Hugging Face's logo

Doctor-Shotgun
/
limarp-deepseek-67b-qlora

PEFT
Safetensors
llama
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
Doctor-Shotgun commited on
Commit
1342776
•
1 Parent(s): f48ddea

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. README.md +150 -0
  2. adapter_config.json +28 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-244/README.md +220 -0
  5. checkpoint-244/adapter_config.json +28 -0
  6. checkpoint-244/adapter_model.safetensors +3 -0
  7. checkpoint-244/optimizer.pt +3 -0
  8. checkpoint-244/rng_state.pth +3 -0
  9. checkpoint-244/scheduler.pt +3 -0
  10. checkpoint-244/trainer_state.json +1485 -0
  11. checkpoint-244/training_args.bin +3 -0
  12. checkpoint-488/README.md +220 -0
  13. checkpoint-488/adapter_config.json +28 -0
  14. checkpoint-488/adapter_model.safetensors +3 -0
  15. checkpoint-488/optimizer.pt +3 -0
  16. checkpoint-488/rng_state.pth +3 -0
  17. checkpoint-488/scheduler.pt +3 -0
  18. checkpoint-488/trainer_state.json +2949 -0
  19. checkpoint-488/training_args.bin +3 -0
  20. config.json +40 -0
  21. special_tokens_map.json +23 -0
  22. tokenizer.json +0 -0
  23. tokenizer_config.json +136 -0
README.md ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - generated_from_trainer
5
+ base_model: deepseekai/deepseek-llm-67b-base
6
+ model-index:
7
+ - name: workspace/volume/limarp-deepseek-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: ./models/deepseek-llm-67b-base
20
+ model_type: LlamaForCausalLM
21
+ tokenizer_type: AutoTokenizer
22
+ is_llama_derived_model: true
23
+
24
+ load_in_8bit: false
25
+ load_in_4bit: true
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: train-all-4k-alpaca-deepseek.jsonl
30
+ type: completion
31
+ dataset_prepared_path:
32
+ val_set_size: 0.0
33
+ output_dir: /workspace/volume/limarp-deepseek-qlora-out
34
+
35
+ adapter: qlora
36
+ lora_model_dir:
37
+
38
+ sequence_len: 4096
39
+ sample_packing: true
40
+ pad_to_sequence_len: true
41
+
42
+ lora_r: 32
43
+ lora_alpha: 16
44
+ lora_dropout: 0.05
45
+ lora_target_modules:
46
+ lora_target_linear: true
47
+ lora_fan_in_fan_out:
48
+
49
+ wandb_project: 70b-lora
50
+ wandb_entity:
51
+ wandb_watch:
52
+ wandb_name:
53
+ wandb_log_model:
54
+
55
+ gradient_accumulation_steps: 8
56
+ micro_batch_size: 1
57
+ num_epochs: 2
58
+ optimizer: adamw_bnb_8bit
59
+ lr_scheduler: cosine
60
+ learning_rate: 0.00015
61
+
62
+ train_on_inputs: true
63
+ group_by_length: false
64
+ bf16: true
65
+ fp16: false
66
+ tf32: true
67
+
68
+ gradient_checkpointing: true
69
+ early_stopping_patience:
70
+ resume_from_checkpoint:
71
+ local_rank:
72
+ logging_steps: 1
73
+ xformers_attention:
74
+ flash_attention: true
75
+
76
+ warmup_steps: 10
77
+ evals_per_epoch:
78
+ eval_table_size:
79
+ saves_per_epoch: 1
80
+ debug:
81
+ deepspeed:
82
+ weight_decay: 0.0
83
+ fsdp:
84
+ fsdp_config:
85
+
86
+ ```
87
+
88
+ </details><br>
89
+
90
+ # workspace/volume/limarp-deepseek-qlora-out
91
+
92
+ This model was trained from scratch on the None dataset.
93
+
94
+ ## Model description
95
+
96
+ More information needed
97
+
98
+ ## Intended uses & limitations
99
+
100
+ More information needed
101
+
102
+ ## Training and evaluation data
103
+
104
+ More information needed
105
+
106
+ ## Training procedure
107
+
108
+ ### Training hyperparameters
109
+
110
+ The following hyperparameters were used during training:
111
+ - learning_rate: 0.00015
112
+ - train_batch_size: 1
113
+ - eval_batch_size: 1
114
+ - seed: 42
115
+ - gradient_accumulation_steps: 8
116
+ - total_train_batch_size: 8
117
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
118
+ - lr_scheduler_type: cosine
119
+ - lr_scheduler_warmup_steps: 10
120
+ - num_epochs: 2
121
+
122
+ ### Training results
123
+
124
+
125
+
126
+ ### Framework versions
127
+
128
+ - Transformers 4.36.2
129
+ - Pytorch 2.0.1+cu118
130
+ - Datasets 2.16.1
131
+ - Tokenizers 0.15.0
132
+ ## Training procedure
133
+
134
+
135
+ The following `bitsandbytes` quantization config was used during training:
136
+ - quant_method: bitsandbytes
137
+ - load_in_8bit: False
138
+ - load_in_4bit: True
139
+ - llm_int8_threshold: 6.0
140
+ - llm_int8_skip_modules: None
141
+ - llm_int8_enable_fp32_cpu_offload: False
142
+ - llm_int8_has_fp16_weight: False
143
+ - bnb_4bit_quant_type: nf4
144
+ - bnb_4bit_use_double_quant: True
145
+ - bnb_4bit_compute_dtype: bfloat16
146
+
147
+ ### Framework versions
148
+
149
+
150
+ - PEFT 0.6.0
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./models/deepseek-llm-67b-base",
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
+ "down_proj",
20
+ "k_proj",
21
+ "q_proj",
22
+ "v_proj",
23
+ "up_proj",
24
+ "o_proj",
25
+ "gate_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea2c25c365a6aff187d4027dc1fe65e1b129feb46fbfadd2a5bd1012eff1a63a
3
+ size 1725060895
checkpoint-244/README.md ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: ./models/deepseek-llm-67b-base
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-244/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./models/deepseek-llm-67b-base",
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
+ "down_proj",
20
+ "k_proj",
21
+ "q_proj",
22
+ "v_proj",
23
+ "up_proj",
24
+ "o_proj",
25
+ "gate_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-244/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a81b34348bd46e7e85581d6c456af9a3657c851df090747b47cec071c49b428c
3
+ size 1724761096
checkpoint-244/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429fd6934d4795dd980ce7f1470932c3cfa9c57cbd82287e1a69a46c01147ceb
3
+ size 865513703
checkpoint-244/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5f0db81340bd5a8bd66fbe5e8fa94bae162b913f07b517a53dea842c13c08e4
3
+ size 14575
checkpoint-244/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0b1814d01de8948ff1b991fb3d2375ee488bb780697894b44447e63e028320e
3
+ size 627
checkpoint-244/trainer_state.json ADDED
@@ -0,0 +1,1485 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9974450689831375,
5
+ "eval_steps": 500,
6
+ "global_step": 244,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 1.4999999999999999e-05,
14
+ "loss": 2.0754,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2.9999999999999997e-05,
20
+ "loss": 2.1342,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 4.4999999999999996e-05,
26
+ "loss": 2.1035,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 5.9999999999999995e-05,
32
+ "loss": 2.09,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 7.5e-05,
38
+ "loss": 2.0643,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 8.999999999999999e-05,
44
+ "loss": 2.124,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "learning_rate": 0.00010499999999999999,
50
+ "loss": 2.1867,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "learning_rate": 0.00011999999999999999,
56
+ "loss": 2.175,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.04,
61
+ "learning_rate": 0.000135,
62
+ "loss": 2.0837,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.04,
67
+ "learning_rate": 0.00015,
68
+ "loss": 2.0431,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.04,
73
+ "learning_rate": 0.00014999838015426563,
74
+ "loss": 2.0665,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.05,
79
+ "learning_rate": 0.00014999352068703324,
80
+ "loss": 2.0668,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.05,
85
+ "learning_rate": 0.0001499854218082118,
86
+ "loss": 2.1312,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.06,
91
+ "learning_rate": 0.00014997408386763957,
92
+ "loss": 2.0758,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.06,
97
+ "learning_rate": 0.00014995950735506895,
98
+ "loss": 2.1173,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.07,
103
+ "learning_rate": 0.00014994169290014528,
104
+ "loss": 2.0044,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.07,
109
+ "learning_rate": 0.00014992064127237976,
110
+ "loss": 2.0054,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.07,
115
+ "learning_rate": 0.00014989635338111612,
116
+ "loss": 2.0509,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.08,
121
+ "learning_rate": 0.0001498688302754913,
122
+ "loss": 2.1071,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.08,
127
+ "learning_rate": 0.0001498380731443903,
128
+ "loss": 1.9549,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.09,
133
+ "learning_rate": 0.00014980408331639463,
134
+ "loss": 1.895,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.09,
139
+ "learning_rate": 0.000149766862259725,
140
+ "loss": 1.9979,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.09,
145
+ "learning_rate": 0.000149726411582178,
146
+ "loss": 2.0151,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.1,
151
+ "learning_rate": 0.00014968273303105645,
152
+ "loss": 1.9236,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.1,
157
+ "learning_rate": 0.0001496358284930941,
158
+ "loss": 1.9613,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.11,
163
+ "learning_rate": 0.00014958569999437403,
164
+ "loss": 1.9975,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.11,
169
+ "learning_rate": 0.00014953234970024114,
170
+ "loss": 1.9804,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.11,
175
+ "learning_rate": 0.00014947577991520874,
176
+ "loss": 1.9211,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.12,
181
+ "learning_rate": 0.00014941599308285872,
182
+ "loss": 2.0278,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.12,
187
+ "learning_rate": 0.0001493529917857364,
188
+ "loss": 1.9682,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.13,
193
+ "learning_rate": 0.0001492867787452386,
194
+ "loss": 1.8728,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.13,
199
+ "learning_rate": 0.00014921735682149628,
200
+ "loss": 2.0241,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.13,
205
+ "learning_rate": 0.00014914472901325095,
206
+ "loss": 1.9737,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.14,
211
+ "learning_rate": 0.00014906889845772516,
212
+ "loss": 1.9329,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.14,
217
+ "learning_rate": 0.00014898986843048698,
218
+ "loss": 1.9861,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.15,
223
+ "learning_rate": 0.00014890764234530847,
224
+ "loss": 1.8872,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.15,
229
+ "learning_rate": 0.00014882222375401822,
230
+ "loss": 1.9282,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.16,
235
+ "learning_rate": 0.00014873361634634805,
236
+ "loss": 2.0487,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.16,
241
+ "learning_rate": 0.00014864182394977337,
242
+ "loss": 1.9907,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.16,
247
+ "learning_rate": 0.0001485468505293482,
248
+ "loss": 2.0665,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.17,
253
+ "learning_rate": 0.00014844870018753355,
254
+ "loss": 2.0757,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.17,
259
+ "learning_rate": 0.00014834737716402043,
260
+ "loss": 1.9599,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.18,
265
+ "learning_rate": 0.0001482428858355466,
266
+ "loss": 1.9655,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.18,
271
+ "learning_rate": 0.0001481352307157077,
272
+ "loss": 1.9234,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.18,
277
+ "learning_rate": 0.00014802441645476192,
278
+ "loss": 2.0089,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.19,
283
+ "learning_rate": 0.00014791044783942956,
284
+ "loss": 1.94,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.19,
289
+ "learning_rate": 0.0001477933297926859,
290
+ "loss": 1.9925,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.2,
295
+ "learning_rate": 0.00014767306737354885,
296
+ "loss": 1.9783,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.2,
301
+ "learning_rate": 0.00014754966577686007,
302
+ "loss": 1.97,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.2,
307
+ "learning_rate": 0.000147423130333061,
308
+ "loss": 1.9398,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.21,
313
+ "learning_rate": 0.00014729346650796223,
314
+ "loss": 1.963,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.21,
319
+ "learning_rate": 0.00014716067990250758,
320
+ "loss": 1.9428,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.22,
325
+ "learning_rate": 0.0001470247762525322,
326
+ "loss": 1.8047,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.22,
331
+ "learning_rate": 0.00014688576142851467,
332
+ "loss": 1.9507,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.22,
337
+ "learning_rate": 0.00014674364143532352,
338
+ "loss": 1.9653,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.23,
343
+ "learning_rate": 0.0001465984224119578,
344
+ "loss": 1.9433,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.23,
349
+ "learning_rate": 0.00014645011063128192,
