Hugging Face's logo

pharaouk
/
CodeLlama-34b-Python-hf_34bCodellama_unnatural-instructions_standardized

Model card Files Community
Farouk commited on
Commit
5d7d619
·
1 Parent(s): f40a659

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 +2452 -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:e24cde49bbdbdfa926b63cf5ddeacb885f909f0185ff48bd760e1a2e8925df52
3
  size 871609293
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3b765278d368b2dedcebc9e016a47aac2fe066d1fc3ca9e35226f4ad62815e0
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
+ "up_proj",
19
+ "q_proj",
20
+ "gate_proj",
21
+ "o_proj",
22
+ "v_proj",
23
+ "k_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:e24cde49bbdbdfa926b63cf5ddeacb885f909f0185ff48bd760e1a2e8925df52
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
+ "up_proj",
19
+ "q_proj",
20
+ "gate_proj",
21
+ "o_proj",
22
+ "v_proj",
23
+ "k_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:c3b765278d368b2dedcebc9e016a47aac2fe066d1fc3ca9e35226f4ad62815e0
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 sha256:6cf97dac6fdd8b3b2f12b0c5ebbe6c3f059fddcb90eb13e1fbfabcd1f9fd090d
3
+ size 873873439
checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f63437b5c442ed826ada37c061fce84c2003c7a71e2c64fb861e62d8df0dd68
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 +1,2452 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 7.106412410736084,
3
+ "best_model_checkpoint": "./output_v2/34bCodellama_CodeLlama-34b-Python-hf_unnatural-instructions_standardized/checkpoint-400",
4
+ "epoch": 0.003055534336567107,
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": 3.0808,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 0.0004,
19
+ "loss": 5.8773,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 0.0004,
25
+ "loss": 0.1965,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.0,
30
+ "learning_rate": 0.0004,
31
+ "loss": 0.118,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.0,
36
+ "learning_rate": 0.0004,
37
+ "loss": 0.1773,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.0,
42
+ "learning_rate": 0.0004,
43
+ "loss": 0.1165,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "learning_rate": 0.0004,
49
+ "loss": 4.2666,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.0,
54
+ "learning_rate": 0.0004,
55
+ "loss": 0.3704,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.0,
60
+ "learning_rate": 0.0004,
61
+ "loss": 4.9976,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.0,
66
+ "learning_rate": 0.0004,
67
+ "loss": 1.985,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.0,
72
+ "learning_rate": 0.0004,
73
+ "loss": 1.0541,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.0,
78
+ "learning_rate": 0.0004,
79
+ "loss": 0.6228,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.0,
84
+ "learning_rate": 0.0004,
85
+ "loss": 1.3651,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.0,
90
+ "learning_rate": 0.0004,
91
+ "loss": 0.0867,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.0,
96
+ "learning_rate": 0.0004,
97
+ "loss": 0.4422,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.0,
102
+ "learning_rate": 0.0004,
103
+ "loss": 0.7759,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.0,
108
+ "learning_rate": 0.0004,
109
+ "loss": 0.1446,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.0,
114
+ "learning_rate": 0.0004,
115
+ "loss": 0.0007,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.0,
120
+ "learning_rate": 0.0004,
121
+ "loss": 0.0894,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.0,
126
+ "learning_rate": 0.0004,
127
+ "loss": 7.2424,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.0,
132
+ "learning_rate": 0.0004,
133
+ "loss": 2.1343,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.0,
138
+ "learning_rate": 0.0004,
139
+ "loss": 0.5354,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.0,
144
+ "learning_rate": 0.0004,
145
+ "loss": 0.1887,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.0,
150
+ "learning_rate": 0.0004,
151
+ "loss": 1.6652,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.0,
156
+ "learning_rate": 0.0004,
157
+ "loss": 0.964,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.0,
162
+ "learning_rate": 0.0004,
163
+ "loss": 0.1872,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.0,
168
+ "learning_rate": 0.0004,
169
+ "loss": 0.4722,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.0,
174
+ "learning_rate": 0.0004,
175
+ "loss": 0.1462,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.0,
180
+ "learning_rate": 0.0004,
181
+ "loss": 3.0485,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.0,
186
+ "learning_rate": 0.0004,
187
+ "loss": 1.148,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.0,
192
+ "learning_rate": 0.0004,
193
+ "loss": 6.7274,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.0,
198
+ "learning_rate": 0.0004,
199
+ "loss": 1.6689,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.0,
204
+ "learning_rate": 0.0004,
205
+ "loss": 0.3384,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.0,
210
+ "learning_rate": 0.0004,
211
+ "loss": 1.5354,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.0,
216
+ "learning_rate": 0.0004,
217
+ "loss": 3.1976,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.0,
222
+ "learning_rate": 0.0004,
223
+ "loss": 0.8593,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.0,
