Hugging Face's logo

Epiculous
/
llmTechChat-lora

PEFT
Safetensors
mistral
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
Epiculous commited on
Commit
475bc99
•
1 Parent(s): 4163589

Upload folder using huggingface_hub

Browse files
Files changed (40) hide show
  1. README.md +207 -0
  2. adapter_config.json +31 -0
  3. adapter_model.safetensors +3 -0
  4. checkpoint-160/README.md +218 -0
  5. checkpoint-160/adapter_config.json +31 -0
  6. checkpoint-160/adapter_model.safetensors +3 -0
  7. checkpoint-160/optimizer.pt +3 -0
  8. checkpoint-160/rng_state.pth +3 -0
  9. checkpoint-160/scheduler.pt +3 -0
  10. checkpoint-160/trainer_state.json +1021 -0
  11. checkpoint-160/training_args.bin +3 -0
  12. checkpoint-320/README.md +218 -0
  13. checkpoint-320/adapter_config.json +31 -0
  14. checkpoint-320/adapter_model.safetensors +3 -0
  15. checkpoint-320/optimizer.pt +3 -0
  16. checkpoint-320/rng_state.pth +3 -0
  17. checkpoint-320/scheduler.pt +3 -0
  18. checkpoint-320/trainer_state.json +2013 -0
  19. checkpoint-320/training_args.bin +3 -0
  20. checkpoint-480/README.md +218 -0
  21. checkpoint-480/adapter_config.json +31 -0
  22. checkpoint-480/adapter_model.safetensors +3 -0
  23. checkpoint-480/optimizer.pt +3 -0
  24. checkpoint-480/rng_state.pth +3 -0
  25. checkpoint-480/scheduler.pt +3 -0
  26. checkpoint-480/trainer_state.json +3005 -0
  27. checkpoint-480/training_args.bin +3 -0
  28. checkpoint-640/README.md +218 -0
  29. checkpoint-640/adapter_config.json +31 -0
  30. checkpoint-640/adapter_model.safetensors +3 -0
  31. checkpoint-640/optimizer.pt +3 -0
  32. checkpoint-640/rng_state.pth +3 -0
  33. checkpoint-640/scheduler.pt +3 -0
  34. checkpoint-640/trainer_state.json +3997 -0
  35. checkpoint-640/training_args.bin +3 -0
  36. config.json +38 -0
  37. epoch2.zip +3 -0
  38. special_tokens_map.json +24 -0
  39. tokenizer.model +3 -0
  40. tokenizer_config.json +45 -0
README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: mistralai/Mistral-7B-v0.1
7
+ model-index:
8
+ - name: llmTechChat-lora
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<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)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.3.0`
19
+ ```yaml
20
+ base_model: mistralai/Mistral-7B-v0.1
21
+ model_type: MistralForCausalLM
22
+ tokenizer_type: LlamaTokenizer
23
+ is_mistral_derived_model: true
24
+
25
+ load_in_8bit: true
26
+ load_in_4bit: false
27
+ strict: false
28
+
29
+ datasets:
30
+ - path: datasets/norobots_150/norobots_150
31
+ type: completion
32
+ - path: datasets/separated/bloke-separate
33
+ type: completion
34
+ - path: datasets/separated/kcpp-separate
35
+ type: completion
36
+ - path: datasets/separated/kcpp-support-separate
37
+ type: completion
38
+ - path: datasets/separated/st-chat-separate
39
+ type: completion
40
+ - path: datasets/separated/exllama2_readme.txt
41
+ type: completion
42
+ - path: datasets/separated/koboldcpp_readme.txt
43
+ type: completion
44
+ - path: datasets/separated/llama_readme.txt
45
+ type: completion
46
+ - path: datasets/separated/ooba_readme.txt
47
+ type: completion
48
+ - path: datasets/separated/sillytavern_readme.txt
49
+ type: completion
50
+ - path: datasets/separated/sillytavern_simple_setup_guide.txt
51
+ type: completion
52
+ - path: datasets/transformer_article.txt
53
+ type: completion
54
+ - path: datasets/lmg_thread.txt
55
+ type: completion
56
+
57
+ dataset_prepared_path: last_run_prepared
58
+ val_set_size: 0.1
59
+ output_dir: ./llmTechChat-lora
60
+
61
+ adapter: lora
62
+ lora_model_dir:
63
+
64
+ chat_template: chatml
65
+
66
+ sequence_len: 8192
67
+ sample_packing: true
68
+ pad_to_sequence_len: true
69
+
70
+ lora_r: 128
71
+ lora_alpha: 64
72
+ lora_dropout: 0.20
73
+ lora_target_linear: true
74
+ lora_fan_in_fan_out:
75
+ lora_target_modules:
76
+ - gate_proj
77
+ - down_proj
78
+ - up_proj
79
+ - q_proj
80
+ - v_proj
81
+ - k_proj
82
+ - o_proj
83
+
84
+ wandb_project: llmTechChat
85
+
86
+ gradient_accumulation_steps: 8
87
+ micro_batch_size: 1
88
+ num_epochs: 4
89
+ optimizer: adamw_bnb_8bit
90
+ lr_scheduler: cosine
91
+ learning_rate: 0.0003
92
+
93
+ train_on_inputs: false
94
+ group_by_length: false
95
+ bf16: true
96
+ fp16: false
97
+ tf32: false
98
+
99
+ gradient_checkpointing: true
100
+ early_stopping_patience:
101
+ resume_from_checkpoint:
102
+ local_rank:
103
+ logging_steps: 1
104
+ xformers_attention:
105
+ flash_attention: true
106
+
107
+ loss_watchdog_threshold: 5.0
108
+ loss_watchdog_patience: 3
109
+
110
+ warmup_steps: 10
111
+ evals_per_epoch: 4
112
+ eval_table_size:
113
+ eval_table_max_new_tokens: 128
114
+ saves_per_epoch: 1
115
+ debug:
116
+ deepspeed:
117
+ weight_decay: 0.0
118
+ fsdp:
119
+ fsdp_config:
120
+ special_tokens:
121
+ bos_token: "<s>"
122
+ eos_token: "</s>"
123
+ unk_token: "<unk>"
124
+
125
+ save_safetensors: true
126
+
127
+ ```
128
+
129
+ </details><br>
130
+
131
+ # llmTechChat-lora
132
+
133
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
134
+ It achieves the following results on the evaluation set:
135
+ - Loss: 1.9365
136
+
137
+ ## Model description
138
+
139
+ More information needed
140
+
141
+ ## Intended uses & limitations
142
+
143
+ More information needed
144
+
145
+ ## Training and evaluation data
146
+
147
+ More information needed
148
+
149
+ ## Training procedure
150
+
151
+
152
+ The following `bitsandbytes` quantization config was used during training:
153
+ - quant_method: bitsandbytes
154
+ - load_in_8bit: True
155
+ - load_in_4bit: False
156
+ - llm_int8_threshold: 6.0
157
+ - llm_int8_skip_modules: None
158
+ - llm_int8_enable_fp32_cpu_offload: False
159
+ - llm_int8_has_fp16_weight: False
160
+ - bnb_4bit_quant_type: fp4
161
+ - bnb_4bit_use_double_quant: False
162
+ - bnb_4bit_compute_dtype: float32
163
+
164
+ ### Training hyperparameters
165
+
166
+ The following hyperparameters were used during training:
167
+ - learning_rate: 0.0003
168
+ - train_batch_size: 1
169
+ - eval_batch_size: 1
170
+ - seed: 42
171
+ - gradient_accumulation_steps: 8
172
+ - total_train_batch_size: 8
173
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
174
+ - lr_scheduler_type: cosine
175
+ - lr_scheduler_warmup_steps: 10
176
+ - num_epochs: 4
177
+
178
+ ### Training results
179
+
180
+ | Training Loss | Epoch | Step | Validation Loss |
181
+ |:-------------:|:-----:|:----:|:---------------:|
182
+ | 4.3577 | 0.01 | 1 | 4.3261 |
183
+ | 2.0615 | 0.25 | 40 | 2.0476 |
184
+ | 1.9905 | 0.5 | 80 | 1.9691 |
185
+ | 1.8699 | 0.75 | 120 | 1.9344 |
186
+ | 1.9604 | 1.0 | 160 | 1.9111 |
187
+ | 1.7684 | 1.23 | 200 | 1.8978 |
188
+ | 1.7673 | 1.48 | 240 | 1.8809 |
189
+ | 1.7296 | 1.73 | 280 | 1.8630 |
190
+ | 1.7737 | 1.98 | 320 | 1.8479 |
191
+ | 1.5871 | 2.22 | 360 | 1.8883 |
192
+ | 1.5339 | 2.47 | 400 | 1.8761 |
193
+ | 1.5589 | 2.72 | 440 | 1.8657 |
194
+ | 1.5651 | 2.96 | 480 | 1.8590 |
195
+ | 1.3134 | 3.2 | 520 | 1.9497 |
196
+ | 1.3423 | 3.45 | 560 | 1.9406 |
197
+ | 1.3635 | 3.7 | 600 | 1.9362 |
198
+ | 1.3235 | 3.95 | 640 | 1.9365 |
199
+
200
+
201
+ ### Framework versions
202
+
203
+ - PEFT 0.7.0
204
+ - Transformers 4.37.0.dev0
205
+ - Pytorch 2.0.1+cu118
206
+ - Datasets 2.16.1
207
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64,
13
+ "lora_dropout": 0.2,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "o_proj",
24
+ "down_proj",
25
+ "up_proj",
26
+ "q_proj",
27
+ "v_proj",
28
+ "k_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f9ace640e0c6166bb08a08f137e33a54cbe48b48a4097de487c017dad866a5
3
+ size 1342238560
checkpoint-160/README.md ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mistral-7B-v0.1
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ## Training procedure
203
+
204
+ The following `bitsandbytes` quantization config was used during training:
205
+ - quant_method: bitsandbytes
206
+ - load_in_8bit: True
207
+ - load_in_4bit: False
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: fp4
213
+ - bnb_4bit_use_double_quant: False
214
+ - bnb_4bit_compute_dtype: float32
215
+
216
+ ### Framework versions
217
+
218
+ - PEFT 0.7.0
checkpoint-160/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64,
13
+ "lora_dropout": 0.2,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "o_proj",
24
+ "down_proj",
25
+ "up_proj",
26
+ "q_proj",
27
+ "v_proj",
28
+ "k_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
checkpoint-160/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b736aa29f996bc32fa2c4c0ee7283d6bf78c301915bcc91de1a9654c25b225
3
+ size 1342238560
checkpoint-160/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9549276ce48879b1458d86dc0dc4c1647d05a2f4cb841eaabc7abf26ad7d85
3
+ size 672929697
checkpoint-160/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42629469acfec1d6619628cbf399e75de48398ce8d39e0873b1fb1b5548d939
3
+ size 14575
checkpoint-160/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1fd44524ba338ee8509623dc55f5b09e0b8b0ed6f7ccc5893f79625dc856d0c
3
+ size 627
checkpoint-160/trainer_state.json ADDED
@@ -0,0 +1,1021 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.911091685295105,
3
+ "best_model_checkpoint": "./llmTechChat-lora/checkpoint-160",
4
+ "epoch": 0.9976617303195635,
5
+ "eval_steps": 40,
6
+ "global_step": 160,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2.9999999999999997e-05,
14
+ "loss": 4.3577,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "eval_loss": 4.326064109802246,
20
+ "eval_runtime": 288.7431,
21
+ "eval_samples_per_second": 206.796,
22
+ "eval_steps_per_second": 206.796,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "learning_rate": 5.9999999999999995e-05,
28
+ "loss": 4.2951,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.02,
33
+ "learning_rate": 8.999999999999999e-05,
34
+ "loss": 3.9156,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.02,
39
+ "learning_rate": 0.00011999999999999999,
40
+ "loss": 3.4836,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.03,
45
+ "learning_rate": 0.00015,
46
+ "loss": 3.1743,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.04,
51
+ "learning_rate": 0.00017999999999999998,
52
+ "loss": 2.8242,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.04,
57
+ "learning_rate": 0.00020999999999999998,
58
+ "loss": 2.7478,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.05,
63
+ "learning_rate": 0.00023999999999999998,
64
+ "loss": 2.7198,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.06,
69
+ "learning_rate": 0.00027,
70
+ "loss": 2.6025,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.06,
75
+ "learning_rate": 0.0003,
76
+ "loss": 2.5337,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.07,
81
+ "learning_rate": 0.00029999813499925374,
82
+ "loss": 2.5019,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.07,
87
+ "learning_rate": 0.0002999925400433914,
88
+ "loss": 2.3393,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.08,
93
+ "learning_rate": 0.00029998321527154097,
94
+ "loss": 2.3796,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.09,
99
+ "learning_rate": 0.0002999701609155785,
100
+ "loss": 2.3054,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.09,
105
+ "learning_rate": 0.0002999533773001224,
106
+ "loss": 2.2898,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.1,
111
+ "learning_rate": 0.00029993286484252544,
112
+ "loss": 2.2254,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.11,
117
+ "learning_rate": 0.00029990862405286433,
118
+ "loss": 2.2197,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.11,
123
+ "learning_rate": 0.0002998806555339269,
124
+ "loss": 2.1797,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.12,
129
+ "learning_rate": 0.0002998489599811972,
130
+ "loss": 2.1854,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.12,
135
+ "learning_rate": 0.0002998135381828383,
136
+ "loss": 2.2105,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.13,
141
+ "learning_rate": 0.00029977439101967274,
142
+ "loss": 2.1866,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.14,
147
+ "learning_rate": 0.00029973151946516025,
148
+ "loss": 2.1718,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.14,
153
+ "learning_rate": 0.0002996849245853739,
154
+ "loss": 2.1158,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.15,
159
+ "learning_rate": 0.0002996346075389736,
160
+ "loss": 2.1495,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.16,
165
+ "learning_rate": 0.00029958056957717696,
166
+ "loss": 2.1326,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.16,
171
+ "learning_rate": 0.00029952281204372863,
172
+ "loss": 2.1391,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.17,
177
+ "learning_rate": 0.0002994613363748664,
178
+ "loss": 2.1039,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.17,
183
+ "learning_rate": 0.00029939614409928584,
184
+ "loss": 2.132,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.18,
189
+ "learning_rate": 0.00029932723683810225,
190
+ "loss": 2.1278,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.19,
195
+ "learning_rate": 0.0002992546163048102,
196
+ "loss": 2.0698,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.19,
201
+ "learning_rate": 0.00029917828430524096,
202
+ "loss": 2.0757,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.2,
207
+ "learning_rate": 0.0002990982427375177,
208
+ "loss": 2.0689,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.21,
213
+ "learning_rate": 0.0002990144935920083,
214
+ "loss": 2.0986,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.21,
219
+ "learning_rate": 0.0002989270389512756,
220
+ "loss": 2.058,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.22,
225
+ "learning_rate": 0.0002988358809900258,
226
+ "loss": 2.0451,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.22,
231
+ "learning_rate": 0.00029874102197505447,
232
+ "loss": 2.0613,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.23,
237
+ "learning_rate": 0.0002986424642651902,
238
+ "loss": 2.0796,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.24,
243
+ "learning_rate": 0.0002985402103112355,
244
+ "loss": 2.086,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.24,
249
+ "learning_rate": 0.00029843426265590656,
250
+ "loss": 2.0275,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.25,
255
+ "learning_rate": 0.0002983246239337692,
256
+ "loss": 2.0615,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.25,
261
+ "eval_loss": 2.0476396083831787,
262
+ "eval_runtime": 289.9408,
263
+ "eval_samples_per_second": 205.942,
264
+ "eval_steps_per_second": 205.942,
265
+ "step": 40
266
+ },
267
+ {
268
+ "epoch": 0.26,
269
+ "learning_rate": 0.0002982112968711744,
270
+ "loss": 2.1012,
271
+ "step": 41
272
+ },
273
+ {
274
+ "epoch": 0.26,
275
+ "learning_rate": 0.0002980942842861893,
276
+ "loss": 2.0537,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.27,
281
+ "learning_rate": 0.00029797358908852816,
282
+ "loss": 2.0595,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.27,
287
+ "learning_rate": 0.00029784921427947946,
288
+ "loss": 2.0409,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.28,
293
+ "learning_rate": 0.0002977211629518312,
294
+ "loss": 2.0045,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.29,
299
+ "learning_rate": 0.00029758943828979444,
300
+ "loss": 2.0176,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.29,
305
+ "learning_rate": 0.0002974540435689237,
306
+ "loss": 2.0189,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.3,
311
+ "learning_rate": 0.0002973149821560358,
312
+ "loss": 2.0169,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.31,
317
+ "learning_rate": 0.00029717225750912585,
318
+ "loss": 2.0553,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.31,
323
+ "learning_rate": 0.00029702587317728153,
324
+ "loss": 2.0569,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.32,
329
+ "learning_rate": 0.0002968758328005947,
330
+ "loss": 2.0522,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.32,
335
+ "learning_rate": 0.0002967221401100708,
336
+ "loss": 2.0285,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.33,
341
+ "learning_rate": 0.00029656479892753635,
342
+ "loss": 2.0266,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.34,
347
+ "learning_rate": 0.0002964038131655436,
348
+ "loss": 2.0161,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.34,
353
+ "learning_rate": 0.0002962391868272735,
354
+ "loss": 2.0122,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.35,
359
+ "learning_rate": 0.00029607092400643593,
360
+ "loss": 1.9926,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.36,
365
+ "learning_rate": 0.000295899028887168,
366
+ "loss": 2.0123,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.36,
371
+ "learning_rate": 0.0002957235057439301,
372
+ "loss": 2.0121,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.37,
377
+ "learning_rate": 0.0002955443589413994,
378
+ "loss": 2.0245,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.37,
383
+ "learning_rate": 0.00029536159293436166,
384
+ "loss": 2.0127,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.38,
389
+ "learning_rate": 0.0002951752122676,
390
+ "loss": 2.0057,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 0.39,
395
+ "learning_rate": 0.000294985221575782,
396
+ "loss": 2.0226,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 0.39,
401
+ "learning_rate": 0.0002947916255833451,
402
+ "loss": 2.0032,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 0.4,
407
+ "learning_rate": 0.00029459442910437797,
408
+ "loss": 2.045,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 0.41,
413
+ "learning_rate": 0.00029439363704250176,
414
+ "loss": 1.9794,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 0.41,
419
+ "learning_rate": 0.0002941892543907478,
420
+ "loss": 2.0009,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 0.42,
425
+ "learning_rate": 0.0002939812862314333,
426
+ "loss": 1.9508,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 0.42,
431
+ "learning_rate": 0.00029376973773603533,
432
+ "loss": 1.9913,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 0.43,
437
+ "learning_rate": 0.0002935546141650618,
438
+ "loss": 1.9762,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 0.44,
443
+ "learning_rate": 0.00029333592086792107,
444
+ "loss": 2.0,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 0.44,
449
+ "learning_rate": 0.0002931136632827886,
450
+ "loss": 1.9629,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 0.45,
455
+ "learning_rate": 0.0002928878469364719,
456
+ "loss": 2.0009,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 0.46,
461
+ "learning_rate": 0.00029265847744427303,
462
+ "loss": 1.9714,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 0.46,
467
+ "learning_rate": 0.0002924255605098489,
468
+ "loss": 1.9474,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 0.47,
473
+ "learning_rate": 0.0002921891019250697,
474
+ "loss": 1.9959,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 0.47,
479
+ "learning_rate": 0.0002919491075698746,
480
+ "loss": 1.9846,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 0.48,
485
+ "learning_rate": 0.00029170558341212554,
486
+ "loss": 1.9978,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 0.49,
491
+ "learning_rate": 0.00029145853550745904,
492
+ "loss": 1.9527,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 0.49,
497
+ "learning_rate": 0.00029120796999913546,
498
+ "loss": 1.9585,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 0.5,
503
+ "learning_rate": 0.0002909538931178862,
504
+ "loss": 1.9905,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 0.5,
509
+ "eval_loss": 1.96906578540802,
510
+ "eval_runtime": 291.8459,
511
+ "eval_samples_per_second": 204.598,
512
+ "eval_steps_per_second": 204.598,
513
+ "step": 80
514
+ },
515
+ {
516
+ "epoch": 0.51,
517
+ "learning_rate": 0.00029069631118175903,
518
+ "loss": 1.9926,
519
+ "step": 81
520
+ },
521
+ {
522
+ "epoch": 0.51,
523
+ "learning_rate": 0.00029043523059596053,
524
+ "loss": 1.9916,
525
+ "step": 82
526
+ },
527
+ {
528
+ "epoch": 0.52,
529
+ "learning_rate": 0.0002901706578526973,
530
+ "loss": 1.9545,
531
+ "step": 83
532
+ },
533
+ {
534
+ "epoch": 0.52,
535
+ "learning_rate": 0.0002899025995310141,
536
+ "loss": 1.9399,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 0.53,
541
+ "learning_rate": 0.00028963106229663063,
542
+ "loss": 1.9515,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 0.54,
547
+ "learning_rate": 0.00028935605290177535,
548
+ "loss": 1.9855,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 0.54,
553
+ "learning_rate": 0.0002890775781850181,
554
+ "loss": 2.0159,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 0.55,
559
+ "learning_rate": 0.00028879564507109946,
560
+ "loss": 1.9885,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 0.55,
565
+ "learning_rate": 0.00028851026057075916,
566
+ "loss": 1.9625,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 0.56,
571
+ "learning_rate": 0.00028822143178056114,
572
+ "loss": 1.9161,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 0.57,
577
+ "learning_rate": 0.0002879291658827176,
578
+ "loss": 1.9141,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 0.57,
583
+ "learning_rate": 0.00028763347014491,
584
+ "loss": 1.9867,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 0.58,
589
+ "learning_rate": 0.00028733435192010887,
590
+ "loss": 1.9325,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 0.59,
595
+ "learning_rate": 0.0002870318186463901,
596
+ "loss": 1.9517,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 0.59,
601
+ "learning_rate": 0.00028672587784675096,
602
+ "loss": 1.9435,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 0.6,
607
+ "learning_rate": 0.0002864165371289223,
608
+ "loss": 1.9428,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 0.6,
613
+ "learning_rate": 0.0002861038041851797,
614
+ "loss": 1.9182,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 0.61,
619
+ "learning_rate": 0.0002857876867921522,
620
+ "loss": 1.9344,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 0.62,
625
+ "learning_rate": 0.0002854681928106287,
626
+ "loss": 1.9652,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 0.62,
631
+ "learning_rate": 0.0002851453301853628,
632
+ "loss": 1.9332,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 0.63,
637
+ "learning_rate": 0.000284819106944875,
638
+ "loss": 1.9042,
639
+ "step": 101
640
+ },
641
+ {
642
+ "epoch": 0.64,
643
+ "learning_rate": 0.0002844895312012531,
644
+ "loss": 1.9571,
645
+ "step": 102
646
+ },
647
+ {
648
+ "epoch": 0.64,
649
+ "learning_rate": 0.0002841566111499505,
650
+ "loss": 1.9129,
651
+ "step": 103
652
+ },
653
+ {
654
+ "epoch": 0.65,
655
+ "learning_rate": 0.0002838203550695825,
656
+ "loss": 1.9347,
657
+ "step": 104
658
+ },
659
+ {
660
+ "epoch": 0.65,
661
+ "learning_rate": 0.00028348077132172027,
662
+ "loss": 1.9461,
663
+ "step": 105
664
+ },
665
+ {
666
+ "epoch": 0.66,
667
+ "learning_rate": 0.0002831378683506831,
668
+ "loss": 1.9188,
669
+ "step": 106
670
+ },
671
+ {
672
+ "epoch": 0.67,
673
+ "learning_rate": 0.00028279165468332823,
674
+ "loss": 1.9491,
675
+ "step": 107
676
+ },
677
+ {
678
+ "epoch": 0.67,
679
+ "learning_rate": 0.000282442138928839,
680
+ "loss": 1.961,
681
+ "step": 108
682
+ },
683
+ {
684
+ "epoch": 0.68,
685
+ "learning_rate": 0.00028208932977851067,
686
+ "loss": 1.9048,
687
+ "step": 109
688
+ },
689
+ {
690
+ "epoch": 0.69,
691
+ "learning_rate": 0.0002817332360055343,
692
+ "loss": 1.9493,
693
+ "step": 110
694
+ },
695
+ {
696
+ "epoch": 0.69,
697
+ "learning_rate": 0.0002813738664647784,
698
+ "loss": 1.9685,
699
+ "step": 111
700
+ },
701
+ {
702
+ "epoch": 0.7,
703
+ "learning_rate": 0.00028101123009256947,
704
+ "loss": 1.9054,
705
+ "step": 112
706
+ },
707
+ {
708
+ "epoch": 0.7,
709
+ "learning_rate": 0.0002806453359064686,
710
+ "loss": 1.9317,
711
+ "step": 113
712
+ },
713
+ {
714
+ "epoch": 0.71,
715
+ "learning_rate": 0.00028027619300504834,
716
+ "loss": 1.9701,
717
+ "step": 114
718
+ },
719
+ {
720
+ "epoch": 0.72,
721
+ "learning_rate": 0.0002799038105676658,
722
+ "loss": 1.9426,
723
+ "step": 115
724
+ },
725
+ {
726
+ "epoch": 0.72,
727
+ "learning_rate": 0.0002795281978542346,
728
+ "loss": 1.957,
729
+ "step": 116
730
+ },
731
+ {
732
+ "epoch": 0.73,
733
+ "learning_rate": 0.0002791493642049947,
734
+ "loss": 1.9535,
735
+ "step": 117
736
+ },
737
+ {
738
+ "epoch": 0.74,
739
+ "learning_rate": 0.0002787673190402799,
740
+ "loss": 1.9045,
741
+ "step": 118
742
+ },
743
+ {
744
+ "epoch": 0.74,
745
+ "learning_rate": 0.00027838207186028376,
746
+ "loss": 1.9575,
747
+ "step": 119
748
+ },
749
+ {
750
+ "epoch": 0.75,
751
+ "learning_rate": 0.0002779936322448233,
752
+ "loss": 1.8699,
753
+ "step": 120
754
+ },
755
+ {
756
+ "epoch": 0.75,
757
+ "eval_loss": 1.9343771934509277,
758
+ "eval_runtime": 292.8194,
759
+ "eval_samples_per_second": 203.917,
760
+ "eval_steps_per_second": 203.917,
761
+ "step": 120
762
+ },
763
+ {
764
+ "epoch": 0.75,
765
+ "learning_rate": 0.0002776020098531009,
766
+ "loss": 1.956,
767
+ "step": 121
768
+ },
769
+ {
770
+ "epoch": 0.76,
771
+ "learning_rate": 0.00027720721442346387,
772
+ "loss": 1.8958,
773
+ "step": 122
774
+ },
775
+ {
776
+ "epoch": 0.77,
777
+ "learning_rate": 0.0002768092557731625,
778
+ "loss": 1.9157,
779
+ "step": 123
780
+ },
781
+ {
782
+ "epoch": 0.77,
783
+ "learning_rate": 0.00027640814379810587,
784
+ "loss": 1.9118,
785
+ "step": 124
786
+ },
787
+ {
788
+ "epoch": 0.78,
789
+ "learning_rate": 0.0002760038884726157,
790
+ "loss": 1.9707,
791
+ "step": 125
792
+ },
793
+ {
794
+ "epoch": 0.79,
795
+ "learning_rate": 0.0002755964998491785,
796
+ "loss": 1.9563,
797
+ "step": 126
798
+ },
799
+ {
800
+ "epoch": 0.79,
801
+ "learning_rate": 0.0002751859880581954,
802
+ "loss": 1.9825,
803
+ "step": 127
804
+ },
805
+ {
806
+ "epoch": 0.8,
807
+ "learning_rate": 0.0002747723633077303,
808
+ "loss": 1.9687,
809
+ "step": 128
810
+ },
811
+ {
812
+ "epoch": 0.8,
813
+ "learning_rate": 0.0002743556358832562,
814
+ "loss": 1.9378,
815
+ "step": 129
816
+ },
817
+ {
818
+ "epoch": 0.81,
819
+ "learning_rate": 0.00027393581614739923,
820
+ "loss": 1.9307,
821
+ "step": 130
822
+ },
823
+ {
824
+ "epoch": 0.82,
825
+ "learning_rate": 0.00027351291453968086,
826
+ "loss": 1.9333,
827
+ "step": 131
828
+ },
829
+ {
830
+ "epoch": 0.82,
831
+ "learning_rate": 0.0002730869415762587,
832
+ "loss": 1.9229,
833
+ "step": 132
834
+ },
835
+ {
836
+ "epoch": 0.83,
837
+ "learning_rate": 0.0002726579078496647,
838
+ "loss": 1.911,
839
+ "step": 133
840
+ },
841
+ {
842
+ "epoch": 0.84,
843
+ "learning_rate": 0.00027222582402854176,
844
+ "loss": 1.9556,
845
+ "step": 134
846
+ },
847
+ {
848
+ "epoch": 0.84,
849
+ "learning_rate": 0.0002717907008573785,
850
+ "loss": 1.9008,
851
+ "step": 135
852
+ },
853
+ {
854
+ "epoch": 0.85,
855
+ "learning_rate": 0.0002713525491562421,
856
+ "loss": 1.9651,
857
+ "step": 136
858
+ },
859
+ {
860
+ "epoch": 0.85,
861
+ "learning_rate": 0.0002709113798205093,
862
+ "loss": 1.9337,
863
+ "step": 137
864
+ },
865
+ {
866
+ "epoch": 0.86,
867
+ "learning_rate": 0.00027046720382059526,
868
+ "loss": 1.9485,
869
+ "step": 138
870
+ },
871
+ {
872
+ "epoch": 0.87,
873
+ "learning_rate": 0.00027002003220168093,
874
+ "loss": 1.8647,
875
+ "step": 139
876
+ },
877
+ {
878
+ "epoch": 0.87,
879
+ "learning_rate": 0.0002695698760834384,
880
+ "loss": 1.9288,
881
+ "step": 140
882
+ },
883
+ {
884
+ "epoch": 0.88,
885
+ "learning_rate": 0.00026911674665975417,
886
+ "loss": 1.9535,
887
+ "step": 141
888
+ },
889
+ {
890
+ "epoch": 0.89,
891
+ "learning_rate": 0.0002686606551984512,
892
+ "loss": 1.932,
893
+ "step": 142
894
+ },
895
+ {
896
+ "epoch": 0.89,
897
+ "learning_rate": 0.00026820161304100823,
898
+ "loss": 1.9516,
899
+ "step": 143
900
+ },
901
+ {
902
+ "epoch": 0.9,
903
+ "learning_rate": 0.0002677396316022783,
904
+ "loss": 1.9347,
905
+ "step": 144
906
+ },
907
+ {
908
+ "epoch": 0.9,
909
+ "learning_rate": 0.00026727472237020447,
910
+ "loss": 1.9473,
911
+ "step": 145
912
+ },
913
+ {
914
+ "epoch": 0.91,
915
+ "learning_rate": 0.0002668068969055341,
916
+ "loss": 1.9428,
917
+ "step": 146
918
+ },
919
+ {
920
+ "epoch": 0.92,
921
+ "learning_rate": 0.0002663361668415318,
922
+ "loss": 1.9204,
923
+ "step": 147
924
+ },
925
+ {
926
+ "epoch": 0.92,
927
+ "learning_rate": 0.0002658625438836899,
928
+ "loss": 1.9039,
929
+ "step": 148
930
+ },
931
+ {
932
+ "epoch": 0.93,
933
+ "learning_rate": 0.0002653860398094373,
934
+ "loss": 1.9166,
935
+ "step": 149
936
+ },
937
+ {
938
+ "epoch": 0.94,
939
+ "learning_rate": 0.00026490666646784665,
940
+ "loss": 1.9072,
941
+ "step": 150
942
+ },
943
+ {
944
+ "epoch": 0.94,
945
+ "learning_rate": 0.00026442443577933994,
946
+ "loss": 1.9014,
