Hugging Face's logo

pharaouk
/
CodeLlama-34b-Python-hf_34bCodellama_codellama_blob_1

Model card Files Community
Farouk commited on
Commit
9f79582
•
1 Parent(s): 6dbca0b

Training in progress, step 400

Browse files
Files changed (16) hide show
  1. adapter_model.bin +1 -1
  2. checkpoint-200/adapter_model/adapter_model/README.md +20 -0
  3. checkpoint-200/adapter_model/adapter_model/adapter_config.json +26 -0
  4. checkpoint-200/adapter_model/adapter_model/adapter_model.bin +3 -0
  5. checkpoint-400/README.md +20 -0
  6. checkpoint-400/adapter_config.json +26 -0
  7. checkpoint-400/adapter_model.bin +3 -0
  8. checkpoint-400/added_tokens.json +3 -0
  9. checkpoint-400/optimizer.pt +3 -0
  10. checkpoint-400/rng_state.pth +3 -0
  11. checkpoint-400/scheduler.pt +3 -0
  12. checkpoint-400/special_tokens_map.json +6 -0
  13. checkpoint-400/tokenizer.model +3 -0
  14. checkpoint-400/tokenizer_config.json +35 -0
  15. checkpoint-400/trainer_state.json +2498 -0
  16. checkpoint-400/training_args.bin +3 -0
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fba458e63454aea3ede4a9870b8af551bb13e6e6064d71e880df1b6cef90a198
3
  size 871609293
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be170cadde542242555c0103b2460f331ff4576d6c4e02ee4d7e7c0a3df799c3
3
  size 871609293
checkpoint-200/adapter_model/adapter_model/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0
checkpoint-200/adapter_model/adapter_model/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "codellama/CodeLlama-34b-Python-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "down_proj",
18
+ "q_proj",
19
+ "k_proj",
20
+ "gate_proj",
21
+ "up_proj",
22
+ "v_proj",
23
+ "o_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-200/adapter_model/adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba458e63454aea3ede4a9870b8af551bb13e6e6064d71e880df1b6cef90a198
3
+ size 871609293
checkpoint-400/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0
checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "codellama/CodeLlama-34b-Python-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "down_proj",
18
+ "q_proj",
19
+ "k_proj",
20
+ "gate_proj",
21
+ "up_proj",
22
+ "v_proj",
23
+ "o_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-400/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be170cadde542242555c0103b2460f331ff4576d6c4e02ee4d7e7c0a3df799c3
3
+ size 871609293
checkpoint-400/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ca85b3b5c16f46361137f74100525de5bf1235a55ff2cbebf9f1ddd6a962c0e
3
+ size 3485881117
checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:267651d35d8f510ab074e5243c6384829c5e557c57b379443b33b48e8ce167ab
3
+ size 14511
checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef1ca3e6fc07b43239ed034e2d8e5ae6ded24ae869473b3f8f48afde040dedc
3
+ size 627
checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-400/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": null,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,2498 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6333504915237427,
3
+ "best_model_checkpoint": "./output_v2/34bCodellama_CodeLlama-34b-Python-hf_codellama_blob_1/checkpoint-400",
4
+ "epoch": 0.2808002808002808,
5
+ "global_step": 400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 0.0004,
13
+ "loss": 1.5667,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 0.0004,
19
+ "loss": 0.9201,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 0.0004,
25
+ "loss": 0.6019,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.0,
30
+ "learning_rate": 0.0004,
31
+ "loss": 0.861,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.0,
36
+ "learning_rate": 0.0004,
37
+ "loss": 1.064,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.0,
42
+ "learning_rate": 0.0004,
43
+ "loss": 1.0007,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "learning_rate": 0.0004,
49
+ "loss": 1.0533,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 0.0004,
55
+ "loss": 0.8498,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.01,
60
+ "learning_rate": 0.0004,
61
+ "loss": 0.9189,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.01,
66
+ "learning_rate": 0.0004,
67
+ "loss": 0.9369,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.01,
72
+ "learning_rate": 0.0004,
73
+ "loss": 1.1375,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.01,
78
+ "learning_rate": 0.0004,
79
+ "loss": 0.8369,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.01,
84
+ "learning_rate": 0.0004,
85
+ "loss": 0.689,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "learning_rate": 0.0004,
91
+ "loss": 0.8885,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.01,
96
+ "learning_rate": 0.0004,
97
+ "loss": 0.9666,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.01,
102
+ "learning_rate": 0.0004,
103
+ "loss": 0.744,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.01,
108
+ "learning_rate": 0.0004,
109
+ "loss": 0.8998,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.01,
114
+ "learning_rate": 0.0004,
115
+ "loss": 0.8371,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.01,
120
+ "learning_rate": 0.0004,
121
+ "loss": 0.7615,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.01,
126
+ "learning_rate": 0.0004,
127
+ "loss": 0.6963,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.01,
132
+ "learning_rate": 0.0004,
133
+ "loss": 0.5974,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.02,
138
+ "learning_rate": 0.0004,
139
+ "loss": 1.4922,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.02,
144
+ "learning_rate": 0.0004,
145
+ "loss": 1.1272,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.02,
150
+ "learning_rate": 0.0004,
151
+ "loss": 0.4373,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.02,
156
+ "learning_rate": 0.0004,
157
+ "loss": 1.0598,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.02,
162
+ "learning_rate": 0.0004,
163
+ "loss": 1.191,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.02,
168
+ "learning_rate": 0.0004,
169
+ "loss": 0.6499,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.02,
174
+ "learning_rate": 0.0004,
175
+ "loss": 0.7526,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.02,
180
+ "learning_rate": 0.0004,
181
+ "loss": 0.7252,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.02,
186
+ "learning_rate": 0.0004,
187
+ "loss": 0.8555,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.02,
192
+ "learning_rate": 0.0004,
193
+ "loss": 0.479,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.02,
198
+ "learning_rate": 0.0004,
199