228
+ "learning_rate": 0.0004,
229
+ "loss": 1.9302,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.0,
234
+ "learning_rate": 0.0004,
235
+ "loss": 0.5968,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.0,
240
+ "learning_rate": 0.0004,
241
+ "loss": 0.3169,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.0,
246
+ "learning_rate": 0.0004,
247
+ "loss": 1.1793,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.0,
252
+ "learning_rate": 0.0004,
253
+ "loss": 1.8457,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.0,
258
+ "learning_rate": 0.0004,
259
+ "loss": 0.5177,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.0,
264
+ "learning_rate": 0.0004,
265
+ "loss": 2.003,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.0,
270
+ "learning_rate": 0.0004,
271
+ "loss": 1.9928,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.0,
276
+ "learning_rate": 0.0004,
277
+ "loss": 15.2574,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.0,
282
+ "learning_rate": 0.0004,
283
+ "loss": 0.3915,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.0,
288
+ "learning_rate": 0.0004,
289
+ "loss": 2.4105,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.0,
294
+ "learning_rate": 0.0004,
295
+ "loss": 1.1184,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.0,
300
+ "learning_rate": 0.0004,
301
+ "loss": 2.72,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.0,
306
+ "learning_rate": 0.0004,
307
+ "loss": 3.9628,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.0,
312
+ "learning_rate": 0.0004,
313
+ "loss": 5.2372,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.0,
318
+ "learning_rate": 0.0004,
319
+ "loss": 7.3733,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.0,
324
+ "learning_rate": 0.0004,
325
+ "loss": 3.8936,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.0,
330
+ "learning_rate": 0.0004,
331
+ "loss": 4.5353,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.0,
336
+ "learning_rate": 0.0004,
337
+ "loss": 2.0754,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.0,
342
+ "learning_rate": 0.0004,
343
+ "loss": 2.6685,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.0,
348
+ "learning_rate": 0.0004,
349
+ "loss": 2.8984,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.0,
354
+ "learning_rate": 0.0004,
355
+ "loss": 5.2265,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.0,
360
+ "learning_rate": 0.0004,
361
+ "loss": 8.7696,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.0,
366
+ "learning_rate": 0.0004,
367
+ "loss": 9.7349,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.0,
372
+ "learning_rate": 0.0004,
373
+ "loss": 10.0221,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.0,
378
+ "learning_rate": 0.0004,
379
+ "loss": 15.1901,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.0,
384
+ "learning_rate": 0.0004,
385
+ "loss": 9.387,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.0,
390
+ "learning_rate": 0.0004,
391
+ "loss": 6.7323,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.0,
396
+ "learning_rate": 0.0004,
397
+ "loss": 10.2077,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.0,
402
+ "learning_rate": 0.0004,
403
+ "loss": 10.3155,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.0,
408
+ "learning_rate": 0.0004,
409
+ "loss": 8.1656,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.0,
414
+ "learning_rate": 0.0004,
415
+ "loss": 13.0828,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.0,
420
+ "learning_rate": 0.0004,
421
+ "loss": 8.5295,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.0,
426
+ "learning_rate": 0.0004,
427
+ "loss": 8.4575,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.0,
432
+ "learning_rate": 0.0004,
433
+ "loss": 14.7654,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.0,
438
+ "learning_rate": 0.0004,
439
+ "loss": 10.6263,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.0,
444
+ "learning_rate": 0.0004,
445
+ "loss": 24.8238,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.0,
450
+ "learning_rate": 0.0004,
451
+ "loss": 15.0654,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.0,
456
+ "learning_rate": 0.0004,
457
+ "loss": 28.1046,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.0,
462
+ "learning_rate": 0.0004,
463
+ "loss": 14.3232,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.0,
468
+ "learning_rate": 0.0004,
469
+ "loss": 22.9712,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.0,
474
+ "learning_rate": 0.0004,
475
+ "loss": 18.8529,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.0,
480
+ "learning_rate": 0.0004,
481
+ "loss": 15.8356,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.0,
486
+ "learning_rate": 0.0004,
487
+ "loss": 16.472,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.0,
492
+ "learning_rate": 0.0004,
493
+ "loss": 12.2369,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.0,
498
+ "learning_rate": 0.0004,
499
+ "loss": 14.0731,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.0,
504
+ "learning_rate": 0.0004,
505
+ "loss": 9.8853,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.0,
510
+ "learning_rate": 0.0004,
511
+ "loss": 7.5438,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.0,
516
+ "learning_rate": 0.0004,
517
+ "loss": 8.2665,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.0,
522
+ "learning_rate": 0.0004,
523