947
+ "step": 151
948
+ },
949
+ {
950
+ "epoch": 0.95,
951
+ "learning_rate": 0.0002639393597353917,
952
+ "loss": 1.9272,
953
+ "step": 152
954
+ },
955
+ {
956
+ "epoch": 0.95,
957
+ "learning_rate": 0.00026345145039823097,
958
+ "loss": 1.9274,
959
+ "step": 153
960
+ },
961
+ {
962
+ "epoch": 0.96,
963
+ "learning_rate": 0.00026296071990054165,
964
+ "loss": 1.9548,
965
+ "step": 154
966
+ },
967
+ {
968
+ "epoch": 0.97,
969
+ "learning_rate": 0.0002624671804451601,
970
+ "loss": 1.928,
971
+ "step": 155
972
+ },
973
+ {
974
+ "epoch": 0.97,
975
+ "learning_rate": 0.0002619708443047725,
976
+ "loss": 1.9072,
977
+ "step": 156
978
+ },
979
+ {
980
+ "epoch": 0.98,
981
+ "learning_rate": 0.00026147172382160914,
982
+ "loss": 1.9116,
983
+ "step": 157
984
+ },
985
+ {
986
+ "epoch": 0.99,
987
+ "learning_rate": 0.0002609698314071376,
988
+ "loss": 1.915,
989
+ "step": 158
990
+ },
991
+ {
992
+ "epoch": 0.99,
993
+ "learning_rate": 0.0002604651795417543,
994
+ "loss": 1.915,
995
+ "step": 159
996
+ },
997
+ {
998
+ "epoch": 1.0,
999
+ "learning_rate": 0.0002599577807744739,
1000
+ "loss": 1.9604,
1001
+ "step": 160
1002
+ },
1003
+ {
1004
+ "epoch": 1.0,
1005
+ "eval_loss": 1.911091685295105,
1006
+ "eval_runtime": 289.5613,
1007
+ "eval_samples_per_second": 206.212,
1008
+ "eval_steps_per_second": 206.212,
1009
+ "step": 160
1010
+ }
1011
+ ],
1012
+ "logging_steps": 1,
1013
+ "max_steps": 640,
1014
+ "num_input_tokens_seen": 0,
1015
+ "num_train_epochs": 4,
1016
+ "save_steps": 160,
1017
+ "total_flos": 4.6847467450269696e+17,
1018
+ "train_batch_size": 1,
1019
+ "trial_name": null,
1020
+ "trial_params": null
1021
+ }
checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0bb8459ca9eb55b57fe6882811eecff75c1f600c94c4d55a31c5f6345a7df8b
3
+ size 4795
checkpoint-320/README.md ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mistral-7B-v0.1
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ## Training procedure
203
+
204
+ The following `bitsandbytes` quantization config was used during training:
205
+ - quant_method: bitsandbytes
206
+ - load_in_8bit: True
207
+ - load_in_4bit: False
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: fp4
213
+ - bnb_4bit_use_double_quant: False
214
+ - bnb_4bit_compute_dtype: float32
215
+
216
+ ### Framework versions
217
+
218
+ - PEFT 0.7.0
checkpoint-320/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64,
13
+ "lora_dropout": 0.2,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "o_proj",
24
+ "down_proj",
25
+ "up_proj",
26
+ "q_proj",
27
+ "v_proj",
28
+ "k_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
checkpoint-320/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f9ace640e0c6166bb08a08f137e33a54cbe48b48a4097de487c017dad866a5
3
+ size 1342238560
checkpoint-320/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fffdc41ff91e5eb4e84f2605af4b0968b342881146ca013bc2fbbf861f938295
3
+ size 672930145
checkpoint-320/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faad06194bb9664a0bfd3eb37684d4073b9f6fd967195ff60afd7acc4def1b6b
3
+ size 14575
checkpoint-320/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b723213f2ff6422770709f2fc4e56f2fe4e48cd1edae319e6fbf4a6ba742b4
3
+ size 627
checkpoint-320/trainer_state.json ADDED
@@ -0,0 +1,2013 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8478573560714722,
3
+ "best_model_checkpoint": "./llmTechChat-lora/checkpoint-320",
4
+ "epoch": 1.981293842556508,
5
+ "eval_steps": 40,
6
+ "global_step": 320,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2.9999999999999997e-05,
14
+ "loss": 4.3577,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "eval_loss": 4.326064109802246,
20
+ "eval_runtime": 288.7431,
21
+ "eval_samples_per_second": 206.796,
22
+ "eval_steps_per_second": 206.796,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "learning_rate": 5.9999999999999995e-05,
28
+ "loss": 4.2951,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.02,
33
+ "learning_rate": 8.999999999999999e-05,
34
+ "loss": 3.9156,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.02,
39
+ "learning_rate": 0.00011999999999999999,
40
+ "loss": 3.4836,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.03,
45
+ "learning_rate": 0.00015,
46
+ "loss": 3.1743,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.04,
51
+ "learning_rate": 0.00017999999999999998,
52
+ "loss": 2.8242,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.04,
57
+ "learning_rate": 0.00020999999999999998,
58
+ "loss": 2.7478,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.05,
63
+ "learning_rate": 0.00023999999999999998,
64
+ "loss": 2.7198,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.06,
69
+ "learning_rate": 0.00027,
70
+ "loss": 2.6025,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.06,
75
+ "learning_rate": 0.0003,
76
+ "loss": 2.5337,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.07,
81
+ "learning_rate": 0.00029999813499925374,
82
+ "loss": 2.5019,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.07,
87
+ "learning_rate": 0.0002999925400433914,
88
+ "loss": 2.3393,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.08,
93
+ "learning_rate": 0.00029998321527154097,
94
+ "loss": 2.3796,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.09,
99
+ "learning_rate": 0.0002999701609155785,
100
+ "loss": 2.3054,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.09,
105
+ "learning_rate": 0.0002999533773001224,
106
+ "loss": 2.2898,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.1,
111
+ "learning_rate": 0.00029993286484252544,
112
+ "loss": 2.2254,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.11,
117
+ "learning_rate": 0.00029990862405286433,
118
+ "loss": 2.2197,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.11,
123
+ "learning_rate": 0.0002998806555339269,
124
+ "loss": 2.1797,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.12,
129
+ "learning_rate": 0.0002998489599811972,
130
+ "loss": 2.1854,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.12,
135
+ "learning_rate": 0.0002998135381828383,
136
+ "loss": 2.2105,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.13,
141
+ "learning_rate": 0.00029977439101967274,
142
+ "loss": 2.1866,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.14,
147
+ "learning_rate": 0.00029973151946516025,
148
+ "loss": 2.1718,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.14,
153
+ "learning_rate": 0.0002996849245853739,
154
+ "loss": 2.1158,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.15,
159
+ "learning_rate": 0.0002996346075389736,
160
+ "loss": 2.1495,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.16,
165
+ "learning_rate": 0.00029958056957717696,
166
+ "loss": 2.1326,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.16,
171
+ "learning_rate": 0.00029952281204372863,
172
+ "loss": 2.1391,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.17,
177
+ "learning_rate": 0.0002994613363748664,
178
+ "loss": 2.1039,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.17,
183
+ "learning_rate": 0.00029939614409928584,
184
+ "loss": 2.132,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.18,
189
+ "learning_rate": 0.00029932723683810225,
190
+ "loss": 2.1278,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.19,
195
+ "learning_rate": 0.0002992546163048102,
196
+ "loss": 2.0698,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.19,
201
+ "learning_rate": 0.00029917828430524096,
202
+ "loss": 2.0757,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.2,
207
+ "learning_rate": 0.0002990982427375177,
208
+ "loss": 2.0689,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.21,
213
+ "learning_rate": 0.0002990144935920083,
214
+ "loss": 2.0986,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.21,
219
+ "learning_rate": 0.0002989270389512756,
220
+ "loss": 2.058,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.22,
225
+ "learning_rate": 0.0002988358809900258,
226
+ "loss": 2.0451,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.22,
231
+ "learning_rate": 0.00029874102197505447,
232
+ "loss": 2.0613,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.23,
237
+ "learning_rate": 0.0002986424642651902,
238
+ "loss": 2.0796,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.24,
243
+ "learning_rate": 0.0002985402103112355,
244
+ "loss": 2.086,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.24,
249
+ "learning_rate": 0.00029843426265590656,
250
+ "loss": 2.0275,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.25,
255
+ "learning_rate": 0.0002983246239337692,
256
+ "loss": 2.0615,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.25,
261
+ "eval_loss": 2.0476396083831787,
262
+ "eval_runtime": 289.9408,
263
+ "eval_samples_per_second": 205.942,
264
+ "eval_steps_per_second": 205.942,
265
+ "step": 40
266
+ },
267
+ {
268
+ "epoch": 0.26,
269
+ "learning_rate": 0.0002982112968711744,
270
+ "loss": 2.1012,
271
+ "step": 41
272
+ },
273
+ {
274
+ "epoch": 0.26,
275
+ "learning_rate": 0.0002980942842861893,
276
+ "loss": 2.0537,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.27,
281
+ "learning_rate": 0.00029797358908852816,
282
+ "loss": 2.0595,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.27,
287
+ "learning_rate": 0.00029784921427947946,
288
+ "loss": 2.0409,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.28,
293
+ "learning_rate": 0.0002977211629518312,
294
+ "loss": 2.0045,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.29,
299
+ "learning_rate": 0.00029758943828979444,
300
+ "loss": 2.0176,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.29,
305
+ "learning_rate": 0.0002974540435689237,
306
+ "loss": 2.0189,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.3,
311
+ "learning_rate": 0.0002973149821560358,
312
+ "loss": 2.0169,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.31,
317
+ "learning_rate": 0.00029717225750912585,
318
+ "loss": 2.0553,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.31,
323
+ "learning_rate": 0.00029702587317728153,
324
+ "loss": 2.0569,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.32,
329
+ "learning_rate": 0.0002968758328005947,
330
+ "loss": 2.0522,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.32,
335
+ "learning_rate": 0.0002967221401100708,
336
+ "loss": 2.0285,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.33,
341
+ "learning_rate": 0.00029656479892753635,
342
+ "loss": 2.0266,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.34,
347
+ "learning_rate": 0.0002964038131655436,
348
+ "loss": 2.0161,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.34,
353
+ "learning_rate": 0.0002962391868272735,
354
+ "loss": 2.0122,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.35,
359
+ "learning_rate": 0.00029607092400643593,
360
+ "loss": 1.9926,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.36,
365
+ "learning_rate": 0.000295899028887168,
366
+ "loss": 2.0123,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.36,
371
+ "learning_rate": 0.0002957235057439301,
372
+ "loss": 2.0121,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.37,
377
+ "learning_rate": 0.0002955443589413994,
378
+ "loss": 2.0245,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.37,
383
+ "learning_rate": 0.00029536159293436166,
384
+ "loss": 2.0127,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.38,
389
+ "learning_rate": 0.0002951752122676,
390
+ "loss": 2.0057,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 0.39,
395
+ "learning_rate": 0.000294985221575782,
396
+ "loss": 2.0226,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 0.39,
401
+ "learning_rate": 0.0002947916255833451,
402
+ "loss": 2.0032,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 0.4,
407
+ "learning_rate": 0.00029459442910437797,
408
+ "loss": 2.045,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 0.41,
413
+ "learning_rate": 0.00029439363704250176,
414
+ "loss": 1.9794,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 0.41,
419
+ "learning_rate": 0.0002941892543907478,
420
+ "loss": 2.0009,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 0.42,
425
+ "learning_rate": 0.0002939812862314333,
426
+ "loss": 1.9508,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 0.42,
431
+ "learning_rate": 0.00029376973773603533,
432
+ "loss": 1.9913,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 0.43,
437
+ "learning_rate": 0.0002935546141650618,
438
+ "loss": 1.9762,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 0.44,
443
+ "learning_rate": 0.00029333592086792107,
444
+ "loss": 2.0,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 0.44,
449
+ "learning_rate": 0.0002931136632827886,
450
+ "loss": 1.9629,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 0.45,
455
+ "learning_rate": 0.0002928878469364719,
456
+ "loss": 2.0009,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 0.46,
461
+ "learning_rate": 0.00029265847744427303,
462
+ "loss": 1.9714,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 0.46,
467
+ "learning_rate": 0.0002924255605098489,
468
+ "loss": 1.9474,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 0.47,
473
+ "learning_rate": 0.0002921891019250697,
474
+ "loss": 1.9959,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 0.47,
479
+ "learning_rate": 0.0002919491075698746,
480
+ "loss": 1.9846,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 0.48,
485
+ "learning_rate": 0.00029170558341212554,
486
+ "loss": 1.9978,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 0.49,
491
+ "learning_rate": 0.00029145853550745904,
492
+ "loss": 1.9527,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 0.49,
497
+ "learning_rate": 0.00029120796999913546,
498
+ "loss": 1.9585,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 0.5,
503
+ "learning_rate": 0.0002909538931178862,
504
+ "loss": 1.9905,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 0.5,
509
+ "eval_loss": 1.96906578540802,
510
+ "eval_runtime": 291.8459,
511
+ "eval_samples_per_second": 204.598,
512
+ "eval_steps_per_second": 204.598,
513
+ "step": 80
514
+ },
515
+ {
516
+ "epoch": 0.51,
517
+ "learning_rate": 0.00029069631118175903,
518
+ "loss": 1.9926,
519
+ "step": 81
520
+ },
521
+ {
522
+ "epoch": 0.51,
523
+ "learning_rate": 0.00029043523059596053,
524
+ "loss": 1.9916,
525
+ "step": 82
526
+ },
527
+ {
528
+ "epoch": 0.52,
529
+ "learning_rate": 0.0002901706578526973,
530
+ "loss": 1.9545,
531
+ "step": 83
532
+ },
533
+ {
534
+ "epoch": 0.52,
535
+ "learning_rate": 0.0002899025995310141,
536
+ "loss": 1.9399,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 0.53,
541
+ "learning_rate": 0.00028963106229663063,
542
+ "loss": 1.9515,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 0.54,
547
+ "learning_rate": 0.00028935605290177535,
548
+ "loss": 1.9855,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 0.54,
553
+ "learning_rate": 0.0002890775781850181,
554
+ "loss": 2.0159,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 0.55,
559
+ "learning_rate": 0.00028879564507109946,
560
+ "loss": 1.9885,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 0.55,
565
+ "learning_rate": 0.00028851026057075916,
566
+ "loss": 1.9625,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 0.56,
571
+ "learning_rate": 0.00028822143178056114,
572
+ "loss": 1.9161,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 0.57,
577
+ "learning_rate": 0.0002879291658827176,
578
+ "loss": 1.9141,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 0.57,
583
+ "learning_rate": 0.00028763347014491,
584
+ "loss": 1.9867,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 0.58,
589
+ "learning_rate": 0.00028733435192010887,
590
+ "loss": 1.9325,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 0.59,
595
+ "learning_rate": 0.0002870318186463901,
596
+ "loss": 1.9517,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 0.59,
601
+ "learning_rate": 0.00028672587784675096,
602
+ "loss": 1.9435,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 0.6,
607
+ "learning_rate": 0.0002864165371289223,
608
+ "loss": 1.9428,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 0.6,
613
+ "learning_rate": 0.0002861038041851797,
614
+ "loss": 1.9182,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 0.61,
619
+ "learning_rate": 0.0002857876867921522,
620
+ "loss": 1.9344,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 0.62,
625
+ "learning_rate": 0.0002854681928106287,
626
+ "loss": 1.9652,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 0.62,
631
+ "learning_rate": 0.0002851453301853628,
632
+ "loss": 1.9332,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 0.63,
637
+ "learning_rate": 0.000284819106944875,
638
+ "loss": 1.9042,
639
+ "step": 101
640
+ },
641
+ {
642
+ "epoch": 0.64,
643
+ "learning_rate": 0.0002844895312012531,
644
+ "loss": 1.9571,
645
+ "step": 102
646
+ },
647
+ {
648
+ "epoch": 0.64,
649
+ "learning_rate": 0.0002841566111499505,
650
+ "loss": 1.9129,
651
+ "step": 103
652
+ },
653
+ {
654
+ "epoch": 0.65,
655
+ "learning_rate": 0.0002838203550695825,
656
+ "loss": 1.9347,
657
+ "step": 104
658
+ },
659
+ {
660
+ "epoch": 0.65,
661
+ "learning_rate": 0.00028348077132172027,
662
+ "loss": 1.9461,
663
+ "step": 105
664
+ },
665
+ {
666
+ "epoch": 0.66,
667
+ "learning_rate": 0.0002831378683506831,
668
+ "loss": 1.9188,
669
+ "step": 106
670
+ },
671
+ {
672
+ "epoch": 0.67,
673
+ "learning_rate": 0.00028279165468332823,
674
+ "loss": 1.9491,
675
+ "step": 107
676
+ },
677
+ {
678
+ "epoch": 0.67,
679
+ "learning_rate": 0.000282442138928839,
680
+ "loss": 1.961,
681
+ "step": 108
682
+ },
683
+ {
684
+ "epoch": 0.68,
685
+ "learning_rate": 0.00028208932977851067,
686
+ "loss": 1.9048,
687
+ "step": 109
688
+ },
689
+ {
690
+ "epoch": 0.69,
691
+ "learning_rate": 0.0002817332360055343,
692
+ "loss": 1.9493,
693
+ "step": 110
694
+ },
695
+ {
696
+ "epoch": 0.69,
697
+ "learning_rate": 0.0002813738664647784,
698
+ "loss": 1.9685,
699
+ "step": 111
700
+ },
701
+ {
702
+ "epoch": 0.7,
703
+ "learning_rate": 0.00028101123009256947,
704
+ "loss": 1.9054,
705
+ "step": 112
706
+ },
707
+ {
708
+ "epoch": 0.7,
709
+ "learning_rate": 0.0002806453359064686,
710
+ "loss": 1.9317,
711
+ "step": 113
712
+ },
713
+ {
714
+ "epoch": 0.71,
715
+ "learning_rate": 0.00028027619300504834,
716
+ "loss": 1.9701,
717
+ "step": 114
718
+ },
719
+ {
720
+ "epoch": 0.72,
721
+ "learning_rate": 0.0002799038105676658,
722
+ "loss": 1.9426,
723
+ "step": 115
724
+ },
725
+ {
726
+ "epoch": 0.72,
727
+ "learning_rate": 0.0002795281978542346,
728
+ "loss": 1.957,
729
+ "step": 116
730
+ },
731
+ {
732
+ "epoch": 0.73,
733
+ "learning_rate": 0.0002791493642049947,
734
+ "loss": 1.9535,
735
+ "step": 117
736
+ },
737
+ {
738
+ "epoch": 0.74,
739
+ "learning_rate": 0.0002787673190402799,
740
+ "loss": 1.9045,
741
+ "step": 118
742
+ },
743
+ {
744
+ "epoch": 0.74,
745
+ "learning_rate": 0.00027838207186028376,
746
+ "loss": 1.9575,
747
+ "step": 119
748
+ },
749
+ {
750
+ "epoch": 0.75,
751
+ "learning_rate": 0.0002779936322448233,
752
+ "loss": 1.8699,
753
+ "step": 120
754
+ },
755
+ {
756
+ "epoch": 0.75,
757
+ "eval_loss": 1.9343771934509277,
758
+ "eval_runtime": 292.8194,
759
+ "eval_samples_per_second": 203.917,
760
+ "eval_steps_per_second": 203.917,
761
+ "step": 120
762
+ },
763
+ {
764
+ "epoch": 0.75,
765
+ "learning_rate": 0.0002776020098531009,
766
+ "loss": 1.956,
767
+ "step": 121
768
+ },
769
+ {
770
+ "epoch": 0.76,
771
+ "learning_rate": 0.00027720721442346387,
772
+ "loss": 1.8958,
773
+ "step": 122
774
+ },
775
+ {
776
+ "epoch": 0.77,
777
+ "learning_rate": 0.0002768092557731625,
778
+ "loss": 1.9157,
779
+ "step": 123
780
+ },
781
+ {
782
+ "epoch": 0.77,
783
+ "learning_rate": 0.00027640814379810587,
784
+ "loss": 1.9118,
785
+ "step": 124
786
+ },
787
+ {
788
+ "epoch": 0.78,
789
+ "learning_rate": 0.0002760038884726157,
790
+ "loss": 1.9707,
791
+ "step": 125
792
+ },
793
+ {
794
+ "epoch": 0.79,
795
+ "learning_rate": 0.0002755964998491785,
796
+ "loss": 1.9563,
797
+ "step": 126
798
+ },
799
+ {
800
+ "epoch": 0.79,
801
+ "learning_rate": 0.0002751859880581954,
802
+ "loss": 1.9825,
803
+ "step": 127
804
+ },
805
+ {
806
+ "epoch": 0.8,
807
+ "learning_rate": 0.0002747723633077303,
808
+ "loss": 1.9687,
809
+ "step": 128
810
+ },
811
+ {
812
+ "epoch": 0.8,
813
+ "learning_rate": 0.0002743556358832562,
814
+ "loss": 1.9378,
815
+ "step": 129
816
+ },
817
+ {
818
+ "epoch": 0.81,
819
+ "learning_rate": 0.00027393581614739923,
820
+ "loss": 1.9307,
821
+ "step": 130
822
+ },
823
+ {
824
+ "epoch": 0.82,
825
+ "learning_rate": 0.00027351291453968086,
826
+ "loss": 1.9333,
827
+ "step": 131
828
+ },
829
+ {
830
+ "epoch": 0.82,
831
+ "learning_rate": 0.0002730869415762587,
832
+ "loss": 1.9229,
833
+ "step": 132
834
+ },
835
+ {
836
+ "epoch": 0.83,
837
+ "learning_rate": 0.0002726579078496647,
838
+ "loss": 1.911,
839
+ "step": 133
840
+ },
841
+ {
842
+ "epoch": 0.84,
843
+ "learning_rate": 0.00027222582402854176,
844
+ "loss": 1.9556,
845
+ "step": 134
846
+ },
847
+ {
848
+ "epoch": 0.84,
849
+ "learning_rate": 0.0002717907008573785,
850
+ "loss": 1.9008,
851
+ "step": 135
852
+ },
853
+ {
854
+ "epoch": 0.85,
855
+ "learning_rate": 0.0002713525491562421,
856
+ "loss": 1.9651,
857
+ "step": 136
858
+ },
859
+ {
860
+ "epoch": 0.85,
861
+ "learning_rate": 0.0002709113798205093,
862
+ "loss": 1.9337,
863
+ "step": 137
864
+ },
865
+ {
866
+ "epoch": 0.86,
867
+ "learning_rate": 0.00027046720382059526,
868
+ "loss": 1.9485,
869
+ "step": 138
870
+ },
871
+ {
872
+ "epoch": 0.87,
873
+ "learning_rate": 0.00027002003220168093,
874
+ "loss": 1.8647,
875
+ "step": 139
876
+ },
877
+ {
878
+ "epoch": 0.87,
879
+ "learning_rate": 0.0002695698760834384,
880
+ "loss": 1.9288,
881
+ "step": 140
882
+ },
883
+ {
884
+ "epoch": 0.88,
885
+ "learning_rate": 0.00026911674665975417,
886
+ "loss": 1.9535,
887
+ "step": 141
888
+ },
889
+ {
890
+ "epoch": 0.89,
891
+ "learning_rate": 0.0002686606551984512,
892
+ "loss": 1.932,
893
+ "step": 142
894
+ },
895
+ {
896
+ "epoch": 0.89,
897
+ "learning_rate": 0.00026820161304100823,
898
+ "loss": 1.9516,
899
+ "step": 143
900
+ },
901
+ {
902
+ "epoch": 0.9,
903
+ "learning_rate": 0.0002677396316022783,
904
+ "loss": 1.9347,
905
+ "step": 144
906
+ },
907
+ {
908
+ "epoch": 0.9,
909
+ "learning_rate": 0.00026727472237020447,
910
+ "loss": 1.9473,
911
+ "step": 145
912
+ },
913
+ {
914
+ "epoch": 0.91,
915
+ "learning_rate": 0.0002668068969055341,
916
+ "loss": 1.9428,
917
+ "step": 146
918
+ },
919
+ {
920
+ "epoch": 0.92,
921
+ "learning_rate": 0.0002663361668415318,
922
+ "loss": 1.9204,
923
+ "step": 147
924
+ },
925
+ {
926
+ "epoch": 0.92,
927
+ "learning_rate": 0.0002658625438836899,
928
+ "loss": 1.9039,
929
+ "step": 148
930
+ },
931
+ {
932
+ "epoch": 0.93,
933
+ "learning_rate": 0.0002653860398094373,
934
+ "loss": 1.9166,
935
+ "step": 149
936
+ },
937
+ {
938
+ "epoch": 0.94,
939
+ "learning_rate": 0.00026490666646784665,
940
+ "loss": 1.9072,
941
+ "step": 150
942
+ },
943
+ {
944
+ "epoch": 0.94,
945
+ "learning_rate": 0.00026442443577933994,
946
+ "loss": 1.9014,
947
+ "step": 151
948
+ },
949
+ {
950
+ "epoch": 0.95,
951
+ "learning_rate": 0.0002639393597353917,
952
+ "loss": 1.9272,
953
+ "step": 152
954
+ },
955
+ {
956
+ "epoch": 0.95,
957
+ "learning_rate": 0.00026345145039823097,
958
+ "loss": 1.9274,
959
+ "step": 153
960
+ },
961
+ {
962
+ "epoch": 0.96,
963
+ "learning_rate": 0.00026296071990054165,
964
+ "loss": 1.9548,
965
+ "step": 154
966
+ },
967
+ {
968
+ "epoch": 0.97,
969
+ "learning_rate": 0.0002624671804451601,
970
+ "loss": 1.928,
971
+ "step": 155
972
+ },
973
+ {
974
+ "epoch": 0.97,
975
+ "learning_rate": 0.0002619708443047725,
976
+ "loss": 1.9072,
977
+ "step": 156
978
+ },
979
+ {
980
+ "epoch": 0.98,
981
+ "learning_rate": 0.00026147172382160914,
982
+ "loss": 1.9116,
983
+ "step": 157
984
+ },
985
+ {
986
+ "epoch": 0.99,
987
+ "learning_rate": 0.0002609698314071376,
988
+ "loss": 1.915,
989
+ "step": 158
990
+ },
991
+ {
992
+ "epoch": 0.99,
993
+ "learning_rate": 0.0002604651795417543,
994
+ "loss": 1.915,
995
+ "step": 159
996
+ },
997
+ {
998
+ "epoch": 1.0,
999
+ "learning_rate": 0.0002599577807744739,
1000
+ "loss": 1.9604,
1001
+ "step": 160
1002
+ },
1003
+ {
1004
+ "epoch": 1.0,
1005
+ "eval_loss": 1.911091685295105,
1006
+ "eval_runtime": 289.5613,
1007
+ "eval_samples_per_second": 206.212,
1008
+ "eval_steps_per_second": 206.212,
1009
+ "step": 160
1010
+ },
1011
+ {
1012
+ "epoch": 1.0,
1013
+ "learning_rate": 0.0002594476477226176,
1014
+ "loss": 1.9335,
1015
+ "step": 161
1016
+ },
1017
+ {
1018
+ "epoch": 1.01,
1019
+ "learning_rate": 0.00025893479307149893,
1020
+ "loss": 1.9033,
1021
+ "step": 162
1022
+ },
1023
+ {
1024
+ "epoch": 1.0,
1025
+ "learning_rate": 0.0002584192295741087,
1026
+ "loss": 1.874,
1027
+ "step": 163
1028
+ },
1029
+ {
1030
+ "epoch": 1.01,
1031
+ "learning_rate": 0.00025790097005079764,
1032
+ "loss": 1.7896,
1033
+ "step": 164
1034
+ },
1035
+ {
1036
+ "epoch": 1.01,
1037
+ "learning_rate": 0.0002573800273889577,
1038
+ "loss": 1.7936,
1039
+ "step": 165
1040
+ },
1041
+ {
1042
+ "epoch": 1.02,
1043
+ "learning_rate": 0.00025685641454270173,
1044
+ "loss": 1.8321,
1045
+ "step": 166
1046
+ },
1047
+ {
1048
+ "epoch": 1.03,
1049
+ "learning_rate": 0.00025633014453254086,
1050
+ "loss": 1.8105,
1051
+ "step": 167
1052
+ },
1053
+ {
1054
+ "epoch": 1.03,
1055
+ "learning_rate": 0.0002558012304450613,
1056
+ "loss": 1.8068,
1057
+ "step": 168
1058
+ },
1059
+ {
1060
+ "epoch": 1.04,
1061
+ "learning_rate": 0.0002552696854325987,
1062
+ "loss": 1.7953,
1063
+ "step": 169
1064
+ },
1065
+ {
1066
+ "epoch": 1.05,
1067
+ "learning_rate": 0.0002547355227129109,
1068
+ "loss": 1.8073,
1069
+ "step": 170
1070
+ },
1071
+ {
1072
+ "epoch": 1.05,
1073
+ "learning_rate": 0.0002541987555688496,
1074
+ "loss": 1.8095,
1075
+ "step": 171
1076
+ },
1077
+ {
1078
+ "epoch": 1.06,
1079
+ "learning_rate": 0.0002536593973480297,
1080
+ "loss": 1.7939,
1081
+ "step": 172
1082
+ },
1083
+ {
1084
+ "epoch": 1.06,
1085
+ "learning_rate": 0.0002531174614624977,
1086
+ "loss": 1.8226,
1087
+ "step": 173
1088
+ },
1089
+ {
1090
+ "epoch": 1.07,
1091
+ "learning_rate": 0.000252572961388398,
1092
+ "loss": 1.7815,
1093
+ "step": 174
1094
+ },
1095
+ {
1096
+ "epoch": 1.08,
1097
+ "learning_rate": 0.00025202591066563786,
1098
+ "loss": 1.7929,
1099
+ "step": 175
1100
+ },
1101
+ {
1102
+ "epoch": 1.08,
1103
+ "learning_rate": 0.00025147632289755075,
1104
+ "loss": 1.8027,
1105
+ "step": 176
1106
+ },
1107
+ {
1108
+ "epoch": 1.09,
1109
+ "learning_rate": 0.0002509242117505579,
1110
+ "loss": 1.8349,
1111
+ "step": 177
1112
+ },
1113
+ {
1114
+ "epoch": 1.1,
1115
+ "learning_rate": 0.0002503695909538287,
1116
+ "loss": 1.7828,
1117
+ "step": 178
1118
+ },
1119
+ {
1120
+ "epoch": 1.1,
1121
+ "learning_rate": 0.0002498124742989391,
1122
+ "loss": 1.814,
1123
+ "step": 179
1124
+ },
1125
+ {
1126
+ "epoch": 1.11,
1127
+ "learning_rate": 0.0002492528756395289,
1128
+ "loss": 1.821,
1129
+ "step": 180
1130
+ },
1131
+ {
1132
+ "epoch": 1.11,
1133
+ "learning_rate": 0.0002486908088909569,
1134
+ "loss": 1.8023,
1135
+ "step": 181
1136
+ },
1137
+ {
1138
+ "epoch": 1.12,
1139
+ "learning_rate": 0.0002481262880299552,
1140
+ "loss": 1.7953,
1141
+ "step": 182
1142
+ },
1143
+ {
1144
+ "epoch": 1.13,
1145
+ "learning_rate": 0.0002475593270942814,
1146
+ "loss": 1.8497,
1147
+ "step": 183
1148
+ },
1149
+ {
1150
+ "epoch": 1.13,
1151
+ "learning_rate": 0.0002469899401823699,
1152
+ "loss": 1.7957,
1153
+ "step": 184
1154
+ },
1155
+ {
1156
+ "epoch": 1.14,
1157
+ "learning_rate": 0.0002464181414529809,
1158
+ "loss": 1.7958,
1159
+ "step": 185
1160
+ },
1161
+ {
1162
+ "epoch": 1.15,
1163
+ "learning_rate": 0.0002458439451248484,
1164
+ "loss": 1.8024,
1165
+ "step": 186
1166
+ },
1167
+ {
1168
+ "epoch": 1.15,
1169
+ "learning_rate": 0.0002452673654763268,
1170
+ "loss": 1.8306,
1171
+ "step": 187
1172
+ },
1173
+ {
1174
+ "epoch": 1.16,
1175
+ "learning_rate": 0.0002446884168450358,
1176
+ "loss": 1.8174,
1177
+ "step": 188
1178
+ },
1179
+ {
1180
+ "epoch": 1.16,
1181
+ "learning_rate": 0.00024410711362750386,
1182
+ "loss": 1.8032,
1183
+ "step": 189
1184
+ },
1185
+ {
1186
+ "epoch": 1.17,
1187
+ "learning_rate": 0.00024352347027881003,
1188
+ "loss": 1.8087,
1189
+ "step": 190
1190
+ },
1191
+ {
1192
+ "epoch": 1.18,
1193
+ "learning_rate": 0.0002429375013122247,
1194
+ "loss": 1.7648,
1195
+ "step": 191
1196
+ },
1197
+ {
1198
+ "epoch": 1.18,
1199
+ "learning_rate": 0.0002423492212988487,
1200
+ "loss": 1.8544,
1201
+ "step": 192
1202
+ },
1203
+ {
1204
+ "epoch": 1.19,
1205
+ "learning_rate": 0.00024175864486725092,
1206
+ "loss": 1.7978,
1207
+ "step": 193
1208
+ },
1209
+ {
1210
+ "epoch": 1.2,
1211
+ "learning_rate": 0.0002411657867031045,
1212
+ "loss": 1.7866,
1213
+ "step": 194
1214
+ },
1215
+ {