+ "loss": 0.5273,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.02,
204
+ "learning_rate": 0.0004,
205
+ "loss": 0.3907,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.02,
210
+ "learning_rate": 0.0004,
211
+ "loss": 0.5284,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.02,
216
+ "learning_rate": 0.0004,
217
+ "loss": 0.8696,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.03,
222
+ "learning_rate": 0.0004,
223
+ "loss": 0.9264,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.03,
228
+ "learning_rate": 0.0004,
229
+ "loss": 0.6812,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.03,
234
+ "learning_rate": 0.0004,
235
+ "loss": 0.4482,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.03,
240
+ "learning_rate": 0.0004,
241
+ "loss": 1.9031,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.03,
246
+ "learning_rate": 0.0004,
247
+ "loss": 1.3295,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.03,
252
+ "learning_rate": 0.0004,
253
+ "loss": 0.7498,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.03,
258
+ "learning_rate": 0.0004,
259
+ "loss": 1.4452,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.03,
264
+ "learning_rate": 0.0004,
265
+ "loss": 1.224,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.03,
270
+ "learning_rate": 0.0004,
271
+ "loss": 0.3272,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.03,
276
+ "learning_rate": 0.0004,
277
+ "loss": 0.7366,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.03,
282
+ "learning_rate": 0.0004,
283
+ "loss": 1.0331,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.03,
288
+ "learning_rate": 0.0004,
289
+ "loss": 0.8471,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.03,
294
+ "learning_rate": 0.0004,
295
+ "loss": 0.8171,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.03,
300
+ "learning_rate": 0.0004,
301
+ "loss": 0.418,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.04,
306
+ "learning_rate": 0.0004,
307
+ "loss": 0.6942,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.04,
312
+ "learning_rate": 0.0004,
313
+ "loss": 0.1712,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.04,
318
+ "learning_rate": 0.0004,
319
+ "loss": 0.5041,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.04,
324
+ "learning_rate": 0.0004,
325
+ "loss": 0.4619,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.04,
330
+ "learning_rate": 0.0004,
331
+ "loss": 0.5011,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.04,
336
+ "learning_rate": 0.0004,
337
+ "loss": 0.5,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.04,
342
+ "learning_rate": 0.0004,
343
+ "loss": 0.917,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.04,
348
+ "learning_rate": 0.0004,
349
+ "loss": 0.8142,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.04,
354
+ "learning_rate": 0.0004,
355
+ "loss": 0.8708,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.04,
360
+ "learning_rate": 0.0004,
361
+ "loss": 0.7987,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.04,
366
+ "learning_rate": 0.0004,
367
+ "loss": 0.9699,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.04,
372
+ "learning_rate": 0.0004,
373
+ "loss": 1.0015,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.04,
378
+ "learning_rate": 0.0004,
379
+ "loss": 0.8052,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.04,
384
+ "learning_rate": 0.0004,
385
+ "loss": 0.8645,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.04,
390
+ "learning_rate": 0.0004,
391
+ "loss": 1.1444,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.05,
396
+ "learning_rate": 0.0004,
397
+ "loss": 1.0087,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.05,
402
+ "learning_rate": 0.0004,
403
+ "loss": 0.5679,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.05,
408
+ "learning_rate": 0.0004,
409
+ "loss": 0.5507,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.05,
414
+ "learning_rate": 0.0004,
415
+ "loss": 1.1764,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.05,
420
+ "learning_rate": 0.0004,
421
+ "loss": 0.6332,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.05,
426
+ "learning_rate": 0.0004,
427
+ "loss": 0.8759,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.05,
432
+ "learning_rate": 0.0004,
433
+ "loss": 0.8385,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.05,
438
+ "learning_rate": 0.0004,
439
+ "loss": 0.7869,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.05,
444
+ "learning_rate": 0.0004,
445
+ "loss": 1.4457,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.05,
450
+ "learning_rate": 0.0004,
451
+ "loss": 0.9331,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.05,
456
+ "learning_rate": 0.0004,
457
+ "loss": 0.8943,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.05,
462
+ "learning_rate": 0.0004,
463
+ "loss": 0.5783,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.05,
468
+ "learning_rate": 0.0004,
469
+ "loss": 0.6433,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.05,
474
+ "learning_rate": 0.0004,
475
+ "loss": 0.7517,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.06,
480
+ "learning_rate": 0.0004,
481
+ "loss": 0.5061,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.06,
486
+ "learning_rate": 0.0004,
487
+ "loss": 0.7332,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.06,
492
+ "learning_rate": 0.0004,
493
+ "loss": 1.6546,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.06,
498
+ "learning_rate": 0.0004,
499
+ "loss": 0.4723,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.06,
504
+ "learning_rate": 0.0004,
505
+ "loss": 0.2814,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.06,
510
+ "learning_rate": 0.0004,
511
+ "loss": 0.4068,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.06,
516
+ "learning_rate": 0.0004,
517
+ "loss": 1.1729,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.06,
522
+ "learning_rate": 0.0004,
523
+ "loss": 0.698,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.06,
528
+ "learning_rate": 0.0004,
529
+ "loss": 0.7746,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.06,
534
+ "learning_rate": 0.0004,
535
+ "loss": 0.5065,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.06,
540
+ "learning_rate": 0.0004,
541
+ "loss": 0.4654,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.06,
546
+ "learning_rate": 0.0004,
547
+ "loss": 0.5724,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.06,
552
+ "learning_rate": 0.0004,
553
+ "loss": 1.1535,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.06,
558
+ "learning_rate": 0.0004,
559
+ "loss": 0.3854,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.07,