+ "loss": 11.5484,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.0,
528
+ "learning_rate": 0.0004,
529
+ "loss": 9.7546,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.0,
534
+ "learning_rate": 0.0004,
535
+ "loss": 9.4309,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.0,
540
+ "learning_rate": 0.0004,
541
+ "loss": 11.5593,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.0,
546
+ "learning_rate": 0.0004,
547
+ "loss": 8.3822,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.0,
552
+ "learning_rate": 0.0004,
553
+ "loss": 9.6315,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.0,
558
+ "learning_rate": 0.0004,
559
+ "loss": 7.6116,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.0,
564
+ "learning_rate": 0.0004,
565
+ "loss": 10.2288,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.0,
570
+ "learning_rate": 0.0004,
571
+ "loss": 5.0053,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.0,
576
+ "learning_rate": 0.0004,
577
+ "loss": 12.359,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.0,
582
+ "learning_rate": 0.0004,
583
+ "loss": 8.9235,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.0,
588
+ "learning_rate": 0.0004,
589
+ "loss": 31.9845,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.0,
594
+ "learning_rate": 0.0004,
595
+ "loss": 11.1385,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.0,
600
+ "learning_rate": 0.0004,
601
+ "loss": 7.6161,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.0,
606
+ "learning_rate": 0.0004,
607
+ "loss": 8.8096,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.0,
612
+ "learning_rate": 0.0004,
613
+ "loss": 9.9918,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.0,
618
+ "learning_rate": 0.0004,
619
+ "loss": 6.344,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.0,
624
+ "learning_rate": 0.0004,
625
+ "loss": 9.1607,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.0,
630
+ "learning_rate": 0.0004,
631
+ "loss": 9.4834,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.0,
636
+ "learning_rate": 0.0004,
637
+ "loss": 4.704,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.0,
642
+ "learning_rate": 0.0004,
643
+ "loss": 9.1238,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.0,
648
+ "learning_rate": 0.0004,
649
+ "loss": 7.8066,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.0,
654
+ "learning_rate": 0.0004,
655
+ "loss": 7.9656,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.0,
660
+ "learning_rate": 0.0004,
661
+ "loss": 7.1979,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.0,
666
+ "learning_rate": 0.0004,
667
+ "loss": 7.2294,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.0,
672
+ "learning_rate": 0.0004,
673
+ "loss": 8.066,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.0,
678
+ "learning_rate": 0.0004,
679
+ "loss": 7.7914,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.0,
684
+ "learning_rate": 0.0004,
685
+ "loss": 6.7344,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.0,
690
+ "learning_rate": 0.0004,
691
+ "loss": 8.6703,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.0,
696
+ "learning_rate": 0.0004,
697
+ "loss": 2.8817,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.0,
702
+ "learning_rate": 0.0004,
703
+ "loss": 11.7733,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.0,
708
+ "learning_rate": 0.0004,
709
+ "loss": 10.469,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.0,
714
+ "learning_rate": 0.0004,
715
+ "loss": 4.1304,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.0,
720
+ "learning_rate": 0.0004,
721
+ "loss": 9.871,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.0,
726
+ "learning_rate": 0.0004,
727
+ "loss": 9.5353,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 0.0,
732
+ "learning_rate": 0.0004,
733
+ "loss": 4.9055,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 0.0,
738
+ "learning_rate": 0.0004,
739
+ "loss": 8.6142,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 0.0,
744
+ "learning_rate": 0.0004,
745
+ "loss": 9.0201,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 0.0,
750
+ "learning_rate": 0.0004,
751
+ "loss": 5.3805,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 0.0,
756
+ "learning_rate": 0.0004,
757
+ "loss": 6.6825,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 0.0,
762
+ "learning_rate": 0.0004,
763
+ "loss": 9.7166,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 0.0,
768
+ "learning_rate": 0.0004,
769
+ "loss": 3.7747,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 0.0,
774
+ "learning_rate": 0.0004,
775
+ "loss": 6.7695,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 0.0,
780
+ "learning_rate": 0.0004,
781
+ "loss": 5.7291,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 0.0,
786
+ "learning_rate": 0.0004,
787
+ "loss": 4.1296,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 0.0,
792
+ "learning_rate": 0.0004,
793
+ "loss": 6.5374,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 0.0,
798
+ "learning_rate": 0.0004,
799
+ "loss": 6.1854,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 0.0,
804
+ "learning_rate": 0.0004,
805
+ "loss": 8.434,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 0.0,
810
+ "learning_rate": 0.0004,
811
+ "loss": 8.438,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 0.0,
816
+ "learning_rate": 0.0004,
817
+ "loss": 7.3027,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 0.0,
822