350
+ "loss": 1.9655,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.24,
355
+ "learning_rate": 0.0001462987124997547,
356
+ "loss": 2.0388,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.24,
361
+ "learning_rate": 0.00014614423455715263,
362
+ "loss": 1.8811,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.25,
367
+ "learning_rate": 0.00014598668347628733,
368
+ "loss": 1.956,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.25,
373
+ "learning_rate": 0.00014582606606271736,
374
+ "loss": 1.9236,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.25,
379
+ "learning_rate": 0.0001456623892544542,
380
+ "loss": 1.9662,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.26,
385
+ "learning_rate": 0.00014549566012166275,
386
+ "loss": 1.9648,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.26,
391
+ "learning_rate": 0.00014532588586635558,
392
+ "loss": 1.913,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.27,
397
+ "learning_rate": 0.00014515307382208215,
398
+ "loss": 2.0282,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.27,
403
+ "learning_rate": 0.00014497723145361183,
404
+ "loss": 2.0331,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.27,
409
+ "learning_rate": 0.0001447983663566116,
410
+ "loss": 2.1089,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.28,
415
+ "learning_rate": 0.00014461648625731783,
416
+ "loss": 2.0694,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.28,
421
+ "learning_rate": 0.00014443159901220262,
422
+ "loss": 1.9098,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.29,
427
+ "learning_rate": 0.0001442437126076343,
428
+ "loss": 1.8582,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.29,
433
+ "learning_rate": 0.00014405283515953277,
434
+ "loss": 1.8942,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.29,
439
+ "learning_rate": 0.00014385897491301844,
440
+ "loss": 1.9396,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.3,
445
+ "learning_rate": 0.00014366214024205654,
446
+ "loss": 1.9624,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.3,
451
+ "learning_rate": 0.00014346233964909508,
452
+ "loss": 1.9123,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.31,
457
+ "learning_rate": 0.00014325958176469777,
458
+ "loss": 1.9146,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.31,
463
+ "learning_rate": 0.0001430538753471711,
464
+ "loss": 1.9646,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.31,
469
+ "learning_rate": 0.00014284522928218612,
470
+ "loss": 1.8241,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.32,
475
+ "learning_rate": 0.0001426336525823945,
476
+ "loss": 1.968,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.32,
481
+ "learning_rate": 0.00014241915438703928,
482
+ "loss": 1.8584,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.33,
487
+ "learning_rate": 0.00014220174396156014,
488
+ "loss": 1.9979,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.33,
493
+ "learning_rate": 0.00014198143069719306,
494
+ "loss": 1.9972,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.34,
499
+ "learning_rate": 0.00014175822411056476,
500
+ "loss": 1.8241,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.34,
505
+ "learning_rate": 0.00014153213384328158,
506
+ "loss": 1.9249,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.34,
511
+ "learning_rate": 0.00014130316966151296,
512
+ "loss": 2.076,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.35,
517
+ "learning_rate": 0.00014107134145556968,
518
+ "loss": 1.9242,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.35,
523
+ "learning_rate": 0.00014083665923947652,
524
+ "loss": 1.9075,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.36,
529
+ "learning_rate": 0.0001405991331505398,
530
+ "loss": 1.9701,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.36,
535
+ "learning_rate": 0.00014035877344890945,
536
+ "loss": 1.9521,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.36,
541
+ "learning_rate": 0.0001401155905171358,
542
+ "loss": 1.9354,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.37,
547
+ "learning_rate": 0.00013986959485972112,
548
+ "loss": 2.0025,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.37,
553
+ "learning_rate": 0.0001396207971026658,
554
+ "loss": 1.9459,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.38,
559
+ "learning_rate": 0.0001393692079930095,
560
+ "loss": 1.9798,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.38,
565
+ "learning_rate": 0.00013911483839836676,
566
+ "loss": 1.8871,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.38,
571
+ "learning_rate": 0.00013885769930645767,
572
+ "loss": 1.9457,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.39,
577
+ "learning_rate": 0.0001385978018246332,
578
+ "loss": 1.9094,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.39,
583
+ "learning_rate": 0.00013833515717939538,
584
+ "loss": 1.9651,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.4,
589
+ "learning_rate": 0.00013806977671591245,
590
+ "loss": 2.0097,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.4,
595
+ "learning_rate": 0.00013780167189752872,
596
+ "loss": 1.9944,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.4,
601
+ "learning_rate": 0.00013753085430526945,
602
+ "loss": 1.8378,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.41,
607
+ "learning_rate": 0.0001372573356373405,
608
+ "loss": 1.9796,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.41,
613
+ "learning_rate": 0.00013698112770862319,
614
+ "loss": 1.8866,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.42,
619
+ "learning_rate": 0.00013670224245016375,
620
+ "loss": 2.0077,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.42,
625
+ "learning_rate": 0.00013642069190865808,
626
+ "loss": 1.8807,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.43,
631
+ "learning_rate": 0.00013613648824593137,
632
+ "loss": 2.0118,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.43,
637
+ "learning_rate": 0.0001358496437384127,
638
+ "loss": 1.9495,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.43,
643
+ "learning_rate": 0.0001355601707766048,
644
+ "loss": 1.927,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.44,
649
+ "learning_rate": 0.0001352680818645488,
650
+ "loss": 1.9418,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.44,
655
+ "learning_rate": 0.00013497338961928406,
656
+ "loss": 1.9557,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.45,
661
+ "learning_rate": 0.00013467610677030337,
662
+ "loss": 1.9239,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.45,
667
+ "learning_rate": 0.0001343762461590028,
668
+ "loss": 2.0298,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.45,
673
+ "learning_rate": 0.00013407382073812724,
674
+ "loss": 1.9778,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.46,
679
+ "learning_rate": 0.00013376884357121075,
680
+ "loss": 1.8697,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.46,
685
+ "learning_rate": 0.00013346132783201233,
686
+ "loss": 1.8659,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.47,
691
+ "learning_rate": 0.0001331512868039469,
692
+ "loss": 1.9608,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.47,
697
+ "learning_rate": 0.00013283873387951142,
698
+ "loss": 1.9881,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.47,
703
+ "learning_rate": 0.0001325236825597065,
704
+ "loss": 1.8963,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.48,
709
+ "learning_rate": 0.00013220614645345304,
710
+ "loss": 1.9821,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.48,
715
+ "learning_rate": 0.00013188613927700462,
716
+ "loss": 1.8786,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.49,
721
+ "learning_rate": 0.00013156367485335483,
722
+ "loss": 1.9391,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.49,
727
+ "learning_rate": 0.0001312387671116402,
728
+ "loss": 1.8749,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.49,
733
+ "learning_rate": 0.00013091143008653864,
734
+ "loss": 1.9711,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.5,
739
+ "learning_rate": 0.000130581677917663,
740
+ "loss": 1.9973,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.5,
745
+ "learning_rate": 0.00013024952484895047,
746
+ "loss": 1.9736,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.51,
751
+ "learning_rate": 0.00012991498522804725,
752
+ "loss": 1.9482,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.51,
757
+ "learning_rate": 0.0001295780735056887,
758
+ "loss": 1.8969,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.52,
763
+ "learning_rate": 0.0001292388042350753,
764
+ "loss": 1.8856,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.52,
769
+ "learning_rate": 0.00012889719207124386,
770
+ "loss": 1.896,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.52,
775
+ "learning_rate": 0.00012855325177043455,
776
+ "loss": 1.9585,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.53,
781
+ "learning_rate": 0.00012820699818945344,
782
+ "loss": 2.0194,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.53,
787
+ "learning_rate": 0.00012785844628503088,
788
+ "loss": 2.0445,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.54,
793
+ "learning_rate": 0.00012750761111317527,
794
+ "loss": 1.9695,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.54,
799
+ "learning_rate": 0.00012715450782852281,
800
+ "loss": 1.9849,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.54,
805
+ "learning_rate": 0.00012679915168368276,
806
+ "loss": 1.9426,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.55,
811
+ "learning_rate": 0.00012644155802857878,
812
+ "loss": 1.8934,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.55,
817
+ "learning_rate": 0.00012608174230978572,
818
+ "loss": 1.9616,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.56,
823
+ "learning_rate": 0.00012571972006986237,
824
+ "loss": 1.926,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.56,
829
+ "learning_rate": 0.00012535550694668034,
830
+ "loss": 1.9333,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.56,
835
+ "learning_rate": 0.00012498911867274816,
836
+ "loss": 1.953,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.57,
841
+ "learning_rate": 0.0001246205710745321,
842
+ "loss": 1.9753,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.57,
847
+ "learning_rate": 0.0001242498800717723,
848
+ "loss": 1.8901,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.58,
853
+ "learning_rate": 0.00012387706167679507,
854
+ "loss": 1.8817,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.58,
859
+ "learning_rate": 0.00012350213199382147,
860
+ "loss": 1.939,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.58,
865
+ "learning_rate": 0.0001231251072182714,
866
+ "loss": 1.9321,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.59,
871
+ "learning_rate": 0.00012274600363606418,
872
+ "loss": 2.0088,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.59,
877
+ "learning_rate": 0.00012236483762291504,
878
+ "loss": 1.9488,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.6,
883
+ "learning_rate": 0.00012198162564362771,
884
+ "loss": 2.0998,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.6,
889
+ "learning_rate": 0.00012159638425138327,
890
+ "loss": 1.8385,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.61,
895
+ "learning_rate": 0.00012120913008702508,
896
+ "loss": 1.9502,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.61,
901
+ "learning_rate": 0.00012081987987833996,
902
+ "loss": 1.9521,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.61,
907
+ "learning_rate": 0.00012042865043933565,
908
+ "loss": 2.01,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.62,
913
+ "learning_rate": 0.00012003545866951448,
914
+ "loss": 1.945,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.62,
919
+ "learning_rate": 0.00011964032155314345,
920
+ "loss": 1.9757,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.63,
925
+ "learning_rate": 0.00011924325615852046,
926
+ "loss": 1.9674,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.63,
931
+ "learning_rate": 0.00011884427963723716,
932
+ "loss": 1.938,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.63,
937
+ "learning_rate": 0.00011844340922343792,
938
+ "loss": 2.0233,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.64,
943
+ "learning_rate": 0.0001180406622330756,
944
+ "loss": 2.0303,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.64,
949
+ "learning_rate": 0.00011763605606316337,
950
+ "loss": 1.9139,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.65,
955
+ "learning_rate": 0.0001172296081910233,
956
+ "loss": 1.8695,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.65,
961
+ "learning_rate": 0.00011682133617353145,
962
+ "loss": 1.9399,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.65,
967
+ "learning_rate": 0.00011641125764635947,