564
+ "learning_rate": 0.0004,
565
+ "loss": 1.6848,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.07,
570
+ "learning_rate": 0.0004,
571
+ "loss": 0.6667,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.07,
576
+ "learning_rate": 0.0004,
577
+ "loss": 0.4526,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.07,
582
+ "learning_rate": 0.0004,
583
+ "loss": 0.7112,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.07,
588
+ "learning_rate": 0.0004,
589
+ "loss": 0.6816,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.07,
594
+ "learning_rate": 0.0004,
595
+ "loss": 0.7496,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.07,
600
+ "learning_rate": 0.0004,
601
+ "loss": 1.189,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.07,
606
+ "learning_rate": 0.0004,
607
+ "loss": 1.4239,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.07,
612
+ "learning_rate": 0.0004,
613
+ "loss": 0.4378,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.07,
618
+ "learning_rate": 0.0004,
619
+ "loss": 2.3054,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.07,
624
+ "learning_rate": 0.0004,
625
+ "loss": 0.1593,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.07,
630
+ "learning_rate": 0.0004,
631
+ "loss": 0.2481,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.07,
636
+ "learning_rate": 0.0004,
637
+ "loss": 0.6469,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.07,
642
+ "learning_rate": 0.0004,
643
+ "loss": 0.7417,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.08,
648
+ "learning_rate": 0.0004,
649
+ "loss": 0.7767,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.08,
654
+ "learning_rate": 0.0004,
655
+ "loss": 0.831,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.08,
660
+ "learning_rate": 0.0004,
661
+ "loss": 0.7954,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.08,
666
+ "learning_rate": 0.0004,
667
+ "loss": 0.6376,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.08,
672
+ "learning_rate": 0.0004,
673
+ "loss": 0.6208,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.08,
678
+ "learning_rate": 0.0004,
679
+ "loss": 0.9038,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.08,
684
+ "learning_rate": 0.0004,
685
+ "loss": 0.9994,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.08,
690
+ "learning_rate": 0.0004,
691
+ "loss": 1.0233,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.08,
696
+ "learning_rate": 0.0004,
697
+ "loss": 0.7573,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.08,
702
+ "learning_rate": 0.0004,
703
+ "loss": 0.5333,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.08,
708
+ "learning_rate": 0.0004,
709
+ "loss": 0.4886,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.08,
714
+ "learning_rate": 0.0004,
715
+ "loss": 0.75,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.08,
720
+ "learning_rate": 0.0004,
721
+ "loss": 0.6377,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.08,
726
+ "learning_rate": 0.0004,
727
+ "loss": 0.6518,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 0.08,
732
+ "learning_rate": 0.0004,
733
+ "loss": 0.6409,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 0.09,
738
+ "learning_rate": 0.0004,
739
+ "loss": 0.5996,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 0.09,
744
+ "learning_rate": 0.0004,
745
+ "loss": 0.7964,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 0.09,
750
+ "learning_rate": 0.0004,
751
+ "loss": 0.5898,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 0.09,
756
+ "learning_rate": 0.0004,
757
+ "loss": 0.8753,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 0.09,
762
+ "learning_rate": 0.0004,
763
+ "loss": 0.6304,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 0.09,
768
+ "learning_rate": 0.0004,
769
+ "loss": 0.5428,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 0.09,
774
+ "learning_rate": 0.0004,
775
+ "loss": 0.8571,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 0.09,
780
+ "learning_rate": 0.0004,
781
+ "loss": 0.8339,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 0.09,
786
+ "learning_rate": 0.0004,
787
+ "loss": 0.6087,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 0.09,
792
+ "learning_rate": 0.0004,
793
+ "loss": 0.3547,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 0.09,
798
+ "learning_rate": 0.0004,
799
+ "loss": 0.3494,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 0.09,
804
+ "learning_rate": 0.0004,
805
+ "loss": 0.5394,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 0.09,
810
+ "learning_rate": 0.0004,
811
+ "loss": 0.4315,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 0.09,
816
+ "learning_rate": 0.0004,
817
+ "loss": 0.3575,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 0.1,
822
+ "learning_rate": 0.0004,
823
+ "loss": 0.4983,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 0.1,
828
+ "learning_rate": 0.0004,
829
+ "loss": 0.4292,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 0.1,
834
+ "learning_rate": 0.0004,
835
+ "loss": 0.6315,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 0.1,
840
+ "learning_rate": 0.0004,
841
+ "loss": 0.9827,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 0.1,
846
+ "learning_rate": 0.0004,
847
+ "loss": 1.4456,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 0.1,
852
+ "learning_rate": 0.0004,
853
+ "loss": 0.5151,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 0.1,
858
+ "learning_rate": 0.0004,
859
+ "loss": 0.4651,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 0.1,
864
+ "learning_rate": 0.0004,
865
+ "loss": 0.8682,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 0.1,
870
+ "learning_rate": 0.0004,
871
+ "loss": 1.1543,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 0.1,
876
+ "learning_rate": 0.0004,
877
+ "loss": 0.3378,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 0.1,
882
+ "learning_rate": 0.0004,
883
+ "loss": 0.5381,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 0.1,
888
+ "learning_rate": 0.0004,
889
+ "loss": 0.5189,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 0.1,
894
+ "learning_rate": 0.0004,
895
+ "loss": 0.3988,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 0.1,
900
+ "learning_rate": 0.0004,
901
+ "loss": 0.9694,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 0.11,
906
+ "learning_rate": 0.0004,
907
+ "loss": 1.2404,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 0.11,
912
+ "learning_rate": 0.0004,
913
+ "loss": 0.3767,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 0.11,
918
+ "learning_rate": 0.0004,
919