+ "learning_rate": 0.0004,
823
+ "loss": 8.382,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 0.0,
828
+ "learning_rate": 0.0004,
829
+ "loss": 9.9277,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 0.0,
834
+ "learning_rate": 0.0004,
835
+ "loss": 7.223,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 0.0,
840
+ "learning_rate": 0.0004,
841
+ "loss": 4.3042,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 0.0,
846
+ "learning_rate": 0.0004,
847
+ "loss": 2.6361,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 0.0,
852
+ "learning_rate": 0.0004,
853
+ "loss": 6.3547,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 0.0,
858
+ "learning_rate": 0.0004,
859
+ "loss": 4.7181,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 0.0,
864
+ "learning_rate": 0.0004,
865
+ "loss": 10.7528,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 0.0,
870
+ "learning_rate": 0.0004,
871
+ "loss": 11.4316,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 0.0,
876
+ "learning_rate": 0.0004,
877
+ "loss": 9.2219,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 0.0,
882
+ "learning_rate": 0.0004,
883
+ "loss": 5.7788,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 0.0,
888
+ "learning_rate": 0.0004,
889
+ "loss": 6.2749,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 0.0,
894
+ "learning_rate": 0.0004,
895
+ "loss": 8.2397,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 0.0,
900
+ "learning_rate": 0.0004,
901
+ "loss": 8.6243,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 0.0,
906
+ "learning_rate": 0.0004,
907
+ "loss": 5.145,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 0.0,
912
+ "learning_rate": 0.0004,
913
+ "loss": 8.7951,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 0.0,
918
+ "learning_rate": 0.0004,
919
+ "loss": 7.1862,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 0.0,
924
+ "learning_rate": 0.0004,
925
+ "loss": 4.1305,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 0.0,
930
+ "learning_rate": 0.0004,
931
+ "loss": 3.5766,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 0.0,
936
+ "learning_rate": 0.0004,
937
+ "loss": 8.9232,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 0.0,
942
+ "learning_rate": 0.0004,
943
+ "loss": 3.9936,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 0.0,
948
+ "learning_rate": 0.0004,
949
+ "loss": 10.9692,
950
+ "step": 157
951
+ },
952
+ {
953
+ "epoch": 0.0,
954
+ "learning_rate": 0.0004,
955
+ "loss": 10.2772,
956
+ "step": 158
957
+ },
958
+ {
959
+ "epoch": 0.0,
960
+ "learning_rate": 0.0004,
961
+ "loss": 9.302,
962
+ "step": 159
963
+ },
964
+ {
965
+ "epoch": 0.0,
966
+ "learning_rate": 0.0004,
967
+ "loss": 8.9931,
968
+ "step": 160
969
+ },
970
+ {
971
+ "epoch": 0.0,
972
+ "learning_rate": 0.0004,
973
+ "loss": 6.9675,
974
+ "step": 161
975
+ },
976
+ {
977
+ "epoch": 0.0,
978
+ "learning_rate": 0.0004,
979
+ "loss": 2.8536,
980
+ "step": 162
981
+ },
982
+ {
983
+ "epoch": 0.0,
984
+ "learning_rate": 0.0004,
985
+ "loss": 7.6589,
986
+ "step": 163
987
+ },
988
+ {
989
+ "epoch": 0.0,
990
+ "learning_rate": 0.0004,
991
+ "loss": 8.932,
992
+ "step": 164
993
+ },
994
+ {
995
+ "epoch": 0.0,
996
+ "learning_rate": 0.0004,
997
+ "loss": 9.0301,
998
+ "step": 165
999
+ },
1000
+ {
1001
+ "epoch": 0.0,
1002
+ "learning_rate": 0.0004,
1003
+ "loss": 6.4861,
1004
+ "step": 166
1005
+ },
1006
+ {
1007
+ "epoch": 0.0,
1008
+ "learning_rate": 0.0004,
1009
+ "loss": 8.1354,
1010
+ "step": 167
1011
+ },
1012
+ {
1013
+ "epoch": 0.0,
1014
+ "learning_rate": 0.0004,
1015
+ "loss": 8.0717,
1016
+ "step": 168
1017
+ },
1018
+ {
1019
+ "epoch": 0.0,
1020
+ "learning_rate": 0.0004,
1021
+ "loss": 4.9346,
1022
+ "step": 169
1023
+ },
1024
+ {
1025
+ "epoch": 0.0,
1026
+ "learning_rate": 0.0004,
1027
+ "loss": 7.9373,
1028
+ "step": 170
1029
+ },
1030
+ {
1031
+ "epoch": 0.0,
1032
+ "learning_rate": 0.0004,
1033
+ "loss": 7.8777,
1034
+ "step": 171
1035
+ },
1036
+ {
1037
+ "epoch": 0.0,
1038
+ "learning_rate": 0.0004,
1039
+ "loss": 8.4193,
1040
+ "step": 172
1041
+ },
1042
+ {
1043
+ "epoch": 0.0,
1044
+ "learning_rate": 0.0004,
1045
+ "loss": 7.6831,
1046
+ "step": 173
1047
+ },
1048
+ {
1049
+ "epoch": 0.0,
1050
+ "learning_rate": 0.0004,
1051
+ "loss": 6.4175,
1052
+ "step": 174
1053
+ },
1054
+ {
1055
+ "epoch": 0.0,
1056
+ "learning_rate": 0.0004,
1057
+ "loss": 5.3629,
1058
+ "step": 175
1059
+ },
1060
+ {
1061
+ "epoch": 0.0,
1062
+ "learning_rate": 0.0004,
1063
+ "loss": 8.118,
1064
+ "step": 176
1065
+ },
1066
+ {
1067
+ "epoch": 0.0,
1068
+ "learning_rate": 0.0004,
1069
+ "loss": 4.633,
1070
+ "step": 177
1071
+ },
1072
+ {
1073
+ "epoch": 0.0,
1074
+ "learning_rate": 0.0004,
1075
+ "loss": 4.8355,
1076
+ "step": 178
1077
+ },
1078
+ {
1079
+ "epoch": 0.0,
1080
+ "learning_rate": 0.0004,
1081
+ "loss": 3.4522,
1082
+ "step": 179
1083
+ },
1084
+ {
1085
+ "epoch": 0.0,
1086
+ "learning_rate": 0.0004,
1087
+ "loss": 9.9272,
1088
+ "step": 180
1089
+ },
1090
+ {
1091
+ "epoch": 0.0,
1092
+ "learning_rate": 0.0004,
1093
+ "loss": 8.4631,
1094
+ "step": 181
1095
+ },
1096
+ {
1097
+ "epoch": 0.0,
1098
+ "learning_rate": 0.0004,
1099
+ "loss": 9.2987,
1100
+ "step": 182
1101
+ },
1102
+ {
1103
+ "epoch": 0.0,
1104
+ "learning_rate": 0.0004,
1105
+ "loss": 8.1183,
1106
+ "step": 183
1107
+ },
1108
+ {
1109
+ "epoch": 0.0,
1110
+ "learning_rate": 0.0004,
1111
+ "loss": 2.9976,
1112
+ "step": 184
1113