968
+ "loss": 1.9003,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.66,
973
+ "learning_rate": 0.00011599939032321271,
974
+ "loss": 1.9971,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.66,
979
+ "learning_rate": 0.00011558575199506527,
980
+ "loss": 2.0124,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.67,
985
+ "learning_rate": 0.00011517036052939132,
986
+ "loss": 1.9316,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.67,
991
+ "learning_rate": 0.00011475323386939331,
992
+ "loss": 2.0054,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.67,
997
+ "learning_rate": 0.00011433439003322706,
998
+ "loss": 1.7991,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.68,
1003
+ "learning_rate": 0.00011391384711322323,
1004
+ "loss": 1.9603,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.68,
1009
+ "learning_rate": 0.00011349162327510597,
1010
+ "loss": 1.8788,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.69,
1015
+ "learning_rate": 0.00011306773675720816,
1016
+ "loss": 1.8611,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.69,
1021
+ "learning_rate": 0.00011264220586968362,
1022
+ "loss": 2.0317,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.69,
1027
+ "learning_rate": 0.00011221504899371616,
1028
+ "loss": 1.8378,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.7,
1033
+ "learning_rate": 0.00011178628458072557,
1034
+ "loss": 1.9995,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.7,
1039
+ "learning_rate": 0.00011135593115157072,
1040
+ "loss": 1.8996,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.71,
1045
+ "learning_rate": 0.00011092400729574934,
1046
+ "loss": 1.8958,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.71,
1051
+ "learning_rate": 0.00011049053167059518,
1052
+ "loss": 2.0009,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.72,
1057
+ "learning_rate": 0.00011005552300047206,
1058
+ "loss": 1.9154,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.72,
1063
+ "learning_rate": 0.00010961900007596499,
1064
+ "loss": 1.9606,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.72,
1069
+ "learning_rate": 0.00010918098175306857,
1070
+ "loss": 1.8051,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.73,
1075
+ "learning_rate": 0.00010874148695237245,
1076
+ "loss": 1.9606,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.73,
1081
+ "learning_rate": 0.00010830053465824405,
1082
+ "loss": 2.0241,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.74,
1087
+ "learning_rate": 0.0001078581439180085,
1088
+ "loss": 1.8999,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.74,
1093
+ "learning_rate": 0.0001074143338411259,
1094
+ "loss": 1.8892,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.74,
1099
+ "learning_rate": 0.00010696912359836585,
1100
+ "loss": 1.9695,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.75,
1105
+ "learning_rate": 0.00010652253242097937,
1106
+ "loss": 1.9828,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.75,
1111
+ "learning_rate": 0.00010607457959986809,
1112
+ "loss": 1.899,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.76,
1117
+ "learning_rate": 0.0001056252844847512,
1118
+ "loss": 2.0682,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.76,
1123
+ "learning_rate": 0.00010517466648332935,
1124
+ "loss": 1.8665,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.76,
1129
+ "learning_rate": 0.00010472274506044646,
1130
+ "loss": 1.9554,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.77,
1135
+ "learning_rate": 0.00010426953973724894,
1136
+ "loss": 2.0293,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.77,
1141
+ "learning_rate": 0.00010381507009034231,
1142
+ "loss": 1.9689,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.78,
1147
+ "learning_rate": 0.00010335935575094584,
1148
+ "loss": 1.9393,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.78,
1153
+ "learning_rate": 0.0001029024164040442,
1154
+ "loss": 1.8898,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.78,
1159
+ "learning_rate": 0.00010244427178753751,
1160
+ "loss": 1.9101,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.79,
1165
+ "learning_rate": 0.00010198494169138847,
1166
+ "loss": 2.0164,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.79,
1171
+ "learning_rate": 0.0001015244459567677,
1172
+ "loss": 1.8392,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.8,
1177
+ "learning_rate": 0.00010106280447519656,
1178
+ "loss": 1.9871,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.8,
1183
+ "learning_rate": 0.00010060003718768793,
1184
+ "loss": 1.9528,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.81,
1189
+ "learning_rate": 0.000100136164083885,
1190
+ "loss": 2.0022,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.81,
1195
+ "learning_rate": 9.967120520119751e-05,
1196
+ "loss": 2.0728,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.81,
1201
+ "learning_rate": 9.920518062393657e-05,
1202
+ "loss": 1.9121,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.82,
1207
+ "learning_rate": 9.873811048244671e-05,
1208
+ "loss": 1.8309,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.82,
1213
+ "learning_rate": 9.82700149522367e-05,
1214
+ "loss": 1.8731,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.83,
1219
+ "learning_rate": 9.780091425310777e-05,
1220
+ "loss": 1.9089,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.83,
1225
+ "learning_rate": 9.733082864828036e-05,
1226
+ "loss": 1.8871,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.83,
1231
+ "learning_rate": 9.685977844351884e-05,
1232
+ "loss": 1.932,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.84,
1237
+ "learning_rate": 9.638778398625421e-05,
1238
+ "loss": 1.8818,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.84,
1243
+ "learning_rate": 9.59148656647054e-05,
1244
+ "loss": 2.0086,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.85,
1249
+ "learning_rate": 9.54410439069984e-05,
1250
+ "loss": 1.9073,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.85,
1255
+ "learning_rate": 9.496633918028397e-05,
1256
+ "loss": 1.868,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.85,
1261
+ "learning_rate": 9.44907719898535e-05,
1262
+ "loss": 1.9662,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.86,
1267
+ "learning_rate": 9.401436287825326e-05,
1268
+ "loss": 1.8944,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.86,
1273
+ "learning_rate": 9.3537132424397e-05,
1274
+ "loss": 1.9545,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.87,
1279
+ "learning_rate": 9.305910124267716e-05,
1280
+ "loss": 2.0606,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.87,
1285
+ "learning_rate": 9.258028998207425e-05,
1286
+ "loss": 1.9157,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.87,
1291
+ "learning_rate": 9.210071932526506e-05,
1292
+ "loss": 1.965,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.88,
1297
+ "learning_rate": 9.162040998772913e-05,
1298
+ "loss": 1.9563,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.88,
1303
+ "learning_rate": 9.113938271685392e-05,
1304
+ "loss": 1.8179,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.89,
1309
+ "learning_rate": 9.065765829103874e-05,
1310
+ "loss": 1.9514,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.89,
1315
+ "learning_rate": 9.01752575187971e-05,
1316
+ "loss": 1.9616,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.9,
1321
+ "learning_rate": 8.969220123785786e-05,
1322
+ "loss": 1.9105,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.9,
1327
+ "learning_rate": 8.920851031426521e-05,
1328
+ "loss": 1.9349,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.9,
1333
+ "learning_rate": 8.872420564147722e-05,
1334
+ "loss": 1.902,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.91,
1339
+ "learning_rate": 8.823930813946351e-05,
1340
+ "loss": 2.0122,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.91,
1345
+ "learning_rate": 8.775383875380138e-05,
1346
+ "loss": 1.9486,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.92,
1351
+ "learning_rate": 8.72678184547712e-05,
1352
+ "loss": 1.9728,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.92,
1357
+ "learning_rate": 8.678126823645052e-05,
1358
+ "loss": 1.919,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.92,
1363
+ "learning_rate": 8.62942091158072e-05,
1364
+ "loss": 1.8079,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.93,
1369
+ "learning_rate": 8.580666213179165e-05,
1370
+ "loss": 1.9733,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.93,
1375
+ "learning_rate": 8.531864834442792e-05,
1376
+ "loss": 1.9641,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.94,
1381
+ "learning_rate": 8.483018883390405e-05,
1382
+ "loss": 2.0346,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.94,
1387
+ "learning_rate": 8.434130469966152e-05,
1388
+ "loss": 1.919,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.94,
1393
+ "learning_rate": 8.385201705948375e-05,
1394
+ "loss": 1.9831,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.95,
1399
+ "learning_rate": 8.336234704858398e-05,
1400
+ "loss": 2.0287,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.95,
1405
+ "learning_rate": 8.287231581869235e-05,
1406
+ "loss": 2.0557,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.96,
1411
+ "learning_rate": 8.238194453714209e-05,
1412
+ "loss": 1.8527,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.96,
1417
+ "learning_rate": 8.189125438595531e-05,
1418
+ "loss": 1.8578,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.96,
1423
+ "learning_rate": 8.140026656092794e-05,
1424
+ "loss": 1.9493,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.97,
1429
+ "learning_rate": 8.090900227071425e-05,
1430
+ "loss": 1.9758,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.97,
1435
+ "learning_rate": 8.04174827359106e-05,
1436
+ "loss": 2.0026,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.98,
1441
+ "learning_rate": 7.992572918813897e-05,
1442
+ "loss": 1.9079,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.98,
1447
+ "learning_rate": 7.943376286912961e-05,
1448
+ "loss": 2.0169,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.99,
1453
+ "learning_rate": 7.894160502980368e-05,
1454
+ "loss": 1.937,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.99,
1459
+ "learning_rate": 7.844927692935528e-05,
1460
+ "loss": 1.912,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.99,
1465
+ "learning_rate": 7.795679983433301e-05,
1466
+ "loss": 1.9314,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 1.0,
1471
+ "learning_rate": 7.74641950177214e-05,
1472
+ "loss": 1.8367,
1473
+ "step": 244
1474
+ }
1475
+ ],
1476
+ "logging_steps": 1,
1477
+ "max_steps": 488,
1478
+ "num_input_tokens_seen": 0,
1479
+ "num_train_epochs": 2,
1480
+ "save_steps": 244,
1481
+ "total_flos": 3.2149768164228465e+18,
1482
+ "train_batch_size": 1,
1483
+ "trial_name": null,
1484
+ "trial_params": null
1485
+ }
checkpoint-244/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7737b8e53a766bba3c736ef45d76502045c9f827e3bd654da1f074b4c957e0b7
3
+ size 4795
checkpoint-488/README.md ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: ./models/deepseek-llm-67b-base
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-488/adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./models/deepseek-llm-67b-base",
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
+ "down_proj",
20
+ "k_proj",
21
+ "q_proj",
22
+ "v_proj",
23
+ "up_proj",
24
+ "o_proj",
25
+ "gate_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
checkpoint-488/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0feee7ceedf48a7611e58b282369848ae96625a6aed5f3be661c6eb70f73dbf7
3
+ size 1724761096
checkpoint-488/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f43b30d024811a95742b29cbae5dee6bcea56f43a68bedf20fa60ab514a808c2
3
+ size 865515047
checkpoint-488/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:460c8028189ba3a7c0133963c4ca4a48f04ec0c5abac7c936a234225acf28a58
3
+ size 14575
checkpoint-488/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f33d15f84f6f7fbab10a9cdfabc41d672685d1f74a7fac777c1132ac237760f8
3
+ size 627
checkpoint-488/trainer_state.json ADDED
@@ -0,0 +1,2949 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9764946346448646,
5
+ "eval_steps": 500,
6
+ "global_step": 488,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 1.4999999999999999e-05,
14
+ "loss": 2.0754,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 2.9999999999999997e-05,
20
+ "loss": 2.1342,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 4.4999999999999996e-05,
26
+ "loss": 2.1035,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 5.9999999999999995e-05,
32
+ "loss": 2.09,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 7.5e-05,
38
+ "loss": 2.0643,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 8.999999999999999e-05,