1216
+ "epoch": 1.2,
1217
+ "learning_rate": 0.0002405706615488216,
1218
+ "loss": 1.8074,
1219
+ "step": 195
1220
+ },
1221
+ {
1222
+ "epoch": 1.21,
1223
+ "learning_rate": 0.00023997328420318704,
1224
+ "loss": 1.7842,
1225
+ "step": 196
1226
+ },
1227
+ {
1228
+ "epoch": 1.21,
1229
+ "learning_rate": 0.00023937366952099005,
1230
+ "loss": 1.781,
1231
+ "step": 197
1232
+ },
1233
+ {
1234
+ "epoch": 1.22,
1235
+ "learning_rate": 0.00023877183241265514,
1236
+ "loss": 1.786,
1237
+ "step": 198
1238
+ },
1239
+ {
1240
+ "epoch": 1.23,
1241
+ "learning_rate": 0.00023816778784387094,
1242
+ "loss": 1.8091,
1243
+ "step": 199
1244
+ },
1245
+ {
1246
+ "epoch": 1.23,
1247
+ "learning_rate": 0.00023756155083521846,
1248
+ "loss": 1.7684,
1249
+ "step": 200
1250
+ },
1251
+ {
1252
+ "epoch": 1.23,
1253
+ "eval_loss": 1.897764801979065,
1254
+ "eval_runtime": 292.524,
1255
+ "eval_samples_per_second": 204.123,
1256
+ "eval_steps_per_second": 204.123,
1257
+ "step": 200
1258
+ },
1259
+ {
1260
+ "epoch": 1.24,
1261
+ "learning_rate": 0.00023695313646179735,
1262
+ "loss": 1.7693,
1263
+ "step": 201
1264
+ },
1265
+ {
1266
+ "epoch": 1.25,
1267
+ "learning_rate": 0.00023634255985285102,
1268
+ "loss": 1.7598,
1269
+ "step": 202
1270
+ },
1271
+ {
1272
+ "epoch": 1.25,
1273
+ "learning_rate": 0.00023572983619139058,
1274
+ "loss": 1.8441,
1275
+ "step": 203
1276
+ },
1277
+ {
1278
+ "epoch": 1.26,
1279
+ "learning_rate": 0.00023511498071381726,
1280
+ "loss": 1.7768,
1281
+ "step": 204
1282
+ },
1283
+ {
1284
+ "epoch": 1.26,
1285
+ "learning_rate": 0.00023449800870954326,
1286
+ "loss": 1.784,
1287
+ "step": 205
1288
+ },
1289
+ {
1290
+ "epoch": 1.27,
1291
+ "learning_rate": 0.00023387893552061199,
1292
+ "loss": 1.7905,
1293
+ "step": 206
1294
+ },
1295
+ {
1296
+ "epoch": 1.28,
1297
+ "learning_rate": 0.00023325777654131623,
1298
+ "loss": 1.7996,
1299
+ "step": 207
1300
+ },
1301
+ {
1302
+ "epoch": 1.28,
1303
+ "learning_rate": 0.00023263454721781537,
1304
+ "loss": 1.7546,
1305
+ "step": 208
1306
+ },
1307
+ {
1308
+ "epoch": 1.29,
1309
+ "learning_rate": 0.0002320092630477515,
1310
+ "loss": 1.8043,
1311
+ "step": 209
1312
+ },
1313
+ {
1314
+ "epoch": 1.3,
1315
+ "learning_rate": 0.0002313819395798639,
1316
+ "loss": 1.7817,
1317
+ "step": 210
1318
+ },
1319
+ {
1320
+ "epoch": 1.3,
1321
+ "learning_rate": 0.00023075259241360233,
1322
+ "loss": 1.8117,
1323
+ "step": 211
1324
+ },
1325
+ {
1326
+ "epoch": 1.31,
1327
+ "learning_rate": 0.00023012123719873926,
1328
+ "loss": 1.7798,
1329
+ "step": 212
1330
+ },
1331
+ {
1332
+ "epoch": 1.31,
1333
+ "learning_rate": 0.0002294878896349807,
1334
+ "loss": 1.763,
1335
+ "step": 213
1336
+ },
1337
+ {
1338
+ "epoch": 1.32,
1339
+ "learning_rate": 0.00022885256547157566,
1340
+ "loss": 1.8169,
1341
+ "step": 214
1342
+ },
1343
+ {
1344
+ "epoch": 1.33,
1345
+ "learning_rate": 0.0002282152805069247,
1346
+ "loss": 1.797,
1347
+ "step": 215
1348
+ },
1349
+ {
1350
+ "epoch": 1.33,
1351
+ "learning_rate": 0.00022757605058818688,
1352
+ "loss": 1.7768,
1353
+ "step": 216
1354
+ },
1355
+ {
1356
+ "epoch": 1.34,
1357
+ "learning_rate": 0.0002269348916108859,
1358
+ "loss": 1.8005,
1359
+ "step": 217
1360
+ },
1361
+ {
1362
+ "epoch": 1.35,
1363
+ "learning_rate": 0.00022629181951851473,
1364
+ "loss": 1.7734,
1365
+ "step": 218
1366
+ },
1367
+ {
1368
+ "epoch": 1.35,
1369
+ "learning_rate": 0.0002256468503021391,
1370
+ "loss": 1.774,
1371
+ "step": 219
1372
+ },
1373
+ {
1374
+ "epoch": 1.36,
1375
+ "learning_rate": 0.000225,
1376
+ "loss": 1.7865,
1377
+ "step": 220
1378
+ },
1379
+ {
1380
+ "epoch": 1.36,
1381
+ "learning_rate": 0.00022435128469711465,
1382
+ "loss": 1.7613,
1383
+ "step": 221
1384
+ },
1385
+ {
1386
+ "epoch": 1.37,
1387
+ "learning_rate": 0.00022370072052487668,
1388
+ "loss": 1.8013,
1389
+ "step": 222
1390
+ },
1391
+ {
1392
+ "epoch": 1.38,
1393
+ "learning_rate": 0.00022304832366065505,
1394
+ "loss": 1.7617,
1395
+ "step": 223
1396
+ },
1397
+ {
1398
+ "epoch": 1.38,
1399
+ "learning_rate": 0.00022239411032739162,
1400
+ "loss": 1.7323,
1401
+ "step": 224
1402
+ },
1403
+ {
1404
+ "epoch": 1.39,
1405
+ "learning_rate": 0.00022173809679319772,
1406
+ "loss": 1.7838,
1407
+ "step": 225
1408
+ },
1409
+ {
1410
+ "epoch": 1.4,
1411
+ "learning_rate": 0.0002210802993709498,
1412
+ "loss": 1.8099,
1413
+ "step": 226
1414
+ },
1415
+ {
1416
+ "epoch": 1.4,
1417
+ "learning_rate": 0.00022042073441788358,
1418
+ "loss": 1.82,
1419
+ "step": 227
1420
+ },
1421
+ {
1422
+ "epoch": 1.41,
1423
+ "learning_rate": 0.00021975941833518757,
1424
+ "loss": 1.772,
1425
+ "step": 228
1426
+ },
1427
+ {
1428
+ "epoch": 1.41,
1429
+ "learning_rate": 0.00021909636756759483,
1430
+ "loss": 1.8044,
1431
+ "step": 229
1432
+ },
1433
+ {
1434
+ "epoch": 1.42,
1435
+ "learning_rate": 0.00021843159860297442,
1436
+ "loss": 1.7679,
1437
+ "step": 230
1438
+ },
1439
+ {
1440
+ "epoch": 1.43,
1441
+ "learning_rate": 0.00021776512797192123,
1442
+ "loss": 1.7786,
1443
+ "step": 231
1444
+ },
1445
+ {
1446
+ "epoch": 1.43,
1447
+ "learning_rate": 0.00021709697224734487,
1448
+ "loss": 1.8305,
1449
+ "step": 232
1450
+ },
1451
+ {
1452
+ "epoch": 1.44,
1453
+ "learning_rate": 0.00021642714804405772,
1454
+ "loss": 1.8044,
1455
+ "step": 233
1456
+ },
1457
+ {
1458
+ "epoch": 1.45,
1459
+ "learning_rate": 0.0002157556720183616,
1460
+ "loss": 1.7838,
1461
+ "step": 234
1462
+ },
1463
+ {
1464
+ "epoch": 1.45,
1465
+ "learning_rate": 0.00021508256086763368,
1466
+ "loss": 1.7639,
1467
+ "step": 235
1468
+ },
1469
+ {
1470
+ "epoch": 1.46,
1471
+ "learning_rate": 0.00021440783132991136,
1472
+ "loss": 1.8067,
1473
+ "step": 236
1474
+ },
1475
+ {
1476
+ "epoch": 1.46,
1477
+ "learning_rate": 0.00021373150018347576,
1478
+ "loss": 1.772,
1479
+ "step": 237
1480
+ },
1481
+ {
1482
+ "epoch": 1.47,
1483
+ "learning_rate": 0.0002130535842464348,
1484
+ "loss": 1.7985,
1485
+ "step": 238
1486
+ },
1487
+ {
1488
+ "epoch": 1.48,
1489
+ "learning_rate": 0.00021237410037630493,
1490
+ "loss": 1.7746,
1491
+ "step": 239
1492
+ },
1493
+ {
1494
+ "epoch": 1.48,
1495
+ "learning_rate": 0.00021169306546959174,
1496
+ "loss": 1.7673,
1497
+ "step": 240
1498
+ },
1499
+ {
1500
+ "epoch": 1.48,
1501
+ "eval_loss": 1.880852222442627,
1502
+ "eval_runtime": 291.0717,
1503
+ "eval_samples_per_second": 205.142,
1504
+ "eval_steps_per_second": 205.142,
1505
+ "step": 240
1506
+ },
1507
+ {
1508
+ "epoch": 1.49,
1509
+ "learning_rate": 0.00021101049646137003,
1510
+ "loss": 1.7555,
1511
+ "step": 241
1512
+ },
1513
+ {
1514
+ "epoch": 1.49,
1515
+ "learning_rate": 0.0002103264103248626,
1516
+ "loss": 1.7722,
1517
+ "step": 242
1518
+ },
1519
+ {
1520
+ "epoch": 1.5,
1521
+ "learning_rate": 0.00020964082407101824,
1522
+ "loss": 1.7686,
1523
+ "step": 243
1524
+ },
1525
+ {
1526
+ "epoch": 1.51,
1527
+ "learning_rate": 0.00020895375474808852,
1528
+ "loss": 1.7625,
1529
+ "step": 244
1530
+ },
1531
+ {
1532
+ "epoch": 1.51,
1533
+ "learning_rate": 0.0002082652194412042,
1534
+ "loss": 1.7524,
1535
+ "step": 245
1536
+ },
1537
+ {
1538
+ "epoch": 1.52,
1539
+ "learning_rate": 0.00020757523527195005,
1540
+ "loss": 1.7785,
1541
+ "step": 246
1542
+ },
1543
+ {
1544
+ "epoch": 1.53,
1545
+ "learning_rate": 0.00020688381939793928,
1546
+ "loss": 1.7901,
1547
+ "step": 247
1548
+ },
1549
+ {
1550
+ "epoch": 1.53,
1551
+ "learning_rate": 0.0002061909890123868,
1552
+ "loss": 1.7941,
1553
+ "step": 248
1554
+ },
1555
+ {
1556
+ "epoch": 1.54,
1557
+ "learning_rate": 0.00020549676134368184,
1558
+ "loss": 1.8157,
1559
+ "step": 249
1560
+ },
1561
+ {
1562
+ "epoch": 1.54,
1563
+ "learning_rate": 0.00020480115365495926,
1564
+ "loss": 1.8354,
1565
+ "step": 250
1566
+ },
1567
+ {
1568
+ "epoch": 1.55,
1569
+ "learning_rate": 0.00020410418324367055,
1570
+ "loss": 1.7764,
1571
+ "step": 251
1572
+ },
1573
+ {
1574
+ "epoch": 1.56,
1575
+ "learning_rate": 0.0002034058674411535,
1576
+ "loss": 1.7677,
1577
+ "step": 252
1578
+ },
1579
+ {
1580
+ "epoch": 1.56,
1581
+ "learning_rate": 0.0002027062236122014,
1582
+ "loss": 1.7739,
1583
+ "step": 253
1584
+ },
1585
+ {
1586
+ "epoch": 1.57,
1587
+ "learning_rate": 0.00020200526915463107,
1588
+ "loss": 1.7746,
1589
+ "step": 254
1590
+ },
1591
+ {
1592
+ "epoch": 1.58,
1593
+ "learning_rate": 0.00020130302149885031,
1594
+ "loss": 1.7675,
1595
+ "step": 255
1596
+ },
1597
+ {
1598
+ "epoch": 1.58,
1599
+ "learning_rate": 0.0002005994981074245,
1600
+ "loss": 1.737,
1601
+ "step": 256
1602
+ },
1603
+ {
1604
+ "epoch": 1.59,
1605
+ "learning_rate": 0.0001998947164746423,
1606
+ "loss": 1.8318,
1607
+ "step": 257
1608
+ },
1609
+ {
1610
+ "epoch": 1.59,
1611
+ "learning_rate": 0.00019918869412608066,
1612
+ "loss": 1.7959,
1613
+ "step": 258
1614
+ },
1615
+ {
1616
+ "epoch": 1.6,
1617
+ "learning_rate": 0.00019848144861816898,
1618
+ "loss": 1.7567,
1619
+ "step": 259
1620
+ },
1621
+ {
1622
+ "epoch": 1.61,
1623
+ "learning_rate": 0.00019777299753775265,
1624
+ "loss": 1.7896,
1625
+ "step": 260
1626
+ },
1627
+ {
1628
+ "epoch": 1.61,
1629
+ "learning_rate": 0.0001970633585016556,
1630
+ "loss": 1.7706,
1631
+ "step": 261
1632
+ },
1633
+ {
1634
+ "epoch": 1.62,
1635
+ "learning_rate": 0.0001963525491562421,
1636
+ "loss": 1.7561,
1637
+ "step": 262
1638
+ },
1639
+ {
1640
+ "epoch": 1.63,
1641
+ "learning_rate": 0.00019564058717697847,
1642
+ "loss": 1.8023,
1643
+ "step": 263
1644
+ },
1645
+ {
1646
+ "epoch": 1.63,
1647
+ "learning_rate": 0.00019492749026799288,
1648
+ "loss": 1.8121,
1649
+ "step": 264
1650
+ },
1651
+ {
1652
+ "epoch": 1.64,
1653
+ "learning_rate": 0.00019421327616163563,
1654
+ "loss": 1.791,
1655
+ "step": 265
1656
+ },
1657
+ {
1658
+ "epoch": 1.64,
1659
+ "learning_rate": 0.00019349796261803793,
1660
+ "loss": 1.7758,
1661
+ "step": 266
1662
+ },
1663
+ {
1664
+ "epoch": 1.65,
1665
+ "learning_rate": 0.00019278156742467032,
1666
+ "loss": 1.755,
1667
+ "step": 267
1668
+ },
1669
+ {
1670
+ "epoch": 1.66,
1671
+ "learning_rate": 0.0001920641083959004,
1672
+ "loss": 1.6986,
1673
+ "step": 268
1674
+ },
1675
+ {
1676
+ "epoch": 1.66,
1677
+ "learning_rate": 0.00019134560337254986,
1678
+ "loss": 1.7569,
1679
+ "step": 269
1680
+ },
1681
+ {
1682
+ "epoch": 1.67,
1683
+ "learning_rate": 0.00019062607022145078,
1684
+ "loss": 1.7849,
1685
+ "step": 270
1686
+ },
1687
+ {
1688
+ "epoch": 1.68,
1689
+ "learning_rate": 0.00018990552683500125,
1690
+ "loss": 1.7833,
1691
+ "step": 271
1692
+ },
1693
+ {
1694
+ "epoch": 1.68,
1695
+ "learning_rate": 0.00018918399113072076,
1696
+ "loss": 1.7739,
1697
+ "step": 272
1698
+ },
1699
+ {
1700
+ "epoch": 1.69,
1701
+ "learning_rate": 0.00018846148105080424,
1702
+ "loss": 1.7765,
1703
+ "step": 273
1704
+ },
1705
+ {
1706
+ "epoch": 1.69,
1707
+ "learning_rate": 0.00018773801456167628,
1708
+ "loss": 1.6825,
1709
+ "step": 274
1710
+ },
1711
+ {
1712
+ "epoch": 1.7,
1713
+ "learning_rate": 0.00018701360965354402,
1714
+ "loss": 1.758,
1715
+ "step": 275
1716
+ },
1717
+ {
1718
+ "epoch": 1.71,
1719
+ "learning_rate": 0.00018628828433995013,
1720
+ "loss": 1.7477,
1721
+ "step": 276
1722
+ },
1723
+ {
1724
+ "epoch": 1.71,
1725
+ "learning_rate": 0.00018556205665732462,
1726
+ "loss": 1.7757,
1727
+ "step": 277
1728
+ },
1729
+ {
1730
+ "epoch": 1.72,
1731
+ "learning_rate": 0.00018483494466453636,
1732
+ "loss": 1.7946,
1733
+ "step": 278
1734
+ },
1735
+ {
1736
+ "epoch": 1.73,
1737
+ "learning_rate": 0.0001841069664424442,
1738
+ "loss": 1.7968,
1739
+ "step": 279
1740
+ },
1741
+ {
1742
+ "epoch": 1.73,
1743
+ "learning_rate": 0.00018337814009344714,
1744
+ "loss": 1.7296,
1745
+ "step": 280
1746
+ },
1747
+ {
1748
+ "epoch": 1.73,
1749
+ "eval_loss": 1.8629968166351318,
1750
+ "eval_runtime": 293.6177,
1751
+ "eval_samples_per_second": 203.363,
1752
+ "eval_steps_per_second": 203.363,
1753
+ "step": 280
1754
+ },
1755
+ {
1756
+ "epoch": 1.74,
1757
+ "learning_rate": 0.00018264848374103433,
1758
+ "loss": 1.7516,
1759
+ "step": 281
1760
+ },
1761
+ {
1762
+ "epoch": 1.74,
1763
+ "learning_rate": 0.00018191801552933432,
1764
+ "loss": 1.7466,
1765
+ "step": 282
1766
+ },
1767
+ {
1768
+ "epoch": 1.75,
1769
+ "learning_rate": 0.00018118675362266385,
1770
+ "loss": 1.7304,
1771
+ "step": 283
1772
+ },
1773
+ {
1774
+ "epoch": 1.76,
1775
+ "learning_rate": 0.0001804547162050764,
1776
+ "loss": 1.7519,
1777
+ "step": 284
1778
+ },
1779
+ {
1780
+ "epoch": 1.76,
1781
+ "learning_rate": 0.0001797219214799096,
1782
+ "loss": 1.7721,
1783
+ "step": 285
1784
+ },
1785
+ {
1786
+ "epoch": 1.77,
1787
+ "learning_rate": 0.00017898838766933298,
1788
+ "loss": 1.7455,
1789
+ "step": 286
1790
+ },
1791
+ {
1792
+ "epoch": 1.78,
1793
+ "learning_rate": 0.00017825413301389453,
1794
+ "loss": 1.7674,
1795
+ "step": 287
1796
+ },
1797
+ {
1798
+ "epoch": 1.78,
1799
+ "learning_rate": 0.00017751917577206734,
1800
+ "loss": 1.7581,
1801
+ "step": 288
1802
+ },
1803
+ {
1804
+ "epoch": 1.79,
1805
+ "learning_rate": 0.00017678353421979548,
1806
+ "loss": 1.7714,
1807
+ "step": 289
1808
+ },
1809
+ {
1810
+ "epoch": 1.79,
1811
+ "learning_rate": 0.00017604722665003956,
1812
+ "loss": 1.7696,
1813
+ "step": 290
1814
+ },
1815
+ {
1816
+ "epoch": 1.8,
1817
+ "learning_rate": 0.0001753102713723217,
1818
+ "loss": 1.7903,
1819
+ "step": 291
1820
+ },
1821
+ {
1822
+ "epoch": 1.81,
1823
+ "learning_rate": 0.00017457268671227063,
1824
+ "loss": 1.7563,
1825
+ "step": 292
1826
+ },
1827
+ {
1828
+ "epoch": 1.81,
1829
+ "learning_rate": 0.00017383449101116547,
1830
+ "loss": 1.7828,
1831
+ "step": 293
1832
+ },
1833
+ {
1834
+ "epoch": 1.82,
1835
+ "learning_rate": 0.00017309570262548,
1836
+ "loss": 1.7417,
1837
+ "step": 294
1838
+ },
1839
+ {
1840
+ "epoch": 1.83,
1841
+ "learning_rate": 0.00017235633992642615,
1842
+ "loss": 1.7491,
1843
+ "step": 295
1844
+ },
1845
+ {
1846
+ "epoch": 1.83,
1847
+ "learning_rate": 0.000171616421299497,
1848
+ "loss": 1.7316,
1849
+ "step": 296
1850
+ },
1851
+ {
1852
+ "epoch": 1.84,
1853
+ "learning_rate": 0.0001708759651440098,
1854
+ "loss": 1.785,
1855
+ "step": 297
1856
+ },
1857
+ {
1858
+ "epoch": 1.84,
1859
+ "learning_rate": 0.00017013498987264832,
1860
+ "loss": 1.7413,
1861
+ "step": 298
1862
+ },
1863
+ {
1864
+ "epoch": 1.85,
1865
+ "learning_rate": 0.00016939351391100497,
1866
+ "loss": 1.7874,
1867
+ "step": 299
1868
+ },
1869
+ {
1870
+ "epoch": 1.86,
1871
+ "learning_rate": 0.00016865155569712278,
1872
+ "loss": 1.7377,
1873
+ "step": 300
1874
+ },
1875
+ {
1876
+ "epoch": 1.86,
1877
+ "learning_rate": 0.0001679091336810366,
1878
+ "loss": 1.7814,
1879
+ "step": 301
1880
+ },
1881
+ {
1882
+ "epoch": 1.87,
1883
+ "learning_rate": 0.00016716626632431477,
1884
+ "loss": 1.7343,
1885
+ "step": 302
1886
+ },
1887
+ {
1888
+ "epoch": 1.88,
1889
+ "learning_rate": 0.00016642297209959955,
1890
+ "loss": 1.7549,
1891
+ "step": 303
1892
+ },
1893
+ {
1894
+ "epoch": 1.88,
1895
+ "learning_rate": 0.000165679269490148,
1896
+ "loss": 1.8005,
1897
+ "step": 304
1898
+ },
1899
+ {
1900
+ "epoch": 1.89,
1901
+ "learning_rate": 0.0001649351769893725,
1902
+ "loss": 1.8071,
1903
+ "step": 305
1904
+ },
1905
+ {
1906
+ "epoch": 1.89,
1907
+ "learning_rate": 0.00016419071310038057,
1908
+ "loss": 1.777,
1909
+ "step": 306
1910
+ },
1911
+ {
1912
+ "epoch": 1.9,
1913
+ "learning_rate": 0.00016344589633551502,
1914
+ "loss": 1.7851,
1915
+ "step": 307
1916
+ },
1917
+ {
1918
+ "epoch": 1.91,
1919
+ "learning_rate": 0.00016270074521589347,
1920
+ "loss": 1.7768,
1921
+ "step": 308
1922
+ },
1923
+ {
1924
+ "epoch": 1.91,
1925
+ "learning_rate": 0.00016195527827094787,
1926
+ "loss": 1.7751,
1927
+ "step": 309
1928
+ },
1929
+ {
1930
+ "epoch": 1.92,
1931
+ "learning_rate": 0.00016120951403796364,
1932
+ "loss": 1.7342,
1933
+ "step": 310
1934
+ },
1935
+ {
1936
+ "epoch": 1.93,
1937
+ "learning_rate": 0.00016046347106161876,
1938
+ "loss": 1.7465,
1939
+ "step": 311
1940
+ },
1941
+ {
1942
+ "epoch": 1.93,
1943
+ "learning_rate": 0.00015971716789352274,
1944
+ "loss": 1.7957,
1945
+ "step": 312
1946
+ },
1947
+ {
1948
+ "epoch": 1.94,
1949
+ "learning_rate": 0.00015897062309175512,
1950
+ "loss": 1.785,
1951
+ "step": 313
1952
+ },
1953
+ {
1954
+ "epoch": 1.94,
1955
+ "learning_rate": 0.000158223855220404,
1956
+ "loss": 1.7575,
1957
+ "step": 314
1958
+ },
1959
+ {
1960
+ "epoch": 1.95,
1961
+ "learning_rate": 0.00015747688284910457,
1962
+ "loss": 1.7998,
1963
+ "step": 315
1964
+ },
1965
+ {
1966
+ "epoch": 1.96,
1967
+ "learning_rate": 0.00015672972455257723,
1968
+ "loss": 1.7767,
1969
+ "step": 316
1970
+ },
1971
+ {
1972
+ "epoch": 1.96,
1973
+ "learning_rate": 0.00015598239891016574,
1974
+ "loss": 1.7811,
1975
+ "step": 317
1976
+ },
1977
+ {
1978
+ "epoch": 1.97,
1979
+ "learning_rate": 0.00015523492450537517,
1980
+ "loss": 1.7671,
1981
+ "step": 318
1982
+ },
1983
+ {
1984
+ "epoch": 1.98,
1985
+ "learning_rate": 0.00015448731992540976,
1986
+ "loss": 1.7707,
1987
+ "step": 319
1988
+ },
1989
+ {
1990
+ "epoch": 1.98,
1991
+ "learning_rate": 0.00015373960376071093,
1992
+ "loss": 1.7737,
1993
+ "step": 320
1994
+ },
1995
+ {
1996
+ "epoch": 1.98,
1997
+ "eval_loss": 1.8478573560714722,
1998
+ "eval_runtime": 291.1645,
1999
+ "eval_samples_per_second": 205.077,
2000
+ "eval_steps_per_second": 205.077,
2001
+ "step": 320
2002
+ }
2003
+ ],
2004
+ "logging_steps": 1,
2005
+ "max_steps": 640,
2006
+ "num_input_tokens_seen": 0,
2007
+ "num_train_epochs": 4,
2008
+ "save_steps": 160,
2009
+ "total_flos": 9.369493490053939e+17,
2010
+ "train_batch_size": 1,
2011
+ "trial_name": null,
2012
+ "trial_params": null
2013
+ }
checkpoint-320/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0bb8459ca9eb55b57fe6882811eecff75c1f600c94c4d55a31c5f6345a7df8b
3
+ size 4795
checkpoint-480/README.md ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mistral-7B-v0.1
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ## Training procedure
203
+
204
+ The following `bitsandbytes` quantization config was used during training:
205
+ - quant_method: bitsandbytes
206
+ - load_in_8bit: True
207
+ - load_in_4bit: False
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: fp4
213
+ - bnb_4bit_use_double_quant: False
214
+ - bnb_4bit_compute_dtype: float32
215
+
216
+ ### Framework versions
217
+
218
+ - PEFT 0.7.0
checkpoint-480/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64,
13
+ "lora_dropout": 0.2,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "o_proj",
24
+ "down_proj",
25
+ "up_proj",
26
+ "q_proj",
27
+ "v_proj",
28
+ "k_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
checkpoint-480/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8159013a743cf8387a1c8425e7cc8ff8261da90be5d8b72a9fd27d0420f3cf89
3
+ size 1342238560
checkpoint-480/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b784f96c4323050e47cdeaf14597abd788de49aef0a1ccd2202e081d741457
3
+ size 672930145
checkpoint-480/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91743f98d2c214fa746fc921a4186ac77a39c364144b645cb384b8c851f27ce3
3
+ size 14575
checkpoint-480/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f49e7127aded5c39f52d8803e87876753b939a8ee18d6ff9a623d0bdf9ad8de
3
+ size 627
checkpoint-480/trainer_state.json ADDED
@@ -0,0 +1,3005 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8478573560714722,
3
+ "best_model_checkpoint": "./llmTechChat-lora/checkpoint-320",
4
+ "epoch": 2.964925954793453,
5
+ "eval_steps": 40,
6
+ "global_step": 480,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2.9999999999999997e-05,
14
+ "loss": 4.3577,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "eval_loss": 4.326064109802246,
20
+ "eval_runtime": 288.7431,
21
+ "eval_samples_per_second": 206.796,
22
+ "eval_steps_per_second": 206.796,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "learning_rate": 5.9999999999999995e-05,
28
+ "loss": 4.2951,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.02,
33
+ "learning_rate": 8.999999999999999e-05,
34
+ "loss": 3.9156,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.02,
39
+ "learning_rate": 0.00011999999999999999,
40
+ "loss": 3.4836,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.03,
45
+ "learning_rate": 0.00015,
46
+ "loss": 3.1743,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.04,
51
+ "learning_rate": 0.00017999999999999998,
52
+ "loss": 2.8242,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.04,
57
+ "learning_rate": 0.00020999999999999998,
58
+ "loss": 2.7478,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.05,
63
+ "learning_rate": 0.00023999999999999998,
64
+ "loss": 2.7198,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.06,
69
+ "learning_rate": 0.00027,
70
+ "loss": 2.6025,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.06,
75
+ "learning_rate": 0.0003,
76
+ "loss": 2.5337,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.07,
81
+ "learning_rate": 0.00029999813499925374,
82
+ "loss": 2.5019,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.07,
87
+ "learning_rate": 0.0002999925400433914,
88
+ "loss": 2.3393,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.08,
93
+ "learning_rate": 0.00029998321527154097,
94
+ "loss": 2.3796,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.09,
99
+ "learning_rate": 0.0002999701609155785,
100
+ "loss": 2.3054,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.09,
105
+ "learning_rate": 0.0002999533773001224,
106
+ "loss": 2.2898,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.1,
111
+ "learning_rate": 0.00029993286484252544,
112
+ "loss": 2.2254,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.11,
117
+ "learning_rate": 0.00029990862405286433,
118
+ "loss": 2.2197,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.11,
123
+ "learning_rate": 0.0002998806555339269,
124
+ "loss": 2.1797,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.12,
129
+ "learning_rate": 0.0002998489599811972,
130
+ "loss": 2.1854,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.12,
135
+ "learning_rate": 0.0002998135381828383,
136
+ "loss": 2.2105,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.13,
141
+ "learning_rate": 0.00029977439101967274,
142
+ "loss": 2.1866,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.14,
147
+ "learning_rate": 0.00029973151946516025,
148
+ "loss": 2.1718,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.14,
153
+ "learning_rate": 0.0002996849245853739,
154
+ "loss": 2.1158,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.15,
159
+ "learning_rate": 0.0002996346075389736,
160
+ "loss": 2.1495,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.16,
165
+ "learning_rate": 0.00029958056957717696,
166
+ "loss": 2.1326,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.16,
171
+ "learning_rate": 0.00029952281204372863,
172
+ "loss": 2.1391,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.17,
177
+ "learning_rate": 0.0002994613363748664,
178
+ "loss": 2.1039,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.17,
183
+ "learning_rate": 0.00029939614409928584,
184
+ "loss": 2.132,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.18,
189
+ "learning_rate": 0.00029932723683810225,
190
+ "loss": 2.1278,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.19,
195
+ "learning_rate": 0.0002992546163048102,
196
+ "loss": 2.0698,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.19,
201
+ "learning_rate": 0.00029917828430524096,
202
+ "loss": 2.0757,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.2,
207
+ "learning_rate": 0.0002990982427375177,
208
+ "loss": 2.0689,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.21,
213
+ "learning_rate": 0.0002990144935920083,
214
+ "loss": 2.0986,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.21,
219
+ "learning_rate": 0.0002989270389512756,
220
+ "loss": 2.058,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.22,
225
+ "learning_rate": 0.0002988358809900258,
226
+ "loss": 2.0451,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.22,
231
+ "learning_rate": 0.00029874102197505447,
232
+ "loss": 2.0613,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.23,
237
+ "learning_rate": 0.0002986424642651902,
238
+ "loss": 2.0796,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.24,
243
+ "learning_rate": 0.0002985402103112355,
244
+ "loss": 2.086,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.24,
249
+ "learning_rate": 0.00029843426265590656,
250
+ "loss": 2.0275,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.25,
255
+ "learning_rate": 0.0002983246239337692,
256
+ "loss": 2.0615,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.25,
261
+ "eval_loss": 2.0476396083831787,
262
+ "eval_runtime": 289.9408,
263
+ "eval_samples_per_second": 205.942,
264
+ "eval_steps_per_second": 205.942,
265
+ "step": 40
266
+ },
267
+ {
268
+ "epoch": 0.26,
269
+ "learning_rate": 0.0002982112968711744,
270
+ "loss": 2.1012,
271
+ "step": 41
272
+ },
273
+ {
274
+ "epoch": 0.26,
275
+ "learning_rate": 0.0002980942842861893,
276
+ "loss": 2.0537,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.27,
281
+ "learning_rate": 0.00029797358908852816,
282
+ "loss": 2.0595,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.27,
287
+ "learning_rate": 0.00029784921427947946,
288
+ "loss": 2.0409,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.28,
293
+ "learning_rate": 0.0002977211629518312,
294
+ "loss": 2.0045,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.29,
299
+ "learning_rate": 0.00029758943828979444,
300
+ "loss": 2.0176,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.29,
305
+ "learning_rate": 0.0002974540435689237,
306
+ "loss": 2.0189,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.3,
311
+ "learning_rate": 0.0002973149821560358,
312
+ "loss": 2.0169,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.31,
317
+ "learning_rate": 0.00029717225750912585,
318
+ "loss": 2.0553,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.31,
323
+ "learning_rate": 0.00029702587317728153,
324
+ "loss": 2.0569,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.32,
329
+ "learning_rate": 0.0002968758328005947,
330
+ "loss": 2.0522,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.32,
335
+ "learning_rate": 0.0002967221401100708,
336
+ "loss": 2.0285,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.33,
341
+ "learning_rate": 0.00029656479892753635,
342
+ "loss": 2.0266,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.34,
347
+ "learning_rate": 0.0002964038131655436,
348
+ "loss": 2.0161,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.34,
353
+ "learning_rate": 0.0002962391868272735,
354
+ "loss": 2.0122,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.35,
359
+ "learning_rate": 0.00029607092400643593,
360
+ "loss": 1.9926,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.36,
365
+ "learning_rate": 0.000295899028887168,
366
+ "loss": 2.0123,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.36,
371
+ "learning_rate": 0.0002957235057439301,
372
+ "loss": 2.0121,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.37,
377
+ "learning_rate": 0.0002955443589413994,
378
+ "loss": 2.0245,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.37,
383
+ "learning_rate": 0.00029536159293436166,
384
+ "loss": 2.0127,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.38,
389
+ "learning_rate": 0.0002951752122676,
390
+ "loss": 2.0057,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 0.39,
395
+ "learning_rate": 0.000294985221575782,
396
+ "loss": 2.0226,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 0.39,
401
+ "learning_rate": 0.0002947916255833451,
402
+ "loss": 2.0032,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 0.4,
407
+ "learning_rate": 0.00029459442910437797,
408
+ "loss": 2.045,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 0.41,
413
+ "learning_rate": 0.00029439363704250176,
414
+ "loss": 1.9794,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 0.41,
419
+ "learning_rate": 0.0002941892543907478,
420
+ "loss": 2.0009,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 0.42,
425
+ "learning_rate": 0.0002939812862314333,
426
+ "loss": 1.9508,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 0.42,
431
+ "learning_rate": 0.00029376973773603533,
432
+ "loss": 1.9913,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 0.43,
437
+ "learning_rate": 0.0002935546141650618,
438
+ "loss": 1.9762,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 0.44,
443
+ "learning_rate": 0.00029333592086792107,
444
+ "loss": 2.0,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 0.44,
449
+ "learning_rate": 0.0002931136632827886,
450
+ "loss": 1.9629,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 0.45,
455
+ "learning_rate": 0.0002928878469364719,
456
+ "loss": 2.0009,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 0.46,
461
+ "learning_rate": 0.00029265847744427303,
462