+ },
1114
+ {
1115
+ "epoch": 0.0,
1116
+ "learning_rate": 0.0004,
1117
+ "loss": 6.0668,
1118
+ "step": 185
1119
+ },
1120
+ {
1121
+ "epoch": 0.0,
1122
+ "learning_rate": 0.0004,
1123
+ "loss": 8.6291,
1124
+ "step": 186
1125
+ },
1126
+ {
1127
+ "epoch": 0.0,
1128
+ "learning_rate": 0.0004,
1129
+ "loss": 8.5937,
1130
+ "step": 187
1131
+ },
1132
+ {
1133
+ "epoch": 0.0,
1134
+ "learning_rate": 0.0004,
1135
+ "loss": 5.7382,
1136
+ "step": 188
1137
+ },
1138
+ {
1139
+ "epoch": 0.0,
1140
+ "learning_rate": 0.0004,
1141
+ "loss": 6.7677,
1142
+ "step": 189
1143
+ },
1144
+ {
1145
+ "epoch": 0.0,
1146
+ "learning_rate": 0.0004,
1147
+ "loss": 4.0293,
1148
+ "step": 190
1149
+ },
1150
+ {
1151
+ "epoch": 0.0,
1152
+ "learning_rate": 0.0004,
1153
+ "loss": 3.6407,
1154
+ "step": 191
1155
+ },
1156
+ {
1157
+ "epoch": 0.0,
1158
+ "learning_rate": 0.0004,
1159
+ "loss": 3.9508,
1160
+ "step": 192
1161
+ },
1162
+ {
1163
+ "epoch": 0.0,
1164
+ "learning_rate": 0.0004,
1165
+ "loss": 2.5053,
1166
+ "step": 193
1167
+ },
1168
+ {
1169
+ "epoch": 0.0,
1170
+ "learning_rate": 0.0004,
1171
+ "loss": 5.5718,
1172
+ "step": 194
1173
+ },
1174
+ {
1175
+ "epoch": 0.0,
1176
+ "learning_rate": 0.0004,
1177
+ "loss": 7.5211,
1178
+ "step": 195
1179
+ },
1180
+ {
1181
+ "epoch": 0.0,
1182
+ "learning_rate": 0.0004,
1183
+ "loss": 7.9557,
1184
+ "step": 196
1185
+ },
1186
+ {
1187
+ "epoch": 0.0,
1188
+ "learning_rate": 0.0004,
1189
+ "loss": 8.1609,
1190
+ "step": 197
1191
+ },
1192
+ {
1193
+ "epoch": 0.0,
1194
+ "learning_rate": 0.0004,
1195
+ "loss": 5.8505,
1196
+ "step": 198
1197
+ },
1198
+ {
1199
+ "epoch": 0.0,
1200
+ "learning_rate": 0.0004,
1201
+ "loss": 5.8278,
1202
+ "step": 199
1203
+ },
1204
+ {
1205
+ "epoch": 0.0,
1206
+ "learning_rate": 0.0004,
1207
+ "loss": 3.8447,
1208
+ "step": 200
1209
+ },
1210
+ {
1211
+ "epoch": 0.0,
1212
+ "eval_loss": 7.883856773376465,
1213
+ "eval_runtime": 22.4254,
1214
+ "eval_samples_per_second": 2.23,
1215
+ "eval_steps_per_second": 1.115,
1216
+ "step": 200
1217
+ },
1218
+ {
1219
+ "epoch": 0.0,
1220
+ "mmlu_eval_accuracy": 0.2525477994227994,
1221
+ "mmlu_eval_accuracy_abstract_algebra": 0.18181818181818182,
1222
+ "mmlu_eval_accuracy_anatomy": 0.07142857142857142,
1223
+ "mmlu_eval_accuracy_astronomy": 0.3125,
1224
+ "mmlu_eval_accuracy_business_ethics": 0.4444444444444444,
1225
+ "mmlu_loss": 4.629522514343262,
1226
+ "step": 200
1227
+ },
1228
+ {
1229
+ "epoch": 0.0,
1230
+ "learning_rate": 0.0004,
1231
+ "loss": 8.3249,
1232
+ "step": 201
1233
+ },
1234
+ {
1235
+ "epoch": 0.0,
1236
+ "learning_rate": 0.0004,
1237
+ "loss": 9.352,
1238
+ "step": 202
1239
+ },
1240
+ {
1241
+ "epoch": 0.0,
1242
+ "learning_rate": 0.0004,
1243
+ "loss": 7.2984,
1244
+ "step": 203
1245
+ },
1246
+ {
1247
+ "epoch": 0.0,
1248
+ "learning_rate": 0.0004,
1249
+ "loss": 11.2734,
1250
+ "step": 204
1251
+ },
1252
+ {
1253
+ "epoch": 0.0,
1254
+ "learning_rate": 0.0004,
1255
+ "loss": 9.1,
1256
+ "step": 205
1257
+ },
1258
+ {
1259
+ "epoch": 0.0,
1260
+ "learning_rate": 0.0004,
1261
+ "loss": 5.448,
1262
+ "step": 206
1263
+ },
1264
+ {
1265
+ "epoch": 0.0,
1266
+ "learning_rate": 0.0004,
1267
+ "loss": 9.2387,
1268
+ "step": 207
1269
+ },
1270
+ {
1271
+ "epoch": 0.0,
1272
+ "learning_rate": 0.0004,
1273
+ "loss": 8.861,
1274
+ "step": 208
1275
+ },
1276
+ {
1277
+ "epoch": 0.0,
1278
+ "learning_rate": 0.0004,
1279
+ "loss": 6.603,
1280
+ "step": 209
1281
+ },
1282
+ {
1283
+ "epoch": 0.0,
1284
+ "learning_rate": 0.0004,
1285
+ "loss": 6.29,
1286
+ "step": 210
1287
+ },
1288
+ {
1289
+ "epoch": 0.0,
1290
+ "learning_rate": 0.0004,
1291
+ "loss": 7.2105,
1292
+ "step": 211
1293
+ },
1294
+ {
1295
+ "epoch": 0.0,
1296
+ "learning_rate": 0.0004,
1297
+ "loss": 6.1949,
1298
+ "step": 212
1299
+ },
1300
+ {
1301
+ "epoch": 0.0,
1302
+ "learning_rate": 0.0004,
1303
+ "loss": 9.0538,
1304
+ "step": 213
1305
+ },
1306
+ {
1307
+ "epoch": 0.0,
1308
+ "learning_rate": 0.0004,
1309
+ "loss": 8.0343,
1310
+ "step": 214
1311
+ },
1312
+ {
1313
+ "epoch": 0.0,
1314
+ "learning_rate": 0.0004,
1315
+ "loss": 8.7794,
1316
+ "step": 215
1317
+ },
1318
+ {
1319
+ "epoch": 0.0,
1320
+ "learning_rate": 0.0004,
1321
+ "loss": 10.5532,
1322
+ "step": 216
1323
+ },
1324
+ {
1325
+ "epoch": 0.0,
1326
+ "learning_rate": 0.0004,
1327
+ "loss": 7.2676,
1328
+ "step": 217
1329
+ },
1330
+ {
1331
+ "epoch": 0.0,
1332
+ "learning_rate": 0.0004,
1333
+ "loss": 9.566,
1334
+ "step": 218
1335
+ },
1336
+ {
1337
+ "epoch": 0.0,
1338
+ "learning_rate": 0.0004,
1339
+ "loss": 9.0432,
1340
+ "step": 219
1341
+ },
1342
+ {
1343
+ "epoch": 0.0,
1344
+ "learning_rate": 0.0004,
1345
+ "loss": 7.9391,
1346
+ "step": 220
1347
+ },
1348
+ {
1349
+ "epoch": 0.0,
1350
+ "learning_rate": 0.0004,
1351
+ "loss": 7.724,
1352
+ "step": 221
1353
+ },
1354
+ {
1355
+ "epoch": 0.0,
1356
+ "learning_rate": 0.0004,
1357
+ "loss": 7.229,
1358
+ "step": 222
1359
+ },
1360
+ {
1361
+ "epoch": 0.0,
1362
+ "learning_rate": 0.0004,
1363
+ "loss": 8.3462,
1364
+ "step": 223
1365
+ },
1366
+ {
1367
+ "epoch": 0.0,
1368
+ "learning_rate": 0.0004,
1369
+ "loss": 8.0752,
1370
+ "step": 224
1371
+ },
1372
+ {
1373
+ "epoch": 0.0,
1374
+ "learning_rate": 0.0004,
1375
+ "loss": 6.1966,
1376
+ "step": 225
1377
+ },
1378
+ {
1379
+ "epoch": 0.0,
1380
+ "learning_rate": 0.0004,
1381
+ "loss": 7.7279,
1382
+ "step": 226
1383
+ },
1384
+ {
1385
+ "epoch": 0.0,
1386