44
+ "loss": 2.124,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "learning_rate": 0.00010499999999999999,
50
+ "loss": 2.1867,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "learning_rate": 0.00011999999999999999,
56
+ "loss": 2.175,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.04,
61
+ "learning_rate": 0.000135,
62
+ "loss": 2.0837,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.04,
67
+ "learning_rate": 0.00015,
68
+ "loss": 2.0431,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.04,
73
+ "learning_rate": 0.00014999838015426563,
74
+ "loss": 2.0665,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.05,
79
+ "learning_rate": 0.00014999352068703324,
80
+ "loss": 2.0668,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.05,
85
+ "learning_rate": 0.0001499854218082118,
86
+ "loss": 2.1312,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.06,
91
+ "learning_rate": 0.00014997408386763957,
92
+ "loss": 2.0758,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.06,
97
+ "learning_rate": 0.00014995950735506895,
98
+ "loss": 2.1173,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.07,
103
+ "learning_rate": 0.00014994169290014528,
104
+ "loss": 2.0044,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.07,
109
+ "learning_rate": 0.00014992064127237976,
110
+ "loss": 2.0054,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.07,
115
+ "learning_rate": 0.00014989635338111612,
116
+ "loss": 2.0509,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.08,
121
+ "learning_rate": 0.0001498688302754913,
122
+ "loss": 2.1071,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.08,
127
+ "learning_rate": 0.0001498380731443903,
128
+ "loss": 1.9549,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.09,
133
+ "learning_rate": 0.00014980408331639463,
134
+ "loss": 1.895,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.09,
139
+ "learning_rate": 0.000149766862259725,
140
+ "loss": 1.9979,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.09,
145
+ "learning_rate": 0.000149726411582178,
146
+ "loss": 2.0151,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.1,
151
+ "learning_rate": 0.00014968273303105645,
152
+ "loss": 1.9236,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.1,
157
+ "learning_rate": 0.0001496358284930941,
158
+ "loss": 1.9613,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.11,
163
+ "learning_rate": 0.00014958569999437403,
164
+ "loss": 1.9975,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.11,
169
+ "learning_rate": 0.00014953234970024114,
170
+ "loss": 1.9804,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.11,
175
+ "learning_rate": 0.00014947577991520874,
176
+ "loss": 1.9211,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.12,
181
+ "learning_rate": 0.00014941599308285872,
182
+ "loss": 2.0278,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.12,
187
+ "learning_rate": 0.0001493529917857364,
188
+ "loss": 1.9682,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.13,
193
+ "learning_rate": 0.0001492867787452386,
194
+ "loss": 1.8728,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.13,
199
+ "learning_rate": 0.00014921735682149628,
200
+ "loss": 2.0241,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.13,
205
+ "learning_rate": 0.00014914472901325095,
206
+ "loss": 1.9737,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.14,
211
+ "learning_rate": 0.00014906889845772516,
212
+ "loss": 1.9329,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.14,
217
+ "learning_rate": 0.00014898986843048698,
218
+ "loss": 1.9861,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.15,
223
+ "learning_rate": 0.00014890764234530847,
224
+ "loss": 1.8872,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.15,
229
+ "learning_rate": 0.00014882222375401822,
230
+ "loss": 1.9282,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.16,
235
+ "learning_rate": 0.00014873361634634805,
236
+ "loss": 2.0487,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.16,
241
+ "learning_rate": 0.00014864182394977337,
242
+ "loss": 1.9907,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.16,
247
+ "learning_rate": 0.0001485468505293482,
248
+ "loss": 2.0665,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.17,
253
+ "learning_rate": 0.00014844870018753355,
254
+ "loss": 2.0757,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.17,
259
+ "learning_rate": 0.00014834737716402043,
260
+ "loss": 1.9599,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.18,
265
+ "learning_rate": 0.0001482428858355466,
266
+ "loss": 1.9655,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.18,
271
+ "learning_rate": 0.0001481352307157077,
272
+ "loss": 1.9234,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.18,
277
+ "learning_rate": 0.00014802441645476192,
278
+ "loss": 2.0089,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.19,
283
+ "learning_rate": 0.00014791044783942956,
284
+ "loss": 1.94,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.19,
289
+ "learning_rate": 0.0001477933297926859,
290
+ "loss": 1.9925,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.2,
295
+ "learning_rate": 0.00014767306737354885,
296
+ "loss": 1.9783,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.2,
301
+ "learning_rate": 0.00014754966577686007,
302
+ "loss": 1.97,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.2,
307
+ "learning_rate": 0.000147423130333061,
308
+ "loss": 1.9398,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.21,
313
+ "learning_rate": 0.00014729346650796223,
314
+ "loss": 1.963,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.21,
319
+ "learning_rate": 0.00014716067990250758,
320
+ "loss": 1.9428,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.22,
325
+ "learning_rate": 0.0001470247762525322,
326
+ "loss": 1.8047,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.22,
331
+ "learning_rate": 0.00014688576142851467,
332
+ "loss": 1.9507,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.22,
337
+ "learning_rate": 0.00014674364143532352,
338
+ "loss": 1.9653,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.23,
343
+ "learning_rate": 0.0001465984224119578,
344
+ "loss": 1.9433,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.23,
349
+ "learning_rate": 0.00014645011063128192,
350
+ "loss": 1.9655,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.24,
355
+ "learning_rate": 0.0001462987124997547,
356
+ "loss": 2.0388,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.24,
361
+ "learning_rate": 0.00014614423455715263,
362
+ "loss": 1.8811,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.25,
367
+ "learning_rate": 0.00014598668347628733,
368
+ "loss": 1.956,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.25,
373
+ "learning_rate": 0.00014582606606271736,
374
+ "loss": 1.9236,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.25,
379
+ "learning_rate": 0.0001456623892544542,
380
+ "loss": 1.9662,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.26,
385
+ "learning_rate": 0.00014549566012166275,
386
+ "loss": 1.9648,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.26,
391
+ "learning_rate": 0.00014532588586635558,
392
+ "loss": 1.913,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.27,
397
+ "learning_rate": 0.00014515307382208215,
398
+ "loss": 2.0282,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.27,
403
+ "learning_rate": 0.00014497723145361183,
404
+ "loss": 2.0331,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.27,
409
+ "learning_rate": 0.0001447983663566116,
410
+ "loss": 2.1089,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.28,
415
+ "learning_rate": 0.00014461648625731783,
416
+ "loss": 2.0694,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.28,
421
+ "learning_rate": 0.00014443159901220262,
422
+ "loss": 1.9098,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.29,
427
+ "learning_rate": 0.0001442437126076343,
428
+ "loss": 1.8582,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.29,
433
+ "learning_rate": 0.00014405283515953277,
434
+ "loss": 1.8942,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.29,
439
+ "learning_rate": 0.00014385897491301844,
440
+ "loss": 1.9396,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.3,
445
+ "learning_rate": 0.00014366214024205654,
446
+ "loss": 1.9624,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.3,
451
+ "learning_rate": 0.00014346233964909508,
452
+ "loss": 1.9123,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.31,
457
+ "learning_rate": 0.00014325958176469777,
458
+ "loss": 1.9146,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.31,
463
+ "learning_rate": 0.0001430538753471711,
464
+ "loss": 1.9646,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.31,
469
+ "learning_rate": 0.00014284522928218612,
470
+ "loss": 1.8241,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.32,
475
+ "learning_rate": 0.0001426336525823945,
476
+ "loss": 1.968,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.32,
481
+ "learning_rate": 0.00014241915438703928,
482
+ "loss": 1.8584,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.33,
487
+ "learning_rate": 0.00014220174396156014,
488
+ "loss": 1.9979,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.33,
493
+ "learning_rate": 0.00014198143069719306,
494
+ "loss": 1.9972,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.34,
499
+ "learning_rate": 0.00014175822411056476,
500
+ "loss": 1.8241,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.34,
505
+ "learning_rate": 0.00014153213384328158,
506
+ "loss": 1.9249,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.34,
511
+ "learning_rate": 0.00014130316966151296,
512
+ "loss": 2.076,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.35,
517
+ "learning_rate": 0.00014107134145556968,
518
+ "loss": 1.9242,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.35,
523
+ "learning_rate": 0.00014083665923947652,
524
+ "loss": 1.9075,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.36,
529
+ "learning_rate": 0.0001405991331505398,
530
+ "loss": 1.9701,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.36,
535
+ "learning_rate": 0.00014035877344890945,
536
+ "loss": 1.9521,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.36,
541
+ "learning_rate": 0.0001401155905171358,
542
+ "loss": 1.9354,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.37,
547
+ "learning_rate": 0.00013986959485972112,
548
+ "loss": 2.0025,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.37,
553
+ "learning_rate": 0.0001396207971026658,
554
+ "loss": 1.9459,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.38,
559
+ "learning_rate": 0.0001393692079930095,
560
+ "loss": 1.9798,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.38,
565
+ "learning_rate": 0.00013911483839836676,
566
+ "loss": 1.8871,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.38,
571
+ "learning_rate": 0.00013885769930645767,
572
+ "loss": 1.9457,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.39,
577
+ "learning_rate": 0.0001385978018246332,
578
+ "loss": 1.9094,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.39,
583
+ "learning_rate": 0.00013833515717939538,
584
+ "loss": 1.9651,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.4,
589
+ "learning_rate": 0.00013806977671591245,
590
+ "loss": 2.0097,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.4,
595
+ "learning_rate": 0.00013780167189752872,
596
+ "loss": 1.9944,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.4,
601
+ "learning_rate": 0.00013753085430526945,
602
+ "loss": 1.8378,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.41,
607
+ "learning_rate": 0.0001372573356373405,
608
+ "loss": 1.9796,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.41,
613
+ "learning_rate": 0.00013698112770862319,
614
+ "loss": 1.8866,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.42,
619
+ "learning_rate": 0.00013670224245016375,
620
+ "loss": 2.0077,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.42,
625
+ "learning_rate": 0.00013642069190865808,
626
+ "loss": 1.8807,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.43,
631
+ "learning_rate": 0.00013613648824593137,
632
+ "loss": 2.0118,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.43,
637
+ "learning_rate": 0.0001358496437384127,
638
+ "loss": 1.9495,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.43,
643
+ "learning_rate": 0.0001355601707766048,
644
+ "loss": 1.927,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.44,
649
+ "learning_rate": 0.0001352680818645488,
650
+ "loss": 1.9418,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.44,
655
+ "learning_rate": 0.00013497338961928406,
656
+ "loss": 1.9557,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.45,
661
+ "learning_rate": 0.00013467610677030337,
662
+ "loss": 1.9239,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.45,
