": 1.710293436992566e-06,
2900
+ "loss": 0.8629,
2901
+ "step": 482
2902
+ },
2903
+ {
2904
+ "epoch": 2.73,
2905
+ "learning_rate": 1.6321005133839885e-06,
2906
+ "loss": 0.9087,
2907
+ "step": 483
2908
+ },
2909
+ {
2910
+ "epoch": 2.73,
2911
+ "learning_rate": 1.555707459898159e-06,
2912
+ "loss": 0.7404,
2913
+ "step": 484
2914
+ },
2915
+ {
2916
+ "epoch": 2.74,
2917
+ "learning_rate": 1.4811171192794627e-06,
2918
+ "loss": 0.8458,
2919
+ "step": 485
2920
+ },
2921
+ {
2922
+ "epoch": 2.74,
2923
+ "learning_rate": 1.408332267189605e-06,
2924
+ "loss": 0.8266,
2925
+ "step": 486
2926
+ },
2927
+ {
2928
+ "epoch": 2.75,
2929
+ "learning_rate": 1.337355612104274e-06,
2930
+ "loss": 0.9266,
2931
+ "step": 487
2932
+ },
2933
+ {
2934
+ "epoch": 2.75,
2935
+ "learning_rate": 1.2681897952124044e-06,
2936
+ "loss": 0.9073,
2937
+ "step": 488
2938
+ },
2939
+ {
2940
+ "epoch": 2.76,
2941
+ "learning_rate": 1.2008373903178827e-06,
2942
+ "loss": 0.8218,
2943
+ "step": 489
2944
+ },
2945
+ {
2946
+ "epoch": 2.77,
2947
+ "learning_rate": 1.1353009037437523e-06,
2948
+ "loss": 0.8244,
2949
+ "step": 490
2950
+ },
2951
+ {
2952
+ "epoch": 2.77,
2953
+ "learning_rate": 1.0715827742389717e-06,
2954
+ "loss": 0.8042,
2955
+ "step": 491
2956
+ },
2957
+ {
2958
+ "epoch": 2.78,
2959
+ "learning_rate": 1.0096853728876365e-06,
2960
+ "loss": 0.8509,
2961
+ "step": 492
2962
+ },
2963
+ {
2964
+ "epoch": 2.78,
2965
+ "learning_rate": 9.496110030207672e-07,
2966
+ "loss": 0.7784,
2967
+ "step": 493
2968
+ },
2969
+ {
2970
+ "epoch": 2.79,
2971
+ "learning_rate": 8.913619001305995e-07,
2972
+ "loss": 0.8437,
2973
+ "step": 494
2974
+ },
2975
+ {
2976
+ "epoch": 2.79,
2977
+ "learning_rate": 8.349402317873789e-07,
2978
+ "loss": 0.8154,
2979
+ "step": 495
2980
+ },
2981
+ {
2982
+ "epoch": 2.8,
2983
+ "learning_rate": 7.803480975587196e-07,
2984
+ "loss": 0.8392,
2985
+ "step": 496
2986
+ },
2987
+ {
2988
+ "epoch": 2.81,
2989
+ "learning_rate": 7.275875289314616e-07,
2990
+ "loss": 0.8328,
2991
+ "step": 497
2992
+ },
2993
+ {
2994
+ "epoch": 2.81,
2995
+ "learning_rate": 6.76660489236075e-07,
2996
+ "loss": 0.7807,
2997
+ "step": 498
2998
+ },
2999
+ {
3000
+ "epoch": 2.82,
3001
+ "learning_rate": 6.275688735736141e-07,
3002
+ "loss": 0.8334,
3003
+ "step": 499
3004
+ },
3005
+ {
3006
+ "epoch": 2.82,
3007
+ "learning_rate": 5.803145087451945e-07,
3008
+ "loss": 0.8813,
3009
+ "step": 500
3010
+ },
3011
+ {
3012
+ "epoch": 2.83,
3013
+ "learning_rate": 5.348991531839876e-07,
3014
+ "loss": 0.809,
3015
+ "step": 501
3016
+ },
3017
+ {
3018
+ "epoch": 2.83,
3019
+ "learning_rate": 4.913244968898279e-07,
3020
+ "loss": 0.8181,
3021
+ "step": 502
3022
+ },
3023
+ {
3024
+ "epoch": 2.84,
3025
+ "learning_rate": 4.4959216136627456e-07,
3026
+ "loss": 0.825,
3027
+ "step": 503
3028
+ },
3029
+ {
3030
+ "epoch": 2.85,
3031
+ "learning_rate": 4.0970369956033203e-07,
3032
+ "loss": 0.8723,
3033
+ "step": 504
3034
+ },
3035
+ {
3036
+ "epoch": 2.85,
3037
+ "learning_rate": 3.716605958046071e-07,
3038
+ "loss": 0.8005,
3039
+ "step": 505
3040
+ },
3041
+ {
3042
+ "epoch": 2.86,
3043
+ "learning_rate": 3.354642657621032e-07,
3044
+ "loss": 0.849,
3045
+ "step": 506
3046
+ },
3047
+ {
3048
+ "epoch": 2.86,
3049
+ "learning_rate": 3.011160563735349e-07,
3050
+ "loss": 0.8722,
3051
+ "step": 507
3052
+ },
3053
+ {
3054
+ "epoch": 2.87,
3055
+ "learning_rate": 2.686172458071956e-07,
3056
+ "loss": 0.8739,
3057
+ "step": 508
3058
+ },
3059
+ {
3060
+ "epoch": 2.87,
3061
+ "learning_rate": 2.3796904341141235e-07,
3062