+ "learning_rate": 0.0004,
1387
+ "loss": 7.8484,
1388
+ "step": 227
1389
+ },
1390
+ {
1391
+ "epoch": 0.0,
1392
+ "learning_rate": 0.0004,
1393
+ "loss": 7.7291,
1394
+ "step": 228
1395
+ },
1396
+ {
1397
+ "epoch": 0.0,
1398
+ "learning_rate": 0.0004,
1399
+ "loss": 4.2665,
1400
+ "step": 229
1401
+ },
1402
+ {
1403
+ "epoch": 0.0,
1404
+ "learning_rate": 0.0004,
1405
+ "loss": 5.3551,
1406
+ "step": 230
1407
+ },
1408
+ {
1409
+ "epoch": 0.0,
1410
+ "learning_rate": 0.0004,
1411
+ "loss": 8.7338,
1412
+ "step": 231
1413
+ },
1414
+ {
1415
+ "epoch": 0.0,
1416
+ "learning_rate": 0.0004,
1417
+ "loss": 6.8407,
1418
+ "step": 232
1419
+ },
1420
+ {
1421
+ "epoch": 0.0,
1422
+ "learning_rate": 0.0004,
1423
+ "loss": 6.3581,
1424
+ "step": 233
1425
+ },
1426
+ {
1427
+ "epoch": 0.0,
1428
+ "learning_rate": 0.0004,
1429
+ "loss": 4.441,
1430
+ "step": 234
1431
+ },
1432
+ {
1433
+ "epoch": 0.0,
1434
+ "learning_rate": 0.0004,
1435
+ "loss": 5.0788,
1436
+ "step": 235
1437
+ },
1438
+ {
1439
+ "epoch": 0.0,
1440
+ "learning_rate": 0.0004,
1441
+ "loss": 6.8404,
1442
+ "step": 236
1443
+ },
1444
+ {
1445
+ "epoch": 0.0,
1446
+ "learning_rate": 0.0004,
1447
+ "loss": 3.4314,
1448
+ "step": 237
1449
+ },
1450
+ {
1451
+ "epoch": 0.0,
1452
+ "learning_rate": 0.0004,
1453
+ "loss": 3.8426,
1454
+ "step": 238
1455
+ },
1456
+ {
1457
+ "epoch": 0.0,
1458
+ "learning_rate": 0.0004,
1459
+ "loss": 2.0205,
1460
+ "step": 239
1461
+ },
1462
+ {
1463
+ "epoch": 0.0,
1464
+ "learning_rate": 0.0004,
1465
+ "loss": 6.4162,
1466
+ "step": 240
1467
+ },
1468
+ {
1469
+ "epoch": 0.0,
1470
+ "learning_rate": 0.0004,
1471
+ "loss": 9.7515,
1472
+ "step": 241
1473
+ },
1474
+ {
1475
+ "epoch": 0.0,
1476
+ "learning_rate": 0.0004,
1477
+ "loss": 9.1442,
1478
+ "step": 242
1479
+ },
1480
+ {
1481
+ "epoch": 0.0,
1482
+ "learning_rate": 0.0004,
1483
+ "loss": 9.5868,
1484
+ "step": 243
1485
+ },
1486
+ {
1487
+ "epoch": 0.0,
1488
+ "learning_rate": 0.0004,
1489
+ "loss": 6.6514,
1490
+ "step": 244
1491
+ },
1492
+ {
1493
+ "epoch": 0.0,
1494
+ "learning_rate": 0.0004,
1495
+ "loss": 7.2683,
1496
+ "step": 245
1497
+ },
1498
+ {
1499
+ "epoch": 0.0,
1500
+ "learning_rate": 0.0004,
1501
+ "loss": 7.31,
1502
+ "step": 246
1503
+ },
1504
+ {
1505
+ "epoch": 0.0,
1506
+ "learning_rate": 0.0004,
1507
+ "loss": 8.0161,
1508
+ "step": 247
1509
+ },
1510
+ {
1511
+ "epoch": 0.0,
1512
+ "learning_rate": 0.0004,
1513
+ "loss": 4.484,
1514
+ "step": 248
1515
+ },
1516
+ {
1517
+ "epoch": 0.0,
1518
+ "learning_rate": 0.0004,
1519
+ "loss": 5.9726,
1520
+ "step": 249
1521
+ },
1522
+ {
1523
+ "epoch": 0.0,
1524
+ "learning_rate": 0.0004,
1525
+ "loss": 3.0926,
1526
+ "step": 250
1527
+ },
1528
+ {
1529
+ "epoch": 0.0,
1530
+ "learning_rate": 0.0004,
1531
+ "loss": 7.5279,
1532
+ "step": 251
1533
+ },
1534
+ {
1535
+ "epoch": 0.0,
1536
+ "learning_rate": 0.0004,
1537
+ "loss": 9.0017,
1538
+ "step": 252
1539
+ },
1540
+ {
1541
+ "epoch": 0.0,
1542
+ "learning_rate": 0.0004,
1543
+ "loss": 7.5684,
1544
+ "step": 253
1545
+ },
1546
+ {
1547
+ "epoch": 0.0,
1548
+ "learning_rate": 0.0004,
1549
+ "loss": 4.3875,
1550
+ "step": 254
1551
+ },
1552
+ {
1553
+ "epoch": 0.0,
1554
+ "learning_rate": 0.0004,
1555
+ "loss": 5.9489,
1556
+ "step": 255
1557
+ },
1558
+ {
1559
+ "epoch": 0.0,
1560
+ "learning_rate": 0.0004,
1561
+ "loss": 9.8948,
1562
+ "step": 256
1563
+ },
1564
+ {
1565
+ "epoch": 0.0,
1566
+ "learning_rate": 0.0004,
1567
+ "loss": 9.0856,
1568
+ "step": 257
1569
+ },
1570
+ {
1571
+ "epoch": 0.0,
1572
+ "learning_rate": 0.0004,
1573
+ "loss": 8.599,
1574
+ "step": 258
1575
+ },
1576
+ {
1577
+ "epoch": 0.0,
1578
+ "learning_rate": 0.0004,
1579
+ "loss": 8.1575,
1580
+ "step": 259
1581
+ },
1582
+ {
1583
+ "epoch": 0.0,
1584
+ "learning_rate": 0.0004,
1585
+ "loss": 8.3701,
1586
+ "step": 260
1587
+ },
1588
+ {
1589
+ "epoch": 0.0,
1590
+ "learning_rate": 0.0004,
1591
+ "loss": 8.464,
1592
+ "step": 261
1593
+ },
1594
+ {
1595
+ "epoch": 0.0,
1596
+ "learning_rate": 0.0004,
1597
+ "loss": 8.9193,
1598
+ "step": 262
1599
+ },
1600
+ {
1601
+ "epoch": 0.0,
1602
+ "learning_rate": 0.0004,
1603
+ "loss": 7.5679,
1604
+ "step": 263
1605
+ },
1606
+ {
1607
+ "epoch": 0.0,
1608
+ "learning_rate": 0.0004,
1609
+ "loss": 7.9424,
1610
+ "step": 264
1611
+ },
1612
+ {
1613
+ "epoch": 0.0,
1614
+ "learning_rate": 0.0004,
1615
+ "loss": 7.6689,
1616
+ "step": 265
1617
+ },
1618
+ {
1619
+ "epoch": 0.0,
1620
+ "learning_rate": 0.0004,
1621
+ "loss": 5.6475,
1622
+ "step": 266
1623
+ },
1624
+ {
1625
+ "epoch": 0.0,
1626
+ "learning_rate": 0.0004,
1627
+ "loss": 8.4311,
1628
+ "step": 267
1629
+ },
1630
+ {
1631
+ "epoch": 0.0,
1632
+ "learning_rate": 0.0004,
1633
+ "loss": 6.7426,
1634
+ "step": 268
1635
+ },
1636
+ {
1637
+ "epoch": 0.0,
1638
+ "learning_rate": 0.0004,
1639
+ "loss": 6.5191,
1640
+ "step": 269
1641
+ },
1642
+ {
1643
+ "epoch": 0.0,
1644
+ "learning_rate": 0.0004,
1645
+ "loss": 8.3059,
1646
+ "step": 270
1647
+ },
1648
+ {
1649
+ "epoch": 0.0,
1650
+ "learning_rate": 0.0004,
1651
+ "loss": 7.0142,
1652
+ "step": 271
1653
+ },
1654
+ {
1655
+ "epoch": 0.0,
1656
+ "learning_rate": 0.0004,
1657
+ "loss": 10.4509,
1658
+ "step": 272
1659
+ },
1660
+ {
1661
+ "epoch": 0.0,
1662
+ "learning_rate": 0.0004,
1663
+ "loss": 10.0831,
1664
+ "step": 273
1665
+ },
1666
+ {
1667
+ "epoch": 0.0,
1668
+ "learning_rate": 0.0004,
1669
+ "loss": 5.6977,
1670
+ "step": 274
1671
+ },
1672