667
+ "learning_rate": 0.0001343762461590028,
668
+ "loss": 2.0298,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.45,
673
+ "learning_rate": 0.00013407382073812724,
674
+ "loss": 1.9778,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.46,
679
+ "learning_rate": 0.00013376884357121075,
680
+ "loss": 1.8697,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.46,
685
+ "learning_rate": 0.00013346132783201233,
686
+ "loss": 1.8659,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.47,
691
+ "learning_rate": 0.0001331512868039469,
692
+ "loss": 1.9608,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.47,
697
+ "learning_rate": 0.00013283873387951142,
698
+ "loss": 1.9881,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.47,
703
+ "learning_rate": 0.0001325236825597065,
704
+ "loss": 1.8963,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.48,
709
+ "learning_rate": 0.00013220614645345304,
710
+ "loss": 1.9821,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.48,
715
+ "learning_rate": 0.00013188613927700462,
716
+ "loss": 1.8786,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.49,
721
+ "learning_rate": 0.00013156367485335483,
722
+ "loss": 1.9391,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.49,
727
+ "learning_rate": 0.0001312387671116402,
728
+ "loss": 1.8749,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.49,
733
+ "learning_rate": 0.00013091143008653864,
734
+ "loss": 1.9711,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.5,
739
+ "learning_rate": 0.000130581677917663,
740
+ "loss": 1.9973,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.5,
745
+ "learning_rate": 0.00013024952484895047,
746
+ "loss": 1.9736,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.51,
751
+ "learning_rate": 0.00012991498522804725,
752
+ "loss": 1.9482,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.51,
757
+ "learning_rate": 0.0001295780735056887,
758
+ "loss": 1.8969,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.52,
763
+ "learning_rate": 0.0001292388042350753,
764
+ "loss": 1.8856,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.52,
769
+ "learning_rate": 0.00012889719207124386,
770
+ "loss": 1.896,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.52,
775
+ "learning_rate": 0.00012855325177043455,
776
+ "loss": 1.9585,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.53,
781
+ "learning_rate": 0.00012820699818945344,
782
+ "loss": 2.0194,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.53,
787
+ "learning_rate": 0.00012785844628503088,
788
+ "loss": 2.0445,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.54,
793
+ "learning_rate": 0.00012750761111317527,
794
+ "loss": 1.9695,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.54,
799
+ "learning_rate": 0.00012715450782852281,
800
+ "loss": 1.9849,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.54,
805
+ "learning_rate": 0.00012679915168368276,
806
+ "loss": 1.9426,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.55,
811
+ "learning_rate": 0.00012644155802857878,
812
+ "loss": 1.8934,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.55,
817
+ "learning_rate": 0.00012608174230978572,
818
+ "loss": 1.9616,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.56,
823
+ "learning_rate": 0.00012571972006986237,
824
+ "loss": 1.926,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.56,
829
+ "learning_rate": 0.00012535550694668034,
830
+ "loss": 1.9333,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.56,
835
+ "learning_rate": 0.00012498911867274816,
836
+ "loss": 1.953,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.57,
841
+ "learning_rate": 0.0001246205710745321,
842
+ "loss": 1.9753,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.57,
847
+ "learning_rate": 0.0001242498800717723,
848
+ "loss": 1.8901,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.58,
853
+ "learning_rate": 0.00012387706167679507,
854
+ "loss": 1.8817,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.58,
859
+ "learning_rate": 0.00012350213199382147,
860
+ "loss": 1.939,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.58,
865
+ "learning_rate": 0.0001231251072182714,
866
+ "loss": 1.9321,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.59,
871
+ "learning_rate": 0.00012274600363606418,
872
+ "loss": 2.0088,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.59,
877
+ "learning_rate": 0.00012236483762291504,
878
+ "loss": 1.9488,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.6,
883
+ "learning_rate": 0.00012198162564362771,
884
+ "loss": 2.0998,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.6,
889
+ "learning_rate": 0.00012159638425138327,
890
+ "loss": 1.8385,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.61,
895
+ "learning_rate": 0.00012120913008702508,
896
+ "loss": 1.9502,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.61,
901
+ "learning_rate": 0.00012081987987833996,
902
+ "loss": 1.9521,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.61,
907
+ "learning_rate": 0.00012042865043933565,
908
+ "loss": 2.01,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.62,
913
+ "learning_rate": 0.00012003545866951448,
914
+ "loss": 1.945,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.62,
919
+ "learning_rate": 0.00011964032155314345,
920
+ "loss": 1.9757,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.63,
925
+ "learning_rate": 0.00011924325615852046,
926
+ "loss": 1.9674,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.63,
931
+ "learning_rate": 0.00011884427963723716,
932
+ "loss": 1.938,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.63,
937
+ "learning_rate": 0.00011844340922343792,
938
+ "loss": 2.0233,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.64,
943
+ "learning_rate": 0.0001180406622330756,
944
+ "loss": 2.0303,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.64,
949
+ "learning_rate": 0.00011763605606316337,
950
+ "loss": 1.9139,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.65,
955
+ "learning_rate": 0.0001172296081910233,
956
+ "loss": 1.8695,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.65,
961
+ "learning_rate": 0.00011682133617353145,
962
+ "loss": 1.9399,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.65,
967
+ "learning_rate": 0.00011641125764635947,
968
+ "loss": 1.9003,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.66,
973
+ "learning_rate": 0.00011599939032321271,
974
+ "loss": 1.9971,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.66,
979
+ "learning_rate": 0.00011558575199506527,
980
+ "loss": 2.0124,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.67,
985
+ "learning_rate": 0.00011517036052939132,
986
+ "loss": 1.9316,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.67,
991
+ "learning_rate": 0.00011475323386939331,
992
+ "loss": 2.0054,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.67,
997
+ "learning_rate": 0.00011433439003322706,
998
+ "loss": 1.7991,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.68,
1003
+ "learning_rate": 0.00011391384711322323,
1004
+ "loss": 1.9603,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.68,
1009
+ "learning_rate": 0.00011349162327510597,
1010
+ "loss": 1.8788,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.69,
1015
+ "learning_rate": 0.00011306773675720816,
1016
+ "loss": 1.8611,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.69,
1021
+ "learning_rate": 0.00011264220586968362,
1022
+ "loss": 2.0317,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.69,
1027
+ "learning_rate": 0.00011221504899371616,
1028
+ "loss": 1.8378,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.7,
1033
+ "learning_rate": 0.00011178628458072557,
1034
+ "loss": 1.9995,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.7,
1039
+ "learning_rate": 0.00011135593115157072,
1040
+ "loss": 1.8996,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.71,
1045
+ "learning_rate": 0.00011092400729574934,
1046
+ "loss": 1.8958,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.71,
1051
+ "learning_rate": 0.00011049053167059518,
1052
+ "loss": 2.0009,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.72,
1057
+ "learning_rate": 0.00011005552300047206,
1058
+ "loss": 1.9154,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.72,
1063
+ "learning_rate": 0.00010961900007596499,
1064
+ "loss": 1.9606,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.72,
1069
+ "learning_rate": 0.00010918098175306857,
1070
+ "loss": 1.8051,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.73,
1075
+ "learning_rate": 0.00010874148695237245,
1076
+ "loss": 1.9606,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.73,
1081
+ "learning_rate": 0.00010830053465824405,
1082
+ "loss": 2.0241,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.74,
1087
+ "learning_rate": 0.0001078581439180085,
1088
+ "loss": 1.8999,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.74,
1093
+ "learning_rate": 0.0001074143338411259,
1094
+ "loss": 1.8892,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.74,
1099
+ "learning_rate": 0.00010696912359836585,
1100
+ "loss": 1.9695,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.75,
1105
+ "learning_rate": 0.00010652253242097937,
1106
+ "loss": 1.9828,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.75,
1111
+ "learning_rate": 0.00010607457959986809,
1112
+ "loss": 1.899,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.76,
1117
+ "learning_rate": 0.0001056252844847512,
1118
+ "loss": 2.0682,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.76,
1123
+ "learning_rate": 0.00010517466648332935,
1124
+ "loss": 1.8665,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.76,
1129
+ "learning_rate": 0.00010472274506044646,
1130
+ "loss": 1.9554,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.77,
1135
+ "learning_rate": 0.00010426953973724894,
1136
+ "loss": 2.0293,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.77,
1141
+ "learning_rate": 0.00010381507009034231,
1142
+ "loss": 1.9689,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.78,
1147
+ "learning_rate": 0.00010335935575094584,
1148
+ "loss": 1.9393,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.78,
1153
+ "learning_rate": 0.0001029024164040442,
1154
+ "loss": 1.8898,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.78,
1159
+ "learning_rate": 0.00010244427178753751,
1160
+ "loss": 1.9101,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.79,
1165
+ "learning_rate": 0.00010198494169138847,
1166
+ "loss": 2.0164,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.79,
1171
+ "learning_rate": 0.0001015244459567677,
1172
+ "loss": 1.8392,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.8,
1177
+ "learning_rate": 0.00010106280447519656,
1178
+ "loss": 1.9871,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.8,
1183
+ "learning_rate": 0.00010060003718768793,
1184
+ "loss": 1.9528,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.81,
1189
+ "learning_rate": 0.000100136164083885,
1190
+ "loss": 2.0022,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.81,
1195
+ "learning_rate": 9.967120520119751e-05,
1196
+ "loss": 2.0728,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.81,
1201
+ "learning_rate": 9.920518062393657e-05,
1202
+ "loss": 1.9121,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.82,
1207
+ "learning_rate": 9.873811048244671e-05,
1208
+ "loss": 1.8309,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.82,
1213
+ "learning_rate": 9.82700149522367e-05,
1214
+ "loss": 1.8731,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.83,
1219
+ "learning_rate": 9.780091425310777e-05,
1220
+ "loss": 1.9089,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.83,
1225
+ "learning_rate": 9.733082864828036e-05,
1226
+ "loss": 1.8871,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.83,
1231
+ "learning_rate": 9.685977844351884e-05,
1232
+ "loss": 1.932,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.84,
1237
+ "learning_rate": 9.638778398625421e-05,
1238
+ "loss": 1.8818,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.84,
1243
+ "learning_rate": 9.59148656647054e-05,
1244
+ "loss": 2.0086,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.85,
1249
+ "learning_rate": 9.54410439069984e-05,
1250
+ "loss": 1.9073,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.85,
1255
+ "learning_rate": 9.496633918028397e-05,
1256
+ "loss": 1.868,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.85,
1261
+ "learning_rate": 9.44907719898535e-05,
1262
+ "loss": 1.9662,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.86,
1267
+ "learning_rate": 9.401436287825326e-05,
1268
+ "loss": 1.8944,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.86,
1273
+ "learning_rate": 9.3537132424397e-05,
1274
+ "loss": 1.9545,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.87,
1279