+ "loss": 1.9714,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 0.46,
467
+ "learning_rate": 0.0002924255605098489,
468
+ "loss": 1.9474,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 0.47,
473
+ "learning_rate": 0.0002921891019250697,
474
+ "loss": 1.9959,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 0.47,
479
+ "learning_rate": 0.0002919491075698746,
480
+ "loss": 1.9846,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 0.48,
485
+ "learning_rate": 0.00029170558341212554,
486
+ "loss": 1.9978,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 0.49,
491
+ "learning_rate": 0.00029145853550745904,
492
+ "loss": 1.9527,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 0.49,
497
+ "learning_rate": 0.00029120796999913546,
498
+ "loss": 1.9585,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 0.5,
503
+ "learning_rate": 0.0002909538931178862,
504
+ "loss": 1.9905,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 0.5,
509
+ "eval_loss": 1.96906578540802,
510
+ "eval_runtime": 291.8459,
511
+ "eval_samples_per_second": 204.598,
512
+ "eval_steps_per_second": 204.598,
513
+ "step": 80
514
+ },
515
+ {
516
+ "epoch": 0.51,
517
+ "learning_rate": 0.00029069631118175903,
518
+ "loss": 1.9926,
519
+ "step": 81
520
+ },
521
+ {
522
+ "epoch": 0.51,
523
+ "learning_rate": 0.00029043523059596053,
524
+ "loss": 1.9916,
525
+ "step": 82
526
+ },
527
+ {
528
+ "epoch": 0.52,
529
+ "learning_rate": 0.0002901706578526973,
530
+ "loss": 1.9545,
531
+ "step": 83
532
+ },
533
+ {
534
+ "epoch": 0.52,
535
+ "learning_rate": 0.0002899025995310141,
536
+ "loss": 1.9399,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 0.53,
541
+ "learning_rate": 0.00028963106229663063,
542
+ "loss": 1.9515,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 0.54,
547
+ "learning_rate": 0.00028935605290177535,
548
+ "loss": 1.9855,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 0.54,
553
+ "learning_rate": 0.0002890775781850181,
554
+ "loss": 2.0159,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 0.55,
559
+ "learning_rate": 0.00028879564507109946,
560
+ "loss": 1.9885,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 0.55,
565
+ "learning_rate": 0.00028851026057075916,
566
+ "loss": 1.9625,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 0.56,
571
+ "learning_rate": 0.00028822143178056114,
572
+ "loss": 1.9161,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 0.57,
577
+ "learning_rate": 0.0002879291658827176,
578
+ "loss": 1.9141,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 0.57,
583
+ "learning_rate": 0.00028763347014491,
584
+ "loss": 1.9867,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 0.58,
589
+ "learning_rate": 0.00028733435192010887,
590
+ "loss": 1.9325,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 0.59,
595
+ "learning_rate": 0.0002870318186463901,
596
+ "loss": 1.9517,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 0.59,
601
+ "learning_rate": 0.00028672587784675096,
602
+ "loss": 1.9435,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 0.6,
607
+ "learning_rate": 0.0002864165371289223,
608
+ "loss": 1.9428,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 0.6,
613
+ "learning_rate": 0.0002861038041851797,
614
+ "loss": 1.9182,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 0.61,
619
+ "learning_rate": 0.0002857876867921522,
620
+ "loss": 1.9344,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 0.62,
625
+ "learning_rate": 0.0002854681928106287,
626
+ "loss": 1.9652,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 0.62,
631
+ "learning_rate": 0.0002851453301853628,
632
+ "loss": 1.9332,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 0.63,
637
+ "learning_rate": 0.000284819106944875,
638
+ "loss": 1.9042,
639
+ "step": 101
640
+ },
641
+ {
642
+ "epoch": 0.64,
643
+ "learning_rate": 0.0002844895312012531,
644
+ "loss": 1.9571,
645
+ "step": 102
646
+ },
647
+ {
648
+ "epoch": 0.64,
649
+ "learning_rate": 0.0002841566111499505,
650
+ "loss": 1.9129,
651
+ "step": 103
652
+ },
653
+ {
654
+ "epoch": 0.65,
655
+ "learning_rate": 0.0002838203550695825,
656
+ "loss": 1.9347,
657
+ "step": 104
658
+ },
659
+ {
660
+ "epoch": 0.65,
661
+ "learning_rate": 0.00028348077132172027,
662
+ "loss": 1.9461,
663
+ "step": 105
664
+ },
665
+ {
666
+ "epoch": 0.66,
667
+ "learning_rate": 0.0002831378683506831,
668
+ "loss": 1.9188,
669
+ "step": 106
670
+ },
671
+ {
672
+ "epoch": 0.67,
673
+ "learning_rate": 0.00028279165468332823,
674
+ "loss": 1.9491,
675
+ "step": 107
676
+ },
677
+ {
678
+ "epoch": 0.67,
679
+ "learning_rate": 0.000282442138928839,
680
+ "loss": 1.961,
681
+ "step": 108
682
+ },
683
+ {
684
+ "epoch": 0.68,
685
+ "learning_rate": 0.00028208932977851067,
686
+ "loss": 1.9048,
687
+ "step": 109
688
+ },
689
+ {
690
+ "epoch": 0.69,
691
+ "learning_rate": 0.0002817332360055343,
692
+ "loss": 1.9493,
693
+ "step": 110
694
+ },
695
+ {
696
+ "epoch": 0.69,
697
+ "learning_rate": 0.0002813738664647784,
698
+ "loss": 1.9685,
699
+ "step": 111
700
+ },
701
+ {
702
+ "epoch": 0.7,
703
+ "learning_rate": 0.00028101123009256947,
704
+ "loss": 1.9054,
705
+ "step": 112
706
+ },
707
+ {
708
+ "epoch": 0.7,
709
+ "learning_rate": 0.0002806453359064686,
710
+ "loss": 1.9317,
711
+ "step": 113
712
+ },
713
+ {
714
+ "epoch": 0.71,
715
+ "learning_rate": 0.00028027619300504834,
716
+ "loss": 1.9701,
717
+ "step": 114
718
+ },
719
+ {
720
+ "epoch": 0.72,
721
+ "learning_rate": 0.0002799038105676658,
722
+ "loss": 1.9426,
723
+ "step": 115
724
+ },
725
+ {
726
+ "epoch": 0.72,
727
+ "learning_rate": 0.0002795281978542346,
728
+ "loss": 1.957,
729
+ "step": 116
730
+ },
731
+ {
732
+ "epoch": 0.73,
733
+ "learning_rate": 0.0002791493642049947,
734
+ "loss": 1.9535,
735
+ "step": 117
736
+ },
737
+ {
738
+ "epoch": 0.74,
739
+ "learning_rate": 0.0002787673190402799,
740
+ "loss": 1.9045,
741
+ "step": 118
742
+ },
743
+ {
744
+ "epoch": 0.74,
745
+ "learning_rate": 0.00027838207186028376,
746
+ "loss": 1.9575,
747
+ "step": 119
748
+ },
749
+ {
750
+ "epoch": 0.75,
751
+ "learning_rate": 0.0002779936322448233,
752
+ "loss": 1.8699,
753
+ "step": 120
754
+ },
755
+ {
756
+ "epoch": 0.75,
757
+ "eval_loss": 1.9343771934509277,
758
+ "eval_runtime": 292.8194,
759
+ "eval_samples_per_second": 203.917,
760
+ "eval_steps_per_second": 203.917,
761
+ "step": 120
762
+ },
763
+ {
764
+ "epoch": 0.75,
765
+ "learning_rate": 0.0002776020098531009,
766
+ "loss": 1.956,
767
+ "step": 121
768
+ },
769
+ {
770
+ "epoch": 0.76,
771
+ "learning_rate": 0.00027720721442346387,
772
+ "loss": 1.8958,
773
+ "step": 122
774
+ },
775
+ {
776
+ "epoch": 0.77,
777
+ "learning_rate": 0.0002768092557731625,
778
+ "loss": 1.9157,
779
+ "step": 123
780
+ },
781
+ {
782
+ "epoch": 0.77,
783
+ "learning_rate": 0.00027640814379810587,
784
+ "loss": 1.9118,
785
+ "step": 124
786
+ },
787
+ {
788
+ "epoch": 0.78,
789
+ "learning_rate": 0.0002760038884726157,
790
+ "loss": 1.9707,
791
+ "step": 125
792
+ },
793
+ {
794
+ "epoch": 0.79,
795
+ "learning_rate": 0.0002755964998491785,
796
+ "loss": 1.9563,
797
+ "step": 126
798
+ },
799
+ {
800
+ "epoch": 0.79,
801
+ "learning_rate": 0.0002751859880581954,
802
+ "loss": 1.9825,
803
+ "step": 127
804
+ },
805
+ {
806
+ "epoch": 0.8,
807
+ "learning_rate": 0.0002747723633077303,
808
+ "loss": 1.9687,
809
+ "step": 128
810
+ },
811
+ {
812
+ "epoch": 0.8,
813
+ "learning_rate": 0.0002743556358832562,
814
+ "loss": 1.9378,
815
+ "step": 129
816
+ },
817
+ {
818
+ "epoch": 0.81,
819
+ "learning_rate": 0.00027393581614739923,
820
+ "loss": 1.9307,
821
+ "step": 130
822
+ },
823
+ {
824
+ "epoch": 0.82,
825
+ "learning_rate": 0.00027351291453968086,
826
+ "loss": 1.9333,
827
+ "step": 131
828
+ },
829
+ {
830
+ "epoch": 0.82,
831
+ "learning_rate": 0.0002730869415762587,
832
+ "loss": 1.9229,
833
+ "step": 132
834
+ },
835
+ {
836
+ "epoch": 0.83,
837
+ "learning_rate": 0.0002726579078496647,
838
+ "loss": 1.911,
839
+ "step": 133
840
+ },
841
+ {
842
+ "epoch": 0.84,
843
+ "learning_rate": 0.00027222582402854176,
844
+ "loss": 1.9556,
845
+ "step": 134
846
+ },
847
+ {
848
+ "epoch": 0.84,
849
+ "learning_rate": 0.0002717907008573785,
850
+ "loss": 1.9008,
851
+ "step": 135
852
+ },
853
+ {
854
+ "epoch": 0.85,
855
+ "learning_rate": 0.0002713525491562421,
856
+ "loss": 1.9651,
857
+ "step": 136
858
+ },
859
+ {
860
+ "epoch": 0.85,
861
+ "learning_rate": 0.0002709113798205093,
862
+ "loss": 1.9337,
863
+ "step": 137
864
+ },
865
+ {
866
+ "epoch": 0.86,
867
+ "learning_rate": 0.00027046720382059526,
868
+ "loss": 1.9485,
869
+ "step": 138
870
+ },
871
+ {
872
+ "epoch": 0.87,
873
+ "learning_rate": 0.00027002003220168093,
874
+ "loss": 1.8647,
875
+ "step": 139
876
+ },
877
+ {
878
+ "epoch": 0.87,
879
+ "learning_rate": 0.0002695698760834384,
880
+ "loss": 1.9288,
881
+ "step": 140
882
+ },
883
+ {
884
+ "epoch": 0.88,
885
+ "learning_rate": 0.00026911674665975417,
886
+ "loss": 1.9535,
887
+ "step": 141
888
+ },
889
+ {
890
+ "epoch": 0.89,
891
+ "learning_rate": 0.0002686606551984512,
892
+ "loss": 1.932,
893
+ "step": 142
894
+ },
895
+ {
896
+ "epoch": 0.89,
897
+ "learning_rate": 0.00026820161304100823,
898
+ "loss": 1.9516,
899
+ "step": 143
900
+ },
901
+ {
902
+ "epoch": 0.9,
903
+ "learning_rate": 0.0002677396316022783,
904
+ "loss": 1.9347,
905
+ "step": 144
906
+ },
907
+ {
908
+ "epoch": 0.9,
909
+ "learning_rate": 0.00026727472237020447,
910
+ "loss": 1.9473,
911
+ "step": 145
912
+ },
913
+ {
914
+ "epoch": 0.91,
915
+ "learning_rate": 0.0002668068969055341,
916
+ "loss": 1.9428,
917
+ "step": 146
918
+ },
919
+ {
920
+ "epoch": 0.92,
921
+ "learning_rate": 0.0002663361668415318,
922
+ "loss": 1.9204,
923
+ "step": 147
924
+ },
925
+ {
926
+ "epoch": 0.92,
927
+ "learning_rate": 0.0002658625438836899,
928
+ "loss": 1.9039,
929
+ "step": 148
930
+ },
931
+ {
932
+ "epoch": 0.93,
933
+ "learning_rate": 0.0002653860398094373,
934
+ "loss": 1.9166,
935
+ "step": 149
936
+ },
937
+ {
938
+ "epoch": 0.94,
939
+ "learning_rate": 0.00026490666646784665,
940
+ "loss": 1.9072,
941
+ "step": 150
942
+ },
943
+ {
944
+ "epoch": 0.94,
945
+ "learning_rate": 0.00026442443577933994,
946
+ "loss": 1.9014,
947
+ "step": 151
948
+ },
949
+ {
950
+ "epoch": 0.95,
951
+ "learning_rate": 0.0002639393597353917,
952
+ "loss": 1.9272,
953
+ "step": 152
954
+ },
955
+ {
956
+ "epoch": 0.95,
957
+ "learning_rate": 0.00026345145039823097,
958
+ "loss": 1.9274,
959
+ "step": 153
960
+ },
961
+ {
962
+ "epoch": 0.96,
963
+ "learning_rate": 0.00026296071990054165,
964
+ "loss": 1.9548,
965
+ "step": 154
966
+ },
967
+ {
968
+ "epoch": 0.97,
969
+ "learning_rate": 0.0002624671804451601,
970
+ "loss": 1.928,
971
+ "step": 155
972
+ },
973
+ {
974
+ "epoch": 0.97,
975
+ "learning_rate": 0.0002619708443047725,
976
+ "loss": 1.9072,
977
+ "step": 156
978
+ },
979
+ {
980
+ "epoch": 0.98,
981
+ "learning_rate": 0.00026147172382160914,
982
+ "loss": 1.9116,
983
+ "step": 157
984
+ },
985
+ {
986
+ "epoch": 0.99,
987
+ "learning_rate": 0.0002609698314071376,
988
+ "loss": 1.915,
989
+ "step": 158
990
+ },
991
+ {
992
+ "epoch": 0.99,
993
+ "learning_rate": 0.0002604651795417543,
994
+ "loss": 1.915,
995
+ "step": 159
996
+ },
997
+ {
998
+ "epoch": 1.0,
999
+ "learning_rate": 0.0002599577807744739,
1000
+ "loss": 1.9604,
1001
+ "step": 160
1002
+ },
1003
+ {
1004
+ "epoch": 1.0,
1005
+ "eval_loss": 1.911091685295105,
1006
+ "eval_runtime": 289.5613,
1007
+ "eval_samples_per_second": 206.212,
1008
+ "eval_steps_per_second": 206.212,
1009
+ "step": 160
1010
+ },
1011
+ {
1012
+ "epoch": 1.0,
1013
+ "learning_rate": 0.0002594476477226176,
1014
+ "loss": 1.9335,
1015
+ "step": 161
1016
+ },
1017
+ {
1018
+ "epoch": 1.01,
1019
+ "learning_rate": 0.00025893479307149893,
1020
+ "loss": 1.9033,
1021
+ "step": 162
1022
+ },
1023
+ {
1024
+ "epoch": 1.0,
1025
+ "learning_rate": 0.0002584192295741087,
1026
+ "loss": 1.874,
1027
+ "step": 163
1028
+ },
1029
+ {
1030
+ "epoch": 1.01,
1031
+ "learning_rate": 0.00025790097005079764,
1032
+ "loss": 1.7896,
1033
+ "step": 164
1034
+ },
1035
+ {
1036
+ "epoch": 1.01,
1037
+ "learning_rate": 0.0002573800273889577,
1038
+ "loss": 1.7936,
1039
+ "step": 165
1040
+ },
1041
+ {
1042
+ "epoch": 1.02,
1043
+ "learning_rate": 0.00025685641454270173,
1044
+ "loss": 1.8321,
1045
+ "step": 166
1046
+ },
1047
+ {
1048
+ "epoch": 1.03,
1049
+ "learning_rate": 0.00025633014453254086,
1050
+ "loss": 1.8105,
1051
+ "step": 167
1052
+ },
1053
+ {
1054
+ "epoch": 1.03,
1055
+ "learning_rate": 0.0002558012304450613,
1056
+ "loss": 1.8068,
1057
+ "step": 168
1058
+ },
1059
+ {
1060
+ "epoch": 1.04,
1061
+ "learning_rate": 0.0002552696854325987,
1062
+ "loss": 1.7953,
1063
+ "step": 169
1064
+ },
1065
+ {
1066
+ "epoch": 1.05,
1067
+ "learning_rate": 0.0002547355227129109,
1068
+ "loss": 1.8073,
1069
+ "step": 170
1070
+ },
1071
+ {
1072
+ "epoch": 1.05,
1073
+ "learning_rate": 0.0002541987555688496,
1074
+ "loss": 1.8095,
1075
+ "step": 171
1076
+ },
1077
+ {
1078
+ "epoch": 1.06,
1079
+ "learning_rate": 0.0002536593973480297,
1080
+ "loss": 1.7939,
1081
+ "step": 172
1082
+ },
1083
+ {
1084
+ "epoch": 1.06,
1085
+ "learning_rate": 0.0002531174614624977,
1086
+ "loss": 1.8226,
1087
+ "step": 173
1088
+ },
1089
+ {
1090
+ "epoch": 1.07,
1091
+ "learning_rate": 0.000252572961388398,
1092
+ "loss": 1.7815,
1093
+ "step": 174
1094
+ },
1095
+ {
1096
+ "epoch": 1.08,
1097
+ "learning_rate": 0.00025202591066563786,
1098
+ "loss": 1.7929,
1099
+ "step": 175
1100
+ },
1101
+ {
1102
+ "epoch": 1.08,
1103
+ "learning_rate": 0.00025147632289755075,
1104
+ "loss": 1.8027,
1105
+ "step": 176
1106
+ },
1107
+ {
1108
+ "epoch": 1.09,
1109
+ "learning_rate": 0.0002509242117505579,
1110
+ "loss": 1.8349,
1111
+ "step": 177
1112
+ },
1113
+ {
1114
+ "epoch": 1.1,
1115
+ "learning_rate": 0.0002503695909538287,
1116
+ "loss": 1.7828,
1117
+ "step": 178
1118
+ },
1119
+ {
1120
+ "epoch": 1.1,
1121
+ "learning_rate": 0.0002498124742989391,
1122
+ "loss": 1.814,
1123
+ "step": 179
1124
+ },
1125
+ {
1126
+ "epoch": 1.11,
1127
+ "learning_rate": 0.0002492528756395289,
1128
+ "loss": 1.821,
1129
+ "step": 180
1130
+ },
1131
+ {
1132
+ "epoch": 1.11,
1133
+ "learning_rate": 0.0002486908088909569,
1134
+ "loss": 1.8023,
1135
+ "step": 181
1136
+ },
1137
+ {
1138
+ "epoch": 1.12,
1139
+ "learning_rate": 0.0002481262880299552,
1140
+ "loss": 1.7953,
1141
+ "step": 182
1142
+ },
1143
+ {
1144
+ "epoch": 1.13,
1145
+ "learning_rate": 0.0002475593270942814,
1146
+ "loss": 1.8497,
1147
+ "step": 183
1148
+ },
1149
+ {
1150
+ "epoch": 1.13,
1151
+ "learning_rate": 0.0002469899401823699,
1152
+ "loss": 1.7957,
1153
+ "step": 184
1154
+ },
1155
+ {
1156
+ "epoch": 1.14,
1157
+ "learning_rate": 0.0002464181414529809,
1158
+ "loss": 1.7958,
1159
+ "step": 185
1160
+ },
1161
+ {
1162
+ "epoch": 1.15,
1163
+ "learning_rate": 0.0002458439451248484,
1164
+ "loss": 1.8024,
1165
+ "step": 186
1166
+ },
1167
+ {
1168
+ "epoch": 1.15,
1169
+ "learning_rate": 0.0002452673654763268,
1170
+ "loss": 1.8306,
1171
+ "step": 187
1172
+ },
1173
+ {
1174
+ "epoch": 1.16,
1175
+ "learning_rate": 0.0002446884168450358,
1176
+ "loss": 1.8174,
1177
+ "step": 188
1178
+ },
1179
+ {
1180
+ "epoch": 1.16,
1181
+ "learning_rate": 0.00024410711362750386,
1182
+ "loss": 1.8032,
1183
+ "step": 189
1184
+ },
1185
+ {
1186
+ "epoch": 1.17,
1187
+ "learning_rate": 0.00024352347027881003,
1188
+ "loss": 1.8087,
1189
+ "step": 190
1190
+ },
1191
+ {
1192
+ "epoch": 1.18,
1193
+ "learning_rate": 0.0002429375013122247,
1194
+ "loss": 1.7648,
1195
+ "step": 191
1196
+ },
1197
+ {
1198
+ "epoch": 1.18,
1199
+ "learning_rate": 0.0002423492212988487,
1200
+ "loss": 1.8544,
1201
+ "step": 192
1202
+ },
1203
+ {
1204
+ "epoch": 1.19,
1205
+ "learning_rate": 0.00024175864486725092,
1206
+ "loss": 1.7978,
1207
+ "step": 193
1208
+ },
1209
+ {
1210
+ "epoch": 1.2,
1211
+ "learning_rate": 0.0002411657867031045,
1212
+ "loss": 1.7866,
1213
+ "step": 194
1214
+ },
1215
+ {
1216
+ "epoch": 1.2,
1217
+ "learning_rate": 0.0002405706615488216,
1218
+ "loss": 1.8074,
1219
+ "step": 195
1220
+ },
1221
+ {
1222
+ "epoch": 1.21,
1223
+ "learning_rate": 0.00023997328420318704,
1224
+ "loss": 1.7842,
1225
+ "step": 196
1226
+ },
1227
+ {
1228
+ "epoch": 1.21,
1229
+ "learning_rate": 0.00023937366952099005,
1230
+ "loss": 1.781,
1231
+ "step": 197
1232
+ },
1233
+ {
1234
+ "epoch": 1.22,
1235
+ "learning_rate": 0.00023877183241265514,
1236
+ "loss": 1.786,
1237
+ "step": 198
1238
+ },
1239
+ {
1240
+ "epoch": 1.23,
1241
+ "learning_rate": 0.00023816778784387094,
1242
+ "loss": 1.8091,
1243
+ "step": 199
1244
+ },
1245
+ {
1246
+ "epoch": 1.23,
1247
+ "learning_rate": 0.00023756155083521846,
1248
+ "loss": 1.7684,
1249
+ "step": 200
1250
+ },
1251
+ {
1252
+ "epoch": 1.23,
1253
+ "eval_loss": 1.897764801979065,
1254
+ "eval_runtime": 292.524,
1255
+ "eval_samples_per_second": 204.123,
1256
+ "eval_steps_per_second": 204.123,
1257
+ "step": 200
1258
+ },
1259
+ {
1260
+ "epoch": 1.24,
1261
+ "learning_rate": 0.00023695313646179735,
1262
+ "loss": 1.7693,
1263
+ "step": 201
1264
+ },
1265
+ {
1266
+ "epoch": 1.25,
1267
+ "learning_rate": 0.00023634255985285102,
1268
+ "loss": 1.7598,
1269
+ "step": 202
1270
+ },
1271
+ {
1272
+ "epoch": 1.25,
1273
+ "learning_rate": 0.00023572983619139058,
1274
+ "loss": 1.8441,
1275
+ "step": 203
1276
+ },
1277
+ {
1278
+ "epoch": 1.26,
1279
+ "learning_rate": 0.00023511498071381726,
1280
+ "loss": 1.7768,
1281
+ "step": 204
1282
+ },
1283
+ {
1284
+ "epoch": 1.26,
1285
+ "learning_rate": 0.00023449800870954326,
1286
+ "loss": 1.784,
1287
+ "step": 205
1288
+ },
1289
+ {
1290
+ "epoch": 1.27,
1291
+ "learning_rate": 0.00023387893552061199,
1292
+ "loss": 1.7905,
1293
+ "step": 206
1294
+ },
1295
+ {
1296
+ "epoch": 1.28,
1297
+ "learning_rate": 0.00023325777654131623,
1298
+ "loss": 1.7996,
1299
+ "step": 207
1300
+ },
1301
+ {
1302
+ "epoch": 1.28,
1303
+ "learning_rate": 0.00023263454721781537,
1304
+ "loss": 1.7546,
1305
+ "step": 208
1306
+ },
1307
+ {
1308
+ "epoch": 1.29,
1309
+ "learning_rate": 0.0002320092630477515,
1310
+ "loss": 1.8043,
1311
+ "step": 209
1312
+ },
1313
+ {
1314
+ "epoch": 1.3,
1315
+ "learning_rate": 0.0002313819395798639,
1316
+ "loss": 1.7817,
1317
+ "step": 210
1318
+ },
1319
+ {
1320
+ "epoch": 1.3,
1321
+ "learning_rate": 0.00023075259241360233,
1322
+ "loss": 1.8117,
1323
+ "step": 211
1324
+ },
1325
+ {
1326
+ "epoch": 1.31,
1327
+ "learning_rate": 0.00023012123719873926,
1328
+ "loss": 1.7798,
1329
+ "step": 212
1330
+ },
1331
+ {
1332
+ "epoch": 1.31,
1333
+ "learning_rate": 0.0002294878896349807,
1334
+ "loss": 1.763,
1335
+ "step": 213
1336
+ },
1337
+ {
1338
+ "epoch": 1.32,
1339
+ "learning_rate": 0.00022885256547157566,
1340
+ "loss": 1.8169,
1341
+ "step": 214
1342
+ },
1343
+ {
1344
+ "epoch": 1.33,
1345
+ "learning_rate": 0.0002282152805069247,
1346
+ "loss": 1.797,
1347
+ "step": 215
1348
+ },
1349
+ {
1350
+ "epoch": 1.33,
1351
+ "learning_rate": 0.00022757605058818688,
1352
+ "loss": 1.7768,
1353
+ "step": 216
1354
+ },
1355
+ {
1356
+ "epoch": 1.34,
1357
+ "learning_rate": 0.0002269348916108859,
1358
+ "loss": 1.8005,
1359
+ "step": 217
1360
+ },
1361
+ {
1362
+ "epoch": 1.35,
1363
+ "learning_rate": 0.00022629181951851473,
1364
+ "loss": 1.7734,
1365
+ "step": 218
1366
+ },
1367
+ {
1368
+ "epoch": 1.35,
1369
+ "learning_rate": 0.0002256468503021391,
1370
+ "loss": 1.774,
1371
+ "step": 219
1372
+ },
1373
+ {
1374
+ "epoch": 1.36,
1375
+ "learning_rate": 0.000225,
1376
+ "loss": 1.7865,
1377
+ "step": 220
1378
+ },
1379
+ {
1380
+ "epoch": 1.36,
1381
+ "learning_rate": 0.00022435128469711465,
1382
+ "loss": 1.7613,
1383
+ "step": 221
1384
+ },
1385
+ {
1386
+ "epoch": 1.37,
1387
+ "learning_rate": 0.00022370072052487668,
1388
+ "loss": 1.8013,
1389
+ "step": 222
1390
+ },
1391
+ {
1392
+ "epoch": 1.38,
1393
+ "learning_rate": 0.00022304832366065505,
1394
+ "loss": 1.7617,
1395
+ "step": 223
1396
+ },
1397
+ {
1398
+ "epoch": 1.38,
1399
+ "learning_rate": 0.00022239411032739162,
1400
+ "loss": 1.7323,
1401
+ "step": 224
1402
+ },
1403
+ {
1404
+ "epoch": 1.39,
1405
+ "learning_rate": 0.00022173809679319772,
1406
+ "loss": 1.7838,
1407
+ "step": 225
1408
+ },
1409
+ {
1410
+ "epoch": 1.4,
1411
+ "learning_rate": 0.0002210802993709498,
1412
+ "loss": 1.8099,
1413
+ "step": 226
1414
+ },
1415
+ {
1416
+ "epoch": 1.4,
1417
+ "learning_rate": 0.00022042073441788358,
1418
+ "loss": 1.82,
1419
+ "step": 227
1420
+ },
1421
+ {
1422
+ "epoch": 1.41,
1423
+ "learning_rate": 0.00021975941833518757,
1424
+ "loss": 1.772,
1425
+ "step": 228
1426
+ },
1427
+ {
1428
+ "epoch": 1.41,
1429
+ "learning_rate": 0.00021909636756759483,
1430
+ "loss": 1.8044,
1431
+ "step": 229
1432
+ },
1433
+ {
1434
+ "epoch": 1.42,
1435
+ "learning_rate": 0.00021843159860297442,
1436
+ "loss": 1.7679,
1437
+ "step": 230
1438
+ },
1439
+ {
1440
+ "epoch": 1.43,
1441
+ "learning_rate": 0.00021776512797192123,
1442
+ "loss": 1.7786,
1443
+ "step": 231
1444
+ },
1445
+ {
1446
+ "epoch": 1.43,
1447
+ "learning_rate": 0.00021709697224734487,
1448
+ "loss": 1.8305,
1449
+ "step": 232
1450
+ },
1451
+ {
1452
+ "epoch": 1.44,
1453
+ "learning_rate": 0.00021642714804405772,
1454
+ "loss": 1.8044,
1455
+ "step": 233
1456
+ },
1457
+ {
1458
+ "epoch": 1.45,
1459
+ "learning_rate": 0.0002157556720183616,
1460
+ "loss": 1.7838,
1461
+ "step": 234
1462
+ },
1463
+ {
1464
+ "epoch": 1.45,
1465
+ "learning_rate": 0.00021508256086763368,
1466
+ "loss": 1.7639,
1467
+ "step": 235
1468
+ },
1469
+ {
1470
+ "epoch": 1.46,
1471
+ "learning_rate": 0.00021440783132991136,
1472
+ "loss": 1.8067,
1473
+ "step": 236
1474
+ },
1475
+ {
1476
+ "epoch": 1.46,
1477
+ "learning_rate": 0.00021373150018347576,
1478
+ "loss": 1.772,
1479
+ "step": 237
1480
+ },
1481
+ {
1482
+ "epoch": 1.47,
1483
+ "learning_rate": 0.0002130535842464348,
1484
+ "loss": 1.7985,
1485
+ "step": 238
1486
+ },
1487
+ {
1488
+ "epoch": 1.48,
1489
+ "learning_rate": 0.00021237410037630493,
1490
+ "loss": 1.7746,
1491
+ "step": 239
1492
+ },
1493
+ {
1494
+ "epoch": 1.48,
1495
+ "learning_rate": 0.00021169306546959174,
1496
+ "loss": 1.7673,
1497
+ "step": 240
1498
+ },
1499
+ {
1500
+ "epoch": 1.48,
1501
+ "eval_loss": 1.880852222442627,
1502
+ "eval_runtime": 291.0717,
1503
+ "eval_samples_per_second": 205.142,
1504
+ "eval_steps_per_second": 205.142,
1505
+ "step": 240
1506
+ },
1507
+ {
1508
+ "epoch": 1.49,
1509
+ "learning_rate": 0.00021101049646137003,
1510
+ "loss": 1.7555,
1511
+ "step": 241
1512
+ },
1513
+ {
1514
+ "epoch": 1.49,
1515
+ "learning_rate": 0.0002103264103248626,
1516
+ "loss": 1.7722,
1517
+ "step": 242
1518
+ },
1519
+ {
1520
+ "epoch": 1.5,
1521
+ "learning_rate": 0.00020964082407101824,
1522
+ "loss": 1.7686,
1523
+ "step": 243
1524
+ },
1525
+ {
1526
+ "epoch": 1.51,
1527
+ "learning_rate": 0.00020895375474808852,
1528
+ "loss": 1.7625,
1529
+ "step": 244
1530
+ },
1531
+ {
1532
+ "epoch": 1.51,
1533
+ "learning_rate": 0.0002082652194412042,
1534
+ "loss": 1.7524,
1535
+ "step": 245
1536
+ },
1537
+ {
1538
+ "epoch": 1.52,
1539
+ "learning_rate": 0.00020757523527195005,
1540
+ "loss": 1.7785,
1541
+ "step": 246
1542
+ },
1543
+ {
1544
+ "epoch": 1.53,
1545
+ "learning_rate": 0.00020688381939793928,
1546
+ "loss": 1.7901,
1547
+ "step": 247
1548
+ },
1549
+ {
1550
+ "epoch": 1.53,
1551
+ "learning_rate": 0.0002061909890123868,
1552
+ "loss": 1.7941,
1553
+ "step": 248
1554
+ },
1555
+ {
1556
+ "epoch": 1.54,
1557
+ "learning_rate": 0.00020549676134368184,
1558
+ "loss": 1.8157,
1559
+ "step": 249
1560
+ },
1561
+ {
1562
+ "epoch": 1.54,
1563
+ "learning_rate": 0.00020480115365495926,
1564
+ "loss": 1.8354,
1565
+ "step": 250
1566
+ },
1567
+ {
1568
+ "epoch": 1.55,
1569
+ "learning_rate": 0.00020410418324367055,
1570
+ "loss": 1.7764,
1571
+ "step": 251
1572
+ },
1573
+ {
1574
+ "epoch": 1.56,
1575
+ "learning_rate": 0.0002034058674411535,
1576
+ "loss": 1.7677,
1577
+ "step": 252
1578
+ },
1579
+ {
1580
+ "epoch": 1.56,
1581
+ "learning_rate": 0.0002027062236122014,
1582
+ "loss": 1.7739,
1583
+ "step": 253
1584
+ },
1585
+ {
1586
+ "epoch": 1.57,
1587
+ "learning_rate": 0.00020200526915463107,
1588
+ "loss": 1.7746,
1589
+ "step": 254
1590
+ },
1591
+ {
1592
+ "epoch": 1.58,
1593
+ "learning_rate": 0.00020130302149885031,
1594
+ "loss": 1.7675,
1595
+ "step": 255
1596
+ },
1597
+ {
1598
+ "epoch": 1.58,
1599
+ "learning_rate": 0.0002005994981074245,
1600
+ "loss": 1.737,
1601
+ "step": 256
1602
+ },
1603
+ {
1604
+ "epoch": 1.59,
1605
+ "learning_rate": 0.0001998947164746423,
1606
+ "loss": 1.8318,
1607
+ "step": 257
1608
+ },
1609
+ {
1610
+ "epoch": 1.59,
1611
+ "learning_rate": 0.00019918869412608066,
1612
+ "loss": 1.7959,
1613
+ "step": 258
1614
+ },
1615
+ {
1616
+ "epoch": 1.6,
1617
+ "learning_rate": 0.00019848144861816898,
1618
+ "loss": 1.7567,
1619
+ "step": 259
1620
+ },
1621
+ {
1622
+ "epoch": 1.61,
1623
+ "learning_rate": 0.00019777299753775265,
1624
+ "loss": 1.7896,
1625
+ "step": 260
1626
+ },
1627
+ {
1628
+ "epoch": 1.61,
1629
+ "learning_rate": 0.0001970633585016556,
1630
+ "loss": 1.7706,
1631
+ "step": 261
1632
+ },
1633
+ {
1634
+ "epoch": 1.62,
1635
+ "learning_rate": 0.0001963525491562421,
1636
+ "loss": 1.7561,
1637
+ "step": 262
1638
+ },
1639
+ {
1640
+ "epoch": 1.63,
1641
+ "learning_rate": 0.00019564058717697847,
1642
+ "loss": 1.8023,
1643
+ "step": 263
1644
+ },
1645
+ {
1646
+ "epoch": 1.63,
1647
+ "learning_rate": 0.00019492749026799288,
1648
+ "loss": 1.8121,
1649
+ "step": 264
1650
+ },
1651
+ {
1652
+ "epoch": 1.64,
1653
+ "learning_rate": 0.00019421327616163563,
1654
+ "loss": 1.791,
1655
+ "step": 265
1656
+ },
1657
+ {
1658
+ "epoch": 1.64,
1659
+ "learning_rate": 0.00019349796261803793,
1660
+ "loss": 1.7758,
1661
+ "step": 266
1662
+ },
1663
+ {
1664
+ "epoch": 1.65,
1665
+ "learning_rate": 0.00019278156742467032,
1666
+ "loss": 1.755,
1667
+ "step": 267
1668
+ },
1669
+ {
1670
+ "epoch": 1.66,
1671
+ "learning_rate": 0.0001920641083959004,
1672
+ "loss": 1.6986,
1673
+ "step": 268
1674
+ },
1675
+ {
1676
+ "epoch": 1.66,
1677
+ "learning_rate": 0.00019134560337254986,
1678
+ "loss": 1.7569,
1679
+ "step": 269
1680
+ },
1681
+ {
1682
+ "epoch": 1.67,
1683
+ "learning_rate": 0.00019062607022145078,
1684
+ "loss": 1.7849,
1685
+ "step": 270
1686
+ },
1687
+ {
1688
+ "epoch": 1.68,
1689
+ "learning_rate": 0.00018990552683500125,
1690
+ "loss": 1.7833,
1691
+ "step": 271
1692
+ },
1693
+ {
1694
+ "epoch": 1.68,
1695
+ "learning_rate": 0.00018918399113072076,
1696
+ "loss": 1.7739,
1697
+ "step": 272
1698
+ },
1699
+ {
1700
+ "epoch": 1.69,
1701
+ "learning_rate": 0.00018846148105080424,
1702
+ "loss": 1.7765,
1703
+ "step": 273
1704
+ },
1705
+ {
1706
+ "epoch": 1.69,
1707
+ "learning_rate": 0.00018773801456167628,
1708
+ "loss": 1.6825,
1709
+ "step": 274
1710
+ },
1711
+ {
1712
+ "epoch": 1.7,
1713
+ "learning_rate": 0.00018701360965354402,
1714
+ "loss": 1.758,
1715
+ "step": 275
1716
+ },
1717
+ {
1718
+ "epoch": 1.71,
1719
+ "learning_rate": 0.00018628828433995013,
1720
+ "loss": 1.7477,
1721
+ "step": 276
1722
+ },
1723
+ {
1724
+ "epoch": 1.71,
1725
+ "learning_rate": 0.00018556205665732462,
1726
+ "loss": 1.7757,
1727
+ "step": 277
1728
+ },
1729
+ {
1730
+ "epoch": 1.72,
1731
+ "learning_rate": 0.00018483494466453636,
1732
+ "loss": 1.7946,
1733
+ "step": 278
1734
+ },
1735
+ {
1736
+ "epoch": 1.73,
1737
+ "learning_rate": 0.0001841069664424442,
1738
+ "loss": 1.7968,
1739
+ "step": 279
1740
+ },
1741
+ {
1742
+ "epoch": 1.73,
1743
+ "learning_rate": 0.00018337814009344714,
1744
+ "loss": 1.7296,
1745
+ "step": 280
1746
+ },
1747
+ {
1748
+ "epoch": 1.73,
1749
+ "eval_loss": 1.8629968166351318,
1750
+ "eval_runtime": 293.6177,
1751
+ "eval_samples_per_second": 203.363,
1752
+ "eval_steps_per_second": 203.363,
1753
+ "step": 280
1754
+ },
1755
+ {
1756
+ "epoch": 1.74,
1757
+ "learning_rate": 0.00018264848374103433,
1758
+ "loss": 1.7516,
1759
+ "step": 281
1760
+ },
1761
+ {
1762
+ "epoch": 1.74,
1763
+ "learning_rate": 0.00018191801552933432,
1764
+ "loss": 1.7466,
1765
+ "step": 282
1766
+ },
1767
+ {
1768
+ "epoch": 1.75,
1769
+ "learning_rate": 0.00018118675362266385,
1770
+ "loss": 1.7304,
1771
+ "step": 283
1772
+ },
1773
+ {
1774
+ "epoch": 1.76,
1775
+ "learning_rate": 0.0001804547162050764,
1776
+ "loss": 1.7519,
1777
+ "step": 284
1778
+ },
1779
+ {
1780
+ "epoch": 1.76,
1781
+ "learning_rate": 0.0001797219214799096,
1782
+ "loss": 1.7721,
1783
+ "step": 285
1784
+ },
1785
+ {
1786
+ "epoch": 1.77,
1787
+ "learning_rate": 0.00017898838766933298,
1788
+ "loss": 1.7455,
1789
+ "step": 286
1790
+ },
1791
+ {
1792
+ "epoch": 1.78,
1793
+ "learning_rate": 0.00017825413301389453,
1794
+ "loss": 1.7674,
1795
+ "step": 287
1796
+ },
1797
+ {
1798
+ "epoch": 1.78,
1799
+ "learning_rate": 0.00017751917577206734,
1800
+ "loss": 1.7581,
1801
+ "step": 288
1802
+ },
1803
+ {
1804
+ "epoch": 1.79,
1805
+ "learning_rate": 0.00017678353421979548,