+ {
1673
+ "epoch": 0.0,
1674
+ "learning_rate": 0.0004,
1675
+ "loss": 5.4236,
1676
+ "step": 275
1677
+ },
1678
+ {
1679
+ "epoch": 0.0,
1680
+ "learning_rate": 0.0004,
1681
+ "loss": 7.2129,
1682
+ "step": 276
1683
+ },
1684
+ {
1685
+ "epoch": 0.0,
1686
+ "learning_rate": 0.0004,
1687
+ "loss": 9.1394,
1688
+ "step": 277
1689
+ },
1690
+ {
1691
+ "epoch": 0.0,
1692
+ "learning_rate": 0.0004,
1693
+ "loss": 7.685,
1694
+ "step": 278
1695
+ },
1696
+ {
1697
+ "epoch": 0.0,
1698
+ "learning_rate": 0.0004,
1699
+ "loss": 5.0275,
1700
+ "step": 279
1701
+ },
1702
+ {
1703
+ "epoch": 0.0,
1704
+ "learning_rate": 0.0004,
1705
+ "loss": 11.3215,
1706
+ "step": 280
1707
+ },
1708
+ {
1709
+ "epoch": 0.0,
1710
+ "learning_rate": 0.0004,
1711
+ "loss": 6.6542,
1712
+ "step": 281
1713
+ },
1714
+ {
1715
+ "epoch": 0.0,
1716
+ "learning_rate": 0.0004,
1717
+ "loss": 6.7614,
1718
+ "step": 282
1719
+ },
1720
+ {
1721
+ "epoch": 0.0,
1722
+ "learning_rate": 0.0004,
1723
+ "loss": 6.2996,
1724
+ "step": 283
1725
+ },
1726
+ {
1727
+ "epoch": 0.0,
1728
+ "learning_rate": 0.0004,
1729
+ "loss": 6.6275,
1730
+ "step": 284
1731
+ },
1732
+ {
1733
+ "epoch": 0.0,
1734
+ "learning_rate": 0.0004,
1735
+ "loss": 7.8736,
1736
+ "step": 285
1737
+ },
1738
+ {
1739
+ "epoch": 0.0,
1740
+ "learning_rate": 0.0004,
1741
+ "loss": 9.4667,
1742
+ "step": 286
1743
+ },
1744
+ {
1745
+ "epoch": 0.0,
1746
+ "learning_rate": 0.0004,
1747
+ "loss": 4.8486,
1748
+ "step": 287
1749
+ },
1750
+ {
1751
+ "epoch": 0.0,
1752
+ "learning_rate": 0.0004,
1753
+ "loss": 7.2125,
1754
+ "step": 288
1755
+ },
1756
+ {
1757
+ "epoch": 0.0,
1758
+ "learning_rate": 0.0004,
1759
+ "loss": 8.4523,
1760
+ "step": 289
1761
+ },
1762
+ {
1763
+ "epoch": 0.0,
1764
+ "learning_rate": 0.0004,
1765
+ "loss": 5.551,
1766
+ "step": 290
1767
+ },
1768
+ {
1769
+ "epoch": 0.0,
1770
+ "learning_rate": 0.0004,
1771
+ "loss": 11.7158,
1772
+ "step": 291
1773
+ },
1774
+ {
1775
+ "epoch": 0.0,
1776
+ "learning_rate": 0.0004,
1777
+ "loss": 3.5092,
1778
+ "step": 292
1779
+ },
1780
+ {
1781
+ "epoch": 0.0,
1782
+ "learning_rate": 0.0004,
1783
+ "loss": 7.9169,
1784
+ "step": 293
1785
+ },
1786
+ {
1787
+ "epoch": 0.0,
1788
+ "learning_rate": 0.0004,
1789
+ "loss": 3.5333,
1790
+ "step": 294
1791
+ },
1792
+ {
1793
+ "epoch": 0.0,
1794
+ "learning_rate": 0.0004,
1795
+ "loss": 7.9949,
1796
+ "step": 295
1797
+ },
1798
+ {
1799
+ "epoch": 0.0,
1800
+ "learning_rate": 0.0004,
1801
+ "loss": 2.7189,
1802
+ "step": 296
1803
+ },
1804
+ {
1805
+ "epoch": 0.0,
1806
+ "learning_rate": 0.0004,
1807
+ "loss": 9.2366,
1808
+ "step": 297
1809
+ },
1810
+ {
1811
+ "epoch": 0.0,
1812
+ "learning_rate": 0.0004,
1813
+ "loss": 8.4745,
1814
+ "step": 298
1815
+ },
1816
+ {
1817
+ "epoch": 0.0,
1818
+ "learning_rate": 0.0004,
1819
+ "loss": 5.2439,
1820
+ "step": 299
1821
+ },
1822
+ {
1823
+ "epoch": 0.0,
1824
+ "learning_rate": 0.0004,
1825
+ "loss": 6.4176,
1826
+ "step": 300
1827
+ },
1828
+ {
1829
+ "epoch": 0.0,
1830
+ "learning_rate": 0.0004,
1831
+ "loss": 10.9365,
1832
+ "step": 301
1833
+ },
1834
+ {
1835
+ "epoch": 0.0,
1836
+ "learning_rate": 0.0004,
1837
+ "loss": 9.5309,
1838
+ "step": 302
1839
+ },
1840
+ {
1841
+ "epoch": 0.0,
1842
+ "learning_rate": 0.0004,
1843
+ "loss": 7.2201,
1844
+ "step": 303
1845
+ },
1846
+ {
1847
+ "epoch": 0.0,
1848
+ "learning_rate": 0.0004,
1849
+ "loss": 10.0312,
1850
+ "step": 304
1851
+ },
1852
+ {
1853
+ "epoch": 0.0,
1854
+ "learning_rate": 0.0004,
1855
+ "loss": 8.4173,
1856
+ "step": 305
1857
+ },
1858
+ {
1859
+ "epoch": 0.0,
1860
+ "learning_rate": 0.0004,
1861
+ "loss": 7.4856,
1862
+ "step": 306
1863
+ },
1864
+ {
1865
+ "epoch": 0.0,
1866
+ "learning_rate": 0.0004,
1867
+ "loss": 7.5041,
1868
+ "step": 307
1869
+ },
1870
+ {
1871
+ "epoch": 0.0,
1872
+ "learning_rate": 0.0004,
1873
+ "loss": 5.3597,
1874
+ "step": 308
1875
+ },
1876
+ {
1877
+ "epoch": 0.0,
1878
+ "learning_rate": 0.0004,
1879
+ "loss": 5.8395,
1880
+ "step": 309
1881
+ },
1882
+ {
1883
+ "epoch": 0.0,
1884
+ "learning_rate": 0.0004,
1885
+ "loss": 7.0776,
1886
+ "step": 310
1887
+ },
1888
+ {
1889
+ "epoch": 0.0,
1890
+ "learning_rate": 0.0004,
1891
+ "loss": 6.7566,
1892
+ "step": 311
1893
+ },
1894
+ {
1895
+ "epoch": 0.0,
1896
+ "learning_rate": 0.0004,
1897
+ "loss": 6.9767,
1898
+ "step": 312
1899
+ },
1900
+ {
1901
+ "epoch": 0.0,
1902
+ "learning_rate": 0.0004,
1903
+ "loss": 5.3804,
1904
+ "step": 313
1905
+ },
1906
+ {
1907
+ "epoch": 0.0,
1908
+ "learning_rate": 0.0004,
1909
+ "loss": 11.5327,
1910
+ "step": 314
1911
+ },
1912
+ {
1913
+ "epoch": 0.0,
1914
+ "learning_rate": 0.0004,
1915
+ "loss": 10.5293,
1916
+ "step": 315
1917
+ },
1918
+ {
1919
+ "epoch": 0.0,
1920
+ "learning_rate": 0.0004,
1921
+ "loss": 6.4531,
1922
+ "step": 316
1923
+ },
1924
+ {
1925
+ "epoch": 0.0,
1926
+ "learning_rate": 0.0004,
1927
+ "loss": 6.3961,
1928
+ "step": 317
1929
+ },
1930
+ {
1931
+ "epoch": 0.0,
1932
+ "learning_rate": 0.0004,
1933
+ "loss": 8.5669,
1934
+ "step": 318
1935
+ },
1936
+ {
1937
+ "epoch": 0.0,
1938
+ "learning_rate": 0.0004,
1939
+ "loss": 8.8559,
1940
+ "step": 319
1941
+ },
1942
+ {
1943
+ "epoch": 0.0,
1944
+ "learning_rate": 0.0004,
1945
+ "loss": 8.117,
1946
+ "step": 320
1947
+ },
1948
+ {
1949
+ "epoch": 0.0,
1950
+ "learning_rate": 0.0004,
1951
+ "loss": 7.4279,
1952
+ "step": 321
1953
+ },
1954
+ {
1955
+ "epoch": 0.0,
1956
+ "learning_rate": 0.0004,
1957