+ "loss": 0.5564,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 0.11,
924
+ "learning_rate": 0.0004,
925
+ "loss": 0.2665,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 0.11,
930
+ "learning_rate": 0.0004,
931
+ "loss": 0.172,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 0.11,
936
+ "learning_rate": 0.0004,
937
+ "loss": 0.6584,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 0.11,
942
+ "learning_rate": 0.0004,
943
+ "loss": 0.7588,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 0.11,
948
+ "learning_rate": 0.0004,
949
+ "loss": 0.9431,
950
+ "step": 157
951
+ },
952
+ {
953
+ "epoch": 0.11,
954
+ "learning_rate": 0.0004,
955
+ "loss": 0.9456,
956
+ "step": 158
957
+ },
958
+ {
959
+ "epoch": 0.11,
960
+ "learning_rate": 0.0004,
961
+ "loss": 0.7471,
962
+ "step": 159
963
+ },
964
+ {
965
+ "epoch": 0.11,
966
+ "learning_rate": 0.0004,
967
+ "loss": 0.8477,
968
+ "step": 160
969
+ },
970
+ {
971
+ "epoch": 0.11,
972
+ "learning_rate": 0.0004,
973
+ "loss": 0.7679,
974
+ "step": 161
975
+ },
976
+ {
977
+ "epoch": 0.11,
978
+ "learning_rate": 0.0004,
979
+ "loss": 0.8937,
980
+ "step": 162
981
+ },
982
+ {
983
+ "epoch": 0.11,
984
+ "learning_rate": 0.0004,
985
+ "loss": 1.2858,
986
+ "step": 163
987
+ },
988
+ {
989
+ "epoch": 0.12,
990
+ "learning_rate": 0.0004,
991
+ "loss": 0.7806,
992
+ "step": 164
993
+ },
994
+ {
995
+ "epoch": 0.12,
996
+ "learning_rate": 0.0004,
997
+ "loss": 0.8034,
998
+ "step": 165
999
+ },
1000
+ {
1001
+ "epoch": 0.12,
1002
+ "learning_rate": 0.0004,
1003
+ "loss": 0.6372,
1004
+ "step": 166
1005
+ },
1006
+ {
1007
+ "epoch": 0.12,
1008
+ "learning_rate": 0.0004,
1009
+ "loss": 0.8217,
1010
+ "step": 167
1011
+ },
1012
+ {
1013
+ "epoch": 0.12,
1014
+ "learning_rate": 0.0004,
1015
+ "loss": 0.3706,
1016
+ "step": 168
1017
+ },
1018
+ {
1019
+ "epoch": 0.12,
1020
+ "learning_rate": 0.0004,
1021
+ "loss": 1.0851,
1022
+ "step": 169
1023
+ },
1024
+ {
1025
+ "epoch": 0.12,
1026
+ "learning_rate": 0.0004,
1027
+ "loss": 0.6719,
1028
+ "step": 170
1029
+ },
1030
+ {
1031
+ "epoch": 0.12,
1032
+ "learning_rate": 0.0004,
1033
+ "loss": 1.0366,
1034
+ "step": 171
1035
+ },
1036
+ {
1037
+ "epoch": 0.12,
1038
+ "learning_rate": 0.0004,
1039
+ "loss": 0.5603,
1040
+ "step": 172
1041
+ },
1042
+ {
1043
+ "epoch": 0.12,
1044
+ "learning_rate": 0.0004,
1045
+ "loss": 0.5651,
1046
+ "step": 173
1047
+ },
1048
+ {
1049
+ "epoch": 0.12,
1050
+ "learning_rate": 0.0004,
1051
+ "loss": 0.3804,
1052
+ "step": 174
1053
+ },
1054
+ {
1055
+ "epoch": 0.12,
1056
+ "learning_rate": 0.0004,
1057
+ "loss": 0.5946,
1058
+ "step": 175
1059
+ },
1060
+ {
1061
+ "epoch": 0.12,
1062
+ "learning_rate": 0.0004,
1063
+ "loss": 0.7649,
1064
+ "step": 176
1065
+ },
1066
+ {
1067
+ "epoch": 0.12,
1068
+ "learning_rate": 0.0004,
1069
+ "loss": 0.5035,
1070
+ "step": 177
1071
+ },
1072
+ {
1073
+ "epoch": 0.12,
1074
+ "learning_rate": 0.0004,
1075
+ "loss": 0.8066,
1076
+ "step": 178
1077
+ },
1078
+ {
1079
+ "epoch": 0.13,
1080
+ "learning_rate": 0.0004,
1081
+ "loss": 0.8046,
1082
+ "step": 179
1083
+ },
1084
+ {
1085
+ "epoch": 0.13,
1086
+ "learning_rate": 0.0004,
1087
+ "loss": 0.4233,
1088
+ "step": 180
1089
+ },
1090
+ {
1091
+ "epoch": 0.13,
1092
+ "learning_rate": 0.0004,
1093
+ "loss": 0.7945,
1094
+ "step": 181
1095
+ },
1096
+ {
1097
+ "epoch": 0.13,
1098
+ "learning_rate": 0.0004,
1099
+ "loss": 0.5722,
1100
+ "step": 182
1101
+ },
1102
+ {
1103
+ "epoch": 0.13,
1104
+ "learning_rate": 0.0004,
1105
+ "loss": 0.6088,
1106
+ "step": 183
1107
+ },
1108
+ {
1109
+ "epoch": 0.13,
1110
+ "learning_rate": 0.0004,
1111
+ "loss": 0.4229,
1112
+ "step": 184
1113
+ },
1114
+ {
1115
+ "epoch": 0.13,
1116
+ "learning_rate": 0.0004,
1117
+ "loss": 0.8723,
1118
+ "step": 185
1119
+ },
1120
+ {
1121
+ "epoch": 0.13,
1122
+ "learning_rate": 0.0004,
1123
+ "loss": 0.9287,
1124
+ "step": 186
1125
+ },
1126
+ {
1127
+ "epoch": 0.13,
1128
+ "learning_rate": 0.0004,
1129
+ "loss": 0.8082,
1130
+ "step": 187
1131
+ },
1132
+ {
1133
+ "epoch": 0.13,
1134
+ "learning_rate": 0.0004,
1135
+ "loss": 0.4144,
1136
+ "step": 188
1137
+ },
1138
+ {
1139
+ "epoch": 0.13,
1140
+ "learning_rate": 0.0004,
1141
+ "loss": 0.372,
1142
+ "step": 189
1143
+ },
1144
+ {
1145
+ "epoch": 0.13,
1146
+ "learning_rate": 0.0004,
1147
+ "loss": 0.5725,
1148
+ "step": 190
1149
+ },
1150
+ {
1151
+ "epoch": 0.13,
1152
+ "learning_rate": 0.0004,
1153
+ "loss": 0.3837,
1154
+ "step": 191
1155
+ },
1156
+ {
1157
+ "epoch": 0.13,
1158
+ "learning_rate": 0.0004,
1159
+ "loss": 0.5155,
1160
+ "step": 192
1161
+ },
1162
+ {
1163
+ "epoch": 0.14,
1164
+ "learning_rate": 0.0004,
1165
+ "loss": 0.5472,
1166
+ "step": 193
1167
+ },
1168
+ {
1169
+ "epoch": 0.14,
1170
+ "learning_rate": 0.0004,
1171
+ "loss": 0.6488,
1172
+ "step": 194
1173
+ },
1174
+ {
1175
+ "epoch": 0.14,
1176
+ "learning_rate": 0.0004,
1177
+ "loss": 1.4385,
1178
+ "step": 195
1179
+ },
1180
+ {
1181
+ "epoch": 0.14,
1182
+ "learning_rate": 0.0004,
1183
+ "loss": 0.3418,
1184
+ "step": 196
1185
+ },
1186
+ {
1187
+ "epoch": 0.14,
1188
+ "learning_rate": 0.0004,
1189
+ "loss": 0.8811,
1190
+ "step": 197
1191
+ },
1192
+ {
1193
+ "epoch": 0.14,
1194
+ "learning_rate": 0.0004,
1195
+ "loss": 0.8176,
1196
+ "step": 198
1197
+ },
1198
+ {
1199
+ "epoch": 0.14,
1200
+ "learning_rate": 0.0004,
1201
+ "loss": 0.5379,
1202
+ "step": 199
1203
+ },
1204
+ {
1205
+ "epoch": 0.14,
1206
+ "learning_rate": 0.0004,
1207
+ "loss": 1.0277,
1208
+ "step": 200
1209
+ },
1210
+ {
1211
+ "epoch": 0.14,
1212
+ "eval_loss": 0.662463366985321,
1213
+ "eval_runtime": 262.5709,
1214
+ "eval_samples_per_second": 1.904,
1215
+ "eval_steps_per_second": 0.952,
1216
+ "step": 200
1217
+ },
1218
+ {
1219
+ "epoch": 0.14,
1220
+ "mmlu_eval_accuracy": 0.41276444254447825,
1221
+ "mmlu_eval_accuracy_abstract_algebra": 0.09090909090909091,
1222
+ "mmlu_eval_accuracy_anatomy": 0.42857142857142855,
1223
+ "mmlu_eval_accuracy_astronomy": 0.5,
1224
+ "mmlu_eval_accuracy_business_ethics": 0.2727272727272727,
1225
+ "mmlu_eval_accuracy_clinical_knowledge": 0.4482758620689655,
1226
+ "mmlu_eval_accuracy_college_biology": 0.3125,
1227
+ "mmlu_eval_accuracy_college_chemistry": 0.375,
1228
+ "mmlu_eval_accuracy_college_computer_science": 0.5454545454545454,
1229
+ "mmlu_eval_accuracy_college_mathematics": 0.2727272727272727,
1230
+ "mmlu_eval_accuracy_college_medicine": 0.6363636363636364,
1231
+ "mmlu_eval_accuracy_college_physics": 0.2727272727272727,
1232
+ "mmlu_eval_accuracy_computer_security": 0.36363636363636365,
1233
+ "mmlu_eval_accuracy_conceptual_physics": 0.3076923076923077,
1234