1806
+ "loss": 1.7714,
1807
+ "step": 289
1808
+ },
1809
+ {
1810
+ "epoch": 1.79,
1811
+ "learning_rate": 0.00017604722665003956,
1812
+ "loss": 1.7696,
1813
+ "step": 290
1814
+ },
1815
+ {
1816
+ "epoch": 1.8,
1817
+ "learning_rate": 0.0001753102713723217,
1818
+ "loss": 1.7903,
1819
+ "step": 291
1820
+ },
1821
+ {
1822
+ "epoch": 1.81,
1823
+ "learning_rate": 0.00017457268671227063,
1824
+ "loss": 1.7563,
1825
+ "step": 292
1826
+ },
1827
+ {
1828
+ "epoch": 1.81,
1829
+ "learning_rate": 0.00017383449101116547,
1830
+ "loss": 1.7828,
1831
+ "step": 293
1832
+ },
1833
+ {
1834
+ "epoch": 1.82,
1835
+ "learning_rate": 0.00017309570262548,
1836
+ "loss": 1.7417,
1837
+ "step": 294
1838
+ },
1839
+ {
1840
+ "epoch": 1.83,
1841
+ "learning_rate": 0.00017235633992642615,
1842
+ "loss": 1.7491,
1843
+ "step": 295
1844
+ },
1845
+ {
1846
+ "epoch": 1.83,
1847
+ "learning_rate": 0.000171616421299497,
1848
+ "loss": 1.7316,
1849
+ "step": 296
1850
+ },
1851
+ {
1852
+ "epoch": 1.84,
1853
+ "learning_rate": 0.0001708759651440098,
1854
+ "loss": 1.785,
1855
+ "step": 297
1856
+ },
1857
+ {
1858
+ "epoch": 1.84,
1859
+ "learning_rate": 0.00017013498987264832,
1860
+ "loss": 1.7413,
1861
+ "step": 298
1862
+ },
1863
+ {
1864
+ "epoch": 1.85,
1865
+ "learning_rate": 0.00016939351391100497,
1866
+ "loss": 1.7874,
1867
+ "step": 299
1868
+ },
1869
+ {
1870
+ "epoch": 1.86,
1871
+ "learning_rate": 0.00016865155569712278,
1872
+ "loss": 1.7377,
1873
+ "step": 300
1874
+ },
1875
+ {
1876
+ "epoch": 1.86,
1877
+ "learning_rate": 0.0001679091336810366,
1878
+ "loss": 1.7814,
1879
+ "step": 301
1880
+ },
1881
+ {
1882
+ "epoch": 1.87,
1883
+ "learning_rate": 0.00016716626632431477,
1884
+ "loss": 1.7343,
1885
+ "step": 302
1886
+ },
1887
+ {
1888
+ "epoch": 1.88,
1889
+ "learning_rate": 0.00016642297209959955,
1890
+ "loss": 1.7549,
1891
+ "step": 303
1892
+ },
1893
+ {
1894
+ "epoch": 1.88,
1895
+ "learning_rate": 0.000165679269490148,
1896
+ "loss": 1.8005,
1897
+ "step": 304
1898
+ },
1899
+ {
1900
+ "epoch": 1.89,
1901
+ "learning_rate": 0.0001649351769893725,
1902
+ "loss": 1.8071,
1903
+ "step": 305
1904
+ },
1905
+ {
1906
+ "epoch": 1.89,
1907
+ "learning_rate": 0.00016419071310038057,
1908
+ "loss": 1.777,
1909
+ "step": 306
1910
+ },
1911
+ {
1912
+ "epoch": 1.9,
1913
+ "learning_rate": 0.00016344589633551502,
1914
+ "loss": 1.7851,
1915
+ "step": 307
1916
+ },
1917
+ {
1918
+ "epoch": 1.91,
1919
+ "learning_rate": 0.00016270074521589347,
1920
+ "loss": 1.7768,
1921
+ "step": 308
1922
+ },
1923
+ {
1924
+ "epoch": 1.91,
1925
+ "learning_rate": 0.00016195527827094787,
1926
+ "loss": 1.7751,
1927
+ "step": 309
1928
+ },
1929
+ {
1930
+ "epoch": 1.92,
1931
+ "learning_rate": 0.00016120951403796364,
1932
+ "loss": 1.7342,
1933
+ "step": 310
1934
+ },
1935
+ {
1936
+ "epoch": 1.93,
1937
+ "learning_rate": 0.00016046347106161876,
1938
+ "loss": 1.7465,
1939
+ "step": 311
1940
+ },
1941
+ {
1942
+ "epoch": 1.93,
1943
+ "learning_rate": 0.00015971716789352274,
1944
+ "loss": 1.7957,
1945
+ "step": 312
1946
+ },
1947
+ {
1948
+ "epoch": 1.94,
1949
+ "learning_rate": 0.00015897062309175512,
1950
+ "loss": 1.785,
1951
+ "step": 313
1952
+ },
1953
+ {
1954
+ "epoch": 1.94,
1955
+ "learning_rate": 0.000158223855220404,
1956
+ "loss": 1.7575,
1957
+ "step": 314
1958
+ },
1959
+ {
1960
+ "epoch": 1.95,
1961
+ "learning_rate": 0.00015747688284910457,
1962
+ "loss": 1.7998,
1963
+ "step": 315
1964
+ },
1965
+ {
1966
+ "epoch": 1.96,
1967
+ "learning_rate": 0.00015672972455257723,
1968
+ "loss": 1.7767,
1969
+ "step": 316
1970
+ },
1971
+ {
1972
+ "epoch": 1.96,
1973
+ "learning_rate": 0.00015598239891016574,
1974
+ "loss": 1.7811,
1975
+ "step": 317
1976
+ },
1977
+ {
1978
+ "epoch": 1.97,
1979
+ "learning_rate": 0.00015523492450537517,
1980
+ "loss": 1.7671,
1981
+ "step": 318
1982
+ },
1983
+ {
1984
+ "epoch": 1.98,
1985
+ "learning_rate": 0.00015448731992540976,
1986
+ "loss": 1.7707,
1987
+ "step": 319
1988
+ },
1989
+ {
1990
+ "epoch": 1.98,
1991
+ "learning_rate": 0.00015373960376071093,
1992
+ "loss": 1.7737,
1993
+ "step": 320
1994
+ },
1995
+ {
1996
+ "epoch": 1.98,
1997
+ "eval_loss": 1.8478573560714722,
1998
+ "eval_runtime": 291.1645,
1999
+ "eval_samples_per_second": 205.077,
2000
+ "eval_steps_per_second": 205.077,
2001
+ "step": 320
2002
+ },
2003
+ {
2004
+ "epoch": 1.99,
2005
+ "learning_rate": 0.0001529917946044947,
2006
+ "loss": 1.7395,
2007
+ "step": 321
2008
+ },
2009
+ {
2010
+ "epoch": 1.99,
2011
+ "learning_rate": 0.00015224391105228953,
2012
+ "loss": 1.7596,
2013
+ "step": 322
2014
+ },
2015
+ {
2016
+ "epoch": 2.0,
2017
+ "learning_rate": 0.00015149597170147387,
2018
+ "loss": 1.7475,
2019
+ "step": 323
2020
+ },
2021
+ {
2022
+ "epoch": 2.01,
2023
+ "learning_rate": 0.0001507479951508137,
2024
+ "loss": 1.7828,
2025
+ "step": 324
2026
+ },
2027
+ {
2028
+ "epoch": 2.01,
2029
+ "learning_rate": 0.00015,
2030
+ "loss": 1.7394,
2031
+ "step": 325
2032
+ },
2033
+ {
2034
+ "epoch": 2.0,
2035
+ "learning_rate": 0.0001492520048491863,
2036
+ "loss": 1.6713,
2037
+ "step": 326
2038
+ },
2039
+ {
2040
+ "epoch": 2.01,
2041
+ "learning_rate": 0.0001485040282985261,
2042
+ "loss": 1.5788,
2043
+ "step": 327
2044
+ },
2045
+ {
2046
+ "epoch": 2.02,
2047
+ "learning_rate": 0.00014775608894771047,
2048
+ "loss": 1.6083,
2049
+ "step": 328
2050
+ },
2051
+ {
2052
+ "epoch": 2.02,
2053
+ "learning_rate": 0.0001470082053955053,
2054
+ "loss": 1.5962,
2055
+ "step": 329
2056
+ },
2057
+ {
2058
+ "epoch": 2.03,
2059
+ "learning_rate": 0.00014626039623928907,
2060
+ "loss": 1.564,
2061
+ "step": 330
2062
+ },
2063
+ {
2064
+ "epoch": 2.04,
2065
+ "learning_rate": 0.00014551268007459024,
2066
+ "loss": 1.5529,
2067
+ "step": 331
2068
+ },
2069
+ {
2070
+ "epoch": 2.04,
2071
+ "learning_rate": 0.0001447650754946249,
2072
+ "loss": 1.5699,
2073
+ "step": 332
2074
+ },
2075
+ {
2076
+ "epoch": 2.05,
2077
+ "learning_rate": 0.0001440176010898343,
2078
+ "loss": 1.5667,
2079
+ "step": 333
2080
+ },
2081
+ {
2082
+ "epoch": 2.05,
2083
+ "learning_rate": 0.0001432702754474228,
2084
+ "loss": 1.5275,
2085
+ "step": 334
2086
+ },
2087
+ {
2088
+ "epoch": 2.06,
2089
+ "learning_rate": 0.0001425231171508954,
2090
+ "loss": 1.5585,
2091
+ "step": 335
2092
+ },
2093
+ {
2094
+ "epoch": 2.07,
2095
+ "learning_rate": 0.00014177614477959595,
2096
+ "loss": 1.5753,
2097
+ "step": 336
2098
+ },
2099
+ {
2100
+ "epoch": 2.07,
2101
+ "learning_rate": 0.00014102937690824486,
2102
+ "loss": 1.5479,
2103
+ "step": 337
2104
+ },
2105
+ {
2106
+ "epoch": 2.08,
2107
+ "learning_rate": 0.00014028283210647718,
2108
+ "loss": 1.5721,
2109
+ "step": 338
2110
+ },
2111
+ {
2112
+ "epoch": 2.09,
2113
+ "learning_rate": 0.00013953652893838119,
2114
+ "loss": 1.5526,
2115
+ "step": 339
2116
+ },
2117
+ {
2118
+ "epoch": 2.09,
2119
+ "learning_rate": 0.00013879048596203636,
2120
+ "loss": 1.5777,
2121
+ "step": 340
2122
+ },
2123
+ {
2124
+ "epoch": 2.1,
2125
+ "learning_rate": 0.00013804472172905213,
2126
+ "loss": 1.5216,
2127
+ "step": 341
2128
+ },
2129
+ {
2130
+ "epoch": 2.1,
2131
+ "learning_rate": 0.0001372992547841065,
2132
+ "loss": 1.5776,
2133
+ "step": 342
2134
+ },
2135
+ {
2136
+ "epoch": 2.11,
2137
+ "learning_rate": 0.00013655410366448498,
2138
+ "loss": 1.5717,
2139
+ "step": 343
2140
+ },
2141
+ {
2142
+ "epoch": 2.12,
2143
+ "learning_rate": 0.00013580928689961943,
2144
+ "loss": 1.5628,
2145
+ "step": 344
2146
+ },
2147
+ {
2148
+ "epoch": 2.12,
2149
+ "learning_rate": 0.0001350648230106275,
2150
+ "loss": 1.5333,
2151
+ "step": 345
2152
+ },
2153
+ {
2154
+ "epoch": 2.13,
2155
+ "learning_rate": 0.000134320730509852,
2156
+ "loss": 1.5271,
2157
+ "step": 346
2158
+ },
2159
+ {
2160
+ "epoch": 2.14,
2161
+ "learning_rate": 0.00013357702790040048,
2162
+ "loss": 1.5672,
2163
+ "step": 347
2164
+ },
2165
+ {
2166
+ "epoch": 2.14,
2167
+ "learning_rate": 0.00013283373367568523,
2168
+ "loss": 1.5619,
2169
+ "step": 348
2170
+ },
2171
+ {
2172
+ "epoch": 2.15,
2173
+ "learning_rate": 0.00013209086631896336,
2174
+ "loss": 1.5461,
2175
+ "step": 349
2176
+ },
2177
+ {
2178
+ "epoch": 2.15,
2179
+ "learning_rate": 0.00013134844430287725,
2180
+ "loss": 1.5724,
2181
+ "step": 350
2182
+ },
2183
+ {
2184
+ "epoch": 2.16,
2185
+ "learning_rate": 0.00013060648608899503,
2186
+ "loss": 1.5292,
2187
+ "step": 351
2188
+ },
2189
+ {
2190
+ "epoch": 2.17,
2191
+ "learning_rate": 0.0001298650101273517,
2192
+ "loss": 1.5703,
2193
+ "step": 352
2194
+ },
2195
+ {
2196
+ "epoch": 2.17,
2197
+ "learning_rate": 0.0001291240348559902,
2198
+ "loss": 1.5444,
2199
+ "step": 353
2200
+ },
2201
+ {
2202
+ "epoch": 2.18,
2203
+ "learning_rate": 0.000128383578700503,
2204
+ "loss": 1.5848,
2205
+ "step": 354
2206
+ },
2207
+ {
2208
+ "epoch": 2.19,
2209
+ "learning_rate": 0.0001276436600735738,
2210
+ "loss": 1.603,
2211
+ "step": 355
2212
+ },
2213
+ {
2214
+ "epoch": 2.19,
2215
+ "learning_rate": 0.00012690429737451992,
2216
+ "loss": 1.5961,
2217
+ "step": 356
2218
+ },
2219
+ {
2220
+ "epoch": 2.2,
2221
+ "learning_rate": 0.0001261655089888345,
2222
+ "loss": 1.5635,
2223
+ "step": 357
2224
+ },
2225
+ {
2226
+ "epoch": 2.2,
2227
+ "learning_rate": 0.00012542731328772934,
2228
+ "loss": 1.5743,
2229
+ "step": 358
2230
+ },
2231
+ {
2232
+ "epoch": 2.21,
2233
+ "learning_rate": 0.00012468972862767825,
2234
+ "loss": 1.5291,
2235
+ "step": 359
2236
+ },
2237
+ {
2238
+ "epoch": 2.22,
2239
+ "learning_rate": 0.00012395277334996044,
2240
+ "loss": 1.5871,
2241
+ "step": 360
2242
+ },
2243
+ {
2244
+ "epoch": 2.22,
2245
+ "eval_loss": 1.8882598876953125,
2246
+ "eval_runtime": 292.5066,
2247
+ "eval_samples_per_second": 204.136,
2248
+ "eval_steps_per_second": 204.136,
2249
+ "step": 360
2250
+ },
2251
+ {
2252
+ "epoch": 2.22,
2253
+ "learning_rate": 0.0001232164657802045,
2254
+ "loss": 1.5044,
2255
+ "step": 361
2256
+ },
2257
+ {
2258
+ "epoch": 2.23,
2259
+ "learning_rate": 0.00012248082422793266,
2260
+ "loss": 1.5682,
2261
+ "step": 362
2262
+ },
2263
+ {
2264
+ "epoch": 2.24,
2265
+ "learning_rate": 0.00012174586698610547,
2266
+ "loss": 1.564,
2267
+ "step": 363
2268
+ },
2269
+ {
2270
+ "epoch": 2.24,
2271
+ "learning_rate": 0.00012101161233066703,
2272
+ "loss": 1.5595,
2273
+ "step": 364
2274
+ },
2275
+ {
2276
+ "epoch": 2.25,
2277
+ "learning_rate": 0.00012027807852009038,
2278
+ "loss": 1.5228,
2279
+ "step": 365
2280
+ },
2281
+ {
2282
+ "epoch": 2.25,
2283
+ "learning_rate": 0.00011954528379492359,
2284
+ "loss": 1.5444,
2285
+ "step": 366
2286
+ },
2287
+ {
2288
+ "epoch": 2.26,
2289
+ "learning_rate": 0.00011881324637733611,
2290
+ "loss": 1.5731,
2291
+ "step": 367
2292
+ },
2293
+ {
2294
+ "epoch": 2.27,
2295
+ "learning_rate": 0.0001180819844706657,
2296
+ "loss": 1.5853,
2297
+ "step": 368
2298
+ },
2299
+ {
2300
+ "epoch": 2.27,
2301
+ "learning_rate": 0.00011735151625896565,
2302
+ "loss": 1.583,
2303
+ "step": 369
2304
+ },
2305
+ {
2306
+ "epoch": 2.28,
2307
+ "learning_rate": 0.00011662185990655284,
2308
+ "loss": 1.5859,
2309
+ "step": 370
2310
+ },
2311
+ {
2312
+ "epoch": 2.29,
2313
+ "learning_rate": 0.00011589303355755579,
2314
+ "loss": 1.5597,
2315
+ "step": 371
2316
+ },
2317
+ {
2318
+ "epoch": 2.29,
2319
+ "learning_rate": 0.00011516505533546363,
2320
+ "loss": 1.5692,
2321
+ "step": 372
2322
+ },
2323
+ {
2324
+ "epoch": 2.3,
2325
+ "learning_rate": 0.00011443794334267538,
2326
+ "loss": 1.5628,
2327
+ "step": 373
2328
+ },
2329
+ {
2330
+ "epoch": 2.3,
2331
+ "learning_rate": 0.00011371171566004985,
2332
+ "loss": 1.5875,
2333
+ "step": 374
2334
+ },
2335
+ {
2336
+ "epoch": 2.31,
2337
+ "learning_rate": 0.00011298639034645593,
2338
+ "loss": 1.545,
2339
+ "step": 375
2340
+ },
2341
+ {
2342
+ "epoch": 2.32,
2343
+ "learning_rate": 0.00011226198543832372,
2344
+ "loss": 1.5687,
2345
+ "step": 376
2346
+ },
2347
+ {
2348
+ "epoch": 2.32,
2349
+ "learning_rate": 0.00011153851894919574,
2350
+ "loss": 1.5379,
2351
+ "step": 377
2352
+ },
2353
+ {
2354
+ "epoch": 2.33,
2355
+ "learning_rate": 0.00011081600886927924,
2356
+ "loss": 1.5287,
2357
+ "step": 378
2358
+ },
2359
+ {
2360
+ "epoch": 2.34,
2361
+ "learning_rate": 0.00011009447316499873,
2362
+ "loss": 1.5763,
2363
+ "step": 379
2364
+ },
2365
+ {
2366
+ "epoch": 2.34,
2367
+ "learning_rate": 0.00010937392977854923,
2368
+ "loss": 1.5675,
2369
+ "step": 380
2370
+ },
2371
+ {
2372
+ "epoch": 2.35,
2373
+ "learning_rate": 0.00010865439662745013,
2374
+ "loss": 1.5487,
2375
+ "step": 381
2376
+ },
2377
+ {
2378
+ "epoch": 2.35,
2379
+ "learning_rate": 0.0001079358916040996,
2380
+ "loss": 1.5471,
2381
+ "step": 382
2382
+ },
2383
+ {
2384
+ "epoch": 2.36,
2385
+ "learning_rate": 0.00010721843257532968,
2386
+ "loss": 1.5631,
2387
+ "step": 383
2388
+ },
2389
+ {
2390
+ "epoch": 2.37,
2391
+ "learning_rate": 0.00010650203738196206,
2392
+ "loss": 1.5721,
2393
+ "step": 384
2394
+ },
2395
+ {
2396
+ "epoch": 2.37,
2397
+ "learning_rate": 0.00010578672383836435,
2398
+ "loss": 1.5811,
2399
+ "step": 385
2400
+ },
2401
+ {
2402
+ "epoch": 2.38,
2403
+ "learning_rate": 0.0001050725097320071,
2404
+ "loss": 1.5824,
2405
+ "step": 386
2406
+ },
2407
+ {
2408
+ "epoch": 2.39,
2409
+ "learning_rate": 0.00010435941282302154,
2410
+ "loss": 1.5706,
2411
+ "step": 387
2412
+ },
2413
+ {
2414
+ "epoch": 2.39,
2415
+ "learning_rate": 0.0001036474508437579,
2416
+ "loss": 1.5383,
2417
+ "step": 388
2418
+ },
2419
+ {
2420
+ "epoch": 2.4,
2421
+ "learning_rate": 0.00010293664149834444,
2422
+ "loss": 1.5719,
2423
+ "step": 389
2424
+ },
2425
+ {
2426
+ "epoch": 2.4,
2427
+ "learning_rate": 0.00010222700246224735,
2428
+ "loss": 1.5167,
2429
+ "step": 390
2430
+ },
2431
+ {
2432
+ "epoch": 2.41,
2433
+ "learning_rate": 0.00010151855138183102,
2434
+ "loss": 1.5552,
2435
+ "step": 391
2436
+ },
2437
+ {
2438
+ "epoch": 2.42,
2439
+ "learning_rate": 0.00010081130587391934,
2440
+ "loss": 1.5735,
2441
+ "step": 392
2442
+ },
2443
+ {
2444
+ "epoch": 2.42,
2445
+ "learning_rate": 0.00010010528352535771,
2446
+ "loss": 1.5604,
2447
+ "step": 393
2448
+ },
2449
+ {
2450
+ "epoch": 2.43,
2451
+ "learning_rate": 9.94005018925755e-05,
2452
+ "loss": 1.5332,
2453
+ "step": 394
2454
+ },
2455
+ {
2456
+ "epoch": 2.43,
2457
+ "learning_rate": 9.869697850114969e-05,
2458
+ "loss": 1.5617,
2459
+ "step": 395
2460
+ },
2461
+ {
2462
+ "epoch": 2.44,
2463
+ "learning_rate": 9.799473084536891e-05,
2464
+ "loss": 1.5573,
2465
+ "step": 396
2466
+ },
2467
+ {
2468
+ "epoch": 2.45,
2469
+ "learning_rate": 9.729377638779857e-05,
2470
+ "loss": 1.5541,
2471
+ "step": 397
2472
+ },
2473
+ {
2474
+ "epoch": 2.45,
2475
+ "learning_rate": 9.659413255884647e-05,
2476
+ "loss": 1.5915,
2477
+ "step": 398
2478
+ },
2479
+ {
2480
+ "epoch": 2.46,
2481
+ "learning_rate": 9.589581675632944e-05,
2482
+ "loss": 1.5829,
2483
+ "step": 399
2484
+ },
2485
+ {
2486
+ "epoch": 2.47,
2487
+ "learning_rate": 9.519884634504074e-05,
2488
+ "loss": 1.5339,
2489
+ "step": 400
2490
+ },
2491
+ {
2492
+ "epoch": 2.47,
2493
+ "eval_loss": 1.8761346340179443,
2494
+ "eval_runtime": 290.7874,
2495
+ "eval_samples_per_second": 205.342,
2496
+ "eval_steps_per_second": 205.342,
2497
+ "step": 400
2498
+ },
2499
+ {
2500
+ "epoch": 2.47,
2501
+ "learning_rate": 9.450323865631816e-05,
2502
+ "loss": 1.5532,
2503
+ "step": 401
2504
+ },
2505
+ {
2506
+ "epoch": 2.48,
2507
+ "learning_rate": 9.380901098761319e-05,
2508
+ "loss": 1.5511,
2509
+ "step": 402
2510
+ },
2511
+ {
2512
+ "epoch": 2.48,
2513
+ "learning_rate": 9.311618060206074e-05,
2514
+ "loss": 1.5456,
2515
+ "step": 403
2516
+ },
2517
+ {
2518
+ "epoch": 2.49,
2519
+ "learning_rate": 9.242476472804995e-05,
2520
+ "loss": 1.5488,
2521
+ "step": 404
2522
+ },
2523
+ {
2524
+ "epoch": 2.5,
2525
+ "learning_rate": 9.17347805587958e-05,
2526
+ "loss": 1.5898,
2527
+ "step": 405
2528
+ },
2529
+ {
2530
+ "epoch": 2.5,
2531
+ "learning_rate": 9.104624525191145e-05,
2532
+ "loss": 1.5482,
2533
+ "step": 406
2534
+ },
2535
+ {
2536
+ "epoch": 2.51,
2537
+ "learning_rate": 9.035917592898177e-05,
2538
+ "loss": 1.5348,
2539
+ "step": 407
2540
+ },
2541
+ {
2542
+ "epoch": 2.52,
2543
+ "learning_rate": 8.967358967513738e-05,
2544
+ "loss": 1.5588,
2545
+ "step": 408
2546
+ },
2547
+ {
2548
+ "epoch": 2.52,
2549
+ "learning_rate": 8.898950353862998e-05,
2550
+ "loss": 1.5553,
2551
+ "step": 409
2552
+ },
2553
+ {
2554
+ "epoch": 2.53,
2555
+ "learning_rate": 8.830693453040829e-05,
2556
+ "loss": 1.5642,
2557
+ "step": 410
2558
+ },
2559
+ {
2560
+ "epoch": 2.53,
2561
+ "learning_rate": 8.762589962369511e-05,
2562
+ "loss": 1.5557,
2563
+ "step": 411
2564
+ },
2565
+ {
2566
+ "epoch": 2.54,
2567
+ "learning_rate": 8.694641575356519e-05,
2568
+ "loss": 1.5578,
2569
+ "step": 412
2570
+ },
2571
+ {
2572
+ "epoch": 2.55,
2573
+ "learning_rate": 8.626849981652424e-05,
2574
+ "loss": 1.574,
2575
+ "step": 413
2576
+ },
2577
+ {
2578
+ "epoch": 2.55,
2579
+ "learning_rate": 8.55921686700886e-05,
2580
+ "loss": 1.5666,
2581
+ "step": 414
2582
+ },
2583
+ {
2584
+ "epoch": 2.56,
2585
+ "learning_rate": 8.491743913236628e-05,
2586
+ "loss": 1.5562,
2587
+ "step": 415
2588
+ },
2589
+ {
2590
+ "epoch": 2.57,
2591
+ "learning_rate": 8.424432798163836e-05,
2592
+ "loss": 1.5529,
2593
+ "step": 416
2594
+ },
2595
+ {
2596
+ "epoch": 2.57,
2597
+ "learning_rate": 8.357285195594228e-05,
2598
+ "loss": 1.538,
2599
+ "step": 417
2600
+ },
2601
+ {
2602
+ "epoch": 2.58,
2603
+ "learning_rate": 8.290302775265509e-05,
2604
+ "loss": 1.5782,
2605
+ "step": 418
2606
+ },
2607
+ {
2608
+ "epoch": 2.58,
2609
+ "learning_rate": 8.223487202807877e-05,
2610
+ "loss": 1.55,
2611
+ "step": 419
2612
+ },
2613
+ {
2614
+ "epoch": 2.59,
2615
+ "learning_rate": 8.156840139702554e-05,
2616
+ "loss": 1.5439,
2617
+ "step": 420
2618
+ },
2619
+ {
2620
+ "epoch": 2.6,
2621
+ "learning_rate": 8.090363243240517e-05,
2622
+ "loss": 1.5627,
2623
+ "step": 421
2624
+ },
2625
+ {
2626
+ "epoch": 2.6,
2627
+ "learning_rate": 8.024058166481243e-05,
2628
+ "loss": 1.5693,
2629
+ "step": 422
2630
+ },
2631
+ {
2632
+ "epoch": 2.61,
2633
+ "learning_rate": 7.957926558211642e-05,
2634
+ "loss": 1.5816,
2635
+ "step": 423
2636
+ },
2637
+ {
2638
+ "epoch": 2.62,
2639
+ "learning_rate": 7.89197006290502e-05,
2640
+ "loss": 1.5464,
2641
+ "step": 424
2642
+ },
2643
+ {
2644
+ "epoch": 2.62,
2645
+ "learning_rate": 7.82619032068023e-05,
2646
+ "loss": 1.5494,
2647
+ "step": 425
2648
+ },
2649
+ {
2650
+ "epoch": 2.63,
2651
+ "learning_rate": 7.760588967260838e-05,
2652
+ "loss": 1.5711,
2653
+ "step": 426
2654
+ },
2655
+ {
2656
+ "epoch": 2.63,
2657
+ "learning_rate": 7.69516763393449e-05,
2658
+ "loss": 1.5801,
2659
+ "step": 427
2660
+ },
2661
+ {
2662
+ "epoch": 2.64,
2663
+ "learning_rate": 7.629927947512331e-05,
2664
+ "loss": 1.5628,
2665
+ "step": 428
2666
+ },
2667
+ {
2668
+ "epoch": 2.65,
2669
+ "learning_rate": 7.564871530288536e-05,
2670
+ "loss": 1.5601,
2671
+ "step": 429
2672
+ },
2673
+ {
2674
+ "epoch": 2.65,
2675
+ "learning_rate": 7.500000000000002e-05,
2676
+ "loss": 1.5453,
2677
+ "step": 430
2678
+ },
2679
+ {
2680
+ "epoch": 2.66,
2681
+ "learning_rate": 7.435314969786088e-05,
2682
+ "loss": 1.5684,
2683
+ "step": 431
2684
+ },
2685
+ {
2686
+ "epoch": 2.67,
2687
+ "learning_rate": 7.370818048148527e-05,
2688
+ "loss": 1.5656,
2689
+ "step": 432
2690
+ },
2691
+ {
2692
+ "epoch": 2.67,
2693
+ "learning_rate": 7.30651083891141e-05,
2694
+ "loss": 1.5735,
2695
+ "step": 433
2696
+ },
2697
+ {
2698
+ "epoch": 2.68,
2699
+ "learning_rate": 7.242394941181308e-05,
2700
+ "loss": 1.5587,
2701
+ "step": 434
2702
+ },
2703
+ {
2704
+ "epoch": 2.68,
2705
+ "learning_rate": 7.17847194930753e-05,
2706
+ "loss": 1.5735,
2707
+ "step": 435
2708
+ },
2709
+ {
2710
+ "epoch": 2.69,
2711
+ "learning_rate": 7.114743452842427e-05,
2712
+ "loss": 1.5656,
2713
+ "step": 436
2714
+ },
2715
+ {
2716
+ "epoch": 2.7,
2717
+ "learning_rate": 7.051211036501928e-05,
2718
+ "loss": 1.5228,
2719
+ "step": 437
2720
+ },
2721
+ {
2722
+ "epoch": 2.7,
2723
+ "learning_rate": 6.987876280126068e-05,
2724
+ "loss": 1.5452,
2725
+ "step": 438
2726
+ },
2727
+ {
2728
+ "epoch": 2.71,
2729
+ "learning_rate": 6.924740758639768e-05,
2730
+ "loss": 1.5777,
2731
+ "step": 439
2732
+ },
2733
+ {
2734
+ "epoch": 2.72,
2735
+ "learning_rate": 6.86180604201361e-05,
2736
+ "loss": 1.5589,
2737
+ "step": 440
2738
+ },
2739
+ {
2740
+ "epoch": 2.72,
2741
+ "eval_loss": 1.8656864166259766,
2742
+ "eval_runtime": 292.9263,
2743
+ "eval_samples_per_second": 203.843,
2744
+ "eval_steps_per_second": 203.843,
2745
+ "step": 440
2746
+ },
2747
+ {
2748
+ "epoch": 2.72,
2749
+ "learning_rate": 6.799073695224846e-05,
2750
+ "loss": 1.562,
2751
+ "step": 441
2752
+ },
2753
+ {
2754
+ "epoch": 2.73,
2755
+ "learning_rate": 6.736545278218463e-05,
2756
+ "loss": 1.5788,
2757
+ "step": 442
2758
+ },
2759
+ {
2760
+ "epoch": 2.73,
2761
+ "learning_rate": 6.674222345868376e-05,
2762
+ "loss": 1.5532,
2763
+ "step": 443
2764
+ },
2765
+ {
2766
+ "epoch": 2.74,
2767
+ "learning_rate": 6.612106447938799e-05,
2768
+ "loss": 1.5986,
2769
+ "step": 444
2770
+ },
2771
+ {
2772
+ "epoch": 2.75,
2773
+ "learning_rate": 6.550199129045668e-05,
2774
+ "loss": 1.573,
2775
+ "step": 445
2776
+ },
2777
+ {
2778
+ "epoch": 2.75,
2779
+ "learning_rate": 6.488501928618274e-05,
2780
+ "loss": 1.5544,
2781
+ "step": 446
2782
+ },
2783
+ {
2784
+ "epoch": 2.76,
2785
+ "learning_rate": 6.427016380860937e-05,
2786
+ "loss": 1.5651,
2787
+ "step": 447
2788
+ },
2789
+ {
2790
+ "epoch": 2.77,
2791
+ "learning_rate": 6.365744014714898e-05,
2792
+ "loss": 1.5261,
2793
+ "step": 448
2794
+ },
2795
+ {
2796
+ "epoch": 2.77,
2797
+ "learning_rate": 6.304686353820266e-05,
2798
+ "loss": 1.5325,
2799
+ "step": 449
2800
+ },
2801
+ {
2802
+ "epoch": 2.78,
2803
+ "learning_rate": 6.243844916478155e-05,
2804
+ "loss": 1.5435,
2805
+ "step": 450
2806
+ },
2807
+ {
2808
+ "epoch": 2.78,
2809
+ "learning_rate": 6.183221215612904e-05,
2810
+ "loss": 1.546,
2811
+ "step": 451
2812
+ },
2813
+ {
2814
+ "epoch": 2.79,
2815
+ "learning_rate": 6.122816758734487e-05,
2816
+ "loss": 1.5508,
2817
+ "step": 452
2818
+ },
2819
+ {
2820
+ "epoch": 2.8,
2821
+ "learning_rate": 6.0626330479009845e-05,
2822
+ "loss": 1.5678,
2823
+ "step": 453
2824
+ },
2825
+ {
2826
+ "epoch": 2.8,
2827
+ "learning_rate": 6.002671579681294e-05,
2828
+ "loss": 1.523,
2829
+ "step": 454
2830
+ },
2831
+ {
2832
+ "epoch": 2.81,
2833
+ "learning_rate": 5.9429338451178355e-05,
2834
+ "loss": 1.5271,
2835
+ "step": 455
2836
+ },
2837
+ {
2838
+ "epoch": 2.82,
2839
+ "learning_rate": 5.88342132968955e-05,
2840
+ "loss": 1.5285,
2841
+ "step": 456
2842
+ },
2843
+ {
2844
+ "epoch": 2.82,
2845
+ "learning_rate": 5.824135513274902e-05,
2846
+ "loss": 1.5476,
2847
+ "step": 457
2848
+ },
2849
+ {
2850
+ "epoch": 2.83,
2851
+ "learning_rate": 5.765077870115125e-05,
2852
+ "loss": 1.5216,
2853
+ "step": 458
2854
+ },
2855
+ {
2856
+ "epoch": 2.83,
2857
+ "learning_rate": 5.706249868777526e-05,
2858
+ "loss": 1.547,
2859
+ "step": 459
2860
+ },
2861
+ {
2862
+ "epoch": 2.84,
2863
+ "learning_rate": 5.6476529721189974e-05,
2864
+ "loss": 1.5398,
2865
+ "step": 460
2866
+ },
2867
+ {
2868
+ "epoch": 2.85,
2869
+ "learning_rate": 5.589288637249612e-05,
2870
+ "loss": 1.579,
2871
+ "step": 461
2872
+ },
2873
+ {
2874
+ "epoch": 2.85,
2875
+ "learning_rate": 5.531158315496417e-05,
2876
+ "loss": 1.4801,
2877
+ "step": 462
2878
+ },
2879
+ {
2880
+ "epoch": 2.86,
2881
+ "learning_rate": 5.473263452367318e-05,
2882
+ "loss": 1.5465,
2883
+ "step": 463
2884
+ },
2885
+ {
2886
+ "epoch": 2.87,
2887
+ "learning_rate": 5.415605487515164e-05,
2888
+ "loss": 1.5303,
2889
+ "step": 464
2890
+ },
2891
+ {
2892
+ "epoch": 2.87,
2893
+ "learning_rate": 5.358185854701909e-05,
2894
+ "loss": 1.5519,
2895
+ "step": 465
2896
+ },
2897
+ {
2898
+ "epoch": 2.88,
2899
+ "learning_rate": 5.3010059817630066e-05,
2900
+ "loss": 1.5818,
2901
+ "step": 466
2902
+ },
2903
+ {
2904
+ "epoch": 2.88,
2905
+ "learning_rate": 5.244067290571856e-05,
2906
+ "loss": 1.5413,
2907
+ "step": 467
2908
+ },
2909
+ {
2910
+ "epoch": 2.89,
2911
+ "learning_rate": 5.187371197004485e-05,
2912
+ "loss": 1.5372,
2913
+ "step": 468
2914
+ },
2915
+ {
2916
+ "epoch": 2.9,
2917
+ "learning_rate": 5.130919110904311e-05,
2918
+ "loss": 1.5459,
2919
+ "step": 469
2920
+ },
2921
+ {
2922
+ "epoch": 2.9,
2923
+ "learning_rate": 5.074712436047112e-05,
2924
+ "loss": 1.5488,
2925
+ "step": 470
2926
+ },
2927
+ {
2928
+ "epoch": 2.91,
2929
+ "learning_rate": 5.018752570106086e-05,
2930
+ "loss": 1.5332,
2931
+ "step": 471
2932
+ },
2933
+ {
2934
+ "epoch": 2.92,
2935
+ "learning_rate": 4.963040904617131e-05,
2936
+ "loss": 1.5684,
2937
+ "step": 472
2938
+ },
2939
+ {
2940
+ "epoch": 2.92,
2941
+ "learning_rate": 4.9075788249442024e-05,
2942
+ "loss": 1.5405,
2943
+ "step": 473
2944
+ },
2945
+ {
2946
+ "epoch": 2.93,
2947
+ "learning_rate": 4.852367710244921e-05,
2948
+ "loss": 1.5361,
2949
+ "step": 474
2950
+ },
2951
+ {
2952
+ "epoch": 2.93,
2953
+ "learning_rate": 4.7974089334362057e-05,
2954
+ "loss": 1.5219,
2955
+ "step": 475
2956
+ },
2957
+ {
2958
+ "epoch": 2.94,
2959
+ "learning_rate": 4.742703861160198e-05,
2960
+ "loss": 1.5518,
2961
+ "step": 476
2962
+ },
2963
+ {
2964
+ "epoch": 2.95,
2965
+ "learning_rate": 4.688253853750227e-05,
2966
+ "loss": 1.5699,
2967
+ "step": 477
2968
+ },
2969
+ {
2970
+ "epoch": 2.95,
2971
+ "learning_rate": 4.63406026519703e-05,
2972
+ "loss": 1.5368,
2973
+ "step": 478
2974
+ },
2975
+ {
2976
+ "epoch": 2.96,
2977
+ "learning_rate": 4.5801244431150394e-05,
2978
+ "loss": 1.5286,
2979
+ "step": 479
2980
+ },
2981
+ {
2982
+ "epoch": 2.96,
2983
+ "learning_rate": 4.526447728708908e-05,
2984
+ "loss": 1.5651,
2985
+ "step": 480
2986
+ },
2987
+ {
2988
+ "epoch": 2.96,
2989
+ "eval_loss": 1.8590147495269775,
2990
+ "eval_runtime": 291.2621,
2991
+ "eval_samples_per_second": 205.008,
2992
+ "eval_steps_per_second": 205.008,
2993
+ "step": 480
2994
+ }
2995
+ ],
2996
+ "logging_steps": 1,
2997
+ "max_steps": 640,
2998
+ "num_input_tokens_seen": 0,
2999
+ "num_train_epochs": 4,
3000
+ "save_steps": 160,
3001
+ "total_flos": 1.405424023508091e+18,
3002
+ "train_batch_size": 1,
3003
+ "trial_name": null,
3004
+ "trial_params": null
3005
+ }
checkpoint-480/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0bb8459ca9eb55b57fe6882811eecff75c1f600c94c4d55a31c5f6345a7df8b
3
+ size 4795
checkpoint-640/README.md ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: mistralai/Mistral-7B-v0.1
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ## Training procedure
203
+
204
+ The following `bitsandbytes` quantization config was used during training:
205
+ - quant_method: bitsandbytes
206
+ - load_in_8bit: True
207
+ - load_in_4bit: False
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: fp4
213
+ - bnb_4bit_use_double_quant: False
214
+ - bnb_4bit_compute_dtype: float32
215
+
216
+ ### Framework versions
217
+
218
+ - PEFT 0.7.0
checkpoint-640/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 64,
13
+ "lora_dropout": 0.2,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "gate_proj",
23
+ "o_proj",
24
+ "down_proj",
25
+ "up_proj",
26
+ "q_proj",
27
+ "v_proj",
28
+ "k_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
checkpoint-640/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72474177f6f69c32dea2f3928f24194aaac5cdc96b641c19f8c16f684cb44fb3
3
+ size 1342238560
checkpoint-640/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d36a2e1fb44ce8dc79d22be827848aac7f56bdaf1388c0de856d960c2dd469
3
+ size 672930145
checkpoint-640/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f26370e1ddacbbabb69ac6558174a83d5551749b9abc459cfbf1a15123d371b
3
+ size 14575
checkpoint-640/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbe3a08d353a9f679171a9817eeb3c016ba85392c56beee9983e52c0f37347cd
3
+ size 627
checkpoint-640/trainer_state.json ADDED
@@ -0,0 +1,3997 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.8478573560714722,
3
+ "best_model_checkpoint": "./llmTechChat-lora/checkpoint-320",
4
+ "epoch": 3.9485580670303975,
5
+ "eval_steps": 40,
6
+ "global_step": 640,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 2.9999999999999997e-05,
14
+ "loss": 4.3577,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "eval_loss": 4.326064109802246,
20
+ "eval_runtime": 288.7431,
21
+ "eval_samples_per_second": 206.796,
22
+ "eval_steps_per_second": 206.796,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "learning_rate": 5.9999999999999995e-05,
28
+ "loss": 4.2951,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.02,
33
+ "learning_rate": 8.999999999999999e-05,
34
+ "loss": 3.9156,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.02,
39
+ "learning_rate": 0.00011999999999999999,
40
+ "loss": 3.4836,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.03,
45
+ "learning_rate": 0.00015,