+ "learning_rate": 9.305910124267716e-05,
1280
+ "loss": 2.0606,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.87,
1285
+ "learning_rate": 9.258028998207425e-05,
1286
+ "loss": 1.9157,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.87,
1291
+ "learning_rate": 9.210071932526506e-05,
1292
+ "loss": 1.965,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.88,
1297
+ "learning_rate": 9.162040998772913e-05,
1298
+ "loss": 1.9563,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.88,
1303
+ "learning_rate": 9.113938271685392e-05,
1304
+ "loss": 1.8179,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.89,
1309
+ "learning_rate": 9.065765829103874e-05,
1310
+ "loss": 1.9514,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.89,
1315
+ "learning_rate": 9.01752575187971e-05,
1316
+ "loss": 1.9616,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.9,
1321
+ "learning_rate": 8.969220123785786e-05,
1322
+ "loss": 1.9105,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.9,
1327
+ "learning_rate": 8.920851031426521e-05,
1328
+ "loss": 1.9349,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.9,
1333
+ "learning_rate": 8.872420564147722e-05,
1334
+ "loss": 1.902,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.91,
1339
+ "learning_rate": 8.823930813946351e-05,
1340
+ "loss": 2.0122,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.91,
1345
+ "learning_rate": 8.775383875380138e-05,
1346
+ "loss": 1.9486,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.92,
1351
+ "learning_rate": 8.72678184547712e-05,
1352
+ "loss": 1.9728,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.92,
1357
+ "learning_rate": 8.678126823645052e-05,
1358
+ "loss": 1.919,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.92,
1363
+ "learning_rate": 8.62942091158072e-05,
1364
+ "loss": 1.8079,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.93,
1369
+ "learning_rate": 8.580666213179165e-05,
1370
+ "loss": 1.9733,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.93,
1375
+ "learning_rate": 8.531864834442792e-05,
1376
+ "loss": 1.9641,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.94,
1381
+ "learning_rate": 8.483018883390405e-05,
1382
+ "loss": 2.0346,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.94,
1387
+ "learning_rate": 8.434130469966152e-05,
1388
+ "loss": 1.919,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.94,
1393
+ "learning_rate": 8.385201705948375e-05,
1394
+ "loss": 1.9831,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.95,
1399
+ "learning_rate": 8.336234704858398e-05,
1400
+ "loss": 2.0287,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.95,
1405
+ "learning_rate": 8.287231581869235e-05,
1406
+ "loss": 2.0557,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.96,
1411
+ "learning_rate": 8.238194453714209e-05,
1412
+ "loss": 1.8527,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.96,
1417
+ "learning_rate": 8.189125438595531e-05,
1418
+ "loss": 1.8578,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.96,
1423
+ "learning_rate": 8.140026656092794e-05,
1424
+ "loss": 1.9493,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.97,
1429
+ "learning_rate": 8.090900227071425e-05,
1430
+ "loss": 1.9758,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.97,
1435
+ "learning_rate": 8.04174827359106e-05,
1436
+ "loss": 2.0026,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.98,
1441
+ "learning_rate": 7.992572918813897e-05,
1442
+ "loss": 1.9079,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.98,
1447
+ "learning_rate": 7.943376286912961e-05,
1448
+ "loss": 2.0169,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.99,
1453
+ "learning_rate": 7.894160502980368e-05,
1454
+ "loss": 1.937,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.99,
1459
+ "learning_rate": 7.844927692935528e-05,
1460
+ "loss": 1.912,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.99,
1465
+ "learning_rate": 7.795679983433301e-05,
1466
+ "loss": 1.9314,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 1.0,
1471
+ "learning_rate": 7.74641950177214e-05,
1472
+ "loss": 1.8367,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 1.0,
1477
+ "learning_rate": 7.697148375802212e-05,
1478
+ "loss": 1.912,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 1.01,
1483
+ "learning_rate": 7.647868733833467e-05,
1484
+ "loss": 2.0636,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 1.01,
1489
+ "learning_rate": 7.598582704543717e-05,
1490
+ "loss": 1.9104,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 1.01,
1495
+ "learning_rate": 7.549292416886673e-05,
1496
+ "loss": 1.8903,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 1.02,
1501
+ "learning_rate": 7.5e-05,
1502
+ "loss": 1.9534,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 1.0,
1507
+ "learning_rate": 7.450707583113325e-05,
1508
+ "loss": 1.9373,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 1.01,
1513
+ "learning_rate": 7.401417295456285e-05,
1514
+ "loss": 1.8636,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 1.01,
1519
+ "learning_rate": 7.35213126616653e-05,
1520
+ "loss": 1.8003,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 1.02,
1525
+ "learning_rate": 7.302851624197787e-05,
1526
+ "loss": 1.8422,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 1.02,
1531
+ "learning_rate": 7.25358049822786e-05,
1532
+ "loss": 1.9057,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 1.02,
1537
+ "learning_rate": 7.2043200165667e-05,
1538
+ "loss": 1.924,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 1.03,
1543
+ "learning_rate": 7.15507230706447e-05,
1544
+ "loss": 1.9789,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 1.03,
1549
+ "learning_rate": 7.105839497019628e-05,
1550
+ "loss": 1.8767,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 1.04,
1555
+ "learning_rate": 7.056623713087037e-05,
1556
+ "loss": 1.9575,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 1.04,
1561
+ "learning_rate": 7.007427081186103e-05,
1562
+ "loss": 1.9154,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 1.04,
1567
+ "learning_rate": 6.958251726408939e-05,
1568
+ "loss": 1.8504,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 1.05,
1573
+ "learning_rate": 6.909099772928576e-05,
1574
+ "loss": 1.9366,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 1.05,
1579
+ "learning_rate": 6.859973343907205e-05,
1580
+ "loss": 1.9566,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 1.06,
1585
+ "learning_rate": 6.810874561404469e-05,
1586
+ "loss": 1.9788,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 1.06,
1591
+ "learning_rate": 6.76180554628579e-05,
1592
+ "loss": 1.8333,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 1.06,
1597
+ "learning_rate": 6.712768418130765e-05,
1598
+ "loss": 1.8818,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 1.07,
1603
+ "learning_rate": 6.6637652951416e-05,
1604
+ "loss": 1.9251,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 1.07,
1609
+ "learning_rate": 6.614798294051624e-05,
1610
+ "loss": 1.8458,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 1.08,
1615
+ "learning_rate": 6.565869530033848e-05,
1616
+ "loss": 1.824,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 1.08,
1621
+ "learning_rate": 6.516981116609593e-05,
1622
+ "loss": 1.9948,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 1.09,
1627
+ "learning_rate": 6.468135165557208e-05,
1628
+ "loss": 1.989,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 1.09,
1633
+ "learning_rate": 6.419333786820835e-05,
1634
+ "loss": 1.9849,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 1.09,
1639
+ "learning_rate": 6.370579088419277e-05,
1640
+ "loss": 1.8671,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 1.1,
1645
+ "learning_rate": 6.321873176354947e-05,
1646
+ "loss": 1.973,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 1.1,
1651
+ "learning_rate": 6.27321815452288e-05,
1652
+ "loss": 1.9833,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 1.11,
1657
+ "learning_rate": 6.224616124619862e-05,
1658
+ "loss": 1.9671,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 1.11,
1663
+ "learning_rate": 6.176069186053648e-05,
1664
+ "loss": 1.9405,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 1.11,
1669
+ "learning_rate": 6.127579435852275e-05,
1670
+ "loss": 1.9513,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 1.12,
1675
+ "learning_rate": 6.0791489685734786e-05,
1676
+ "loss": 1.9244,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 1.12,
1681
+ "learning_rate": 6.030779876214214e-05,
1682
+ "loss": 1.9151,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 1.13,
1687
+ "learning_rate": 5.9824742481202905e-05,
1688
+ "loss": 1.8968,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 1.13,
1693
+ "learning_rate": 5.9342341708961266e-05,
1694
+ "loss": 2.0065,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 1.13,
1699
+ "learning_rate": 5.8860617283146075e-05,
1700
+ "loss": 2.0009,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 1.14,
1705
+ "learning_rate": 5.837959001227088e-05,
1706
+ "loss": 1.8829,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 1.14,
1711
+ "learning_rate": 5.789928067473493e-05,
1712
+ "loss": 1.9626,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 1.15,
1717
+ "learning_rate": 5.741971001792574e-05,
1718
+ "loss": 1.9111,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 1.15,
1723
+ "learning_rate": 5.694089875732285e-05,
1724
+ "loss": 1.9293,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 1.15,
1729
+ "learning_rate": 5.6462867575602995e-05,
1730
+ "loss": 1.8539,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 1.16,
1735
+ "learning_rate": 5.598563712174675e-05,
1736
+ "loss": 1.888,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 1.16,
1741
+ "learning_rate": 5.550922801014649e-05,
1742
+ "loss": 1.9423,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 1.17,
1747
+ "learning_rate": 5.503366081971603e-05,
1748
+ "loss": 1.9689,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 1.17,
1753
+ "learning_rate": 5.455895609300161e-05,
1754
+ "loss": 2.041,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 1.18,
1759
+ "learning_rate": 5.408513433529459e-05,
1760
+ "loss": 1.9372,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 1.18,
1765
+ "learning_rate": 5.361221601374577e-05,
1766
+ "loss": 1.901,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 1.18,
1771
+ "learning_rate": 5.3140221556481165e-05,
1772
+ "loss": 2.0761,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 1.19,
1777
+ "learning_rate": 5.266917135171963e-05,
1778
+ "loss": 1.9059,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 1.19,
1783
+ "learning_rate": 5.2199085746892245e-05,
1784
+ "loss": 1.8997,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 1.2,
1789
+ "learning_rate": 5.1729985047763314e-05,
1790
+ "loss": 1.9531,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 1.2,
1795
+ "learning_rate": 5.1261889517553287e-05,
1796
+ "loss": 2.0348,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 1.2,
1801
+ "learning_rate": 5.079481937606344e-05,
1802
+ "loss": 1.8781,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 1.21,
1807
+ "learning_rate": 5.032879479880247e-05,
1808
+ "loss": 1.8855,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 1.21,
1813
+ "learning_rate": 4.9863835916115014e-05,
1814
+ "loss": 1.8598,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 1.22,
1819
+ "learning_rate": 4.939996281231204e-05,
1820
+ "loss": 1.8692,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 1.22,
1825
+ "learning_rate": 4.893719552480343e-05,
1826
+ "loss": 1.806,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 1.22,
1831
+ "learning_rate": 4.847555404323228e-05,
1832
+ "loss": 1.8881,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 1.23,
1837
+ "learning_rate": 4.8015058308611507e-05,
1838
+ "loss": 1.8989,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 1.23,
1843
+ "learning_rate": 4.7555728212462486e-05,
1844
+ "loss": 1.7977,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 1.24,
1849
+ "learning_rate": 4.709758359595576e-05,
1850
+ "loss": 1.988,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 1.24,
1855
+ "learning_rate": 4.664064424905415e-05,
1856
+ "loss": 1.897,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 1.24,
1861
+ "learning_rate": 4.6184929909657676e-05,
1862
+ "loss": 1.8587,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 1.25,
1867
+ "learning_rate": 4.5730460262751087e-05,
1868
+ "loss": 1.7904,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 1.25,
1873
+ "learning_rate": 4.5277254939553545e-05,
1874
+ "loss": 1.839,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 1.26,
1879
+ "learning_rate": 4.482533351667064e-05,
1880
+ "loss": 1.8073,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 1.26,
1885