+ "mmlu_eval_accuracy_econometrics": 0.4166666666666667,
1235
+ "mmlu_eval_accuracy_electrical_engineering": 0.5,
1236
+ "mmlu_eval_accuracy_elementary_mathematics": 0.4146341463414634,
1237
+ "mmlu_eval_accuracy_formal_logic": 0.5714285714285714,
1238
+ "mmlu_eval_accuracy_global_facts": 0.2,
1239
+ "mmlu_eval_accuracy_high_school_biology": 0.1875,
1240
+ "mmlu_eval_accuracy_high_school_chemistry": 0.4090909090909091,
1241
+ "mmlu_eval_accuracy_high_school_computer_science": 0.6666666666666666,
1242
+ "mmlu_eval_accuracy_high_school_european_history": 0.4444444444444444,
1243
+ "mmlu_eval_accuracy_high_school_geography": 0.5909090909090909,
1244
+ "mmlu_eval_accuracy_high_school_government_and_politics": 0.5714285714285714,
1245
+ "mmlu_eval_accuracy_high_school_macroeconomics": 0.32558139534883723,
1246
+ "mmlu_eval_accuracy_high_school_mathematics": 0.4482758620689655,
1247
+ "mmlu_eval_accuracy_high_school_microeconomics": 0.5714285714285714,
1248
+ "mmlu_loss": 0.7435930466353893,
1249
+ "step": 200
1250
+ },
1251
+ {
1252
+ "epoch": 0.14,
1253
+ "learning_rate": 0.0004,
1254
+ "loss": 1.6342,
1255
+ "step": 201
1256
+ },
1257
+ {
1258
+ "epoch": 0.14,
1259
+ "learning_rate": 0.0004,
1260
+ "loss": 0.1179,
1261
+ "step": 202
1262
+ },
1263
+ {
1264
+ "epoch": 0.14,
1265
+ "learning_rate": 0.0004,
1266
+ "loss": 0.1083,
1267
+ "step": 203
1268
+ },
1269
+ {
1270
+ "epoch": 0.14,
1271
+ "learning_rate": 0.0004,
1272
+ "loss": 0.6355,
1273
+ "step": 204
1274
+ },
1275
+ {
1276
+ "epoch": 0.14,
1277
+ "learning_rate": 0.0004,
1278
+ "loss": 0.5694,
1279
+ "step": 205
1280
+ },
1281
+ {
1282
+ "epoch": 0.14,
1283
+ "learning_rate": 0.0004,
1284
+ "loss": 0.7707,
1285
+ "step": 206
1286
+ },
1287
+ {
1288
+ "epoch": 0.15,
1289
+ "learning_rate": 0.0004,
1290
+ "loss": 0.3314,
1291
+ "step": 207
1292
+ },
1293
+ {
1294
+ "epoch": 0.15,
1295
+ "learning_rate": 0.0004,
1296
+ "loss": 1.0069,
1297
+ "step": 208
1298
+ },
1299
+ {
1300
+ "epoch": 0.15,
1301
+ "learning_rate": 0.0004,
1302
+ "loss": 0.9113,
1303
+ "step": 209
1304
+ },
1305
+ {
1306
+ "epoch": 0.15,
1307
+ "learning_rate": 0.0004,
1308
+ "loss": 0.8692,
1309
+ "step": 210
1310
+ },
1311
+ {
1312
+ "epoch": 0.15,
1313
+ "learning_rate": 0.0004,
1314
+ "loss": 0.7362,
1315
+ "step": 211
1316
+ },
1317
+ {
1318
+ "epoch": 0.15,
1319
+ "learning_rate": 0.0004,
1320
+ "loss": 0.926,
1321
+ "step": 212
1322
+ },
1323
+ {
1324
+ "epoch": 0.15,
1325
+ "learning_rate": 0.0004,
1326
+ "loss": 0.7405,
1327
+ "step": 213
1328
+ },
1329
+ {
1330
+ "epoch": 0.15,
1331
+ "learning_rate": 0.0004,
1332
+ "loss": 0.9191,
1333
+ "step": 214
1334
+ },
1335
+ {
1336
+ "epoch": 0.15,
1337
+ "learning_rate": 0.0004,
1338
+ "loss": 0.9301,
1339
+ "step": 215
1340
+ },
1341
+ {
1342
+ "epoch": 0.15,
1343
+ "learning_rate": 0.0004,
1344
+ "loss": 0.8581,
1345
+ "step": 216
1346
+ },
1347
+ {
1348
+ "epoch": 0.15,
1349
+ "learning_rate": 0.0004,
1350
+ "loss": 0.4548,
1351
+ "step": 217
1352
+ },
1353
+ {
1354
+ "epoch": 0.15,
1355
+ "learning_rate": 0.0004,
1356
+ "loss": 0.6516,
1357
+ "step": 218
1358
+ },
1359
+ {
1360
+ "epoch": 0.15,
1361
+ "learning_rate": 0.0004,
1362
+ "loss": 0.7194,
1363
+ "step": 219
1364
+ },
1365
+ {
1366
+ "epoch": 0.15,
1367
+ "learning_rate": 0.0004,
1368
+ "loss": 1.0441,
1369
+ "step": 220
1370
+ },
1371
+ {
1372
+ "epoch": 0.16,
1373
+ "learning_rate": 0.0004,
1374
+ "loss": 0.9499,
1375
+ "step": 221
1376
+ },
1377
+ {
1378
+ "epoch": 0.16,
1379
+ "learning_rate": 0.0004,
1380
+ "loss": 0.5447,
1381
+ "step": 222
1382
+ },
1383
+ {
1384
+ "epoch": 0.16,
1385
+ "learning_rate": 0.0004,
1386
+ "loss": 0.8795,
1387
+ "step": 223
1388
+ },
1389
+ {
1390
+ "epoch": 0.16,
1391
+ "learning_rate": 0.0004,
1392
+ "loss": 0.5347,
1393
+ "step": 224
1394
+ },
1395
+ {
1396
+ "epoch": 0.16,
1397
+ "learning_rate": 0.0004,
1398
+ "loss": 0.5827,
1399
+ "step": 225
1400
+ },
1401
+ {
1402
+ "epoch": 0.16,
1403
+ "learning_rate": 0.0004,
1404
+ "loss": 0.311,
1405
+ "step": 226
1406
+ },
1407
+ {
1408
+ "epoch": 0.16,
1409
+ "learning_rate": 0.0004,
1410
+ "loss": 0.1071,
1411
+ "step": 227
1412
+ },
1413
+ {
1414
+ "epoch": 0.16,
1415
+ "learning_rate": 0.0004,
1416
+ "loss": 0.6336,
1417
+ "step": 228
1418
+ },
1419
+ {
1420
+ "epoch": 0.16,
1421
+ "learning_rate": 0.0004,
1422
+ "loss": 0.6212,
1423
+ "step": 229
1424
+ },
1425
+ {
1426
+ "epoch": 0.16,
1427
+ "learning_rate": 0.0004,
1428
+ "loss": 0.4345,
1429
+ "step": 230
1430
+ },
1431
+ {
1432
+ "epoch": 0.16,
1433
+ "learning_rate": 0.0004,
1434
+ "loss": 0.5373,
1435
+ "step": 231
1436
+ },
1437
+ {
1438
+ "epoch": 0.16,
1439
+ "learning_rate": 0.0004,
1440
+ "loss": 0.9612,
1441
+ "step": 232
1442
+ },
1443
+ {
1444
+ "epoch": 0.16,
1445
+ "learning_rate": 0.0004,
1446
+ "loss": 1.0251,
1447
+ "step": 233
1448
+ },
1449
+ {
1450
+ "epoch": 0.16,
1451
+ "learning_rate": 0.0004,
1452
+ "loss": 0.4267,
1453
+ "step": 234
1454
+ },
1455
+ {
1456
+ "epoch": 0.16,
1457
+ "learning_rate": 0.0004,
1458
+ "loss": 0.5767,
1459
+ "step": 235
1460
+ },
1461
+ {
1462
+ "epoch": 0.17,
1463
+ "learning_rate": 0.0004,
1464
+ "loss": 0.5123,
1465
+ "step": 236
1466
+ },
1467
+ {
1468
+ "epoch": 0.17,
1469
+ "learning_rate": 0.0004,
1470
+ "loss": 0.354,
1471
+ "step": 237
1472
+ },
1473
+ {
1474
+ "epoch": 0.17,
1475
+ "learning_rate": 0.0004,
1476
+ "loss": 1.1279,
1477
+ "step": 238
1478
+ },
1479
+ {
1480
+ "epoch": 0.17,
1481
+ "learning_rate": 0.0004,
1482
+ "loss": 0.6464,
1483
+ "step": 239
1484
+ },
1485
+ {
1486
+ "epoch": 0.17,
1487
+ "learning_rate": 0.0004,
1488
+ "loss": 0.7227,
1489
+ "step": 240
1490
+ },
1491
+ {
1492
+ "epoch": 0.17,
1493
+ "learning_rate": 0.0004,
1494
+ "loss": 1.3533,
1495
+ "step": 241
1496
+ },
1497
+ {
1498
+ "epoch": 0.17,
1499
+ "learning_rate": 0.0004,
1500
+ "loss": 0.3986,
1501
+ "step": 242
1502
+ },
1503
+ {
1504
+ "epoch": 0.17,
1505
+ "learning_rate": 0.0004,
1506
+ "loss": 1.0402,
1507
+ "step": 243
1508
+ },
1509
+ {
1510
+ "epoch": 0.17,
1511
+ "learning_rate": 0.0004,
1512
+ "loss": 0.4558,
1513
+ "step": 244
1514
+ },
1515
+ {
1516
+ "epoch": 0.17,
1517
+ "learning_rate": 0.0004,
1518
+ "loss": 0.5525,
1519
+ "step": 245
1520
+ },
1521
+ {
1522
+ "epoch": 0.17,
1523
+ "learning_rate": 0.0004,
1524
+ "loss": 1.5916,
1525
+ "step": 246
1526
+ },
1527
+ {
1528
+ "epoch": 0.17,
1529
+ "learning_rate": 0.0004,
1530
+ "loss": 0.9311,
1531
+ "step": 247
1532
+ },
1533
+ {
1534
+ "epoch": 0.17,
1535
+ "learning_rate": 0.0004,
1536
+ "loss": 0.3011,
1537
+ "step": 248
1538
+ },
1539
+ {
1540
+ "epoch": 0.17,
1541
+ "learning_rate": 0.0004,
1542