46
+ "loss": 3.1743,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.04,
51
+ "learning_rate": 0.00017999999999999998,
52
+ "loss": 2.8242,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.04,
57
+ "learning_rate": 0.00020999999999999998,
58
+ "loss": 2.7478,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.05,
63
+ "learning_rate": 0.00023999999999999998,
64
+ "loss": 2.7198,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.06,
69
+ "learning_rate": 0.00027,
70
+ "loss": 2.6025,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.06,
75
+ "learning_rate": 0.0003,
76
+ "loss": 2.5337,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.07,
81
+ "learning_rate": 0.00029999813499925374,
82
+ "loss": 2.5019,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.07,
87
+ "learning_rate": 0.0002999925400433914,
88
+ "loss": 2.3393,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.08,
93
+ "learning_rate": 0.00029998321527154097,
94
+ "loss": 2.3796,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.09,
99
+ "learning_rate": 0.0002999701609155785,
100
+ "loss": 2.3054,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.09,
105
+ "learning_rate": 0.0002999533773001224,
106
+ "loss": 2.2898,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.1,
111
+ "learning_rate": 0.00029993286484252544,
112
+ "loss": 2.2254,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.11,
117
+ "learning_rate": 0.00029990862405286433,
118
+ "loss": 2.2197,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.11,
123
+ "learning_rate": 0.0002998806555339269,
124
+ "loss": 2.1797,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.12,
129
+ "learning_rate": 0.0002998489599811972,
130
+ "loss": 2.1854,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.12,
135
+ "learning_rate": 0.0002998135381828383,
136
+ "loss": 2.2105,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.13,
141
+ "learning_rate": 0.00029977439101967274,
142
+ "loss": 2.1866,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.14,
147
+ "learning_rate": 0.00029973151946516025,
148
+ "loss": 2.1718,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.14,
153
+ "learning_rate": 0.0002996849245853739,
154
+ "loss": 2.1158,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.15,
159
+ "learning_rate": 0.0002996346075389736,
160
+ "loss": 2.1495,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.16,
165
+ "learning_rate": 0.00029958056957717696,
166
+ "loss": 2.1326,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.16,
171
+ "learning_rate": 0.00029952281204372863,
172
+ "loss": 2.1391,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.17,
177
+ "learning_rate": 0.0002994613363748664,
178
+ "loss": 2.1039,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.17,
183
+ "learning_rate": 0.00029939614409928584,
184
+ "loss": 2.132,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.18,
189
+ "learning_rate": 0.00029932723683810225,
190
+ "loss": 2.1278,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.19,
195
+ "learning_rate": 0.0002992546163048102,
196
+ "loss": 2.0698,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.19,
201
+ "learning_rate": 0.00029917828430524096,
202
+ "loss": 2.0757,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.2,
207
+ "learning_rate": 0.0002990982427375177,
208
+ "loss": 2.0689,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.21,
213
+ "learning_rate": 0.0002990144935920083,
214
+ "loss": 2.0986,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.21,
219
+ "learning_rate": 0.0002989270389512756,
220
+ "loss": 2.058,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.22,
225
+ "learning_rate": 0.0002988358809900258,
226
+ "loss": 2.0451,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.22,
231
+ "learning_rate": 0.00029874102197505447,
232
+ "loss": 2.0613,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.23,
237
+ "learning_rate": 0.0002986424642651902,
238
+ "loss": 2.0796,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.24,
243
+ "learning_rate": 0.0002985402103112355,
244
+ "loss": 2.086,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.24,
249
+ "learning_rate": 0.00029843426265590656,
250
+ "loss": 2.0275,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.25,
255
+ "learning_rate": 0.0002983246239337692,
256
+ "loss": 2.0615,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.25,
261
+ "eval_loss": 2.0476396083831787,
262
+ "eval_runtime": 289.9408,
263
+ "eval_samples_per_second": 205.942,
264
+ "eval_steps_per_second": 205.942,
265
+ "step": 40
266
+ },
267
+ {
268
+ "epoch": 0.26,
269
+ "learning_rate": 0.0002982112968711744,
270
+ "loss": 2.1012,
271
+ "step": 41
272
+ },
273
+ {
274
+ "epoch": 0.26,
275
+ "learning_rate": 0.0002980942842861893,
276
+ "loss": 2.0537,
277
+ "step": 42
278
+ },
279
+ {
280
+ "epoch": 0.27,
281
+ "learning_rate": 0.00029797358908852816,
282
+ "loss": 2.0595,
283
+ "step": 43
284
+ },
285
+ {
286
+ "epoch": 0.27,
287
+ "learning_rate": 0.00029784921427947946,
288
+ "loss": 2.0409,
289
+ "step": 44
290
+ },
291
+ {
292
+ "epoch": 0.28,
293
+ "learning_rate": 0.0002977211629518312,
294
+ "loss": 2.0045,
295
+ "step": 45
296
+ },
297
+ {
298
+ "epoch": 0.29,
299
+ "learning_rate": 0.00029758943828979444,
300
+ "loss": 2.0176,
301
+ "step": 46
302
+ },
303
+ {
304
+ "epoch": 0.29,
305
+ "learning_rate": 0.0002974540435689237,
306
+ "loss": 2.0189,
307
+ "step": 47
308
+ },
309
+ {
310
+ "epoch": 0.3,
311
+ "learning_rate": 0.0002973149821560358,
312
+ "loss": 2.0169,
313
+ "step": 48
314
+ },
315
+ {
316
+ "epoch": 0.31,
317
+ "learning_rate": 0.00029717225750912585,
318
+ "loss": 2.0553,
319
+ "step": 49
320
+ },
321
+ {
322
+ "epoch": 0.31,
323
+ "learning_rate": 0.00029702587317728153,
324
+ "loss": 2.0569,
325
+ "step": 50
326
+ },
327
+ {
328
+ "epoch": 0.32,
329
+ "learning_rate": 0.0002968758328005947,
330
+ "loss": 2.0522,
331
+ "step": 51
332
+ },
333
+ {
334
+ "epoch": 0.32,
335
+ "learning_rate": 0.0002967221401100708,
336
+ "loss": 2.0285,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 0.33,
341
+ "learning_rate": 0.00029656479892753635,
342
+ "loss": 2.0266,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 0.34,
347
+ "learning_rate": 0.0002964038131655436,
348
+ "loss": 2.0161,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 0.34,
353
+ "learning_rate": 0.0002962391868272735,
354
+ "loss": 2.0122,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 0.35,
359
+ "learning_rate": 0.00029607092400643593,
360
+ "loss": 1.9926,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 0.36,
365
+ "learning_rate": 0.000295899028887168,
366
+ "loss": 2.0123,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 0.36,
371
+ "learning_rate": 0.0002957235057439301,
372
+ "loss": 2.0121,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 0.37,
377
+ "learning_rate": 0.0002955443589413994,
378
+ "loss": 2.0245,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 0.37,
383
+ "learning_rate": 0.00029536159293436166,
384
+ "loss": 2.0127,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 0.38,
389
+ "learning_rate": 0.0002951752122676,
390
+ "loss": 2.0057,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 0.39,
395
+ "learning_rate": 0.000294985221575782,
396
+ "loss": 2.0226,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 0.39,
401
+ "learning_rate": 0.0002947916255833451,
402
+ "loss": 2.0032,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 0.4,
407
+ "learning_rate": 0.00029459442910437797,
408
+ "loss": 2.045,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 0.41,
413
+ "learning_rate": 0.00029439363704250176,
414
+ "loss": 1.9794,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 0.41,
419
+ "learning_rate": 0.0002941892543907478,
420
+ "loss": 2.0009,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 0.42,
425
+ "learning_rate": 0.0002939812862314333,
426
+ "loss": 1.9508,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 0.42,
431
+ "learning_rate": 0.00029376973773603533,
432
+ "loss": 1.9913,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 0.43,
437
+ "learning_rate": 0.0002935546141650618,
438
+ "loss": 1.9762,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 0.44,
443
+ "learning_rate": 0.00029333592086792107,
444
+ "loss": 2.0,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 0.44,
449
+ "learning_rate": 0.0002931136632827886,
450
+ "loss": 1.9629,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 0.45,
455
+ "learning_rate": 0.0002928878469364719,
456
+ "loss": 2.0009,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 0.46,
461
+ "learning_rate": 0.00029265847744427303,
462
+ "loss": 1.9714,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 0.46,
467
+ "learning_rate": 0.0002924255605098489,
468
+ "loss": 1.9474,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 0.47,
473
+ "learning_rate": 0.0002921891019250697,
474
+ "loss": 1.9959,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 0.47,
479
+ "learning_rate": 0.0002919491075698746,
480
+ "loss": 1.9846,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 0.48,
485
+ "learning_rate": 0.00029170558341212554,
486
+ "loss": 1.9978,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 0.49,
491
+ "learning_rate": 0.00029145853550745904,
492
+ "loss": 1.9527,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 0.49,
497
+ "learning_rate": 0.00029120796999913546,
498
+ "loss": 1.9585,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 0.5,
503
+ "learning_rate": 0.0002909538931178862,
504
+ "loss": 1.9905,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 0.5,
509
+ "eval_loss": 1.96906578540802,
510
+ "eval_runtime": 291.8459,
511
+ "eval_samples_per_second": 204.598,
512
+ "eval_steps_per_second": 204.598,
513
+ "step": 80
514
+ },
515
+ {
516
+ "epoch": 0.51,
517
+ "learning_rate": 0.00029069631118175903,
518
+ "loss": 1.9926,
519
+ "step": 81
520
+ },
521
+ {
522
+ "epoch": 0.51,
523
+ "learning_rate": 0.00029043523059596053,
524
+ "loss": 1.9916,
525
+ "step": 82
526
+ },
527
+ {
528
+ "epoch": 0.52,
529
+ "learning_rate": 0.0002901706578526973,
530
+ "loss": 1.9545,
531
+ "step": 83
532
+ },
533
+ {
534
+ "epoch": 0.52,
535
+ "learning_rate": 0.0002899025995310141,
536
+ "loss": 1.9399,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 0.53,
541
+ "learning_rate": 0.00028963106229663063,
542
+ "loss": 1.9515,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 0.54,
547
+ "learning_rate": 0.00028935605290177535,
548
+ "loss": 1.9855,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 0.54,
553
+ "learning_rate": 0.0002890775781850181,
554
+ "loss": 2.0159,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 0.55,
559
+ "learning_rate": 0.00028879564507109946,
560
+ "loss": 1.9885,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 0.55,
565
+ "learning_rate": 0.00028851026057075916,
566
+ "loss": 1.9625,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 0.56,
571
+ "learning_rate": 0.00028822143178056114,
572
+ "loss": 1.9161,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 0.57,
577
+ "learning_rate": 0.0002879291658827176,
578
+ "loss": 1.9141,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 0.57,
583
+ "learning_rate": 0.00028763347014491,
584
+ "loss": 1.9867,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 0.58,
589
+ "learning_rate": 0.00028733435192010887,
590
+ "loss": 1.9325,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 0.59,
595
+ "learning_rate": 0.0002870318186463901,
596
+ "loss": 1.9517,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 0.59,
601
+ "learning_rate": 0.00028672587784675096,
602
+ "loss": 1.9435,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 0.6,
607
+ "learning_rate": 0.0002864165371289223,
608
+ "loss": 1.9428,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 0.6,
613
+ "learning_rate": 0.0002861038041851797,
614
+ "loss": 1.9182,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 0.61,
619
+ "learning_rate": 0.0002857876867921522,
620
+ "loss": 1.9344,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 0.62,
625
+ "learning_rate": 0.0002854681928106287,
626
+ "loss": 1.9652,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 0.62,
631
+ "learning_rate": 0.0002851453301853628,
632
+ "loss": 1.9332,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 0.63,
637
+ "learning_rate": 0.000284819106944875,
638
+ "loss": 1.9042,
639
+ "step": 101
640
+ },
641
+ {
642
+ "epoch": 0.64,
643
+ "learning_rate": 0.0002844895312012531,
644
+ "loss": 1.9571,
645
+ "step": 102
646
+ },
647
+ {
648
+ "epoch": 0.64,
649
+ "learning_rate": 0.0002841566111499505,
650
+ "loss": 1.9129,
651
+ "step": 103
652
+ },
653
+ {
654
+ "epoch": 0.65,
655
+ "learning_rate": 0.0002838203550695825,
656
+ "loss": 1.9347,
657
+ "step": 104
658
+ },
659
+ {
660
+ "epoch": 0.65,
661
+ "learning_rate": 0.00028348077132172027,
662
+ "loss": 1.9461,
663
+ "step": 105
664
+ },
665
+ {
666
+ "epoch": 0.66,
667
+ "learning_rate": 0.0002831378683506831,
668
+ "loss": 1.9188,
669
+ "step": 106
670
+ },
671
+ {
672
+ "epoch": 0.67,
673
+ "learning_rate": 0.00028279165468332823,
674
+ "loss": 1.9491,
675
+ "step": 107
676
+ },
677
+ {
678
+ "epoch": 0.67,
679
+ "learning_rate": 0.000282442138928839,
680
+ "loss": 1.961,
681
+ "step": 108
682
+ },
683
+ {
684
+ "epoch": 0.68,
685
+ "learning_rate": 0.00028208932977851067,
686
+ "loss": 1.9048,
687
+ "step": 109
688
+ },
689
+ {
690
+ "epoch": 0.69,
691
+ "learning_rate": 0.0002817332360055343,
692
+ "loss": 1.9493,
693
+ "step": 110
694
+ },
695
+ {
696
+ "epoch": 0.69,
697
+ "learning_rate": 0.0002813738664647784,
698
+ "loss": 1.9685,
699
+ "step": 111
700
+ },
701
+ {
702
+ "epoch": 0.7,
703
+ "learning_rate": 0.00028101123009256947,
704
+ "loss": 1.9054,
705
+ "step": 112
706
+ },
707
+ {
708
+ "epoch": 0.7,
709
+ "learning_rate": 0.0002806453359064686,
710
+ "loss": 1.9317,
711
+ "step": 113
712
+ },
713
+ {
714
+ "epoch": 0.71,
715
+ "learning_rate": 0.00028027619300504834,
716
+ "loss": 1.9701,
717
+ "step": 114
718
+ },
719
+ {
720
+ "epoch": 0.72,
721
+ "learning_rate": 0.0002799038105676658,
722
+ "loss": 1.9426,
723
+ "step": 115
724
+ },
725
+ {
726
+ "epoch": 0.72,
727
+ "learning_rate": 0.0002795281978542346,
728
+ "loss": 1.957,
729
+ "step": 116
730
+ },
731
+ {
732
+ "epoch": 0.73,
733
+ "learning_rate": 0.0002791493642049947,
734
+ "loss": 1.9535,
735
+ "step": 117
736
+ },
737
+ {
738
+ "epoch": 0.74,
739
+ "learning_rate": 0.0002787673190402799,
740
+ "loss": 1.9045,
741
+ "step": 118
742
+ },
743
+ {
744
+ "epoch": 0.74,
745
+ "learning_rate": 0.00027838207186028376,
746
+ "loss": 1.9575,
747
+ "step": 119
748
+ },
749
+ {
750
+ "epoch": 0.75,
751
+ "learning_rate": 0.0002779936322448233,
752
+ "loss": 1.8699,
753
+ "step": 120
754
+ },
755
+ {
756
+ "epoch": 0.75,
757
+ "eval_loss": 1.9343771934509277,
758
+ "eval_runtime": 292.8194,
759
+ "eval_samples_per_second": 203.917,
760
+ "eval_steps_per_second": 203.917,
761
+ "step": 120
762
+ },
763
+ {
764
+ "epoch": 0.75,
765
+ "learning_rate": 0.0002776020098531009,
766
+ "loss": 1.956,
767
+ "step": 121
768
+ },
769
+ {
770
+ "epoch": 0.76,
771
+ "learning_rate": 0.00027720721442346387,
772
+ "loss": 1.8958,
773
+ "step": 122
774
+ },
775
+ {
776
+ "epoch": 0.77,
777
+ "learning_rate": 0.0002768092557731625,
778
+ "loss": 1.9157,
779
+ "step": 123
780
+ },
781
+ {
782
+ "epoch": 0.77,
783
+ "learning_rate": 0.00027640814379810587,
784
+ "loss": 1.9118,
785
+ "step": 124
786
+ },
787
+ {
788
+ "epoch": 0.78,
789
+ "learning_rate": 0.0002760038884726157,
790
+ "loss": 1.9707,
791
+ "step": 125
792
+ },
793
+ {
794
+ "epoch": 0.79,
795
+ "learning_rate": 0.0002755964998491785,
796
+ "loss": 1.9563,
797
+ "step": 126
798
+ },
799
+ {
800
+ "epoch": 0.79,
801
+ "learning_rate": 0.0002751859880581954,
802
+ "loss": 1.9825,
803
+ "step": 127
804
+ },
805
+ {
806
+ "epoch": 0.8,
807
+ "learning_rate": 0.0002747723633077303,
808
+ "loss": 1.9687,
809
+ "step": 128
810
+ },
811
+ {
812
+ "epoch": 0.8,
813
+ "learning_rate": 0.0002743556358832562,
814
+ "loss": 1.9378,
815
+ "step": 129
816
+ },
817
+ {
818
+ "epoch": 0.81,
819
+ "learning_rate": 0.00027393581614739923,
820
+ "loss": 1.9307,
821
+ "step": 130
822
+ },
823
+ {
824
+ "epoch": 0.82,
825
+ "learning_rate": 0.00027351291453968086,
826
+ "loss": 1.9333,
827
+ "step": 131
828
+ },
829
+ {
830
+ "epoch": 0.82,
831
+ "learning_rate": 0.0002730869415762587,
832
+ "loss": 1.9229,
833
+ "step": 132
834
+ },
835
+ {
836
+ "epoch": 0.83,
837
+ "learning_rate": 0.0002726579078496647,
838
+ "loss": 1.911,
839
+ "step": 133
840
+ },
841
+ {
842
+ "epoch": 0.84,
843
+ "learning_rate": 0.00027222582402854176,
844
+ "loss": 1.9556,
845
+ "step": 134
846
+ },
847
+ {
848
+ "epoch": 0.84,
849
+ "learning_rate": 0.0002717907008573785,
850
+ "loss": 1.9008,
851
+ "step": 135
852
+ },
853
+ {
854
+ "epoch": 0.85,
855
+ "learning_rate": 0.0002713525491562421,
856
+ "loss": 1.9651,
857
+ "step": 136
858
+ },
859
+ {
860
+ "epoch": 0.85,
861
+ "learning_rate": 0.0002709113798205093,
862
+ "loss": 1.9337,
863
+ "step": 137
864
+ },
865
+ {
866
+ "epoch": 0.86,
867
+ "learning_rate": 0.00027046720382059526,
868
+ "loss": 1.9485,
869
+ "step": 138
870
+ },
871
+ {
872
+ "epoch": 0.87,
873
+ "learning_rate": 0.00027002003220168093,
874
+ "loss": 1.8647,
875
+ "step": 139
876
+ },
877
+ {
878
+ "epoch": 0.87,
879
+ "learning_rate": 0.0002695698760834384,
880
+ "loss": 1.9288,
881
+ "step": 140
882
+ },
883
+ {
884
+ "epoch": 0.88,
885
+ "learning_rate": 0.00026911674665975417,
886
+ "loss": 1.9535,
887
+ "step": 141
888
+ },
889
+ {
890
+ "epoch": 0.89,
891
+ "learning_rate": 0.0002686606551984512,
892
+ "loss": 1.932,
893
+ "step": 142
894
+ },
895
+ {
896
+ "epoch": 0.89,
897
+ "learning_rate": 0.00026820161304100823,
898
+ "loss": 1.9516,
899
+ "step": 143
900
+ },
901
+ {
902
+ "epoch": 0.9,
903
+ "learning_rate": 0.0002677396316022783,
904
+ "loss": 1.9347,
905
+ "step": 144
906
+ },
907
+ {
908
+ "epoch": 0.9,
909
+ "learning_rate": 0.00026727472237020447,
910
+ "loss": 1.9473,
911
+ "step": 145
912
+ },
913
+ {
914
+ "epoch": 0.91,
915
+ "learning_rate": 0.0002668068969055341,
916
+ "loss": 1.9428,
917
+ "step": 146
918
+ },
919
+ {
920
+ "epoch": 0.92,
921
+ "learning_rate": 0.0002663361668415318,
922
+ "loss": 1.9204,
923
+ "step": 147
924
+ },
925
+ {
926
+ "epoch": 0.92,
927
+ "learning_rate": 0.0002658625438836899,
928
+ "loss": 1.9039,
929
+ "step": 148
930
+ },
931
+ {
932
+ "epoch": 0.93,
933
+ "learning_rate": 0.0002653860398094373,
934
+ "loss": 1.9166,
935
+ "step": 149
936
+ },
937
+ {
938
+ "epoch": 0.94,
939
+ "learning_rate": 0.00026490666646784665,
940
+ "loss": 1.9072,
941
+ "step": 150
942
+ },
943
+ {
944
+ "epoch": 0.94,
945
+ "learning_rate": 0.00026442443577933994,
946
+ "loss": 1.9014,
947
+ "step": 151
948
+ },
949
+ {
950
+ "epoch": 0.95,
951
+ "learning_rate": 0.0002639393597353917,
952
+ "loss": 1.9272,
953
+ "step": 152
954
+ },
955
+ {
956
+ "epoch": 0.95,
957
+ "learning_rate": 0.00026345145039823097,
958
+ "loss": 1.9274,
959
+ "step": 153
960
+ },
961
+ {
962
+ "epoch": 0.96,
963
+ "learning_rate": 0.00026296071990054165,
964
+ "loss": 1.9548,
965
+ "step": 154
966
+ },
967
+ {
968
+ "epoch": 0.97,
969
+ "learning_rate": 0.0002624671804451601,
970
+ "loss": 1.928,
971
+ "step": 155
972
+ },
973
+ {
974
+ "epoch": 0.97,
975
+ "learning_rate": 0.0002619708443047725,
976
+ "loss": 1.9072,
977
+ "step": 156
978
+ },
979
+ {
980
+ "epoch": 0.98,
981
+ "learning_rate": 0.00026147172382160914,
982
+ "loss": 1.9116,
983
+ "step": 157
984
+ },
985
+ {
986
+ "epoch": 0.99,
987
+ "learning_rate": 0.0002609698314071376,
988
+ "loss": 1.915,
989
+ "step": 158
990
+ },
991
+ {
992
+ "epoch": 0.99,
993
+ "learning_rate": 0.0002604651795417543,
994
+ "loss": 1.915,
995
+ "step": 159
996
+ },
997
+ {
998
+ "epoch": 1.0,
999
+ "learning_rate": 0.0002599577807744739,
1000
+ "loss": 1.9604,
1001
+ "step": 160
1002
+ },
1003
+ {
1004
+ "epoch": 1.0,
1005
+ "eval_loss": 1.911091685295105,
1006
+ "eval_runtime": 289.5613,
1007
+ "eval_samples_per_second": 206.212,
1008
+ "eval_steps_per_second": 206.212,
1009
+ "step": 160
1010
+ },
1011
+ {
1012
+ "epoch": 1.0,
1013
+ "learning_rate": 0.0002594476477226176,
1014
+ "loss": 1.9335,
1015
+ "step": 161
1016
+ },
1017
+ {
1018
+ "epoch": 1.01,
1019
+ "learning_rate": 0.00025893479307149893,
1020
+ "loss": 1.9033,
1021
+ "step": 162
1022
+ },
1023
+ {
1024
+ "epoch": 1.0,
1025
+ "learning_rate": 0.0002584192295741087,
1026
+ "loss": 1.874,
1027
+ "step": 163
1028
+ },
1029
+ {
1030
+ "epoch": 1.01,
1031
+ "learning_rate": 0.00025790097005079764,
1032
+ "loss": 1.7896,
1033
+ "step": 164
1034
+ },
1035
+ {
1036
+ "epoch": 1.01,
1037
+ "learning_rate": 0.0002573800273889577,
1038
+ "loss": 1.7936,
1039
+ "step": 165
1040
+ },
1041
+ {
1042
+ "epoch": 1.02,
1043
+ "learning_rate": 0.00025685641454270173,
1044
+ "loss": 1.8321,
1045
+ "step": 166
1046
+ },
1047
+ {
1048
+ "epoch": 1.03,
1049
+ "learning_rate": 0.00025633014453254086,
1050
+ "loss": 1.8105,
1051
+ "step": 167
1052
+ },
1053
+ {
1054
+ "epoch": 1.03,
1055
+ "learning_rate": 0.0002558012304450613,
1056
+ "loss": 1.8068,
1057
+ "step": 168
1058
+ },
1059
+ {
1060
+ "epoch": 1.04,
1061
+ "learning_rate": 0.0002552696854325987,
1062
+ "loss": 1.7953,
1063
+ "step": 169
1064
+ },
1065
+ {
1066
+ "epoch": 1.05,
1067
+ "learning_rate": 0.0002547355227129109,
1068
+ "loss": 1.8073,
1069
+ "step": 170
1070
+ },
1071
+ {
1072
+ "epoch": 1.05,
1073
+ "learning_rate": 0.0002541987555688496,
1074
+ "loss": 1.8095,
1075
+ "step": 171
1076
+ },
1077
+ {
1078
+ "epoch": 1.06,
1079
+ "learning_rate": 0.0002536593973480297,
1080
+ "loss": 1.7939,
1081
+ "step": 172
1082
+ },
1083
+ {
1084
+ "epoch": 1.06,
1085
+ "learning_rate": 0.0002531174614624977,
1086
+ "loss": 1.8226,
1087
+ "step": 173
1088
+ },
1089
+ {
1090
+ "epoch": 1.07,
1091
+ "learning_rate": 0.000252572961388398,
1092
+ "loss": 1.7815,
1093
+ "step": 174
1094
+ },
1095
+ {
1096
+ "epoch": 1.08,
1097
+ "learning_rate": 0.00025202591066563786,
1098
+ "loss": 1.7929,
1099
+ "step": 175
1100
+ },
1101
+ {
1102
+ "epoch": 1.08,
1103
+ "learning_rate": 0.00025147632289755075,
1104
+ "loss": 1.8027,
1105
+ "step": 176
1106
+ },
1107
+ {
1108
+ "epoch": 1.09,
1109
+ "learning_rate": 0.0002509242117505579,
1110
+ "loss": 1.8349,
1111
+ "step": 177
1112
+ },
1113
+ {
1114
+ "epoch": 1.1,
1115
+ "learning_rate": 0.0002503695909538287,
1116
+ "loss": 1.7828,
1117
+ "step": 178
1118
+ },
1119
+ {
1120
+ "epoch": 1.1,
1121
+ "learning_rate": 0.0002498124742989391,
1122
+ "loss": 1.814,
1123
+ "step": 179
1124
+ },
1125
+ {
1126
+ "epoch": 1.11,
1127
+ "learning_rate": 0.0002492528756395289,
1128
+ "loss": 1.821,
1129
+ "step": 180
1130
+ },
1131
+ {
1132
+ "epoch": 1.11,
1133
+ "learning_rate": 0.0002486908088909569,
1134
+ "loss": 1.8023,
1135
+ "step": 181
1136
+ },
1137
+ {
1138
+ "epoch": 1.12,
1139
+ "learning_rate": 0.0002481262880299552,
1140
+ "loss": 1.7953,
1141
+ "step": 182
1142
+ },
1143
+ {
1144
+ "epoch": 1.13,
1145
+ "learning_rate": 0.0002475593270942814,
1146
+ "loss": 1.8497,
1147
+ "step": 183
1148
+ },
1149
+ {
1150
+ "epoch": 1.13,
1151
+ "learning_rate": 0.0002469899401823699,
1152
+ "loss": 1.7957,
1153
+ "step": 184
1154
+ },
1155
+ {
1156
+ "epoch": 1.14,
1157
+ "learning_rate": 0.0002464181414529809,
1158
+ "loss": 1.7958,
1159
+ "step": 185
1160
+ },
1161
+ {
1162
+ "epoch": 1.15,
1163
+ "learning_rate": 0.0002458439451248484,
1164
+ "loss": 1.8024,
1165
+ "step": 186
1166
+ },
1167
+ {
1168
+ "epoch": 1.15,
1169
+ "learning_rate": 0.0002452673654763268,
1170
+ "loss": 1.8306,
1171
+ "step": 187
1172
+ },
1173
+ {
1174
+ "epoch": 1.16,
1175
+ "learning_rate": 0.0002446884168450358,
1176
+ "loss": 1.8174,
1177
+ "step": 188
1178
+ },
1179
+ {
1180
+ "epoch": 1.16,
1181
+ "learning_rate": 0.00024410711362750386,
1182
+ "loss": 1.8032,
1183
+ "step": 189
1184
+ },
1185
+ {
1186
+ "epoch": 1.17,
1187
+ "learning_rate": 0.00024352347027881003,
1188
+ "loss": 1.8087,
1189
+ "step": 190
1190
+ },
1191
+ {
1192
+ "epoch": 1.18,
1193
+ "learning_rate": 0.0002429375013122247,
1194
+ "loss": 1.7648,
1195
+ "step": 191
1196
+ },
1197
+ {
1198
+ "epoch": 1.18,
1199
+ "learning_rate": 0.0002423492212988487,
1200
+ "loss": 1.8544,
1201
+ "step": 192
1202
+ },
1203
+ {
1204
+ "epoch": 1.19,
1205
+ "learning_rate": 0.00024175864486725092,
1206
+ "loss": 1.7978,
1207
+ "step": 193
1208
+ },
1209
+ {
1210
+ "epoch": 1.2,
1211
+ "learning_rate": 0.0002411657867031045,
1212
+ "loss": 1.7866,
1213
+ "step": 194
1214
+ },
1215
+ {
1216
+ "epoch": 1.2,
1217
+ "learning_rate": 0.0002405706615488216,
1218
+ "loss": 1.8074,
1219
+ "step": 195
1220
+ },
1221
+ {
1222
+ "epoch": 1.21,
1223
+ "learning_rate": 0.00023997328420318704,
1224
+ "loss": 1.7842,
1225
+ "step": 196
1226
+ },
1227
+ {
1228
+ "epoch": 1.21,
1229
+ "learning_rate": 0.00023937366952099005,
1230
+ "loss": 1.781,
1231
+ "step": 197
1232
+ },
1233
+ {
1234
+ "epoch": 1.22,
1235
+ "learning_rate": 0.00023877183241265514,
1236
+ "loss": 1.786,
1237
+ "step": 198
1238
+ },
1239
+ {
1240
+ "epoch": 1.23,
1241
+ "learning_rate": 0.00023816778784387094,
1242
+ "loss": 1.8091,
1243
+ "step": 199
1244
+ },
1245
+ {
1246
+ "epoch": 1.23,
1247
+ "learning_rate": 0.00023756155083521846,
1248
+ "loss": 1.7684,
1249
+ "step": 200
1250
+ },
1251
+ {
1252
+ "epoch": 1.23,
1253
+ "eval_loss": 1.897764801979065,
1254
+ "eval_runtime": 292.524,
1255
+ "eval_samples_per_second": 204.123,
1256
+ "eval_steps_per_second": 204.123,
1257
+ "step": 200
1258
+ },
1259
+ {
1260
+ "epoch": 1.24,
1261
+ "learning_rate": 0.00023695313646179735,
1262
+ "loss": 1.7693,
1263
+ "step": 201
1264
+ },
1265
+ {
1266
+ "epoch": 1.25,
1267
+ "learning_rate": 0.00023634255985285102,
1268
+ "loss": 1.7598,
1269
+ "step": 202
1270
+ },
1271
+ {
1272
+ "epoch": 1.25,
1273
+ "learning_rate": 0.00023572983619139058,
1274
+ "loss": 1.8441,
1275
+ "step": 203
1276
+ },
1277
+ {
1278
+ "epoch": 1.26,
1279
+ "learning_rate": 0.00023511498071381726,
1280
+ "loss": 1.7768,
1281
+ "step": 204
1282
+ },
1283
+ {
1284
+ "epoch": 1.26,
1285
+ "learning_rate": 0.00023449800870954326,
1286
+ "loss": 1.784,
1287
+ "step": 205
1288
+ },
1289
+ {
1290
+ "epoch": 1.27,
1291
+ "learning_rate": 0.00023387893552061199,
1292
+ "loss": 1.7905,
1293
+ "step": 206
1294
+ },
1295
+ {
1296
+ "epoch": 1.28,
1297
+ "learning_rate": 0.00023325777654131623,
1298
+ "loss": 1.7996,
1299
+ "step": 207
1300
+ },
1301
+ {
1302
+ "epoch": 1.28,
1303
+ "learning_rate": 0.00023263454721781537,
1304
+ "loss": 1.7546,
1305
+ "step": 208
1306
+ },
1307
+ {
1308
+ "epoch": 1.29,
1309
+ "learning_rate": 0.0002320092630477515,
1310
+ "loss": 1.8043,
1311
+ "step": 209
1312
+ },
1313
+ {
1314
+ "epoch": 1.3,
1315
+ "learning_rate": 0.0002313819395798639,
1316
+ "loss": 1.7817,
1317
+ "step": 210
1318
+ },
1319
+ {
1320
+ "epoch": 1.3,
1321
+ "learning_rate": 0.00023075259241360233,
1322
+ "loss": 1.8117,
1323
+ "step": 211
1324
+ },
1325
+ {
1326
+ "epoch": 1.31,
1327
+ "learning_rate": 0.00023012123719873926,
1328
+ "loss": 1.7798,
1329
+ "step": 212
1330
+ },
1331
+ {
1332
+ "epoch": 1.31,
1333
+ "learning_rate": 0.0002294878896349807,
1334
+ "loss": 1.763,
1335
+ "step": 213
1336
+ },
1337
+ {
1338
+ "epoch": 1.32,
1339
+ "learning_rate": 0.00022885256547157566,
1340
+ "loss": 1.8169,
1341
+ "step": 214
1342
+ },
1343
+ {
1344
+ "epoch": 1.33,
1345
+ "learning_rate": 0.0002282152805069247,
1346
+ "loss": 1.797,
1347
+ "step": 215
1348
+ },
1349
+ {
1350
+ "epoch": 1.33,
1351
+ "learning_rate": 0.00022757605058818688,
1352
+ "loss": 1.7768,
1353
+ "step": 216
1354
+ },
1355
+ {
1356
+ "epoch": 1.34,
1357
+ "learning_rate": 0.0002269348916108859,
1358
+ "loss": 1.8005,
1359
+ "step": 217
1360
+ },
1361
+ {
1362
+ "epoch": 1.35,
1363
+ "learning_rate": 0.00022629181951851473,
1364
+ "loss": 1.7734,
1365
+ "step": 218
1366
+ },
1367
+ {
1368
+ "epoch": 1.35,
1369
+ "learning_rate": 0.0002256468503021391,
1370
+ "loss": 1.774,
1371
+ "step": 219
1372
+ },
1373
+ {
1374
+ "epoch": 1.36,
1375
+ "learning_rate": 0.000225,
1376
+ "loss": 1.7865,
1377
+ "step": 220
1378
+ },
1379
+ {
1380
+ "epoch": 1.36,
1381
+ "learning_rate": 0.00022435128469711465,
1382
+ "loss": 1.7613,
1383
+ "step": 221
1384
+ },
1385
+ {
1386
+ "epoch": 1.37,
1387
+ "learning_rate": 0.00022370072052487668,
1388
+ "loss": 1.8013,
1389
+ "step": 222
1390
+ },
1391
+ {
1392
+ "epoch": 1.38,
1393
+ "learning_rate": 0.00022304832366065505,
1394
+ "loss": 1.7617,
1395
+ "step": 223
1396
+ },
1397
+ {
1398
+ "epoch": 1.38,
1399
+ "learning_rate": 0.00022239411032739162,
1400
+ "loss": 1.7323,
1401
+ "step": 224
1402
+ },
1403
+ {
1404
+ "epoch": 1.39,
1405
+ "learning_rate": 0.00022173809679319772,
1406
+ "loss": 1.7838,
1407
+ "step": 225