+ "learning_rate": 4.437471551524878e-05,
1886
+ "loss": 1.8392,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 1.27,
1891
+ "learning_rate": 4.392542040013189e-05,
1892
+ "loss": 1.806,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 1.27,
1897
+ "learning_rate": 4.3477467579020645e-05,
1898
+ "loss": 1.846,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 1.27,
1903
+ "learning_rate": 4.303087640163415e-05,
1904
+ "loss": 1.8647,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 1.28,
1909
+ "learning_rate": 4.258566615887408e-05,
1910
+ "loss": 1.9028,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 1.28,
1915
+ "learning_rate": 4.2141856081991485e-05,
1916
+ "loss": 1.8374,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 1.29,
1921
+ "learning_rate": 4.169946534175594e-05,
1922
+ "loss": 1.8919,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 1.29,
1927
+ "learning_rate": 4.125851304762755e-05,
1928
+ "loss": 1.9218,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 1.29,
1933
+ "learning_rate": 4.081901824693143e-05,
1934
+ "loss": 1.9217,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 1.3,
1939
+ "learning_rate": 4.038099992403499e-05,
1940
+ "loss": 1.8645,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 1.3,
1945
+ "learning_rate": 3.994447699952792e-05,
1946
+ "loss": 1.9031,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 1.31,
1951
+ "learning_rate": 3.95094683294048e-05,
1952
+ "loss": 1.869,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 1.31,
1957
+ "learning_rate": 3.907599270425066e-05,
1958
+ "loss": 1.8876,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 1.31,
1963
+ "learning_rate": 3.864406884842929e-05,
1964
+ "loss": 1.9243,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 1.32,
1969
+ "learning_rate": 3.821371541927443e-05,
1970
+ "loss": 1.7585,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 1.32,
1975
+ "learning_rate": 3.778495100628386e-05,
1976
+ "loss": 2.0222,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 1.33,
1981
+ "learning_rate": 3.735779413031639e-05,
1982
+ "loss": 1.9437,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 1.33,
1987
+ "learning_rate": 3.693226324279185e-05,
1988
+ "loss": 2.0334,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 1.33,
1993
+ "learning_rate": 3.650837672489404e-05,
1994
+ "loss": 1.9342,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 1.34,
1999
+ "learning_rate": 3.608615288677676e-05,
2000
+ "loss": 1.8273,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 1.34,
2005
+ "learning_rate": 3.566560996677293e-05,
2006
+ "loss": 1.9291,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 1.35,
2011
+ "learning_rate": 3.5246766130606676e-05,
2012
+ "loss": 1.9478,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 1.35,
2017
+ "learning_rate": 3.482963947060869e-05,
2018
+ "loss": 1.9685,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 1.36,
2023
+ "learning_rate": 3.441424800493473e-05,
2024
+ "loss": 1.9329,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 1.36,
2029
+ "learning_rate": 3.400060967678727e-05,
2030
+ "loss": 1.9505,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 1.36,
2035
+ "learning_rate": 3.358874235364053e-05,
2036
+ "loss": 1.9189,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 1.37,
2041
+ "learning_rate": 3.317866382646854e-05,
2042
+ "loss": 1.828,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 1.37,
2047
+ "learning_rate": 3.27703918089767e-05,
2048
+ "loss": 1.8514,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 1.38,
2053
+ "learning_rate": 3.236394393683663e-05,
2054
+ "loss": 1.8606,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 1.38,
2059
+ "learning_rate": 3.195933776692437e-05,
2060
+ "loss": 1.9089,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 1.38,
2065
+ "learning_rate": 3.155659077656206e-05,
2066
+ "loss": 1.8341,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 1.39,
2071
+ "learning_rate": 3.1155720362762844e-05,
2072
+ "loss": 1.8308,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 1.39,
2077
+ "learning_rate": 3.0756743841479536e-05,
2078
+ "loss": 1.9733,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 1.4,
2083
+ "learning_rate": 3.0359678446856554e-05,
2084
+ "loss": 1.8709,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 1.4,
2089
+ "learning_rate": 2.9964541330485517e-05,
2090
+ "loss": 1.882,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 1.4,
2095
+ "learning_rate": 2.957134956066437e-05,
2096
+ "loss": 1.9983,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 1.41,
2101
+ "learning_rate": 2.9180120121660057e-05,
2102
+ "loss": 1.9671,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 1.41,
2107
+ "learning_rate": 2.8790869912974938e-05,
2108
+ "loss": 1.9121,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 1.42,
2113
+ "learning_rate": 2.840361574861674e-05,
2114
+ "loss": 1.9546,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 1.42,
2119
+ "learning_rate": 2.8018374356372282e-05,
2120
+ "loss": 1.8248,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 1.42,
2125
+ "learning_rate": 2.7635162377084962e-05,
2126
+ "loss": 1.9603,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 1.43,
2131
+ "learning_rate": 2.725399636393582e-05,
2132
+ "loss": 1.9236,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 1.43,
2137
+ "learning_rate": 2.6874892781728615e-05,
2138
+ "loss": 1.8867,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 1.44,
2143
+ "learning_rate": 2.6497868006178548e-05,
2144
+ "loss": 1.878,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 1.44,
2149
+ "learning_rate": 2.6122938323204917e-05,
2150
+ "loss": 1.9567,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 1.45,
2155
+ "learning_rate": 2.5750119928227718e-05,
2156
+ "loss": 1.8999,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 1.45,
2161
+ "learning_rate": 2.5379428925467886e-05,
2162
+ "loss": 1.8767,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 1.45,
2167
+ "learning_rate": 2.5010881327251836e-05,
2168
+ "loss": 1.8728,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 1.46,
2173
+ "learning_rate": 2.4644493053319672e-05,
2174
+ "loss": 1.8647,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 1.46,
2179
+ "learning_rate": 2.428027993013759e-05,
2180
+ "loss": 1.8399,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 1.47,
2185
+ "learning_rate": 2.391825769021428e-05,
2186
+ "loss": 1.8709,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 1.47,
2191
+ "learning_rate": 2.35584419714212e-05,
2192
+ "loss": 1.8312,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 1.47,
2197
+ "learning_rate": 2.3200848316317225e-05,
2198
+ "loss": 1.8838,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 1.48,
2203
+ "learning_rate": 2.2845492171477187e-05,
2204
+ "loss": 1.9383,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 1.48,
2209
+ "learning_rate": 2.249238888682469e-05,
2210
+ "loss": 1.8239,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 1.49,
2215
+ "learning_rate": 2.214155371496909e-05,
2216
+ "loss": 1.8893,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 1.49,
2221
+ "learning_rate": 2.179300181054656e-05,
2222
+ "loss": 1.926,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 1.49,
2227
+ "learning_rate": 2.144674822956548e-05,
2228
+ "loss": 1.9655,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 1.5,
2233
+ "learning_rate": 2.110280792875614e-05,
2234
+ "loss": 1.8537,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 1.5,
2239
+ "learning_rate": 2.0761195764924697e-05,
2240
+ "loss": 1.8934,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 1.51,
2245
+ "learning_rate": 2.042192649431129e-05,
2246
+ "loss": 1.7972,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 1.51,
2251
+ "learning_rate": 2.0085014771952753e-05,
2252
+ "loss": 1.8966,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 1.51,
2257
+ "learning_rate": 1.9750475151049527e-05,
2258
+ "loss": 1.967,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 1.52,
2263
+ "learning_rate": 1.941832208233698e-05,
2264
+ "loss": 1.8424,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 1.52,
2269
+ "learning_rate": 1.9088569913461348e-05,
2270
+ "loss": 1.9071,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 1.53,
2275
+ "learning_rate": 1.8761232888359766e-05,
2276
+ "loss": 1.9795,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 1.53,
2281
+ "learning_rate": 1.8436325146645164e-05,
2282
+ "loss": 1.8199,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 1.54,
2287
+ "learning_rate": 1.8113860722995367e-05,
2288
+ "loss": 1.8128,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 1.54,
2293
+ "learning_rate": 1.7793853546546932e-05,
2294
+ "loss": 1.976,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 1.54,
2299
+ "learning_rate": 1.747631744029349e-05,
2300
+ "loss": 1.8586,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 1.55,
2305
+ "learning_rate": 1.716126612048855e-05,
2306
+ "loss": 1.9837,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 1.55,
2311
+ "learning_rate": 1.6848713196053076e-05,
2312
+ "loss": 1.9341,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 1.56,
2317
+ "learning_rate": 1.6538672167987648e-05,
2318
+ "loss": 1.8867,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 1.56,
2323
+ "learning_rate": 1.623115642878923e-05,
2324
+ "loss": 1.8695,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 1.56,
2329
+ "learning_rate": 1.5926179261872737e-05,
2330
+ "loss": 1.8172,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 1.57,
2335
+ "learning_rate": 1.5623753840997173e-05,
2336
+ "loss": 1.9729,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 1.57,
2341
+ "learning_rate": 1.5323893229696614e-05,
2342
+ "loss": 1.997,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 1.58,
2347
+ "learning_rate": 1.502661038071591e-05,
2348
+ "loss": 1.8883,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 1.58,
2353
+ "learning_rate": 1.4731918135451198e-05,
2354
+ "loss": 1.8572,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 1.58,
2359
+ "learning_rate": 1.4439829223395183e-05,
2360
+ "loss": 1.9229,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 1.59,
2365
+ "learning_rate": 1.4150356261587278e-05,
2366
+ "loss": 1.8225,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 1.59,
2371
+ "learning_rate": 1.3863511754068612e-05,
2372
+ "loss": 1.9897,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 1.6,
2377
+ "learning_rate": 1.3579308091341918e-05,
2378
+ "loss": 1.8384,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 1.6,
2383
+ "learning_rate": 1.329775754983625e-05,
2384
+ "loss": 1.7911,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 1.6,
2389
+ "learning_rate": 1.3018872291376813e-05,
2390
+ "loss": 1.9267,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 1.61,
2395
+ "learning_rate": 1.2742664362659493e-05,
2396
+ "loss": 1.9139,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 1.61,
2401
+ "learning_rate": 1.2469145694730555e-05,
2402
+ "loss": 1.9288,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 1.62,
2407
+ "learning_rate": 1.2198328102471274e-05,
2408
+ "loss": 1.9111,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 1.62,
2413
+ "learning_rate": 1.1930223284087528e-05,
2414
+ "loss": 1.8559,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 1.62,
2419
+ "learning_rate": 1.1664842820604605e-05,
2420
+ "loss": 1.9282,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 1.63,
2425
+ "learning_rate": 1.140219817536679e-05,
2426
+ "loss": 1.9222,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 1.63,
2431
+ "learning_rate": 1.1142300693542309e-05,
2432
+ "loss": 1.8489,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 1.64,
2437
+ "learning_rate": 1.0885161601633224e-05,
2438
+ "loss": 1.8483,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 1.64,
2443
+ "learning_rate": 1.0630792006990476e-05,
2444
+ "loss": 1.8454,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 1.65,
2449
+ "learning_rate": 1.0379202897334183e-05,
2450
+ "loss": 1.9625,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 1.65,
2455
+ "learning_rate": 1.0130405140278882e-05,
2456
+ "loss": 1.934,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 1.65,
2461
+ "learning_rate": 9.884409482864194e-06,
2462
+ "loss": 1.8342,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 1.66,
2467
+ "learning_rate": 9.641226551090547e-06,
2468
+ "loss": 1.9461,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 1.66,
2473
+ "learning_rate": 9.4008668494602e-06,
2474
+ "loss": 1.9028,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 1.67,
2479
+ "learning_rate": 9.16334076052349e-06,
2480
+ "loss": 1.9395,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 1.67,
2485
+ "learning_rate": 8.928658544430332e-06,