+ "loss": 0.5813,
1543
+ "step": 249
1544
+ },
1545
+ {
1546
+ "epoch": 0.18,
1547
+ "learning_rate": 0.0004,
1548
+ "loss": 1.134,
1549
+ "step": 250
1550
+ },
1551
+ {
1552
+ "epoch": 0.18,
1553
+ "learning_rate": 0.0004,
1554
+ "loss": 0.3062,
1555
+ "step": 251
1556
+ },
1557
+ {
1558
+ "epoch": 0.18,
1559
+ "learning_rate": 0.0004,
1560
+ "loss": 0.2848,
1561
+ "step": 252
1562
+ },
1563
+ {
1564
+ "epoch": 0.18,
1565
+ "learning_rate": 0.0004,
1566
+ "loss": 0.1995,
1567
+ "step": 253
1568
+ },
1569
+ {
1570
+ "epoch": 0.18,
1571
+ "learning_rate": 0.0004,
1572
+ "loss": 0.8426,
1573
+ "step": 254
1574
+ },
1575
+ {
1576
+ "epoch": 0.18,
1577
+ "learning_rate": 0.0004,
1578
+ "loss": 0.8062,
1579
+ "step": 255
1580
+ },
1581
+ {
1582
+ "epoch": 0.18,
1583
+ "learning_rate": 0.0004,
1584
+ "loss": 1.0046,
1585
+ "step": 256
1586
+ },
1587
+ {
1588
+ "epoch": 0.18,
1589
+ "learning_rate": 0.0004,
1590
+ "loss": 0.6235,
1591
+ "step": 257
1592
+ },
1593
+ {
1594
+ "epoch": 0.18,
1595
+ "learning_rate": 0.0004,
1596
+ "loss": 1.0021,
1597
+ "step": 258
1598
+ },
1599
+ {
1600
+ "epoch": 0.18,
1601
+ "learning_rate": 0.0004,
1602
+ "loss": 0.8788,
1603
+ "step": 259
1604
+ },
1605
+ {
1606
+ "epoch": 0.18,
1607
+ "learning_rate": 0.0004,
1608
+ "loss": 0.883,
1609
+ "step": 260
1610
+ },
1611
+ {
1612
+ "epoch": 0.18,
1613
+ "learning_rate": 0.0004,
1614
+ "loss": 0.8167,
1615
+ "step": 261
1616
+ },
1617
+ {
1618
+ "epoch": 0.18,
1619
+ "learning_rate": 0.0004,
1620
+ "loss": 0.8068,
1621
+ "step": 262
1622
+ },
1623
+ {
1624
+ "epoch": 0.18,
1625
+ "learning_rate": 0.0004,
1626
+ "loss": 0.4259,
1627
+ "step": 263
1628
+ },
1629
+ {
1630
+ "epoch": 0.19,
1631
+ "learning_rate": 0.0004,
1632
+ "loss": 0.8339,
1633
+ "step": 264
1634
+ },
1635
+ {
1636
+ "epoch": 0.19,
1637
+ "learning_rate": 0.0004,
1638
+ "loss": 0.8149,
1639
+ "step": 265
1640
+ },
1641
+ {
1642
+ "epoch": 0.19,
1643
+ "learning_rate": 0.0004,
1644
+ "loss": 0.6023,
1645
+ "step": 266
1646
+ },
1647
+ {
1648
+ "epoch": 0.19,
1649
+ "learning_rate": 0.0004,
1650
+ "loss": 0.8297,
1651
+ "step": 267
1652
+ },
1653
+ {
1654
+ "epoch": 0.19,
1655
+ "learning_rate": 0.0004,
1656
+ "loss": 1.0205,
1657
+ "step": 268
1658
+ },
1659
+ {
1660
+ "epoch": 0.19,
1661
+ "learning_rate": 0.0004,
1662
+ "loss": 0.5643,
1663
+ "step": 269
1664
+ },
1665
+ {
1666
+ "epoch": 0.19,
1667
+ "learning_rate": 0.0004,
1668
+ "loss": 0.719,
1669
+ "step": 270
1670
+ },
1671
+ {
1672
+ "epoch": 0.19,
1673
+ "learning_rate": 0.0004,
1674
+ "loss": 0.812,
1675
+ "step": 271
1676
+ },
1677
+ {
1678
+ "epoch": 0.19,
1679
+ "learning_rate": 0.0004,
1680
+ "loss": 0.5513,
1681
+ "step": 272
1682
+ },
1683
+ {
1684
+ "epoch": 0.19,
1685
+ "learning_rate": 0.0004,
1686
+ "loss": 0.7669,
1687
+ "step": 273
1688
+ },
1689
+ {
1690
+ "epoch": 0.19,
1691
+ "learning_rate": 0.0004,
1692
+ "loss": 0.6044,
1693
+ "step": 274
1694
+ },
1695
+ {
1696
+ "epoch": 0.19,
1697
+ "learning_rate": 0.0004,
1698
+ "loss": 0.7956,
1699
+ "step": 275
1700
+ },
1701
+ {
1702
+ "epoch": 0.19,
1703
+ "learning_rate": 0.0004,
1704
+ "loss": 0.569,
1705
+ "step": 276
1706
+ },
1707
+ {
1708
+ "epoch": 0.19,
1709
+ "learning_rate": 0.0004,
1710
+ "loss": 0.5728,
1711
+ "step": 277
1712
+ },
1713
+ {
1714
+ "epoch": 0.2,
1715
+ "learning_rate": 0.0004,
1716
+ "loss": 0.534,
1717
+ "step": 278
1718
+ },
1719
+ {
1720
+ "epoch": 0.2,
1721
+ "learning_rate": 0.0004,
1722
+ "loss": 0.4182,
1723
+ "step": 279
1724
+ },
1725
+ {
1726
+ "epoch": 0.2,
1727
+ "learning_rate": 0.0004,
1728
+ "loss": 0.9406,
1729
+ "step": 280
1730
+ },
1731
+ {
1732
+ "epoch": 0.2,
1733
+ "learning_rate": 0.0004,
1734
+ "loss": 0.8158,
1735
+ "step": 281
1736
+ },
1737
+ {
1738
+ "epoch": 0.2,
1739
+ "learning_rate": 0.0004,
1740
+ "loss": 0.674,
1741
+ "step": 282
1742
+ },
1743
+ {
1744
+ "epoch": 0.2,
1745
+ "learning_rate": 0.0004,
1746
+ "loss": 0.4463,
1747
+ "step": 283
1748
+ },
1749
+ {
1750
+ "epoch": 0.2,
1751
+ "learning_rate": 0.0004,
1752
+ "loss": 0.5038,
1753
+ "step": 284
1754
+ },
1755
+ {
1756
+ "epoch": 0.2,
1757
+ "learning_rate": 0.0004,
1758
+ "loss": 0.5103,
1759
+ "step": 285
1760
+ },
1761
+ {
1762
+ "epoch": 0.2,
1763
+ "learning_rate": 0.0004,
1764
+ "loss": 0.4692,
1765
+ "step": 286
1766
+ },
1767
+ {
1768
+ "epoch": 0.2,
1769
+ "learning_rate": 0.0004,
1770
+ "loss": 0.4955,
1771
+ "step": 287
1772
+ },
1773
+ {
1774
+ "epoch": 0.2,
1775
+ "learning_rate": 0.0004,
1776
+ "loss": 1.068,
1777
+ "step": 288
1778
+ },
1779
+ {
1780
+ "epoch": 0.2,
1781
+ "learning_rate": 0.0004,
1782
+ "loss": 0.5165,
1783
+ "step": 289
1784
+ },
1785
+ {
1786
+ "epoch": 0.2,
1787
+ "learning_rate": 0.0004,
1788
+ "loss": 0.6199,
1789
+ "step": 290
1790
+ },
1791
+ {
1792
+ "epoch": 0.2,
1793
+ "learning_rate": 0.0004,
1794
+ "loss": 1.1037,
1795
+ "step": 291
1796
+ },
1797
+ {
1798
+ "epoch": 0.2,
1799
+ "learning_rate": 0.0004,
1800
+ "loss": 0.155,
1801
+ "step": 292
1802
+ },
1803
+ {
1804
+ "epoch": 0.21,
1805
+ "learning_rate": 0.0004,
1806
+ "loss": 1.4112,
1807
+ "step": 293
1808
+ },
1809
+ {
1810
+ "epoch": 0.21,
1811
+ "learning_rate": 0.0004,
1812
+ "loss": 0.5906,
1813
+ "step": 294
1814
+ },
1815
+ {
1816
+ "epoch": 0.21,
1817
+ "learning_rate": 0.0004,
1818
+ "loss": 0.5932,
1819
+ "step": 295
1820
+ },
1821
+ {
1822
+ "epoch": 0.21,
1823
+ "learning_rate": 0.0004,
1824
+ "loss": 0.8826,
1825
+ "step": 296
1826
+ },
1827
+ {
1828
+ "epoch": 0.21,
1829
+ "learning_rate": 0.0004,
1830
+ "loss": 0.5626,
1831
+ "step": 297
1832
+ },
1833
+ {
1834
+ "epoch": 0.21,
1835
+ "learning_rate": 0.0004,
1836
+ "loss": 0.3403,
1837
+ "step": 298
1838
+ },
1839
+ {
1840
+ "epoch": 0.21,
1841
+ "learning_rate": 0.0004,
1842
+ "loss": 1.3782,
1843
+ "step": 299
1844
+ },
1845
+ {
1846
+ "epoch": 0.21,
1847
+ "learning_rate": 0.0004,
1848
+ "loss": 1.2619,
1849
+ "step": 300
1850
+ },
1851
+ {
1852
+ "epoch": 0.21,
1853
+ "learning_rate": 0.0004,
1854
+ "loss": 0.4879,
1855
+ "step": 301
1856
+ },
1857
+ {
1858
+ "epoch": 0.21,
1859
+ "learning_rate": 0.0004,
1860
+ "loss": 0.426,
1861
+ "step": 302
1862
+ },
1863
+ {
1864
+ "epoch": 0.21,
1865
+ "learning_rate": 0.0004,
1866
+ "loss": 0.2672,
1867
+ "step": 303
1868
+ },
1869
+ {
1870
+ "epoch": 0.21,
1871
+ "learning_rate": 0.0004,
1872
+ "loss": 0.4627,
1873
+ "step": 304
1874
+ },
1875
+ {
1876
+ "epoch": 0.21,
1877
+ "learning_rate": 0.0004,
1878
+ "loss": 0.8008,
1879
+ "step": 305
1880
+ },
1881
+ {
1882
+ "epoch": 0.21,
1883
+ "learning_rate": 0.0004,
1884
+ "loss": 0.8396,
1885
+ "step": 306
1886
+ },
1887
+ {
1888
+ "epoch": 0.22,