1408
+ },
1409
+ {
1410
+ "epoch": 1.4,
1411
+ "learning_rate": 0.0002210802993709498,
1412
+ "loss": 1.8099,
1413
+ "step": 226
1414
+ },
1415
+ {
1416
+ "epoch": 1.4,
1417
+ "learning_rate": 0.00022042073441788358,
1418
+ "loss": 1.82,
1419
+ "step": 227
1420
+ },
1421
+ {
1422
+ "epoch": 1.41,
1423
+ "learning_rate": 0.00021975941833518757,
1424
+ "loss": 1.772,
1425
+ "step": 228
1426
+ },
1427
+ {
1428
+ "epoch": 1.41,
1429
+ "learning_rate": 0.00021909636756759483,
1430
+ "loss": 1.8044,
1431
+ "step": 229
1432
+ },
1433
+ {
1434
+ "epoch": 1.42,
1435
+ "learning_rate": 0.00021843159860297442,
1436
+ "loss": 1.7679,
1437
+ "step": 230
1438
+ },
1439
+ {
1440
+ "epoch": 1.43,
1441
+ "learning_rate": 0.00021776512797192123,
1442
+ "loss": 1.7786,
1443
+ "step": 231
1444
+ },
1445
+ {
1446
+ "epoch": 1.43,
1447
+ "learning_rate": 0.00021709697224734487,
1448
+ "loss": 1.8305,
1449
+ "step": 232
1450
+ },
1451
+ {
1452
+ "epoch": 1.44,
1453
+ "learning_rate": 0.00021642714804405772,
1454
+ "loss": 1.8044,
1455
+ "step": 233
1456
+ },
1457
+ {
1458
+ "epoch": 1.45,
1459
+ "learning_rate": 0.0002157556720183616,
1460
+ "loss": 1.7838,
1461
+ "step": 234
1462
+ },
1463
+ {
1464
+ "epoch": 1.45,
1465
+ "learning_rate": 0.00021508256086763368,
1466
+ "loss": 1.7639,
1467
+ "step": 235
1468
+ },
1469
+ {
1470
+ "epoch": 1.46,
1471
+ "learning_rate": 0.00021440783132991136,
1472
+ "loss": 1.8067,
1473
+ "step": 236
1474
+ },
1475
+ {
1476
+ "epoch": 1.46,
1477
+ "learning_rate": 0.00021373150018347576,
1478
+ "loss": 1.772,
1479
+ "step": 237
1480
+ },
1481
+ {
1482
+ "epoch": 1.47,
1483
+ "learning_rate": 0.0002130535842464348,
1484
+ "loss": 1.7985,
1485
+ "step": 238
1486
+ },
1487
+ {
1488
+ "epoch": 1.48,
1489
+ "learning_rate": 0.00021237410037630493,
1490
+ "loss": 1.7746,
1491
+ "step": 239
1492
+ },
1493
+ {
1494
+ "epoch": 1.48,
1495
+ "learning_rate": 0.00021169306546959174,
1496
+ "loss": 1.7673,
1497
+ "step": 240
1498
+ },
1499
+ {
1500
+ "epoch": 1.48,
1501
+ "eval_loss": 1.880852222442627,
1502
+ "eval_runtime": 291.0717,
1503
+ "eval_samples_per_second": 205.142,
1504
+ "eval_steps_per_second": 205.142,
1505
+ "step": 240
1506
+ },
1507
+ {
1508
+ "epoch": 1.49,
1509
+ "learning_rate": 0.00021101049646137003,
1510
+ "loss": 1.7555,
1511
+ "step": 241
1512
+ },
1513
+ {
1514
+ "epoch": 1.49,
1515
+ "learning_rate": 0.0002103264103248626,
1516
+ "loss": 1.7722,
1517
+ "step": 242
1518
+ },
1519
+ {
1520
+ "epoch": 1.5,
1521
+ "learning_rate": 0.00020964082407101824,
1522
+ "loss": 1.7686,
1523
+ "step": 243
1524
+ },
1525
+ {
1526
+ "epoch": 1.51,
1527
+ "learning_rate": 0.00020895375474808852,
1528
+ "loss": 1.7625,
1529
+ "step": 244
1530
+ },
1531
+ {
1532
+ "epoch": 1.51,
1533
+ "learning_rate": 0.0002082652194412042,
1534
+ "loss": 1.7524,
1535
+ "step": 245
1536
+ },
1537
+ {
1538
+ "epoch": 1.52,
1539
+ "learning_rate": 0.00020757523527195005,
1540
+ "loss": 1.7785,
1541
+ "step": 246
1542
+ },
1543
+ {
1544
+ "epoch": 1.53,
1545
+ "learning_rate": 0.00020688381939793928,
1546
+ "loss": 1.7901,
1547
+ "step": 247
1548
+ },
1549
+ {
1550
+ "epoch": 1.53,
1551
+ "learning_rate": 0.0002061909890123868,
1552
+ "loss": 1.7941,
1553
+ "step": 248
1554
+ },
1555
+ {
1556
+ "epoch": 1.54,
1557
+ "learning_rate": 0.00020549676134368184,
1558
+ "loss": 1.8157,
1559
+ "step": 249
1560
+ },
1561
+ {
1562
+ "epoch": 1.54,
1563
+ "learning_rate": 0.00020480115365495926,
1564
+ "loss": 1.8354,
1565
+ "step": 250
1566
+ },
1567
+ {
1568
+ "epoch": 1.55,
1569
+ "learning_rate": 0.00020410418324367055,
1570
+ "loss": 1.7764,
1571
+ "step": 251
1572
+ },
1573
+ {
1574
+ "epoch": 1.56,
1575
+ "learning_rate": 0.0002034058674411535,
1576
+ "loss": 1.7677,
1577
+ "step": 252
1578
+ },
1579
+ {
1580
+ "epoch": 1.56,
1581
+ "learning_rate": 0.0002027062236122014,
1582
+ "loss": 1.7739,
1583
+ "step": 253
1584
+ },
1585
+ {
1586
+ "epoch": 1.57,
1587
+ "learning_rate": 0.00020200526915463107,
1588
+ "loss": 1.7746,
1589
+ "step": 254
1590
+ },
1591
+ {
1592
+ "epoch": 1.58,
1593
+ "learning_rate": 0.00020130302149885031,
1594
+ "loss": 1.7675,
1595
+ "step": 255
1596
+ },
1597
+ {
1598
+ "epoch": 1.58,
1599
+ "learning_rate": 0.0002005994981074245,
1600
+ "loss": 1.737,
1601
+ "step": 256
1602
+ },
1603
+ {
1604
+ "epoch": 1.59,
1605
+ "learning_rate": 0.0001998947164746423,
1606
+ "loss": 1.8318,
1607
+ "step": 257
1608
+ },
1609
+ {
1610
+ "epoch": 1.59,
1611
+ "learning_rate": 0.00019918869412608066,
1612
+ "loss": 1.7959,
1613
+ "step": 258
1614
+ },
1615
+ {
1616
+ "epoch": 1.6,
1617
+ "learning_rate": 0.00019848144861816898,
1618
+ "loss": 1.7567,
1619
+ "step": 259
1620
+ },
1621
+ {
1622
+ "epoch": 1.61,
1623
+ "learning_rate": 0.00019777299753775265,
1624
+ "loss": 1.7896,
1625
+ "step": 260
1626
+ },
1627
+ {
1628
+ "epoch": 1.61,
1629
+ "learning_rate": 0.0001970633585016556,
1630
+ "loss": 1.7706,
1631
+ "step": 261
1632
+ },
1633
+ {
1634
+ "epoch": 1.62,
1635
+ "learning_rate": 0.0001963525491562421,
1636
+ "loss": 1.7561,
1637
+ "step": 262
1638
+ },
1639
+ {
1640
+ "epoch": 1.63,
1641
+ "learning_rate": 0.00019564058717697847,
1642
+ "loss": 1.8023,
1643
+ "step": 263
1644
+ },
1645
+ {
1646
+ "epoch": 1.63,
1647
+ "learning_rate": 0.00019492749026799288,
1648
+ "loss": 1.8121,
1649
+ "step": 264
1650
+ },
1651
+ {
1652
+ "epoch": 1.64,
1653
+ "learning_rate": 0.00019421327616163563,
1654
+ "loss": 1.791,
1655
+ "step": 265
1656
+ },
1657
+ {
1658
+ "epoch": 1.64,
1659
+ "learning_rate": 0.00019349796261803793,
1660
+ "loss": 1.7758,
1661
+ "step": 266
1662
+ },
1663
+ {
1664
+ "epoch": 1.65,
1665
+ "learning_rate": 0.00019278156742467032,
1666
+ "loss": 1.755,
1667
+ "step": 267
1668
+ },
1669
+ {
1670
+ "epoch": 1.66,
1671
+ "learning_rate": 0.0001920641083959004,
1672
+ "loss": 1.6986,
1673
+ "step": 268
1674
+ },
1675
+ {
1676
+ "epoch": 1.66,
1677
+ "learning_rate": 0.00019134560337254986,
1678
+ "loss": 1.7569,
1679
+ "step": 269
1680
+ },
1681
+ {
1682
+ "epoch": 1.67,
1683
+ "learning_rate": 0.00019062607022145078,
1684
+ "loss": 1.7849,
1685
+ "step": 270
1686
+ },
1687
+ {
1688
+ "epoch": 1.68,
1689
+ "learning_rate": 0.00018990552683500125,
1690
+ "loss": 1.7833,
1691
+ "step": 271
1692
+ },
1693
+ {
1694
+ "epoch": 1.68,
1695
+ "learning_rate": 0.00018918399113072076,
1696
+ "loss": 1.7739,
1697
+ "step": 272
1698
+ },
1699
+ {
1700
+ "epoch": 1.69,
1701
+ "learning_rate": 0.00018846148105080424,
1702
+ "loss": 1.7765,
1703
+ "step": 273
1704
+ },
1705
+ {
1706
+ "epoch": 1.69,
1707
+ "learning_rate": 0.00018773801456167628,
1708
+ "loss": 1.6825,
1709
+ "step": 274
1710
+ },
1711
+ {
1712
+ "epoch": 1.7,
1713
+ "learning_rate": 0.00018701360965354402,
1714
+ "loss": 1.758,
1715
+ "step": 275
1716
+ },
1717
+ {
1718
+ "epoch": 1.71,
1719
+ "learning_rate": 0.00018628828433995013,
1720
+ "loss": 1.7477,
1721
+ "step": 276
1722
+ },
1723
+ {
1724
+ "epoch": 1.71,
1725
+ "learning_rate": 0.00018556205665732462,
1726
+ "loss": 1.7757,
1727
+ "step": 277
1728
+ },
1729
+ {
1730
+ "epoch": 1.72,
1731
+ "learning_rate": 0.00018483494466453636,
1732
+ "loss": 1.7946,
1733
+ "step": 278
1734
+ },
1735
+ {
1736
+ "epoch": 1.73,
1737
+ "learning_rate": 0.0001841069664424442,
1738
+ "loss": 1.7968,
1739
+ "step": 279
1740
+ },
1741
+ {
1742
+ "epoch": 1.73,
1743
+ "learning_rate": 0.00018337814009344714,
1744
+ "loss": 1.7296,
1745
+ "step": 280
1746
+ },
1747
+ {
1748
+ "epoch": 1.73,
1749
+ "eval_loss": 1.8629968166351318,
1750
+ "eval_runtime": 293.6177,
1751
+ "eval_samples_per_second": 203.363,
1752
+ "eval_steps_per_second": 203.363,
1753
+ "step": 280
1754
+ },
1755
+ {
1756
+ "epoch": 1.74,
1757
+ "learning_rate": 0.00018264848374103433,
1758
+ "loss": 1.7516,
1759
+ "step": 281
1760
+ },
1761
+ {
1762
+ "epoch": 1.74,
1763
+ "learning_rate": 0.00018191801552933432,
1764
+ "loss": 1.7466,
1765
+ "step": 282
1766
+ },
1767
+ {
1768
+ "epoch": 1.75,
1769
+ "learning_rate": 0.00018118675362266385,
1770
+ "loss": 1.7304,
1771
+ "step": 283
1772
+ },
1773
+ {
1774
+ "epoch": 1.76,
1775
+ "learning_rate": 0.0001804547162050764,
1776
+ "loss": 1.7519,
1777
+ "step": 284
1778
+ },
1779
+ {
1780
+ "epoch": 1.76,
1781
+ "learning_rate": 0.0001797219214799096,
1782
+ "loss": 1.7721,
1783
+ "step": 285
1784
+ },
1785
+ {
1786
+ "epoch": 1.77,
1787
+ "learning_rate": 0.00017898838766933298,
1788
+ "loss": 1.7455,
1789
+ "step": 286
1790
+ },
1791
+ {
1792
+ "epoch": 1.78,
1793
+ "learning_rate": 0.00017825413301389453,
1794
+ "loss": 1.7674,
1795
+ "step": 287
1796
+ },
1797
+ {
1798
+ "epoch": 1.78,
1799
+ "learning_rate": 0.00017751917577206734,
1800
+ "loss": 1.7581,
1801
+ "step": 288
1802
+ },
1803
+ {
1804
+ "epoch": 1.79,
1805
+ "learning_rate": 0.00017678353421979548,
1806
+ "loss": 1.7714,
1807
+ "step": 289
1808
+ },
1809
+ {
1810
+ "epoch": 1.79,
1811
+ "learning_rate": 0.00017604722665003956,
1812
+ "loss": 1.7696,
1813
+ "step": 290
1814
+ },
1815
+ {
1816
+ "epoch": 1.8,
1817
+ "learning_rate": 0.0001753102713723217,
1818
+ "loss": 1.7903,
1819
+ "step": 291
1820
+ },
1821
+ {
1822
+ "epoch": 1.81,
1823
+ "learning_rate": 0.00017457268671227063,
1824
+ "loss": 1.7563,
1825
+ "step": 292
1826
+ },
1827
+ {
1828
+ "epoch": 1.81,
1829
+ "learning_rate": 0.00017383449101116547,
1830
+ "loss": 1.7828,
1831
+ "step": 293
1832
+ },
1833
+ {
1834
+ "epoch": 1.82,
1835
+ "learning_rate": 0.00017309570262548,
1836
+ "loss": 1.7417,
1837
+ "step": 294
1838
+ },
1839
+ {
1840
+ "epoch": 1.83,
1841
+ "learning_rate": 0.00017235633992642615,
1842
+ "loss": 1.7491,
1843
+ "step": 295
1844
+ },
1845
+ {
1846
+ "epoch": 1.83,
1847
+ "learning_rate": 0.000171616421299497,
1848
+ "loss": 1.7316,
1849
+ "step": 296
1850
+ },
1851
+ {
1852
+ "epoch": 1.84,
1853
+ "learning_rate": 0.0001708759651440098,
1854
+ "loss": 1.785,
1855
+ "step": 297
1856
+ },
1857
+ {
1858
+ "epoch": 1.84,
1859
+ "learning_rate": 0.00017013498987264832,
1860
+ "loss": 1.7413,
1861
+ "step": 298
1862
+ },
1863
+ {
1864
+ "epoch": 1.85,
1865
+ "learning_rate": 0.00016939351391100497,
1866
+ "loss": 1.7874,
1867
+ "step": 299
1868
+ },
1869
+ {
1870
+ "epoch": 1.86,
1871
+ "learning_rate": 0.00016865155569712278,
1872
+ "loss": 1.7377,
1873
+ "step": 300
1874
+ },
1875
+ {
1876
+ "epoch": 1.86,
1877
+ "learning_rate": 0.0001679091336810366,
1878
+ "loss": 1.7814,
1879
+ "step": 301
1880
+ },
1881
+ {
1882
+ "epoch": 1.87,
1883
+ "learning_rate": 0.00016716626632431477,
1884
+ "loss": 1.7343,
1885
+ "step": 302
1886
+ },
1887
+ {
1888
+ "epoch": 1.88,
1889
+ "learning_rate": 0.00016642297209959955,
1890
+ "loss": 1.7549,
1891
+ "step": 303
1892
+ },
1893
+ {
1894
+ "epoch": 1.88,
1895
+ "learning_rate": 0.000165679269490148,
1896
+ "loss": 1.8005,
1897
+ "step": 304
1898
+ },
1899
+ {
1900
+ "epoch": 1.89,
1901
+ "learning_rate": 0.0001649351769893725,
1902
+ "loss": 1.8071,
1903
+ "step": 305
1904
+ },
1905
+ {
1906
+ "epoch": 1.89,
1907
+ "learning_rate": 0.00016419071310038057,
1908
+ "loss": 1.777,
1909
+ "step": 306
1910
+ },
1911
+ {
1912
+ "epoch": 1.9,
1913
+ "learning_rate": 0.00016344589633551502,
1914
+ "loss": 1.7851,
1915
+ "step": 307
1916
+ },
1917
+ {
1918
+ "epoch": 1.91,
1919
+ "learning_rate": 0.00016270074521589347,
1920
+ "loss": 1.7768,
1921
+ "step": 308
1922
+ },
1923
+ {
1924
+ "epoch": 1.91,
1925
+ "learning_rate": 0.00016195527827094787,
1926
+ "loss": 1.7751,
1927
+ "step": 309
1928
+ },
1929
+ {
1930
+ "epoch": 1.92,
1931
+ "learning_rate": 0.00016120951403796364,
1932
+ "loss": 1.7342,
1933
+ "step": 310
1934
+ },
1935
+ {
1936
+ "epoch": 1.93,
1937
+ "learning_rate": 0.00016046347106161876,
1938
+ "loss": 1.7465,
1939
+ "step": 311
1940
+ },
1941
+ {
1942
+ "epoch": 1.93,
1943
+ "learning_rate": 0.00015971716789352274,
1944
+ "loss": 1.7957,
1945
+ "step": 312
1946
+ },
1947
+ {
1948
+ "epoch": 1.94,
1949
+ "learning_rate": 0.00015897062309175512,
1950
+ "loss": 1.785,
1951
+ "step": 313
1952
+ },
1953
+ {
1954
+ "epoch": 1.94,
1955
+ "learning_rate": 0.000158223855220404,
1956
+ "loss": 1.7575,
1957
+ "step": 314
1958
+ },
1959
+ {
1960
+ "epoch": 1.95,
1961
+ "learning_rate": 0.00015747688284910457,
1962
+ "loss": 1.7998,
1963
+ "step": 315
1964
+ },
1965
+ {
1966
+ "epoch": 1.96,
1967
+ "learning_rate": 0.00015672972455257723,
1968
+ "loss": 1.7767,
1969
+ "step": 316
1970
+ },
1971
+ {
1972
+ "epoch": 1.96,
1973
+ "learning_rate": 0.00015598239891016574,
1974
+ "loss": 1.7811,
1975
+ "step": 317
1976
+ },
1977
+ {
1978
+ "epoch": 1.97,
1979
+ "learning_rate": 0.00015523492450537517,
1980
+ "loss": 1.7671,
1981
+ "step": 318
1982
+ },
1983
+ {
1984
+ "epoch": 1.98,
1985
+ "learning_rate": 0.00015448731992540976,
1986
+ "loss": 1.7707,
1987
+ "step": 319
1988
+ },
1989
+ {
1990
+ "epoch": 1.98,
1991
+ "learning_rate": 0.00015373960376071093,
1992
+ "loss": 1.7737,
1993
+ "step": 320
1994
+ },
1995
+ {
1996
+ "epoch": 1.98,
1997
+ "eval_loss": 1.8478573560714722,
1998
+ "eval_runtime": 291.1645,
1999
+ "eval_samples_per_second": 205.077,
2000
+ "eval_steps_per_second": 205.077,
2001
+ "step": 320
2002
+ },
2003
+ {
2004
+ "epoch": 1.99,
2005
+ "learning_rate": 0.0001529917946044947,
2006
+ "loss": 1.7395,
2007
+ "step": 321
2008
+ },
2009
+ {
2010
+ "epoch": 1.99,
2011
+ "learning_rate": 0.00015224391105228953,
2012
+ "loss": 1.7596,
2013
+ "step": 322
2014
+ },
2015
+ {
2016
+ "epoch": 2.0,
2017
+ "learning_rate": 0.00015149597170147387,
2018
+ "loss": 1.7475,
2019
+ "step": 323
2020
+ },
2021
+ {
2022
+ "epoch": 2.01,
2023
+ "learning_rate": 0.0001507479951508137,
2024
+ "loss": 1.7828,
2025
+ "step": 324
2026
+ },
2027
+ {
2028
+ "epoch": 2.01,
2029
+ "learning_rate": 0.00015,
2030
+ "loss": 1.7394,
2031
+ "step": 325
2032
+ },
2033
+ {
2034
+ "epoch": 2.0,
2035
+ "learning_rate": 0.0001492520048491863,
2036
+ "loss": 1.6713,
2037
+ "step": 326
2038
+ },
2039
+ {
2040
+ "epoch": 2.01,
2041
+ "learning_rate": 0.0001485040282985261,
2042
+ "loss": 1.5788,
2043
+ "step": 327
2044
+ },
2045
+ {
2046
+ "epoch": 2.02,
2047
+ "learning_rate": 0.00014775608894771047,
2048
+ "loss": 1.6083,
2049
+ "step": 328
2050
+ },
2051
+ {
2052
+ "epoch": 2.02,
2053
+ "learning_rate": 0.0001470082053955053,
2054
+ "loss": 1.5962,
2055
+ "step": 329
2056
+ },
2057
+ {
2058
+ "epoch": 2.03,
2059
+ "learning_rate": 0.00014626039623928907,
2060
+ "loss": 1.564,
2061
+ "step": 330
2062
+ },
2063
+ {
2064
+ "epoch": 2.04,
2065
+ "learning_rate": 0.00014551268007459024,
2066
+ "loss": 1.5529,
2067
+ "step": 331
2068
+ },
2069
+ {
2070
+ "epoch": 2.04,
2071
+ "learning_rate": 0.0001447650754946249,
2072
+ "loss": 1.5699,
2073
+ "step": 332
2074
+ },
2075
+ {
2076
+ "epoch": 2.05,
2077
+ "learning_rate": 0.0001440176010898343,
2078
+ "loss": 1.5667,
2079
+ "step": 333
2080
+ },
2081
+ {
2082
+ "epoch": 2.05,
2083
+ "learning_rate": 0.0001432702754474228,
2084
+ "loss": 1.5275,
2085
+ "step": 334
2086
+ },
2087
+ {
2088
+ "epoch": 2.06,
2089
+ "learning_rate": 0.0001425231171508954,
2090
+ "loss": 1.5585,
2091
+ "step": 335
2092
+ },
2093
+ {
2094
+ "epoch": 2.07,
2095
+ "learning_rate": 0.00014177614477959595,
2096
+ "loss": 1.5753,
2097
+ "step": 336
2098
+ },
2099
+ {
2100
+ "epoch": 2.07,
2101
+ "learning_rate": 0.00014102937690824486,
2102
+ "loss": 1.5479,
2103
+ "step": 337
2104
+ },
2105
+ {
2106
+ "epoch": 2.08,
2107
+ "learning_rate": 0.00014028283210647718,
2108
+ "loss": 1.5721,
2109
+ "step": 338
2110
+ },
2111
+ {
2112
+ "epoch": 2.09,
2113
+ "learning_rate": 0.00013953652893838119,
2114
+ "loss": 1.5526,
2115
+ "step": 339
2116
+ },
2117
+ {
2118
+ "epoch": 2.09,
2119
+ "learning_rate": 0.00013879048596203636,
2120
+ "loss": 1.5777,
2121
+ "step": 340
2122
+ },
2123
+ {
2124
+ "epoch": 2.1,
2125
+ "learning_rate": 0.00013804472172905213,
2126
+ "loss": 1.5216,
2127
+ "step": 341
2128
+ },
2129
+ {
2130
+ "epoch": 2.1,
2131
+ "learning_rate": 0.0001372992547841065,
2132
+ "loss": 1.5776,
2133
+ "step": 342
2134
+ },
2135
+ {
2136
+ "epoch": 2.11,
2137
+ "learning_rate": 0.00013655410366448498,
2138
+ "loss": 1.5717,
2139
+ "step": 343
2140
+ },
2141
+ {
2142
+ "epoch": 2.12,
2143
+ "learning_rate": 0.00013580928689961943,
2144
+ "loss": 1.5628,
2145
+ "step": 344
2146
+ },
2147
+ {
2148
+ "epoch": 2.12,
2149
+ "learning_rate": 0.0001350648230106275,
2150
+ "loss": 1.5333,
2151
+ "step": 345
2152
+ },
2153
+ {
2154
+ "epoch": 2.13,
2155
+ "learning_rate": 0.000134320730509852,
2156
+ "loss": 1.5271,
2157
+ "step": 346
2158
+ },
2159
+ {
2160
+ "epoch": 2.14,
2161
+ "learning_rate": 0.00013357702790040048,
2162
+ "loss": 1.5672,
2163
+ "step": 347
2164
+ },
2165
+ {
2166
+ "epoch": 2.14,
2167
+ "learning_rate": 0.00013283373367568523,
2168
+ "loss": 1.5619,
2169
+ "step": 348
2170
+ },
2171
+ {
2172
+ "epoch": 2.15,
2173
+ "learning_rate": 0.00013209086631896336,
2174
+ "loss": 1.5461,
2175
+ "step": 349
2176
+ },
2177
+ {
2178
+ "epoch": 2.15,
2179
+ "learning_rate": 0.00013134844430287725,
2180
+ "loss": 1.5724,
2181
+ "step": 350
2182
+ },
2183
+ {
2184
+ "epoch": 2.16,
2185
+ "learning_rate": 0.00013060648608899503,
2186
+ "loss": 1.5292,
2187
+ "step": 351
2188
+ },
2189
+ {
2190
+ "epoch": 2.17,
2191
+ "learning_rate": 0.0001298650101273517,
2192
+ "loss": 1.5703,
2193
+ "step": 352
2194
+ },
2195
+ {
2196
+ "epoch": 2.17,
2197
+ "learning_rate": 0.0001291240348559902,
2198
+ "loss": 1.5444,
2199
+ "step": 353
2200
+ },
2201
+ {
2202
+ "epoch": 2.18,
2203
+ "learning_rate": 0.000128383578700503,
2204
+ "loss": 1.5848,
2205
+ "step": 354
2206
+ },
2207
+ {
2208
+ "epoch": 2.19,
2209
+ "learning_rate": 0.0001276436600735738,
2210
+ "loss": 1.603,
2211
+ "step": 355
2212
+ },
2213
+ {
2214
+ "epoch": 2.19,
2215
+ "learning_rate": 0.00012690429737451992,
2216
+ "loss": 1.5961,
2217
+ "step": 356
2218
+ },
2219
+ {
2220
+ "epoch": 2.2,
2221
+ "learning_rate": 0.0001261655089888345,
2222
+ "loss": 1.5635,
2223
+ "step": 357
2224
+ },
2225
+ {
2226
+ "epoch": 2.2,
2227
+ "learning_rate": 0.00012542731328772934,
2228
+ "loss": 1.5743,
2229
+ "step": 358
2230
+ },
2231
+ {
2232
+ "epoch": 2.21,
2233
+ "learning_rate": 0.00012468972862767825,
2234
+ "loss": 1.5291,
2235
+ "step": 359
2236
+ },
2237
+ {
2238
+ "epoch": 2.22,
2239
+ "learning_rate": 0.00012395277334996044,
2240
+ "loss": 1.5871,
2241
+ "step": 360
2242
+ },
2243
+ {
2244
+ "epoch": 2.22,
2245
+ "eval_loss": 1.8882598876953125,
2246
+ "eval_runtime": 292.5066,
2247
+ "eval_samples_per_second": 204.136,
2248
+ "eval_steps_per_second": 204.136,
2249
+ "step": 360
2250
+ },
2251
+ {
2252
+ "epoch": 2.22,
2253
+ "learning_rate": 0.0001232164657802045,
2254
+ "loss": 1.5044,
2255
+ "step": 361
2256
+ },
2257
+ {
2258
+ "epoch": 2.23,
2259
+ "learning_rate": 0.00012248082422793266,
2260
+ "loss": 1.5682,
2261
+ "step": 362
2262
+ },
2263
+ {
2264
+ "epoch": 2.24,
2265
+ "learning_rate": 0.00012174586698610547,
2266
+ "loss": 1.564,
2267
+ "step": 363
2268
+ },
2269
+ {
2270
+ "epoch": 2.24,
2271
+ "learning_rate": 0.00012101161233066703,
2272
+ "loss": 1.5595,
2273
+ "step": 364
2274
+ },
2275
+ {
2276
+ "epoch": 2.25,
2277
+ "learning_rate": 0.00012027807852009038,
2278
+ "loss": 1.5228,
2279
+ "step": 365
2280
+ },
2281
+ {
2282
+ "epoch": 2.25,
2283
+ "learning_rate": 0.00011954528379492359,
2284
+ "loss": 1.5444,
2285
+ "step": 366
2286
+ },
2287
+ {
2288
+ "epoch": 2.26,
2289
+ "learning_rate": 0.00011881324637733611,
2290
+ "loss": 1.5731,
2291
+ "step": 367
2292
+ },
2293
+ {
2294
+ "epoch": 2.27,
2295
+ "learning_rate": 0.0001180819844706657,
2296
+ "loss": 1.5853,
2297
+ "step": 368
2298
+ },
2299
+ {
2300
+ "epoch": 2.27,
2301
+ "learning_rate": 0.00011735151625896565,
2302
+ "loss": 1.583,
2303
+ "step": 369
2304
+ },
2305
+ {
2306
+ "epoch": 2.28,
2307
+ "learning_rate": 0.00011662185990655284,
2308
+ "loss": 1.5859,
2309
+ "step": 370
2310
+ },
2311
+ {
2312
+ "epoch": 2.29,
2313
+ "learning_rate": 0.00011589303355755579,
2314
+ "loss": 1.5597,
2315
+ "step": 371
2316
+ },
2317
+ {
2318
+ "epoch": 2.29,
2319
+ "learning_rate": 0.00011516505533546363,
2320
+ "loss": 1.5692,
2321
+ "step": 372
2322
+ },
2323
+ {
2324
+ "epoch": 2.3,
2325
+ "learning_rate": 0.00011443794334267538,
2326
+ "loss": 1.5628,
2327
+ "step": 373
2328
+ },
2329
+ {
2330
+ "epoch": 2.3,
2331
+ "learning_rate": 0.00011371171566004985,
2332
+ "loss": 1.5875,
2333
+ "step": 374
2334
+ },
2335
+ {
2336
+ "epoch": 2.31,
2337
+ "learning_rate": 0.00011298639034645593,
2338
+ "loss": 1.545,
2339
+ "step": 375
2340
+ },
2341
+ {
2342
+ "epoch": 2.32,
2343
+ "learning_rate": 0.00011226198543832372,
2344
+ "loss": 1.5687,
2345
+ "step": 376
2346
+ },
2347
+ {
2348
+ "epoch": 2.32,
2349
+ "learning_rate": 0.00011153851894919574,
2350
+ "loss": 1.5379,
2351
+ "step": 377
2352
+ },
2353
+ {
2354
+ "epoch": 2.33,
2355
+ "learning_rate": 0.00011081600886927924,
2356
+ "loss": 1.5287,
2357
+ "step": 378
2358
+ },
2359
+ {
2360
+ "epoch": 2.34,
2361
+ "learning_rate": 0.00011009447316499873,
2362
+ "loss": 1.5763,
2363
+ "step": 379
2364
+ },
2365
+ {
2366
+ "epoch": 2.34,
2367
+ "learning_rate": 0.00010937392977854923,
2368
+ "loss": 1.5675,
2369
+ "step": 380
2370
+ },
2371
+ {
2372
+ "epoch": 2.35,
2373
+ "learning_rate": 0.00010865439662745013,
2374
+ "loss": 1.5487,
2375
+ "step": 381
2376
+ },
2377
+ {
2378
+ "epoch": 2.35,
2379
+ "learning_rate": 0.0001079358916040996,
2380
+ "loss": 1.5471,
2381
+ "step": 382
2382
+ },
2383
+ {
2384
+ "epoch": 2.36,
2385
+ "learning_rate": 0.00010721843257532968,
2386
+ "loss": 1.5631,
2387
+ "step": 383
2388
+ },
2389
+ {
2390
+ "epoch": 2.37,
2391
+ "learning_rate": 0.00010650203738196206,
2392
+ "loss": 1.5721,
2393
+ "step": 384
2394
+ },
2395
+ {
2396
+ "epoch": 2.37,
2397
+ "learning_rate": 0.00010578672383836435,
2398
+ "loss": 1.5811,
2399
+ "step": 385
2400
+ },
2401
+ {
2402
+ "epoch": 2.38,
2403
+ "learning_rate": 0.0001050725097320071,
2404
+ "loss": 1.5824,
2405
+ "step": 386
2406
+ },
2407
+ {
2408
+ "epoch": 2.39,
2409
+ "learning_rate": 0.00010435941282302154,
2410
+ "loss": 1.5706,
2411
+ "step": 387
2412
+ },
2413
+ {
2414
+ "epoch": 2.39,
2415
+ "learning_rate": 0.0001036474508437579,
2416
+ "loss": 1.5383,
2417
+ "step": 388
2418
+ },
2419
+ {
2420
+ "epoch": 2.4,
2421
+ "learning_rate": 0.00010293664149834444,
2422
+ "loss": 1.5719,
2423
+ "step": 389
2424
+ },
2425
+ {
2426
+ "epoch": 2.4,
2427
+ "learning_rate": 0.00010222700246224735,
2428
+ "loss": 1.5167,
2429
+ "step": 390
2430
+ },
2431
+ {
2432
+ "epoch": 2.41,
2433
+ "learning_rate": 0.00010151855138183102,
2434
+ "loss": 1.5552,
2435
+ "step": 391
2436
+ },
2437
+ {
2438
+ "epoch": 2.42,
2439
+ "learning_rate": 0.00010081130587391934,
2440
+ "loss": 1.5735,
2441
+ "step": 392
2442
+ },
2443
+ {
2444
+ "epoch": 2.42,
2445
+ "learning_rate": 0.00010010528352535771,
2446
+ "loss": 1.5604,
2447
+ "step": 393
2448
+ },
2449
+ {
2450
+ "epoch": 2.43,
2451
+ "learning_rate": 9.94005018925755e-05,
2452
+ "loss": 1.5332,
2453
+ "step": 394
2454
+ },
2455
+ {
2456
+ "epoch": 2.43,
2457
+ "learning_rate": 9.869697850114969e-05,
2458
+ "loss": 1.5617,
2459
+ "step": 395
2460
+ },
2461
+ {
2462
+ "epoch": 2.44,
2463
+ "learning_rate": 9.799473084536891e-05,
2464
+ "loss": 1.5573,
2465
+ "step": 396
2466
+ },
2467
+ {
2468
+ "epoch": 2.45,
2469
+ "learning_rate": 9.729377638779857e-05,
2470
+ "loss": 1.5541,
2471
+ "step": 397
2472
+ },
2473
+ {
2474
+ "epoch": 2.45,
2475
+ "learning_rate": 9.659413255884647e-05,
2476
+ "loss": 1.5915,
2477
+ "step": 398
2478
+ },
2479
+ {
2480
+ "epoch": 2.46,
2481
+ "learning_rate": 9.589581675632944e-05,
2482
+ "loss": 1.5829,
2483
+ "step": 399
2484
+ },
2485
+ {
2486
+ "epoch": 2.47,
2487
+ "learning_rate": 9.519884634504074e-05,
2488
+ "loss": 1.5339,
2489
+ "step": 400
2490
+ },
2491
+ {
2492
+ "epoch": 2.47,
2493
+ "eval_loss": 1.8761346340179443,
2494
+ "eval_runtime": 290.7874,
2495
+ "eval_samples_per_second": 205.342,
2496
+ "eval_steps_per_second": 205.342,
2497
+ "step": 400
2498
+ },
2499
+ {
2500
+ "epoch": 2.47,
2501
+ "learning_rate": 9.450323865631816e-05,
2502
+ "loss": 1.5532,
2503
+ "step": 401
2504
+ },
2505
+ {
2506
+ "epoch": 2.48,
2507
+ "learning_rate": 9.380901098761319e-05,
2508
+ "loss": 1.5511,
2509
+ "step": 402
2510
+ },
2511
+ {
2512
+ "epoch": 2.48,
2513
+ "learning_rate": 9.311618060206074e-05,
2514
+ "loss": 1.5456,
2515
+ "step": 403
2516
+ },
2517
+ {
2518
+ "epoch": 2.49,
2519
+ "learning_rate": 9.242476472804995e-05,
2520
+ "loss": 1.5488,
2521
+ "step": 404
2522
+ },
2523
+ {
2524
+ "epoch": 2.5,
2525
+ "learning_rate": 9.17347805587958e-05,
2526
+ "loss": 1.5898,
2527
+ "step": 405
2528
+ },
2529
+ {
2530
+ "epoch": 2.5,
2531
+ "learning_rate": 9.104624525191145e-05,
2532
+ "loss": 1.5482,
2533
+ "step": 406
2534
+ },
2535
+ {
2536
+ "epoch": 2.51,
2537
+ "learning_rate": 9.035917592898177e-05,
2538
+ "loss": 1.5348,
2539
+ "step": 407
2540
+ },
2541
+ {
2542
+ "epoch": 2.52,
2543
+ "learning_rate": 8.967358967513738e-05,
2544
+ "loss": 1.5588,
2545
+ "step": 408
2546
+ },
2547
+ {
2548
+ "epoch": 2.52,
2549
+ "learning_rate": 8.898950353862998e-05,
2550
+ "loss": 1.5553,
2551
+ "step": 409
2552
+ },
2553
+ {
2554
+ "epoch": 2.53,
2555
+ "learning_rate": 8.830693453040829e-05,
2556
+ "loss": 1.5642,
2557
+ "step": 410
2558
+ },
2559
+ {
2560
+ "epoch": 2.53,
2561
+ "learning_rate": 8.762589962369511e-05,
2562
+ "loss": 1.5557,
2563
+ "step": 411
2564
+ },
2565
+ {
2566
+ "epoch": 2.54,
2567
+ "learning_rate": 8.694641575356519e-05,
2568
+ "loss": 1.5578,
2569
+ "step": 412
2570
+ },
2571
+ {
2572
+ "epoch": 2.55,
2573
+ "learning_rate": 8.626849981652424e-05,
2574
+ "loss": 1.574,
2575
+ "step": 413
2576
+ },
2577
+ {
2578
+ "epoch": 2.55,
2579
+ "learning_rate": 8.55921686700886e-05,
2580
+ "loss": 1.5666,
2581
+ "step": 414
2582
+ },
2583
+ {
2584
+ "epoch": 2.56,
2585
+ "learning_rate": 8.491743913236628e-05,
2586
+ "loss": 1.5562,
2587
+ "step": 415
2588
+ },
2589
+ {
2590
+ "epoch": 2.57,
2591
+ "learning_rate": 8.424432798163836e-05,
2592
+ "loss": 1.5529,
2593
+ "step": 416
2594
+ },
2595
+ {
2596
+ "epoch": 2.57,
2597
+ "learning_rate": 8.357285195594228e-05,
2598
+ "loss": 1.538,
2599
+ "step": 417
2600
+ },
2601
+ {
2602
+ "epoch": 2.58,
2603
+ "learning_rate": 8.290302775265509e-05,
2604
+ "loss": 1.5782,
2605
+ "step": 418
2606
+ },
2607
+ {
2608
+ "epoch": 2.58,
2609
+ "learning_rate": 8.223487202807877e-05,
2610
+ "loss": 1.55,
2611
+ "step": 419
2612
+ },
2613
+ {
2614
+ "epoch": 2.59,
2615
+ "learning_rate": 8.156840139702554e-05,
2616
+ "loss": 1.5439,
2617
+ "step": 420
2618
+ },
2619
+ {
2620
+ "epoch": 2.6,
2621
+ "learning_rate": 8.090363243240517e-05,
2622
+ "loss": 1.5627,
2623
+ "step": 421
2624
+ },
2625
+ {
2626
+ "epoch": 2.6,
2627
+ "learning_rate": 8.024058166481243e-05,
2628
+ "loss": 1.5693,
2629
+ "step": 422
2630
+ },
2631
+ {
2632
+ "epoch": 2.61,
2633
+ "learning_rate": 7.957926558211642e-05,
2634
+ "loss": 1.5816,
2635
+ "step": 423
2636
+ },
2637
+ {
2638
+ "epoch": 2.62,
2639
+ "learning_rate": 7.89197006290502e-05,
2640
+ "loss": 1.5464,
2641
+ "step": 424
2642
+ },
2643
+ {
2644
+ "epoch": 2.62,
2645
+ "learning_rate": 7.82619032068023e-05,
2646
+ "loss": 1.5494,
2647
+ "step": 425
2648
+ },
2649
+ {
2650
+ "epoch": 2.63,
2651
+ "learning_rate": 7.760588967260838e-05,
2652
+ "loss": 1.5711,
2653
+ "step": 426
2654
+ },
2655
+ {
2656
+ "epoch": 2.63,
2657
+ "learning_rate": 7.69516763393449e-05,
2658
+ "loss": 1.5801,
2659
+ "step": 427
2660
+ },
2661
+ {
2662
+ "epoch": 2.64,
2663
+ "learning_rate": 7.629927947512331e-05,
2664
+ "loss": 1.5628,
2665
+ "step": 428
2666
+ },
2667
+ {
2668
+ "epoch": 2.65,
2669
+ "learning_rate": 7.564871530288536e-05,
2670
+ "loss": 1.5601,
2671
+ "step": 429
2672
+ },
2673
+ {
2674
+ "epoch": 2.65,
2675
+ "learning_rate": 7.500000000000002e-05,
2676
+ "loss": 1.5453,
2677
+ "step": 430
2678
+ },
2679
+ {
2680
+ "epoch": 2.66,
2681
+ "learning_rate": 7.435314969786088e-05,
2682
+ "loss": 1.5684,
2683
+ "step": 431
2684
+ },
2685
+ {
2686
+ "epoch": 2.67,
2687
+ "learning_rate": 7.370818048148527e-05,
2688
+ "loss": 1.5656,
2689
+ "step": 432
2690
+ },
2691
+ {
2692
+ "epoch": 2.67,
2693
+ "learning_rate": 7.30651083891141e-05,
2694
+ "loss": 1.5735,
2695
+ "step": 433
2696
+ },
2697
+ {
2698
+ "epoch": 2.68,
2699
+ "learning_rate": 7.242394941181308e-05,
2700
+ "loss": 1.5587,
2701
+ "step": 434
2702
+ },
2703
+ {
2704
+ "epoch": 2.68,
2705
+ "learning_rate": 7.17847194930753e-05,
2706
+ "loss": 1.5735,
2707
+ "step": 435
2708
+ },
2709
+ {
2710
+ "epoch": 2.69,
2711
+ "learning_rate": 7.114743452842427e-05,
2712
+ "loss": 1.5656,
2713
+ "step": 436
2714
+ },
2715
+ {
2716
+ "epoch": 2.7,
2717
+ "learning_rate": 7.051211036501928e-05,
2718
+ "loss": 1.5228,
2719
+ "step": 437
2720
+ },
2721
+ {
2722
+ "epoch": 2.7,
2723
+ "learning_rate": 6.987876280126068e-05,
2724
+ "loss": 1.5452,
2725
+ "step": 438
2726
+ },
2727
+ {
2728
+ "epoch": 2.71,
2729
+ "learning_rate": 6.924740758639768e-05,