2486
+ "loss": 1.8259,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 1.67,
2491
+ "learning_rate": 8.69683033848704e-06,
2492
+ "loss": 1.9031,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 1.68,
2497
+ "learning_rate": 8.46786615671842e-06,
2498
+ "loss": 1.9081,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 1.68,
2503
+ "learning_rate": 8.241775889435215e-06,
2504
+ "loss": 1.9114,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 1.69,
2509
+ "learning_rate": 8.018569302806923e-06,
2510
+ "loss": 1.8288,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 1.69,
2515
+ "learning_rate": 7.798256038439852e-06,
2516
+ "loss": 1.9282,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 1.69,
2521
+ "learning_rate": 7.580845612960709e-06,
2522
+ "loss": 1.917,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 1.7,
2527
+ "learning_rate": 7.366347417605503e-06,
2528
+ "loss": 1.959,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 1.7,
2533
+ "learning_rate": 7.154770717813865e-06,
2534
+ "loss": 1.9238,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 1.71,
2539
+ "learning_rate": 6.946124652828883e-06,
2540
+ "loss": 1.8778,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 1.71,
2545
+ "learning_rate": 6.740418235302231e-06,
2546
+ "loss": 2.0161,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 1.71,
2551
+ "learning_rate": 6.537660350904925e-06,
2552
+ "loss": 1.8644,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 1.72,
2557
+ "learning_rate": 6.33785975794347e-06,
2558
+ "loss": 1.8616,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 1.72,
2563
+ "learning_rate": 6.141025086981538e-06,
2564
+ "loss": 1.898,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 1.73,
2569
+ "learning_rate": 5.947164840467225e-06,
2570
+ "loss": 1.9701,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 1.73,
2575
+ "learning_rate": 5.75628739236566e-06,
2576
+ "loss": 2.0035,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 1.74,
2581
+ "learning_rate": 5.5684009877973886e-06,
2582
+ "loss": 1.82,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 1.74,
2587
+ "learning_rate": 5.383513742682155e-06,
2588
+ "loss": 1.9245,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 1.74,
2593
+ "learning_rate": 5.201633643388375e-06,
2594
+ "loss": 1.983,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 1.75,
2599
+ "learning_rate": 5.022768546388148e-06,
2600
+ "loss": 2.0048,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 1.75,
2605
+ "learning_rate": 4.8469261779178395e-06,
2606
+ "loss": 1.9272,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 1.76,
2611
+ "learning_rate": 4.674114133644397e-06,
2612
+ "loss": 1.9476,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 1.76,
2617
+ "learning_rate": 4.504339878337238e-06,
2618
+ "loss": 1.8769,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 1.76,
2623
+ "learning_rate": 4.337610745545764e-06,
2624
+ "loss": 1.9138,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 1.77,
2629
+ "learning_rate": 4.1739339372826445e-06,
2630
+ "loss": 1.954,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 1.77,
2635
+ "learning_rate": 4.013316523712667e-06,
2636
+ "loss": 1.8691,
2637
+ "step": 438
2638
+ },
2639
+ {
2640
+ "epoch": 1.78,
2641
+ "learning_rate": 3.855765442847356e-06,
2642
+ "loss": 1.9924,
2643
+ "step": 439
2644
+ },
2645
+ {
2646
+ "epoch": 1.78,
2647
+ "learning_rate": 3.7012875002452842e-06,
2648
+ "loss": 1.8644,
2649
+ "step": 440
2650
+ },
2651
+ {
2652
+ "epoch": 1.78,
2653
+ "learning_rate": 3.5498893687180646e-06,
2654
+ "loss": 1.8645,
2655
+ "step": 441
2656
+ },
2657
+ {
2658
+ "epoch": 1.79,
2659
+ "learning_rate": 3.4015775880422006e-06,
2660
+ "loss": 1.9275,
2661
+ "step": 442
2662
+ },
2663
+ {
2664
+ "epoch": 1.79,
2665
+ "learning_rate": 3.2563585646764895e-06,
2666
+ "loss": 1.8615,
2667
+ "step": 443
2668
+ },
2669
+ {
2670
+ "epoch": 1.8,
2671
+ "learning_rate": 3.1142385714853334e-06,
2672
+ "loss": 1.8877,
2673
+ "step": 444
2674
+ },
2675
+ {
2676
+ "epoch": 1.8,
2677
+ "learning_rate": 2.9752237474678004e-06,
2678
+ "loss": 1.9007,
2679
+ "step": 445
2680
+ },
2681
+ {
2682
+ "epoch": 1.8,
2683
+ "learning_rate": 2.8393200974924006e-06,
2684
+ "loss": 1.9692,
2685
+ "step": 446
2686
+ },
2687
+ {
2688
+ "epoch": 1.81,
2689
+ "learning_rate": 2.706533492037771e-06,
2690
+ "loss": 1.9871,
2691
+ "step": 447
2692
+ },
2693
+ {
2694
+ "epoch": 1.81,
2695
+ "learning_rate": 2.5768696669389938e-06,
2696
+ "loss": 2.0339,
2697
+ "step": 448
2698
+ },
2699
+ {
2700
+ "epoch": 1.82,
2701
+ "learning_rate": 2.45033422313991e-06,
2702
+ "loss": 1.8736,
2703
+ "step": 449
2704
+ },
2705
+ {
2706
+ "epoch": 1.82,
2707
+ "learning_rate": 2.3269326264511582e-06,
2708
+ "loss": 1.9459,
2709
+ "step": 450
2710
+ },
2711
+ {
2712
+ "epoch": 1.83,
2713
+ "learning_rate": 2.206670207314068e-06,
2714
+ "loss": 1.9323,
2715
+ "step": 451
2716
+ },
2717
+ {
2718
+ "epoch": 1.83,
2719
+ "learning_rate": 2.0895521605704292e-06,
2720
+ "loss": 1.985,
2721
+ "step": 452
2722
+ },
2723
+ {
2724
+ "epoch": 1.83,
2725
+ "learning_rate": 1.975583545238063e-06,
2726
+ "loss": 1.8159,
2727
+ "step": 453
2728
+ },
2729
+ {
2730
+ "epoch": 1.84,
2731
+ "learning_rate": 1.8647692842923057e-06,
2732
+ "loss": 1.8752,
2733
+ "step": 454
2734
+ },
2735
+ {
2736
+ "epoch": 1.84,
2737
+ "learning_rate": 1.7571141644533687e-06,
2738
+ "loss": 1.9724,
2739
+ "step": 455
2740
+ },
2741
+ {
2742
+ "epoch": 1.85,
2743
+ "learning_rate": 1.6526228359795724e-06,
2744
+ "loss": 1.9712,
2745
+ "step": 456
2746
+ },
2747
+ {
2748
+ "epoch": 1.85,
2749
+ "learning_rate": 1.551299812466447e-06,
2750
+ "loss": 1.9641,
2751
+ "step": 457
2752
+ },
2753
+ {
2754
+ "epoch": 1.85,
2755
+ "learning_rate": 1.4531494706517904e-06,
2756
+ "loss": 1.9311,
2757
+ "step": 458
2758
+ },
2759
+ {
2760
+ "epoch": 1.86,
2761
+ "learning_rate": 1.3581760502266088e-06,
2762
+ "loss": 1.8642,
2763
+ "step": 459
2764
+ },
2765
+ {
2766
+ "epoch": 1.86,
2767
+ "learning_rate": 1.2663836536519561e-06,
2768
+ "loss": 1.7754,
2769
+ "step": 460
2770
+ },
2771
+ {
2772
+ "epoch": 1.87,
2773
+ "learning_rate": 1.1777762459817598e-06,
2774
+ "loss": 1.8012,
2775
+ "step": 461
2776
+ },
2777
+ {
2778
+ "epoch": 1.87,
2779
+ "learning_rate": 1.0923576546915309e-06,
2780
+ "loss": 1.9116,
2781
+ "step": 462
2782
+ },
2783
+ {
2784
+ "epoch": 1.87,
2785
+ "learning_rate": 1.0101315695130147e-06,
2786
+ "loss": 1.8041,
2787
+ "step": 463
2788
+ },
2789
+ {
2790
+ "epoch": 1.88,
2791
+ "learning_rate": 9.311015422748341e-07,
2792
+ "loss": 1.9848,
2793
+ "step": 464
2794
+ },
2795
+ {
2796
+ "epoch": 1.88,
2797
+ "learning_rate": 8.552709867490543e-07,
2798
+ "loss": 1.8567,
2799
+ "step": 465
2800
+ },
2801
+ {
2802
+ "epoch": 1.89,
2803
+ "learning_rate": 7.826431785037168e-07,
2804
+ "loss": 1.9504,
2805
+ "step": 466
2806
+ },
2807
+ {
2808
+ "epoch": 1.89,
2809
+ "learning_rate": 7.132212547613869e-07,
2810
+ "loss": 1.8917,
2811
+ "step": 467
2812
+ },
2813
+ {
2814
+ "epoch": 1.89,
2815
+ "learning_rate": 6.47008214263578e-07,
2816
+ "loss": 1.9535,
2817
+ "step": 468
2818
+ },
2819
+ {
2820
+ "epoch": 1.9,
2821
+ "learning_rate": 5.84006917141247e-07,
2822
+ "loss": 1.9072,
2823
+ "step": 469
2824
+ },
2825
+ {
2826
+ "epoch": 1.9,
2827
+ "learning_rate": 5.242200847912686e-07,
2828
+ "loss": 1.8816,
2829
+ "step": 470
2830
+ },
2831
+ {
2832
+ "epoch": 1.91,
2833
+ "learning_rate": 4.676502997588372e-07,
2834
+ "loss": 1.9819,
2835
+ "step": 471
2836
+ },
2837
+ {
2838
+ "epoch": 1.91,
2839
+ "learning_rate": 4.1430000562597266e-07,
2840
+ "loss": 1.891,
2841
+ "step": 472
2842
+ },
2843
+ {
2844
+ "epoch": 1.92,
2845
+ "learning_rate": 3.6417150690589705e-07,
2846
+ "loss": 1.8959,
2847
+ "step": 473
2848
+ },
2849
+ {
2850
+ "epoch": 1.92,
2851
+ "learning_rate": 3.1726696894353863e-07,
2852
+ "loss": 1.8832,
2853
+ "step": 474
2854
+ },
2855
+ {
2856
+ "epoch": 1.92,
2857
+ "learning_rate": 2.735884178219905e-07,
2858
+ "loss": 1.8204,
2859
+ "step": 475
2860
+ },
2861
+ {
2862
+ "epoch": 1.93,
2863
+ "learning_rate": 2.331377402749801e-07,
2864
+ "loss": 1.9253,
2865
+ "step": 476
2866
+ },
2867
+ {
2868
+ "epoch": 1.93,
2869
+ "learning_rate": 1.9591668360536826e-07,
2870
+ "loss": 1.8768,
2871
+ "step": 477
2872
+ },
2873
+ {
2874
+ "epoch": 1.94,
2875
+ "learning_rate": 1.6192685560968423e-07,
2876
+ "loss": 1.8834,
2877
+ "step": 478
2878
+ },
2879
+ {
2880
+ "epoch": 1.94,
2881
+ "learning_rate": 1.311697245086729e-07,
2882
+ "loss": 1.9348,
2883
+ "step": 479
2884
+ },
2885
+ {
2886
+ "epoch": 1.94,
2887
+ "learning_rate": 1.0364661888387083e-07,
2888
+ "loss": 1.9604,
2889
+ "step": 480
2890
+ },
2891
+ {
2892
+ "epoch": 1.95,
2893
+ "learning_rate": 7.935872762021844e-08,
2894
+ "loss": 1.8398,
2895
+ "step": 481
2896
+ },
2897
+ {
2898
+ "epoch": 1.95,
2899
+ "learning_rate": 5.830709985470139e-08,
2900
+ "loss": 1.932,
2901
+ "step": 482
2902
+ },
2903
+ {
2904
+ "epoch": 1.96,
2905
+ "learning_rate": 4.049264493104498e-08,
2906
+ "loss": 1.8913,
2907
+ "step": 483
2908
+ },
2909
+ {
2910
+ "epoch": 1.96,
2911
+ "learning_rate": 2.5916132360412345e-08,
2912
+ "loss": 1.8472,
2913
+ "step": 484
2914
+ },
2915
+ {
2916
+ "epoch": 1.96,
2917
+ "learning_rate": 1.4578191788180982e-08,
2918
+ "loss": 1.899,
2919
+ "step": 485
2920
+ },
2921
+ {
2922
+ "epoch": 1.97,
2923
+ "learning_rate": 6.479312966747862e-09,
2924
+ "loss": 1.9221,
2925
+ "step": 486
2926
+ },
2927
+ {
2928
+ "epoch": 1.97,
2929
+ "learning_rate": 1.6198457343546966e-09,
2930
+ "loss": 1.9443,
2931
+ "step": 487
2932
+ },
2933
+ {
2934
+ "epoch": 1.98,
2935
+ "learning_rate": 0.0,
2936
+ "loss": 1.8836,
2937
+ "step": 488
2938
+ }
2939
+ ],
2940
+ "logging_steps": 1,
2941
+ "max_steps": 488,
2942
+ "num_input_tokens_seen": 0,
2943
+ "num_train_epochs": 2,
2944
+ "save_steps": 244,
2945
+ "total_flos": 6.429953632845693e+18,
2946
+ "train_batch_size": 1,
2947
+ "trial_name": null,
2948
+ "trial_params": null
2949
+ }
checkpoint-488/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7737b8e53a766bba3c736ef45d76502045c9f827e3bd654da1f074b4c957e0b7
3
+ size 4795
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/deepseek-llm-67b-base",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 100000,
9
+ "eos_token_id": 100001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 22016,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 95,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "bnb_4bit_compute_dtype": "bfloat16",
22
+ "bnb_4bit_quant_type": "nf4",
23
+ "bnb_4bit_use_double_quant": true,
24
+ "llm_int8_enable_fp32_cpu_offload": false,
25
+ "llm_int8_has_fp16_weight": false,
26
+ "llm_int8_skip_modules": null,
27
+ "llm_int8_threshold": 6.0,
28
+ "load_in_4bit": true,
29
+ "load_in_8bit": false,
30
+ "quant_method": "bitsandbytes"
31
+ },
32
+ "rms_norm_eps": 1e-06,
33
+ "rope_scaling": null,
34
+ "rope_theta": 10000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.36.2",
38
+ "use_cache": false,
39
+ "vocab_size": 102400
40
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<｜end▁of▁sentence｜>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "100000": {
6
+ "content": "<｜begin▁of▁sentence｜>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "100001": {
14
+ "content": "<｜end▁of▁sentence｜>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "100002": {
22
+ "content": "ø",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "100003": {
30
+ "content": "ö",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "100004": {
38
+ "content": "ú",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "100005": {
46
+ "content": "ÿ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "100006": {
54
+ "content": "õ",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "100007": {
62
+ "content": "÷",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "100008": {
70
+ "content": "û",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "100009": {
78
+ "content": "ý",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "100010": {
86
+ "content": "À",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "100011": {
94
+ "content": "ù",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "100012": {
102
+ "content": "Á",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "100013": {
110
+ "content": "þ",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "100014": {
118
+ "content": "ü",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ }
125
+ },
126
+ "bos_token": "<｜begin▁of▁sentence｜>",
127
+ "clean_up_tokenization_spaces": false,
128
+ "eos_token": "<｜end▁of▁sentence｜>",
129
+ "legacy": true,
130
+ "model_max_length": 4096,
131
+ "pad_token": "<｜end▁of▁sentence｜>",
132
+ "sp_model_kwargs": {},
133
+ "tokenizer_class": "LlamaTokenizer",
134
+ "unk_token": null,
135
+ "use_default_system_prompt": false
136
+ }