1889
+ "learning_rate": 0.0004,
1890
+ "loss": 0.826,
1891
+ "step": 307
1892
+ },
1893
+ {
1894
+ "epoch": 0.22,
1895
+ "learning_rate": 0.0004,
1896
+ "loss": 0.9369,
1897
+ "step": 308
1898
+ },
1899
+ {
1900
+ "epoch": 0.22,
1901
+ "learning_rate": 0.0004,
1902
+ "loss": 0.8878,
1903
+ "step": 309
1904
+ },
1905
+ {
1906
+ "epoch": 0.22,
1907
+ "learning_rate": 0.0004,
1908
+ "loss": 0.8131,
1909
+ "step": 310
1910
+ },
1911
+ {
1912
+ "epoch": 0.22,
1913
+ "learning_rate": 0.0004,
1914
+ "loss": 0.8733,
1915
+ "step": 311
1916
+ },
1917
+ {
1918
+ "epoch": 0.22,
1919
+ "learning_rate": 0.0004,
1920
+ "loss": 0.6789,
1921
+ "step": 312
1922
+ },
1923
+ {
1924
+ "epoch": 0.22,
1925
+ "learning_rate": 0.0004,
1926
+ "loss": 0.9527,
1927
+ "step": 313
1928
+ },
1929
+ {
1930
+ "epoch": 0.22,
1931
+ "learning_rate": 0.0004,
1932
+ "loss": 0.4861,
1933
+ "step": 314
1934
+ },
1935
+ {
1936
+ "epoch": 0.22,
1937
+ "learning_rate": 0.0004,
1938
+ "loss": 0.6534,
1939
+ "step": 315
1940
+ },
1941
+ {
1942
+ "epoch": 0.22,
1943
+ "learning_rate": 0.0004,
1944
+ "loss": 0.7253,
1945
+ "step": 316
1946
+ },
1947
+ {
1948
+ "epoch": 0.22,
1949
+ "learning_rate": 0.0004,
1950
+ "loss": 0.626,
1951
+ "step": 317
1952
+ },
1953
+ {
1954
+ "epoch": 0.22,
1955
+ "learning_rate": 0.0004,
1956
+ "loss": 0.7153,
1957
+ "step": 318
1958
+ },
1959
+ {
1960
+ "epoch": 0.22,
1961
+ "learning_rate": 0.0004,
1962
+ "loss": 0.5901,
1963
+ "step": 319
1964
+ },
1965
+ {
1966
+ "epoch": 0.22,
1967
+ "learning_rate": 0.0004,
1968
+ "loss": 0.5152,
1969
+ "step": 320
1970
+ },
1971
+ {
1972
+ "epoch": 0.23,
1973
+ "learning_rate": 0.0004,
1974
+ "loss": 0.6235,
1975
+ "step": 321
1976
+ },
1977
+ {
1978
+ "epoch": 0.23,
1979
+ "learning_rate": 0.0004,
1980
+ "loss": 0.7336,
1981
+ "step": 322
1982
+ },
1983
+ {
1984
+ "epoch": 0.23,
1985
+ "learning_rate": 0.0004,
1986
+ "loss": 0.8437,
1987
+ "step": 323
1988
+ },
1989
+ {
1990
+ "epoch": 0.23,
1991
+ "learning_rate": 0.0004,
1992
+ "loss": 0.8042,
1993
+ "step": 324
1994
+ },
1995
+ {
1996
+ "epoch": 0.23,
1997
+ "learning_rate": 0.0004,
1998
+ "loss": 0.524,
1999
+ "step": 325
2000
+ },
2001
+ {
2002
+ "epoch": 0.23,
2003
+ "learning_rate": 0.0004,
2004
+ "loss": 0.882,
2005
+ "step": 326
2006
+ },
2007
+ {
2008
+ "epoch": 0.23,
2009
+ "learning_rate": 0.0004,
2010
+ "loss": 0.5542,
2011
+ "step": 327
2012
+ },
2013
+ {
2014
+ "epoch": 0.23,
2015
+ "learning_rate": 0.0004,
2016
+ "loss": 0.5666,
2017
+ "step": 328
2018
+ },
2019
+ {
2020
+ "epoch": 0.23,
2021
+ "learning_rate": 0.0004,
2022
+ "loss": 0.7223,
2023
+ "step": 329
2024
+ },
2025
+ {
2026
+ "epoch": 0.23,
2027
+ "learning_rate": 0.0004,
2028
+ "loss": 0.4367,
2029
+ "step": 330
2030
+ },
2031
+ {
2032
+ "epoch": 0.23,
2033
+ "learning_rate": 0.0004,
2034
+ "loss": 0.6358,
2035
+ "step": 331
2036
+ },
2037
+ {
2038
+ "epoch": 0.23,
2039
+ "learning_rate": 0.0004,
2040
+ "loss": 0.6793,
2041
+ "step": 332
2042
+ },
2043
+ {
2044
+ "epoch": 0.23,
2045
+ "learning_rate": 0.0004,
2046
+ "loss": 0.3485,
2047
+ "step": 333
2048
+ },
2049
+ {
2050
+ "epoch": 0.23,
2051
+ "learning_rate": 0.0004,
2052
+ "loss": 0.6813,
2053
+ "step": 334
2054
+ },
2055
+ {
2056
+ "epoch": 0.24,
2057
+ "learning_rate": 0.0004,
2058
+ "loss": 0.8295,
2059
+ "step": 335
2060
+ },
2061
+ {
2062
+ "epoch": 0.24,
2063
+ "learning_rate": 0.0004,
2064
+ "loss": 0.4777,
2065
+ "step": 336
2066
+ },
2067
+ {
2068
+ "epoch": 0.24,
2069
+ "learning_rate": 0.0004,
2070
+ "loss": 0.8557,
2071
+ "step": 337
2072
+ },
2073
+ {
2074
+ "epoch": 0.24,
2075
+ "learning_rate": 0.0004,
2076
+ "loss": 0.7415,
2077
+ "step": 338
2078
+ },
2079
+ {
2080
+ "epoch": 0.24,
2081
+ "learning_rate": 0.0004,
2082
+ "loss": 0.5843,
2083
+ "step": 339
2084
+ },
2085
+ {
2086
+ "epoch": 0.24,
2087
+ "learning_rate": 0.0004,
2088
+ "loss": 0.4585,
2089
+ "step": 340
2090
+ },
2091
+ {
2092
+ "epoch": 0.24,
2093
+ "learning_rate": 0.0004,
2094
+ "loss": 0.2676,
2095
+ "step": 341
2096
+ },
2097
+ {
2098
+ "epoch": 0.24,
2099
+ "learning_rate": 0.0004,
2100
+ "loss": 0.2997,
2101
+ "step": 342
2102
+ },
2103
+ {
2104
+ "epoch": 0.24,
2105
+ "learning_rate": 0.0004,
2106
+ "loss": 0.5732,
2107
+ "step": 343
2108
+ },
2109
+ {
2110
+ "epoch": 0.24,
2111
+ "learning_rate": 0.0004,
2112
+ "loss": 0.3759,
2113
+ "step": 344
2114
+ },
2115
+ {
2116
+ "epoch": 0.24,
2117
+ "learning_rate": 0.0004,
2118
+ "loss": 0.4395,
2119
+ "step": 345
2120
+ },
2121
+ {
2122
+ "epoch": 0.24,
2123
+ "learning_rate": 0.0004,
2124
+ "loss": 0.4864,
2125
+ "step": 346
2126
+ },
2127
+ {
2128
+ "epoch": 0.24,
2129
+ "learning_rate": 0.0004,
2130
+ "loss": 0.3492,
2131
+ "step": 347
2132
+ },
2133
+ {
2134
+ "epoch": 0.24,
2135
+ "learning_rate": 0.0004,
2136
+ "loss": 0.5787,
2137
+ "step": 348
2138
+ },
2139
+ {
2140
+ "epoch": 0.24,
2141
+ "learning_rate": 0.0004,
2142
+ "loss": 0.8384,
2143
+ "step": 349
2144
+ },
2145
+ {
2146
+ "epoch": 0.25,
2147
+ "learning_rate": 0.0004,
2148
+ "loss": 1.2399,
2149
+ "step": 350
2150
+ },
2151
+ {
2152
+ "epoch": 0.25,
2153
+ "learning_rate": 0.0004,
2154
+ "loss": 0.248,
2155
+ "step": 351
2156
+ },
2157
+ {
2158
+ "epoch": 0.25,
2159
+ "learning_rate": 0.0004,
2160
+ "loss": 0.2635,
2161
+ "step": 352
2162
+ },
2163
+ {
2164
+ "epoch": 0.25,
2165
+ "learning_rate": 0.0004,
2166
+ "loss": 0.3762,
2167
+ "step": 353
2168
+ },
2169
+ {
2170
+ "epoch": 0.25,
2171
+ "learning_rate": 0.0004,
2172
+ "loss": 0.5572,
2173
+ "step": 354
2174
+ },
2175
+ {
2176
+ "epoch": 0.25,
2177
+ "learning_rate": 0.0004,
2178
+ "loss": 1.0953,
2179
+ "step": 355
2180
+ },
2181
+ {
2182
+ "epoch": 0.25,
2183
+ "learning_rate": 0.0004,
2184
+ "loss": 0.8513,
2185
+ "step": 356
2186
+ },
2187
+ {
2188
+ "epoch": 0.25,
2189
+ "learning_rate": 0.0004,
2190
+ "loss": 0.8504,
2191
+ "step": 357
2192
+ },
2193
+ {
2194
+ "epoch": 0.25,
2195
+ "learning_rate": 0.0004,
2196
+ "loss": 0.9141,
2197
+ "step": 358
2198
+ },
2199
+ {
2200
+ "epoch": 0.25,
2201
+ "learning_rate": 0.0004,
2202
+ "loss": 0.7751,
2203
+ "step": 359
2204
+ },
2205
+ {
2206
+ "epoch": 0.25,
2207
+ "learning_rate": 0.0004,
2208
+ "loss": 0.8659,
2209
+ "step": 360
2210
+ },
2211
+ {
2212
+ "epoch": 0.25,
2213
+ "learning_rate": 0.0004,
2214
+ "loss": 0.9634,
2215
+ "step": 361
2216
+ },
2217
+ {
2218
+ "epoch": 0.25,
2219
+ "learning_rate": 0.0004,
2220
+ "loss": 0.9354,
2221
+ "step": 362
2222
+ },
2223
+ {
2224
+ "epoch": 0.25,
2225
+ "learning_rate": 0.0004,
2226
+ "loss": 0.6382,
2227
+ "step": 363
2228
+ },
2229
+ {
2230
+ "epoch": 0.26,
2231
+ "learning_rate": 0.0004,
2232
+ "loss": 0.9403,
2233