2730
+ "loss": 1.5777,
2731
+ "step": 439
2732
+ },
2733
+ {
2734
+ "epoch": 2.72,
2735
+ "learning_rate": 6.86180604201361e-05,
2736
+ "loss": 1.5589,
2737
+ "step": 440
2738
+ },
2739
+ {
2740
+ "epoch": 2.72,
2741
+ "eval_loss": 1.8656864166259766,
2742
+ "eval_runtime": 292.9263,
2743
+ "eval_samples_per_second": 203.843,
2744
+ "eval_steps_per_second": 203.843,
2745
+ "step": 440
2746
+ },
2747
+ {
2748
+ "epoch": 2.72,
2749
+ "learning_rate": 6.799073695224846e-05,
2750
+ "loss": 1.562,
2751
+ "step": 441
2752
+ },
2753
+ {
2754
+ "epoch": 2.73,
2755
+ "learning_rate": 6.736545278218463e-05,
2756
+ "loss": 1.5788,
2757
+ "step": 442
2758
+ },
2759
+ {
2760
+ "epoch": 2.73,
2761
+ "learning_rate": 6.674222345868376e-05,
2762
+ "loss": 1.5532,
2763
+ "step": 443
2764
+ },
2765
+ {
2766
+ "epoch": 2.74,
2767
+ "learning_rate": 6.612106447938799e-05,
2768
+ "loss": 1.5986,
2769
+ "step": 444
2770
+ },
2771
+ {
2772
+ "epoch": 2.75,
2773
+ "learning_rate": 6.550199129045668e-05,
2774
+ "loss": 1.573,
2775
+ "step": 445
2776
+ },
2777
+ {
2778
+ "epoch": 2.75,
2779
+ "learning_rate": 6.488501928618274e-05,
2780
+ "loss": 1.5544,
2781
+ "step": 446
2782
+ },
2783
+ {
2784
+ "epoch": 2.76,
2785
+ "learning_rate": 6.427016380860937e-05,
2786
+ "loss": 1.5651,
2787
+ "step": 447
2788
+ },
2789
+ {
2790
+ "epoch": 2.77,
2791
+ "learning_rate": 6.365744014714898e-05,
2792
+ "loss": 1.5261,
2793
+ "step": 448
2794
+ },
2795
+ {
2796
+ "epoch": 2.77,
2797
+ "learning_rate": 6.304686353820266e-05,
2798
+ "loss": 1.5325,
2799
+ "step": 449
2800
+ },
2801
+ {
2802
+ "epoch": 2.78,
2803
+ "learning_rate": 6.243844916478155e-05,
2804
+ "loss": 1.5435,
2805
+ "step": 450
2806
+ },
2807
+ {
2808
+ "epoch": 2.78,
2809
+ "learning_rate": 6.183221215612904e-05,
2810
+ "loss": 1.546,
2811
+ "step": 451
2812
+ },
2813
+ {
2814
+ "epoch": 2.79,
2815
+ "learning_rate": 6.122816758734487e-05,
2816
+ "loss": 1.5508,
2817
+ "step": 452
2818
+ },
2819
+ {
2820
+ "epoch": 2.8,
2821
+ "learning_rate": 6.0626330479009845e-05,
2822
+ "loss": 1.5678,
2823
+ "step": 453
2824
+ },
2825
+ {
2826
+ "epoch": 2.8,
2827
+ "learning_rate": 6.002671579681294e-05,
2828
+ "loss": 1.523,
2829
+ "step": 454
2830
+ },
2831
+ {
2832
+ "epoch": 2.81,
2833
+ "learning_rate": 5.9429338451178355e-05,
2834
+ "loss": 1.5271,
2835
+ "step": 455
2836
+ },
2837
+ {
2838
+ "epoch": 2.82,
2839
+ "learning_rate": 5.88342132968955e-05,
2840
+ "loss": 1.5285,
2841
+ "step": 456
2842
+ },
2843
+ {
2844
+ "epoch": 2.82,
2845
+ "learning_rate": 5.824135513274902e-05,
2846
+ "loss": 1.5476,
2847
+ "step": 457
2848
+ },
2849
+ {
2850
+ "epoch": 2.83,
2851
+ "learning_rate": 5.765077870115125e-05,
2852
+ "loss": 1.5216,
2853
+ "step": 458
2854
+ },
2855
+ {
2856
+ "epoch": 2.83,
2857
+ "learning_rate": 5.706249868777526e-05,
2858
+ "loss": 1.547,
2859
+ "step": 459
2860
+ },
2861
+ {
2862
+ "epoch": 2.84,
2863
+ "learning_rate": 5.6476529721189974e-05,
2864
+ "loss": 1.5398,
2865
+ "step": 460
2866
+ },
2867
+ {
2868
+ "epoch": 2.85,
2869
+ "learning_rate": 5.589288637249612e-05,
2870
+ "loss": 1.579,
2871
+ "step": 461
2872
+ },
2873
+ {
2874
+ "epoch": 2.85,
2875
+ "learning_rate": 5.531158315496417e-05,
2876
+ "loss": 1.4801,
2877
+ "step": 462
2878
+ },
2879
+ {
2880
+ "epoch": 2.86,
2881
+ "learning_rate": 5.473263452367318e-05,
2882
+ "loss": 1.5465,
2883
+ "step": 463
2884
+ },
2885
+ {
2886
+ "epoch": 2.87,
2887
+ "learning_rate": 5.415605487515164e-05,
2888
+ "loss": 1.5303,
2889
+ "step": 464
2890
+ },
2891
+ {
2892
+ "epoch": 2.87,
2893
+ "learning_rate": 5.358185854701909e-05,
2894
+ "loss": 1.5519,
2895
+ "step": 465
2896
+ },
2897
+ {
2898
+ "epoch": 2.88,
2899
+ "learning_rate": 5.3010059817630066e-05,
2900
+ "loss": 1.5818,
2901
+ "step": 466
2902
+ },
2903
+ {
2904
+ "epoch": 2.88,
2905
+ "learning_rate": 5.244067290571856e-05,
2906
+ "loss": 1.5413,
2907
+ "step": 467
2908
+ },
2909
+ {
2910
+ "epoch": 2.89,
2911
+ "learning_rate": 5.187371197004485e-05,
2912
+ "loss": 1.5372,
2913
+ "step": 468
2914
+ },
2915
+ {
2916
+ "epoch": 2.9,
2917
+ "learning_rate": 5.130919110904311e-05,
2918
+ "loss": 1.5459,
2919
+ "step": 469
2920
+ },
2921
+ {
2922
+ "epoch": 2.9,
2923
+ "learning_rate": 5.074712436047112e-05,
2924
+ "loss": 1.5488,
2925
+ "step": 470
2926
+ },
2927
+ {
2928
+ "epoch": 2.91,
2929
+ "learning_rate": 5.018752570106086e-05,
2930
+ "loss": 1.5332,
2931
+ "step": 471
2932
+ },
2933
+ {
2934
+ "epoch": 2.92,
2935
+ "learning_rate": 4.963040904617131e-05,
2936
+ "loss": 1.5684,
2937
+ "step": 472
2938
+ },
2939
+ {
2940
+ "epoch": 2.92,
2941
+ "learning_rate": 4.9075788249442024e-05,
2942
+ "loss": 1.5405,
2943
+ "step": 473
2944
+ },
2945
+ {
2946
+ "epoch": 2.93,
2947
+ "learning_rate": 4.852367710244921e-05,
2948
+ "loss": 1.5361,
2949
+ "step": 474
2950
+ },
2951
+ {
2952
+ "epoch": 2.93,
2953
+ "learning_rate": 4.7974089334362057e-05,
2954
+ "loss": 1.5219,
2955
+ "step": 475
2956
+ },
2957
+ {
2958
+ "epoch": 2.94,
2959
+ "learning_rate": 4.742703861160198e-05,
2960
+ "loss": 1.5518,
2961
+ "step": 476
2962
+ },
2963
+ {
2964
+ "epoch": 2.95,
2965
+ "learning_rate": 4.688253853750227e-05,
2966
+ "loss": 1.5699,
2967
+ "step": 477
2968
+ },
2969
+ {
2970
+ "epoch": 2.95,
2971
+ "learning_rate": 4.63406026519703e-05,
2972
+ "loss": 1.5368,
2973
+ "step": 478
2974
+ },
2975
+ {
2976
+ "epoch": 2.96,
2977
+ "learning_rate": 4.5801244431150394e-05,
2978
+ "loss": 1.5286,
2979
+ "step": 479
2980
+ },
2981
+ {
2982
+ "epoch": 2.96,
2983
+ "learning_rate": 4.526447728708908e-05,
2984
+ "loss": 1.5651,
2985
+ "step": 480
2986
+ },
2987
+ {
2988
+ "epoch": 2.96,
2989
+ "eval_loss": 1.8590147495269775,
2990
+ "eval_runtime": 291.2621,
2991
+ "eval_samples_per_second": 205.008,
2992
+ "eval_steps_per_second": 205.008,
2993
+ "step": 480
2994
+ },
2995
+ {
2996
+ "epoch": 2.97,
2997
+ "learning_rate": 4.4730314567401275e-05,
2998
+ "loss": 1.5242,
2999
+ "step": 481
3000
+ },
3001
+ {
3002
+ "epoch": 2.98,
3003
+ "learning_rate": 4.419876955493869e-05,
3004
+ "loss": 1.5424,
3005
+ "step": 482
3006
+ },
3007
+ {
3008
+ "epoch": 2.98,
3009
+ "learning_rate": 4.3669855467459144e-05,
3010
+ "loss": 1.5329,
3011
+ "step": 483
3012
+ },
3013
+ {
3014
+ "epoch": 2.99,
3015
+ "learning_rate": 4.31435854572983e-05,
3016
+ "loss": 1.5417,
3017
+ "step": 484
3018
+ },
3019
+ {
3020
+ "epoch": 3.0,
3021
+ "learning_rate": 4.261997261104223e-05,
3022
+ "loss": 1.5558,
3023
+ "step": 485
3024
+ },
3025
+ {
3026
+ "epoch": 3.0,
3027
+ "learning_rate": 4.209902994920235e-05,
3028
+ "loss": 1.5102,
3029
+ "step": 486
3030
+ },
3031
+ {
3032
+ "epoch": 3.01,
3033
+ "learning_rate": 4.158077042589128e-05,
3034
+ "loss": 1.5143,
3035
+ "step": 487
3036
+ },
3037
+ {
3038
+ "epoch": 3.0,
3039
+ "learning_rate": 4.1065206928501055e-05,
3040
+ "loss": 1.5588,
3041
+ "step": 488
3042
+ },
3043
+ {
3044
+ "epoch": 3.01,
3045
+ "learning_rate": 4.055235227738237e-05,
3046
+ "loss": 1.375,
3047
+ "step": 489
3048
+ },
3049
+ {
3050
+ "epoch": 3.01,
3051
+ "learning_rate": 4.004221922552608e-05,
3052
+ "loss": 1.3812,
3053
+ "step": 490
3054
+ },
3055
+ {
3056
+ "epoch": 3.02,
3057
+ "learning_rate": 3.953482045824573e-05,
3058
+ "loss": 1.3902,
3059
+ "step": 491
3060
+ },
3061
+ {
3062
+ "epoch": 3.03,
3063
+ "learning_rate": 3.903016859286243e-05,
3064
+ "loss": 1.3749,
3065
+ "step": 492
3066
+ },
3067
+ {
3068
+ "epoch": 3.03,
3069
+ "learning_rate": 3.852827617839084e-05,
3070
+ "loss": 1.3684,
3071
+ "step": 493
3072
+ },
3073
+ {
3074
+ "epoch": 3.04,
3075
+ "learning_rate": 3.8029155695227474e-05,
3076
+ "loss": 1.383,
3077
+ "step": 494
3078
+ },
3079
+ {
3080
+ "epoch": 3.04,
3081
+ "learning_rate": 3.753281955483985e-05,
3082
+ "loss": 1.3497,
3083
+ "step": 495
3084
+ },
3085
+ {
3086
+ "epoch": 3.05,
3087
+ "learning_rate": 3.7039280099458366e-05,
3088
+ "loss": 1.3742,
3089
+ "step": 496
3090
+ },
3091
+ {
3092
+ "epoch": 3.06,
3093
+ "learning_rate": 3.654854960176895e-05,
3094
+ "loss": 1.3838,
3095
+ "step": 497
3096
+ },
3097
+ {
3098
+ "epoch": 3.06,
3099
+ "learning_rate": 3.60606402646083e-05,
3100
+ "loss": 1.3758,
3101
+ "step": 498
3102
+ },
3103
+ {
3104
+ "epoch": 3.07,
3105
+ "learning_rate": 3.557556422066002e-05,
3106
+ "loss": 1.365,
3107
+ "step": 499
3108
+ },
3109
+ {
3110
+ "epoch": 3.08,
3111
+ "learning_rate": 3.509333353215331e-05,
3112
+ "loss": 1.3621,
3113
+ "step": 500
3114
+ },
3115
+ {
3116
+ "epoch": 3.08,
3117
+ "learning_rate": 3.4613960190562696e-05,
3118
+ "loss": 1.3515,
3119
+ "step": 501
3120
+ },
3121
+ {
3122
+ "epoch": 3.09,
3123
+ "learning_rate": 3.413745611631009e-05,
3124
+ "loss": 1.3561,
3125
+ "step": 502
3126
+ },
3127
+ {
3128
+ "epoch": 3.09,
3129
+ "learning_rate": 3.366383315846815e-05,
3130
+ "loss": 1.3699,
3131
+ "step": 503
3132
+ },
3133
+ {
3134
+ "epoch": 3.1,
3135
+ "learning_rate": 3.3193103094465906e-05,
3136
+ "loss": 1.3388,
3137
+ "step": 504
3138
+ },
3139
+ {
3140
+ "epoch": 3.11,
3141
+ "learning_rate": 3.2725277629795526e-05,
3142
+ "loss": 1.3341,
3143
+ "step": 505
3144
+ },
3145
+ {
3146
+ "epoch": 3.11,
3147
+ "learning_rate": 3.226036839772165e-05,
3148
+ "loss": 1.3279,
3149
+ "step": 506
3150
+ },
3151
+ {
3152
+ "epoch": 3.12,
3153
+ "learning_rate": 3.1798386958991714e-05,
3154
+ "loss": 1.374,
3155
+ "step": 507
3156
+ },
3157
+ {
3158
+ "epoch": 3.13,
3159
+ "learning_rate": 3.133934480154885e-05,
3160
+ "loss": 1.3762,
3161
+ "step": 508
3162
+ },
3163
+ {
3164
+ "epoch": 3.13,
3165
+ "learning_rate": 3.0883253340245845e-05,
3166
+ "loss": 1.3613,
3167
+ "step": 509
3168
+ },
3169
+ {
3170
+ "epoch": 3.14,
3171
+ "learning_rate": 3.0430123916561672e-05,
3172
+ "loss": 1.3593,
3173
+ "step": 510
3174
+ },
3175
+ {
3176
+ "epoch": 3.14,
3177
+ "learning_rate": 2.997996779831907e-05,
3178
+ "loss": 1.3717,
3179
+ "step": 511
3180
+ },
3181
+ {
3182
+ "epoch": 3.15,
3183
+ "learning_rate": 2.953279617940478e-05,
3184
+ "loss": 1.3379,
3185
+ "step": 512
3186
+ },
3187
+ {
3188
+ "epoch": 3.16,
3189
+ "learning_rate": 2.9088620179490675e-05,
3190
+ "loss": 1.3429,
3191
+ "step": 513
3192
+ },
3193
+ {
3194
+ "epoch": 3.16,
3195
+ "learning_rate": 2.8647450843757897e-05,
3196
+ "loss": 1.3596,
3197
+ "step": 514
3198
+ },
3199
+ {
3200
+ "epoch": 3.17,
3201
+ "learning_rate": 2.8209299142621522e-05,
3202
+ "loss": 1.3652,
3203
+ "step": 515
3204
+ },
3205
+ {
3206
+ "epoch": 3.18,
3207
+ "learning_rate": 2.7774175971458283e-05,
3208
+ "loss": 1.3752,
3209
+ "step": 516
3210
+ },
3211
+ {
3212
+ "epoch": 3.18,
3213
+ "learning_rate": 2.7342092150335292e-05,
3214
+ "loss": 1.3611,
3215
+ "step": 517
3216
+ },
3217
+ {
3218
+ "epoch": 3.19,
3219
+ "learning_rate": 2.691305842374128e-05,
3220
+ "loss": 1.3731,
3221
+ "step": 518
3222
+ },
3223
+ {
3224
+ "epoch": 3.19,
3225
+ "learning_rate": 2.648708546031911e-05,
3226
+ "loss": 1.3582,
3227
+ "step": 519
3228
+ },
3229
+ {
3230
+ "epoch": 3.2,
3231
+ "learning_rate": 2.6064183852600797e-05,
3232
+ "loss": 1.3134,
3233
+ "step": 520
3234
+ },
3235
+ {
3236
+ "epoch": 3.2,
3237
+ "eval_loss": 1.949735164642334,
3238
+ "eval_runtime": 295.0075,
3239
+ "eval_samples_per_second": 202.405,
3240
+ "eval_steps_per_second": 202.405,
3241
+ "step": 520
3242
+ },
3243
+ {
3244
+ "epoch": 3.21,
3245
+ "learning_rate": 2.5644364116743755e-05,
3246
+ "loss": 1.38,
3247
+ "step": 521
3248
+ },
3249
+ {
3250
+ "epoch": 3.21,
3251
+ "learning_rate": 2.5227636692269688e-05,
3252
+ "loss": 1.3663,
3253
+ "step": 522
3254
+ },
3255
+ {
3256
+ "epoch": 3.22,
3257
+ "learning_rate": 2.48140119418046e-05,
3258
+ "loss": 1.3502,
3259
+ "step": 523
3260
+ },
3261
+ {
3262
+ "epoch": 3.23,
3263
+ "learning_rate": 2.440350015082152e-05,
3264
+ "loss": 1.3493,
3265
+ "step": 524
3266
+ },
3267
+ {
3268
+ "epoch": 3.23,
3269
+ "learning_rate": 2.3996111527384288e-05,
3270
+ "loss": 1.3288,
3271
+ "step": 525
3272
+ },
3273
+ {
3274
+ "epoch": 3.24,
3275
+ "learning_rate": 2.359185620189412e-05,
3276
+ "loss": 1.3119,
3277
+ "step": 526
3278
+ },
3279
+ {
3280
+ "epoch": 3.24,
3281
+ "learning_rate": 2.31907442268375e-05,
3282
+ "loss": 1.3279,
3283
+ "step": 527
3284
+ },
3285
+ {
3286
+ "epoch": 3.25,
3287
+ "learning_rate": 2.2792785576536105e-05,
3288
+ "loss": 1.332,
3289
+ "step": 528
3290
+ },
3291
+ {
3292
+ "epoch": 3.26,
3293
+ "learning_rate": 2.239799014689908e-05,
3294
+ "loss": 1.357,
3295
+ "step": 529
3296
+ },
3297
+ {
3298
+ "epoch": 3.26,
3299
+ "learning_rate": 2.2006367755176655e-05,
3300
+ "loss": 1.3447,
3301
+ "step": 530
3302
+ },
3303
+ {
3304
+ "epoch": 3.27,
3305
+ "learning_rate": 2.1617928139716247e-05,
3306
+ "loss": 1.3639,
3307
+ "step": 531
3308
+ },
3309
+ {
3310
+ "epoch": 3.28,
3311
+ "learning_rate": 2.1232680959720082e-05,
3312
+ "loss": 1.33,
3313
+ "step": 532
3314
+ },
3315
+ {
3316
+ "epoch": 3.28,
3317
+ "learning_rate": 2.0850635795005262e-05,
3318
+ "loss": 1.3419,
3319
+ "step": 533
3320
+ },
3321
+ {
3322
+ "epoch": 3.29,
3323
+ "learning_rate": 2.0471802145765376e-05,
3324
+ "loss": 1.3326,
3325
+ "step": 534
3326
+ },
3327
+ {
3328
+ "epoch": 3.29,
3329
+ "learning_rate": 2.009618943233419e-05,
3330
+ "loss": 1.347,
3331
+ "step": 535
3332
+ },
3333
+ {
3334
+ "epoch": 3.3,
3335
+ "learning_rate": 1.9723806994951675e-05,
3336
+ "loss": 1.3543,
3337
+ "step": 536
3338
+ },
3339
+ {
3340
+ "epoch": 3.31,
3341
+ "learning_rate": 1.935466409353139e-05,
3342
+ "loss": 1.3428,
3343
+ "step": 537
3344
+ },
3345
+ {
3346
+ "epoch": 3.31,
3347
+ "learning_rate": 1.8988769907430552e-05,
3348
+ "loss": 1.3416,
3349
+ "step": 538
3350
+ },
3351
+ {
3352
+ "epoch": 3.32,
3353
+ "learning_rate": 1.8626133535221517e-05,
3354
+ "loss": 1.3571,
3355
+ "step": 539
3356
+ },
3357
+ {
3358
+ "epoch": 3.33,
3359
+ "learning_rate": 1.82667639944657e-05,
3360
+ "loss": 1.3599,
3361
+ "step": 540
3362
+ },
3363
+ {
3364
+ "epoch": 3.33,
3365
+ "learning_rate": 1.79106702214893e-05,
3366
+ "loss": 1.3225,
3367
+ "step": 541
3368
+ },
3369
+ {
3370
+ "epoch": 3.34,
3371
+ "learning_rate": 1.755786107116095e-05,
3372
+ "loss": 1.3576,
3373
+ "step": 542
3374
+ },
3375
+ {
3376
+ "epoch": 3.34,
3377
+ "learning_rate": 1.7208345316671747e-05,
3378
+ "loss": 1.3816,
3379
+ "step": 543
3380
+ },
3381
+ {
3382
+ "epoch": 3.35,
3383
+ "learning_rate": 1.6862131649316884e-05,
3384
+ "loss": 1.3527,
3385
+ "step": 544
3386
+ },
3387
+ {
3388
+ "epoch": 3.36,
3389
+ "learning_rate": 1.6519228678279718e-05,
3390
+ "loss": 1.3533,
3391
+ "step": 545
3392
+ },
3393
+ {
3394
+ "epoch": 3.36,
3395
+ "learning_rate": 1.6179644930417497e-05,
3396
+ "loss": 1.348,
3397
+ "step": 546
3398
+ },
3399
+ {
3400
+ "epoch": 3.37,
3401
+ "learning_rate": 1.5843388850049498e-05,
3402
+ "loss": 1.3487,
3403
+ "step": 547
3404
+ },
3405
+ {
3406
+ "epoch": 3.37,
3407
+ "learning_rate": 1.5510468798746878e-05,
3408
+ "loss": 1.3597,
3409
+ "step": 548
3410
+ },
3411
+ {
3412
+ "epoch": 3.38,
3413
+ "learning_rate": 1.5180893055124977e-05,
3414
+ "loss": 1.3334,
3415
+ "step": 549
3416
+ },
3417
+ {
3418
+ "epoch": 3.39,
3419
+ "learning_rate": 1.4854669814637143e-05,
3420
+ "loss": 1.3969,
3421
+ "step": 550
3422
+ },
3423
+ {
3424
+ "epoch": 3.39,
3425
+ "learning_rate": 1.4531807189371264e-05,
3426
+ "loss": 1.3682,
3427
+ "step": 551
3428
+ },
3429
+ {
3430
+ "epoch": 3.4,
3431
+ "learning_rate": 1.4212313207847786e-05,
3432
+ "loss": 1.3385,
3433
+ "step": 552
3434
+ },
3435
+ {
3436
+ "epoch": 3.41,
3437
+ "learning_rate": 1.3896195814820266e-05,
3438
+ "loss": 1.3322,
3439
+ "step": 553
3440
+ },
3441
+ {
3442
+ "epoch": 3.41,
3443
+ "learning_rate": 1.3583462871077672e-05,
3444
+ "loss": 1.3438,
3445
+ "step": 554
3446
+ },
3447
+ {
3448
+ "epoch": 3.42,
3449
+ "learning_rate": 1.3274122153249028e-05,
3450
+ "loss": 1.3818,
3451
+ "step": 555
3452
+ },
3453
+ {
3454
+ "epoch": 3.42,
3455
+ "learning_rate": 1.2968181353609852e-05,
3456
+ "loss": 1.3426,
3457
+ "step": 556
3458
+ },
3459
+ {
3460
+ "epoch": 3.43,
3461
+ "learning_rate": 1.2665648079891139e-05,
3462
+ "loss": 1.3623,
3463
+ "step": 557
3464
+ },
3465
+ {
3466
+ "epoch": 3.44,
3467
+ "learning_rate": 1.2366529855089913e-05,
3468
+ "loss": 1.3458,
3469
+ "step": 558
3470
+ },
3471
+ {
3472
+ "epoch": 3.44,
3473
+ "learning_rate": 1.2070834117282412e-05,
3474
+ "loss": 1.3632,
3475
+ "step": 559
3476
+ },
3477
+ {
3478
+ "epoch": 3.45,
3479
+ "learning_rate": 1.1778568219438839e-05,
3480
+ "loss": 1.3423,
3481
+ "step": 560
3482
+ },
3483
+ {
3484
+ "epoch": 3.45,
3485
+ "eval_loss": 1.9406418800354004,
3486
+ "eval_runtime": 291.1096,
3487
+ "eval_samples_per_second": 205.115,
3488
+ "eval_steps_per_second": 205.115,
3489
+ "step": 560
3490
+ },
3491
+ {
3492
+ "epoch": 3.46,
3493
+ "learning_rate": 1.1489739429240845e-05,
3494
+ "loss": 1.3542,
3495
+ "step": 561
3496
+ },
3497
+ {
3498
+ "epoch": 3.46,
3499
+ "learning_rate": 1.1204354928900494e-05,
3500
+ "loss": 1.392,
3501
+ "step": 562
3502
+ },
3503
+ {
3504
+ "epoch": 3.47,
3505
+ "learning_rate": 1.0922421814981901e-05,
3506
+ "loss": 1.3587,
3507
+ "step": 563
3508
+ },
3509
+ {
3510
+ "epoch": 3.47,
3511
+ "learning_rate": 1.0643947098224609e-05,
3512
+ "loss": 1.3266,
3513
+ "step": 564
3514
+ },
3515
+ {
3516
+ "epoch": 3.48,
3517
+ "learning_rate": 1.036893770336938e-05,
3518
+ "loss": 1.3765,
3519
+ "step": 565
3520
+ },
3521
+ {
3522
+ "epoch": 3.49,
3523
+ "learning_rate": 1.0097400468985855e-05,
3524
+ "loss": 1.3446,
3525
+ "step": 566
3526
+ },
3527
+ {
3528
+ "epoch": 3.49,
3529
+ "learning_rate": 9.829342147302683e-06,
3530
+ "loss": 1.3355,
3531
+ "step": 567
3532
+ },
3533
+ {
3534
+ "epoch": 3.5,
3535
+ "learning_rate": 9.564769404039419e-06,
3536
+ "loss": 1.3728,
3537
+ "step": 568
3538
+ },
3539
+ {
3540
+ "epoch": 3.51,
3541
+ "learning_rate": 9.303688818240957e-06,
3542
+ "loss": 1.3629,
3543
+ "step": 569
3544
+ },
3545
+ {
3546
+ "epoch": 3.51,
3547
+ "learning_rate": 9.046106882113751e-06,
3548
+ "loss": 1.3474,
3549
+ "step": 570
3550
+ },
3551
+ {
3552
+ "epoch": 3.52,
3553
+ "learning_rate": 8.792030000864536e-06,
3554
+ "loss": 1.3797,
3555
+ "step": 571
3556
+ },
3557
+ {
3558
+ "epoch": 3.52,
3559
+ "learning_rate": 8.541464492540912e-06,
3560
+ "loss": 1.3478,
3561
+ "step": 572
3562
+ },
3563
+ {
3564
+ "epoch": 3.53,
3565
+ "learning_rate": 8.294416587874425e-06,
3566
+ "loss": 1.3632,
3567
+ "step": 573
3568
+ },
3569
+ {
3570
+ "epoch": 3.54,
3571
+ "learning_rate": 8.050892430125361e-06,
3572
+ "loss": 1.3596,
3573
+ "step": 574
3574
+ },
3575
+ {
3576
+ "epoch": 3.54,
3577
+ "learning_rate": 7.810898074930243e-06,
3578
+ "loss": 1.3701,
3579
+ "step": 575
3580
+ },
3581
+ {
3582
+ "epoch": 3.55,
3583
+ "learning_rate": 7.574439490151046e-06,
3584
+ "loss": 1.363,
3585
+ "step": 576
3586
+ },
3587
+ {
3588
+ "epoch": 3.56,
3589
+ "learning_rate": 7.34152255572697e-06,
3590
+ "loss": 1.3881,
3591
+ "step": 577
3592
+ },
3593
+ {
3594
+ "epoch": 3.56,
3595
+ "learning_rate": 7.112153063528064e-06,
3596
+ "loss": 1.3419,
3597
+ "step": 578
3598
+ },
3599
+ {
3600
+ "epoch": 3.57,
3601
+ "learning_rate": 6.886336717211361e-06,
3602
+ "loss": 1.3458,
3603
+ "step": 579
3604
+ },
3605
+ {
3606
+ "epoch": 3.57,
3607
+ "learning_rate": 6.664079132078881e-06,
3608
+ "loss": 1.3603,
3609
+ "step": 580
3610
+ },
3611
+ {
3612
+ "epoch": 3.58,
3613
+ "learning_rate": 6.4453858349381544e-06,
3614
+ "loss": 1.3583,
3615
+ "step": 581
3616
+ },
3617
+ {
3618
+ "epoch": 3.59,
3619
+ "learning_rate": 6.230262263964641e-06,
3620
+ "loss": 1.3598,
3621
+ "step": 582
3622
+ },
3623
+ {
3624
+ "epoch": 3.59,
3625
+ "learning_rate": 6.018713768566658e-06,
3626
+ "loss": 1.3314,
3627
+ "step": 583
3628
+ },
3629
+ {
3630
+ "epoch": 3.6,
3631
+ "learning_rate": 5.810745609252165e-06,
3632
+ "loss": 1.3479,
3633
+ "step": 584
3634
+ },
3635
+ {
3636
+ "epoch": 3.61,
3637
+ "learning_rate": 5.606362957498195e-06,
3638
+ "loss": 1.3465,
3639
+ "step": 585
3640
+ },
3641
+ {
3642
+ "epoch": 3.61,
3643
+ "learning_rate": 5.405570895622013e-06,
3644
+ "loss": 1.3364,
3645
+ "step": 586
3646
+ },
3647
+ {
3648
+ "epoch": 3.62,
3649
+ "learning_rate": 5.208374416654909e-06,
3650
+ "loss": 1.3697,
3651
+ "step": 587
3652
+ },
3653
+ {
3654
+ "epoch": 3.62,
3655
+ "learning_rate": 5.014778424217924e-06,
3656
+ "loss": 1.3575,
3657
+ "step": 588
3658
+ },
3659
+ {
3660
+ "epoch": 3.63,
3661
+ "learning_rate": 4.8247877324000375e-06,
3662
+ "loss": 1.3657,
3663
+ "step": 589
3664
+ },
3665
+ {
3666
+ "epoch": 3.64,
3667
+ "learning_rate": 4.638407065638322e-06,
3668
+ "loss": 1.3613,
3669
+ "step": 590
3670
+ },
3671
+ {
3672
+ "epoch": 3.64,
3673
+ "learning_rate": 4.455641058600528e-06,
3674
+ "loss": 1.356,
3675
+ "step": 591
3676
+ },
3677
+ {
3678
+ "epoch": 3.65,
3679
+ "learning_rate": 4.276494256069873e-06,
3680
+ "loss": 1.3337,
3681
+ "step": 592
3682
+ },
3683
+ {
3684
+ "epoch": 3.66,
3685
+ "learning_rate": 4.10097111283198e-06,
3686
+ "loss": 1.3734,
3687
+ "step": 593
3688
+ },
3689
+ {
3690
+ "epoch": 3.66,
3691
+ "learning_rate": 3.929075993564052e-06,
3692
+ "loss": 1.3329,
3693
+ "step": 594
3694
+ },
3695
+ {
3696
+ "epoch": 3.67,
3697
+ "learning_rate": 3.760813172726457e-06,
3698
+ "loss": 1.3533,
3699
+ "step": 595
3700
+ },
3701
+ {
3702
+ "epoch": 3.67,
3703
+ "learning_rate": 3.5961868344563325e-06,
3704
+ "loss": 1.3683,
3705
+ "step": 596
3706
+ },
3707
+ {
3708
+ "epoch": 3.68,
3709
+ "learning_rate": 3.435201072463617e-06,
3710
+ "loss": 1.3476,
3711
+ "step": 597
3712
+ },
3713
+ {
3714
+ "epoch": 3.69,
3715
+ "learning_rate": 3.2778598899291465e-06,
3716
+ "loss": 1.3682,
3717
+ "step": 598
3718
+ },
3719
+ {
3720
+ "epoch": 3.69,
3721
+ "learning_rate": 3.1241671994052864e-06,
3722
+ "loss": 1.3557,
3723
+ "step": 599
3724
+ },
3725
+ {
3726
+ "epoch": 3.7,
3727
+ "learning_rate": 2.9741268227184255e-06,
3728
+ "loss": 1.3635,
3729
+ "step": 600
3730
+ },
3731
+ {
3732
+ "epoch": 3.7,
3733
+ "eval_loss": 1.9362093210220337,
3734
+ "eval_runtime": 291.4007,
3735
+ "eval_samples_per_second": 204.91,
3736
+ "eval_steps_per_second": 204.91,
3737
+ "step": 600
3738
+ },
3739
+ {
3740
+ "epoch": 3.71,
3741
+ "learning_rate": 2.8277424908741188e-06,
3742
+ "loss": 1.3398,
3743
+ "step": 601
3744
+ },
3745
+ {
3746
+ "epoch": 3.71,
3747
+ "learning_rate": 2.685017843964177e-06,
3748
+ "loss": 1.3149,
3749
+ "step": 602
3750
+ },
3751
+ {
3752
+ "epoch": 3.72,
3753
+ "learning_rate": 2.5459564310762735e-06,
3754
+ "loss": 1.3404,
3755
+ "step": 603
3756
+ },
3757
+ {
3758
+ "epoch": 3.72,
3759
+ "learning_rate": 2.4105617102055496e-06,
3760
+ "loss": 1.3221,
3761
+ "step": 604
3762
+ },
3763
+ {
3764
+ "epoch": 3.73,
3765
+ "learning_rate": 2.2788370481687965e-06,
3766
+ "loss": 1.3568,
3767
+ "step": 605
3768
+ },
3769
+ {
3770
+ "epoch": 3.74,
3771
+ "learning_rate": 2.150785720520559e-06,
3772
+ "loss": 1.3547,
3773
+ "step": 606
3774
+ },
3775
+ {
3776
+ "epoch": 3.74,
3777
+ "learning_rate": 2.0264109114717987e-06,
3778
+ "loss": 1.3684,
3779
+ "step": 607
3780
+ },
3781
+ {
3782
+ "epoch": 3.75,
3783
+ "learning_rate": 1.905715713810657e-06,
3784
+ "loss": 1.3559,
3785
+ "step": 608
3786
+ },
3787
+ {
3788
+ "epoch": 3.76,
3789
+ "learning_rate": 1.7887031288256026e-06,
3790
+ "loss": 1.3349,
3791
+ "step": 609
3792
+ },
3793
+ {
3794
+ "epoch": 3.76,
3795
+ "learning_rate": 1.6753760662307215e-06,
3796
+ "loss": 1.3337,
3797
+ "step": 610
3798
+ },
3799
+ {
3800
+ "epoch": 3.77,
3801
+ "learning_rate": 1.5657373440934595e-06,
3802
+ "loss": 1.336,
3803
+ "step": 611
3804
+ },
3805
+ {
3806
+ "epoch": 3.77,
3807
+ "learning_rate": 1.4597896887644456e-06,
3808
+ "loss": 1.3671,
3809
+ "step": 612
3810
+ },
3811
+ {
3812
+ "epoch": 3.78,
3813
+ "learning_rate": 1.3575357348097948e-06,
3814
+ "loss": 1.3377,
3815
+ "step": 613
3816
+ },
3817
+ {
3818
+ "epoch": 3.79,
3819
+ "learning_rate": 1.2589780249454618e-06,
3820
+ "loss": 1.3552,
3821
+ "step": 614
3822
+ },
3823
+ {
3824
+ "epoch": 3.79,
3825
+ "learning_rate": 1.1641190099741904e-06,
3826
+ "loss": 1.3821,
3827
+ "step": 615
3828
+ },
3829
+ {
3830
+ "epoch": 3.8,
3831
+ "learning_rate": 1.0729610487243966e-06,
3832
+ "loss": 1.3359,
3833
+ "step": 616
3834
+ },
3835
+ {
3836
+ "epoch": 3.81,
3837
+ "learning_rate": 9.855064079916653e-07,
3838
+ "loss": 1.3513,
3839
+ "step": 617
3840
+ },
3841
+ {
3842
+ "epoch": 3.81,
3843
+ "learning_rate": 9.017572624822112e-07,
3844
+ "loss": 1.372,
3845
+ "step": 618
3846
+ },
3847
+ {
3848
+ "epoch": 3.82,
3849
+ "learning_rate": 8.217156947590064e-07,
3850
+ "loss": 1.3418,
3851
+ "step": 619
3852
+ },
3853
+ {
3854
+ "epoch": 3.82,
3855
+ "learning_rate": 7.453836951897885e-07,
3856
+ "loss": 1.3239,
3857
+ "step": 620
3858
+ },
3859
+ {
3860
+ "epoch": 3.83,
3861
+ "learning_rate": 6.727631618977325e-07,
3862
+ "loss": 1.3551,
3863
+ "step": 621
3864
+ },
3865
+ {
3866
+ "epoch": 3.84,
3867
+ "learning_rate": 6.038559007141397e-07,
3868
+ "loss": 1.3454,
3869
+ "step": 622
3870
+ },
3871
+ {
3872
+ "epoch": 3.84,
3873
+ "learning_rate": 5.386636251336229e-07,
3874
+ "loss": 1.3146,
3875
+ "step": 623
3876
+ },
3877
+ {
3878
+ "epoch": 3.85,
3879
+ "learning_rate": 4.771879562713576e-07,
3880
+ "loss": 1.3709,
3881
+ "step": 624
3882
+ },
3883
+ {
3884
+ "epoch": 3.86,
3885
+ "learning_rate": 4.194304228229806e-07,
3886
+ "loss": 1.3441,
3887
+ "step": 625
3888
+ },
3889
+ {
3890
+ "epoch": 3.86,
3891
+ "learning_rate": 3.653924610263703e-07,
3892
+ "loss": 1.3294,
3893
+ "step": 626
3894
+ },
3895
+ {
3896
+ "epoch": 3.87,
3897
+ "learning_rate": 3.1507541462604255e-07,
3898
+ "loss": 1.3424,
3899
+ "step": 627
3900
+ },
3901
+ {
3902
+ "epoch": 3.87,
3903
+ "learning_rate": 2.6848053483972677e-07,
3904
+ "loss": 1.3857,
3905
+ "step": 628
3906
+ },
3907
+ {
3908
+ "epoch": 3.88,
3909
+ "learning_rate": 2.2560898032724096e-07,
3910
+ "loss": 1.3648,
3911
+ "step": 629
3912
+ },
3913
+ {
3914
+ "epoch": 3.89,
3915
+ "learning_rate": 1.8646181716164831e-07,
3916
+ "loss": 1.3508,
3917
+ "step": 630
3918
+ },
3919
+ {
3920
+ "epoch": 3.89,
3921
+ "learning_rate": 1.5104001880281157e-07,
3922
+ "loss": 1.3322,
3923
+ "step": 631
3924
+ },
3925
+ {
3926
+ "epoch": 3.9,
3927
+ "learning_rate": 1.1934446607311243e-07,
3928
+ "loss": 1.366,
3929
+ "step": 632
3930
+ },
3931
+ {
3932
+ "epoch": 3.9,
3933
+ "learning_rate": 9.137594713563568e-08,
3934
+ "loss": 1.371,
3935
+ "step": 633
3936
+ },
3937
+ {
3938
+ "epoch": 3.91,
3939
+ "learning_rate": 6.71351574745016e-08,
3940
+ "loss": 1.3304,
3941
+ "step": 634
3942
+ },
3943
+ {
3944
+ "epoch": 3.92,
3945
+ "learning_rate": 4.662269987756317e-08,
3946
+ "loss": 1.3275,
3947
+ "step": 635
3948
+ },
3949
+ {
3950
+ "epoch": 3.92,
3951
+ "learning_rate": 2.9839084421467984e-08,
3952
+ "loss": 1.3887,
3953
+ "step": 636
3954
+ },
3955
+ {
3956
+ "epoch": 3.93,
3957
+ "learning_rate": 1.6784728458985042e-08,
3958
+ "loss": 1.3698,
3959
+ "step": 637
3960
+ },
3961
+ {
3962
+ "epoch": 3.94,
3963
+ "learning_rate": 7.45995660854648e-09,
3964
+ "loss": 1.3629,
3965
+ "step": 638
3966
+ },
3967
+ {
3968
+ "epoch": 3.94,
3969
+ "learning_rate": 1.865000746220646e-09,
3970
+ "loss": 1.3392,
3971
+ "step": 639
3972
+ },
3973
+ {
3974
+ "epoch": 3.95,
3975
+ "learning_rate": 0.0,
3976
+ "loss": 1.3235,
3977
+ "step": 640
3978
+ },
3979
+ {
3980
+ "epoch": 3.95,
3981
+ "eval_loss": 1.9365400075912476,
3982
+ "eval_runtime": 290.1841,
3983
+ "eval_samples_per_second": 205.769,
3984
+ "eval_steps_per_second": 205.769,
3985
+ "step": 640
3986
+ }
3987
+ ],
3988
+ "logging_steps": 1,
3989
+ "max_steps": 640,
3990
+ "num_input_tokens_seen": 0,
3991
+ "num_train_epochs": 4,
3992
+ "save_steps": 160,
3993
+ "total_flos": 1.8738986980107878e+18,
3994
+ "train_batch_size": 1,
3995
+ "trial_name": null,
3996
+ "trial_params": null
3997
+ }
checkpoint-640/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0bb8459ca9eb55b57fe6882811eecff75c1f600c94c4d55a31c5f6345a7df8b
3
+ size 4795
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "bnb_4bit_compute_dtype": "float32",
20
+ "bnb_4bit_quant_type": "fp4",
21
+ "bnb_4bit_use_double_quant": false,
22
+ "llm_int8_enable_fp32_cpu_offload": false,
23
+ "llm_int8_has_fp16_weight": false,
24
+ "llm_int8_skip_modules": null,
25
+ "llm_int8_threshold": 6.0,
26
+ "load_in_4bit": false,
27
+ "load_in_8bit": true,
28
+ "quant_method": "bitsandbytes"
29
+ },
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_theta": 10000.0,
32
+ "sliding_window": 4096,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.37.0.dev0",
36
+ "use_cache": false,
37
+ "vocab_size": 32000
38
+ }
epoch2.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4ee5be99f4f192ffc7db9b9c947ec3a398eaea702f8d1a8b1368266b541754b
3
+ size 1792515509
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "trust_remote_code": false,
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false,
44
+ "use_fast": true
45
+ }