+ "loss": 0.8618,
3063
+ "step": 509
3064
+ },
3065
+ {
3066
+ "epoch": 2.88,
3067
+ "learning_rate": 2.0917258966953733e-07,
3068
+ "loss": 0.8305,
3069
+ "step": 510
3070
+ },
3071
+ {
3072
+ "epoch": 2.89,
3073
+ "learning_rate": 1.8222895615748747e-07,
3074
+ "loss": 0.8004,
3075
+ "step": 511
3076
+ },
3077
+ {
3078
+ "epoch": 2.89,
3079
+ "learning_rate": 1.571391455038984e-07,
3080
+ "loss": 0.9137,
3081
+ "step": 512
3082
+ },
3083
+ {
3084
+ "epoch": 2.9,
3085
+ "learning_rate": 1.3390409135281002e-07,
3086
+ "loss": 0.8819,
3087
+ "step": 513
3088
+ },
3089
+ {
3090
+ "epoch": 2.9,
3091
+ "learning_rate": 1.1252465832888859e-07,
3092
+ "loss": 0.8171,
3093
+ "step": 514
3094
+ },
3095
+ {
3096
+ "epoch": 2.91,
3097
+ "learning_rate": 9.300164200530814e-08,
3098
+ "loss": 0.8429,
3099
+ "step": 515
3100
+ },
3101
+ {
3102
+ "epoch": 2.91,
3103
+ "learning_rate": 7.533576887410187e-08,
3104
+ "loss": 0.8408,
3105
+ "step": 516
3106
+ },
3107
+ {
3108
+ "epoch": 2.92,
3109
+ "learning_rate": 5.95276963191449e-08,
3110
+ "loss": 0.8236,
3111
+ "step": 517
3112
+ },
3113
+ {
3114
+ "epoch": 2.93,
3115
+ "learning_rate": 4.5578012591690475e-08,
3116
+ "loss": 0.8688,
3117
+ "step": 518
3118
+ },
3119
+ {
3120
+ "epoch": 2.93,
3121
+ "learning_rate": 3.348723678847643e-08,
3122
+ "loss": 0.837,
3123
+ "step": 519
3124
+ },
3125
+ {
3126
+ "epoch": 2.94,
3127
+ "learning_rate": 2.3255818832423894e-08,
3128
+ "loss": 0.8389,
3129
+ "step": 520
3130
+ },
3131
+ {
3132
+ "epoch": 2.94,
3133
+ "learning_rate": 1.4884139455861867e-08,
3134
+ "loss": 0.7877,
3135
+ "step": 521
3136
+ },
3137
+ {
3138
+ "epoch": 2.95,
3139
+ "learning_rate": 8.372510186388516e-09,
3140
+ "loss": 0.8615,
3141
+ "step": 522
3142
+ },
3143
+ {
3144
+ "epoch": 2.95,
3145
+ "learning_rate": 3.7211733352748857e-09,
3146
+ "loss": 0.8643,
3147
+ "step": 523
3148
+ },
3149
+ {
3150
+ "epoch": 2.96,
3151
+ "learning_rate": 9.303019884387976e-10,
3152
+ "loss": 1.0185,
3153
+ "step": 524
3154
+ },
3155
+ {
3156
+ "epoch": 2.97,
3157
+ "learning_rate": 0.0,
3158
+ "loss": 0.8112,
3159
+ "step": 525
3160
+ }
3161
+ ],
3162
+ "logging_steps": 1,
3163
+ "max_steps": 525,
3164
+ "num_input_tokens_seen": 0,
3165
+ "num_train_epochs": 3,
3166
+ "save_steps": 175,
3167
+ "total_flos": 1.9428401306035814e+19,
3168
+ "train_batch_size": 1,
3169
+ "trial_name": null,
3170
+ "trial_params": null
3171
+ }
checkpoint-525/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:862899d2d90e28bcdb2d7301eb97d6ede02950401db2351f4f6591f98d8e42bd
3
+ size 5240
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/Mixtral-8x7B-v0.1",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": true,
21
+ "quantization_config": {
22
+ "bnb_4bit_compute_dtype": "bfloat16",
23
+ "bnb_4bit_quant_type": "nf4",
24
+ "bnb_4bit_use_double_quant": true,
25
+ "llm_int8_enable_fp32_cpu_offload": false,
26
+ "llm_int8_has_fp16_weight": false,
27
+ "llm_int8_skip_modules": null,
28
+ "llm_int8_threshold": 6.0,
29
+ "load_in_4bit": true,
30
+ "load_in_8bit": false,
31
+ "quant_method": "bitsandbytes"
32
+ },
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_theta": 1000000.0,
35
+ "router_aux_loss_coef": 0.02,
36
+ "router_z_loss_coef": 0.001,
37
+ "sliding_window": null,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.37.0.dev0",
41
+ "use_cache": false,
42
+ "vocab_size": 32000
43
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "trust_remote_code": true,
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false,
43
+ "use_fast": true
44
+ }