+ "step": 364
2234
+ },
2235
+ {
2236
+ "epoch": 0.26,
2237
+ "learning_rate": 0.0004,
2238
+ "loss": 0.8036,
2239
+ "step": 365
2240
+ },
2241
+ {
2242
+ "epoch": 0.26,
2243
+ "learning_rate": 0.0004,
2244
+ "loss": 0.5506,
2245
+ "step": 366
2246
+ },
2247
+ {
2248
+ "epoch": 0.26,
2249
+ "learning_rate": 0.0004,
2250
+ "loss": 0.4639,
2251
+ "step": 367
2252
+ },
2253
+ {
2254
+ "epoch": 0.26,
2255
+ "learning_rate": 0.0004,
2256
+ "loss": 0.8315,
2257
+ "step": 368
2258
+ },
2259
+ {
2260
+ "epoch": 0.26,
2261
+ "learning_rate": 0.0004,
2262
+ "loss": 0.6634,
2263
+ "step": 369
2264
+ },
2265
+ {
2266
+ "epoch": 0.26,
2267
+ "learning_rate": 0.0004,
2268
+ "loss": 0.6388,
2269
+ "step": 370
2270
+ },
2271
+ {
2272
+ "epoch": 0.26,
2273
+ "learning_rate": 0.0004,
2274
+ "loss": 0.7629,
2275
+ "step": 371
2276
+ },
2277
+ {
2278
+ "epoch": 0.26,
2279
+ "learning_rate": 0.0004,
2280
+ "loss": 0.6548,
2281
+ "step": 372
2282
+ },
2283
+ {
2284
+ "epoch": 0.26,
2285
+ "learning_rate": 0.0004,
2286
+ "loss": 0.5165,
2287
+ "step": 373
2288
+ },
2289
+ {
2290
+ "epoch": 0.26,
2291
+ "learning_rate": 0.0004,
2292
+ "loss": 0.2858,
2293
+ "step": 374
2294
+ },
2295
+ {
2296
+ "epoch": 0.26,
2297
+ "learning_rate": 0.0004,
2298
+ "loss": 0.3376,
2299
+ "step": 375
2300
+ },
2301
+ {
2302
+ "epoch": 0.26,
2303
+ "learning_rate": 0.0004,
2304
+ "loss": 0.5373,
2305
+ "step": 376
2306
+ },
2307
+ {
2308
+ "epoch": 0.26,
2309
+ "learning_rate": 0.0004,
2310
+ "loss": 0.6229,
2311
+ "step": 377
2312
+ },
2313
+ {
2314
+ "epoch": 0.27,
2315
+ "learning_rate": 0.0004,
2316
+ "loss": 0.5867,
2317
+ "step": 378
2318
+ },
2319
+ {
2320
+ "epoch": 0.27,
2321
+ "learning_rate": 0.0004,
2322
+ "loss": 0.5533,
2323
+ "step": 379
2324
+ },
2325
+ {
2326
+ "epoch": 0.27,
2327
+ "learning_rate": 0.0004,
2328
+ "loss": 0.4804,
2329
+ "step": 380
2330
+ },
2331
+ {
2332
+ "epoch": 0.27,
2333
+ "learning_rate": 0.0004,
2334
+ "loss": 0.313,
2335
+ "step": 381
2336
+ },
2337
+ {
2338
+ "epoch": 0.27,
2339
+ "learning_rate": 0.0004,
2340
+ "loss": 0.7077,
2341
+ "step": 382
2342
+ },
2343
+ {
2344
+ "epoch": 0.27,
2345
+ "learning_rate": 0.0004,
2346
+ "loss": 0.5241,
2347
+ "step": 383
2348
+ },
2349
+ {
2350
+ "epoch": 0.27,
2351
+ "learning_rate": 0.0004,
2352
+ "loss": 0.3367,
2353
+ "step": 384
2354
+ },
2355
+ {
2356
+ "epoch": 0.27,
2357
+ "learning_rate": 0.0004,
2358
+ "loss": 0.8614,
2359
+ "step": 385
2360
+ },
2361
+ {
2362
+ "epoch": 0.27,
2363
+ "learning_rate": 0.0004,
2364
+ "loss": 0.4548,
2365
+ "step": 386
2366
+ },
2367
+ {
2368
+ "epoch": 0.27,
2369
+ "learning_rate": 0.0004,
2370
+ "loss": 0.6221,
2371
+ "step": 387
2372
+ },
2373
+ {
2374
+ "epoch": 0.27,
2375
+ "learning_rate": 0.0004,
2376
+ "loss": 0.8041,
2377
+ "step": 388
2378
+ },
2379
+ {
2380
+ "epoch": 0.27,
2381
+ "learning_rate": 0.0004,
2382
+ "loss": 0.2546,
2383
+ "step": 389
2384
+ },
2385
+ {
2386
+ "epoch": 0.27,
2387
+ "learning_rate": 0.0004,
2388
+ "loss": 0.5016,
2389
+ "step": 390
2390
+ },
2391
+ {
2392
+ "epoch": 0.27,
2393
+ "learning_rate": 0.0004,
2394
+ "loss": 0.4664,
2395
+ "step": 391
2396
+ },
2397
+ {
2398
+ "epoch": 0.28,
2399
+ "learning_rate": 0.0004,
2400
+ "loss": 0.2124,
2401
+ "step": 392
2402
+ },
2403
+ {
2404
+ "epoch": 0.28,
2405
+ "learning_rate": 0.0004,
2406
+ "loss": 0.4019,
2407
+ "step": 393
2408
+ },
2409
+ {
2410
+ "epoch": 0.28,
2411
+ "learning_rate": 0.0004,
2412
+ "loss": 0.8749,
2413
+ "step": 394
2414
+ },
2415
+ {
2416
+ "epoch": 0.28,
2417
+ "learning_rate": 0.0004,
2418
+ "loss": 0.2319,
2419
+ "step": 395
2420
+ },
2421
+ {
2422
+ "epoch": 0.28,
2423
+ "learning_rate": 0.0004,
2424
+ "loss": 0.9602,
2425
+ "step": 396
2426
+ },
2427
+ {
2428
+ "epoch": 0.28,
2429
+ "learning_rate": 0.0004,
2430
+ "loss": 0.9182,
2431
+ "step": 397
2432
+ },
2433
+ {
2434
+ "epoch": 0.28,
2435
+ "learning_rate": 0.0004,
2436
+ "loss": 0.2092,
2437
+ "step": 398
2438
+ },
2439
+ {
2440
+ "epoch": 0.28,
2441
+ "learning_rate": 0.0004,
2442
+ "loss": 0.2311,
2443
+ "step": 399
2444
+ },
2445
+ {
2446
+ "epoch": 0.28,
2447
+ "learning_rate": 0.0004,
2448
+ "loss": 1.6764,
2449
+ "step": 400
2450
+ },
2451
+ {
2452
+ "epoch": 0.28,
2453
+ "eval_loss": 0.6333504915237427,
2454
+ "eval_runtime": 261.9428,
2455
+ "eval_samples_per_second": 1.909,
2456
+ "eval_steps_per_second": 0.954,
2457
+ "step": 400
2458
+ },
2459
+ {
2460
+ "epoch": 0.28,
2461
+ "mmlu_eval_accuracy": 0.4098082068017773,
2462
+ "mmlu_eval_accuracy_abstract_algebra": 0.09090909090909091,
2463
+ "mmlu_eval_accuracy_anatomy": 0.2857142857142857,
2464
+ "mmlu_eval_accuracy_astronomy": 0.375,
2465
+ "mmlu_eval_accuracy_business_ethics": 0.36363636363636365,
2466
+ "mmlu_eval_accuracy_clinical_knowledge": 0.4482758620689655,
2467
+ "mmlu_eval_accuracy_college_biology": 0.4375,
2468
+ "mmlu_eval_accuracy_college_chemistry": 0.25,
2469
+ "mmlu_eval_accuracy_college_computer_science": 0.5454545454545454,
2470
+ "mmlu_eval_accuracy_college_mathematics": 0.45454545454545453,
2471
+ "mmlu_eval_accuracy_college_medicine": 0.5,
2472
+ "mmlu_eval_accuracy_college_physics": 0.36363636363636365,
2473
+ "mmlu_eval_accuracy_computer_security": 0.5454545454545454,
2474
+ "mmlu_eval_accuracy_conceptual_physics": 0.34615384615384615,
2475
+ "mmlu_eval_accuracy_econometrics": 0.16666666666666666,
2476
+ "mmlu_eval_accuracy_electrical_engineering": 0.5625,
2477
+ "mmlu_eval_accuracy_elementary_mathematics": 0.4146341463414634,
2478
+ "mmlu_eval_accuracy_formal_logic": 0.35714285714285715,
2479
+ "mmlu_eval_accuracy_global_facts": 0.2,
2480
+ "mmlu_eval_accuracy_high_school_biology": 0.3125,
2481
+ "mmlu_eval_accuracy_high_school_chemistry": 0.36363636363636365,
2482
+ "mmlu_eval_accuracy_high_school_computer_science": 0.7777777777777778,
2483
+ "mmlu_eval_accuracy_high_school_european_history": 0.6111111111111112,
2484
+ "mmlu_eval_accuracy_high_school_geography": 0.7272727272727273,
2485
+ "mmlu_eval_accuracy_high_school_government_and_politics": 0.5714285714285714,
2486
+ "mmlu_eval_accuracy_high_school_macroeconomics": 0.3953488372093023,
2487
+ "mmlu_eval_accuracy_high_school_mathematics": 0.2413793103448276,
2488
+ "mmlu_eval_accuracy_high_school_microeconomics": 0.35714285714285715,
2489
+ "mmlu_loss": 0.6790264239534736,
2490
+ "step": 400
2491
+ }
2492
+ ],
2493
+ "max_steps": 30000,
2494
+ "num_train_epochs": 22,
2495
+ "total_flos": 8.026383920273818e+16,
2496
+ "trial_name": null,
2497
+ "trial_params": null
2498
+ }
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc158bb44d89730af0d9db1f6729c5ae345af1012509e2cacbb0c714f3af20c7
3
+ size 5947