+ "loss": 8.7977,
1958
+ "step": 322
1959
+ },
1960
+ {
1961
+ "epoch": 0.0,
1962
+ "learning_rate": 0.0004,
1963
+ "loss": 4.955,
1964
+ "step": 323
1965
+ },
1966
+ {
1967
+ "epoch": 0.0,
1968
+ "learning_rate": 0.0004,
1969
+ "loss": 8.0164,
1970
+ "step": 324
1971
+ },
1972
+ {
1973
+ "epoch": 0.0,
1974
+ "learning_rate": 0.0004,
1975
+ "loss": 12.0495,
1976
+ "step": 325
1977
+ },
1978
+ {
1979
+ "epoch": 0.0,
1980
+ "learning_rate": 0.0004,
1981
+ "loss": 6.2768,
1982
+ "step": 326
1983
+ },
1984
+ {
1985
+ "epoch": 0.0,
1986
+ "learning_rate": 0.0004,
1987
+ "loss": 8.3162,
1988
+ "step": 327
1989
+ },
1990
+ {
1991
+ "epoch": 0.0,
1992
+ "learning_rate": 0.0004,
1993
+ "loss": 6.88,
1994
+ "step": 328
1995
+ },
1996
+ {
1997
+ "epoch": 0.0,
1998
+ "learning_rate": 0.0004,
1999
+ "loss": 9.2157,
2000
+ "step": 329
2001
+ },
2002
+ {
2003
+ "epoch": 0.0,
2004
+ "learning_rate": 0.0004,
2005
+ "loss": 5.8427,
2006
+ "step": 330
2007
+ },
2008
+ {
2009
+ "epoch": 0.0,
2010
+ "learning_rate": 0.0004,
2011
+ "loss": 9.9729,
2012
+ "step": 331
2013
+ },
2014
+ {
2015
+ "epoch": 0.0,
2016
+ "learning_rate": 0.0004,
2017
+ "loss": 5.1779,
2018
+ "step": 332
2019
+ },
2020
+ {
2021
+ "epoch": 0.0,
2022
+ "learning_rate": 0.0004,
2023
+ "loss": 7.1302,
2024
+ "step": 333
2025
+ },
2026
+ {
2027
+ "epoch": 0.0,
2028
+ "learning_rate": 0.0004,
2029
+ "loss": 7.7705,
2030
+ "step": 334
2031
+ },
2032
+ {
2033
+ "epoch": 0.0,
2034
+ "learning_rate": 0.0004,
2035
+ "loss": 7.523,
2036
+ "step": 335
2037
+ },
2038
+ {
2039
+ "epoch": 0.0,
2040
+ "learning_rate": 0.0004,
2041
+ "loss": 7.9375,
2042
+ "step": 336
2043
+ },
2044
+ {
2045
+ "epoch": 0.0,
2046
+ "learning_rate": 0.0004,
2047
+ "loss": 10.1409,
2048
+ "step": 337
2049
+ },
2050
+ {
2051
+ "epoch": 0.0,
2052
+ "learning_rate": 0.0004,
2053
+ "loss": 4.633,
2054
+ "step": 338
2055
+ },
2056
+ {
2057
+ "epoch": 0.0,
2058
+ "learning_rate": 0.0004,
2059
+ "loss": 6.6481,
2060
+ "step": 339
2061
+ },
2062
+ {
2063
+ "epoch": 0.0,
2064
+ "learning_rate": 0.0004,
2065
+ "loss": 5.933,
2066
+ "step": 340
2067
+ },
2068
+ {
2069
+ "epoch": 0.0,
2070
+ "learning_rate": 0.0004,
2071
+ "loss": 3.9179,
2072
+ "step": 341
2073
+ },
2074
+ {
2075
+ "epoch": 0.0,
2076
+ "learning_rate": 0.0004,
2077
+ "loss": 6.9332,
2078
+ "step": 342
2079
+ },
2080
+ {
2081
+ "epoch": 0.0,
2082
+ "learning_rate": 0.0004,
2083
+ "loss": 7.6553,
2084
+ "step": 343
2085
+ },
2086
+ {
2087
+ "epoch": 0.0,
2088
+ "learning_rate": 0.0004,
2089
+ "loss": 5.7412,
2090
+ "step": 344
2091
+ },
2092
+ {
2093
+ "epoch": 0.0,
2094
+ "learning_rate": 0.0004,
2095
+ "loss": 6.849,
2096
+ "step": 345
2097
+ },
2098
+ {
2099
+ "epoch": 0.0,
2100
+ "learning_rate": 0.0004,
2101
+ "loss": 4.7321,
2102
+ "step": 346
2103
+ },
2104
+ {
2105
+ "epoch": 0.0,
2106
+ "learning_rate": 0.0004,
2107
+ "loss": 8.9717,
2108
+ "step": 347
2109
+ },
2110
+ {
2111
+ "epoch": 0.0,
2112
+ "learning_rate": 0.0004,
2113
+ "loss": 4.3465,
2114
+ "step": 348
2115
+ },
2116
+ {
2117
+ "epoch": 0.0,
2118
+ "learning_rate": 0.0004,
2119
+ "loss": 6.4535,
2120
+ "step": 349
2121
+ },
2122
+ {
2123
+ "epoch": 0.0,
2124
+ "learning_rate": 0.0004,
2125
+ "loss": 4.2376,
2126
+ "step": 350
2127
+ },
2128
+ {
2129
+ "epoch": 0.0,
2130
+ "learning_rate": 0.0004,
2131
+ "loss": 7.9025,
2132
+ "step": 351
2133
+ },
2134
+ {
2135
+ "epoch": 0.0,
2136
+ "learning_rate": 0.0004,
2137
+ "loss": 5.916,
2138
+ "step": 352
2139
+ },
2140
+ {
2141
+ "epoch": 0.0,
2142
+ "learning_rate": 0.0004,
2143
+ "loss": 10.3785,
2144
+ "step": 353
2145
+ },
2146
+ {
2147
+ "epoch": 0.0,
2148
+ "learning_rate": 0.0004,
2149
+ "loss": 8.0576,
2150
+ "step": 354
2151
+ },
2152
+ {
2153
+ "epoch": 0.0,
2154
+ "learning_rate": 0.0004,
2155
+ "loss": 9.5081,
2156
+ "step": 355
2157
+ },
2158
+ {
2159
+ "epoch": 0.0,
2160
+ "learning_rate": 0.0004,
2161
+ "loss": 8.1303,
2162
+ "step": 356
2163
+ },
2164
+ {
2165
+ "epoch": 0.0,
2166
+ "learning_rate": 0.0004,
2167
+ "loss": 4.3854,
2168
+ "step": 357
2169
+ },
2170
+ {
2171
+ "epoch": 0.0,
2172
+ "learning_rate": 0.0004,
2173
+ "loss": 11.5553,
2174
+ "step": 358
2175
+ },
2176
+ {
2177
+ "epoch": 0.0,
2178
+ "learning_rate": 0.0004,
2179
+ "loss": 8.9627,
2180
+ "step": 359
2181
+ },
2182
+ {
2183
+ "epoch": 0.0,
2184
+ "learning_rate": 0.0004,
2185
+ "loss": 6.402,
2186
+ "step": 360
2187
+ },
2188
+ {
2189
+ "epoch": 0.0,
2190
+ "learning_rate": 0.0004,
2191
+ "loss": 7.3484,
2192
+ "step": 361
2193
+ },
2194
+ {
2195
+ "epoch": 0.0,
2196
+ "learning_rate": 0.0004,
2197
+ "loss": 9.5428,
2198
+ "step": 362
2199
+ },
2200
+ {
2201
+ "epoch": 0.0,
2202
+ "learning_rate": 0.0004,
2203
+ "loss": 8.9128,
2204
+ "step": 363
2205
+ },
2206
+ {
2207
+ "epoch": 0.0,
2208
+ "learning_rate": 0.0004,
2209
+ "loss": 7.3934,
2210
+ "step": 364
2211
+ },
2212
+ {
2213
+ "epoch": 0.0,
2214
+ "learning_rate": 0.0004,
2215
+ "loss": 5.4812,
2216
+ "step": 365
2217
+ },
2218
+ {
2219
+ "epoch": 0.0,
2220
+ "learning_rate": 0.0004,
2221
+ "loss": 8.5395,
2222
+ "step": 366
2223
+ },
2224
+ {
2225
+ "epoch": 0.0,
2226
+ "learning_rate": 0.0004,
2227
+ "loss": 6.6304,
2228
+ "step": 367
2229
+ },
2230
+ {
2231
+ "epoch": 0.0,
2232
+ "learning_rate": 0.0004,
2233
+ "loss": 4.5626,
2234
+ "step": 368
2235
+ },
2236
+ {
2237
+ "epoch": 0.0,
2238
+ "learning_rate": 0.0004,
2239
+ "loss": 10.5693,
2240
+ "step": 369
2241
+ },
2242
+ {
2243
+ "epoch": 0.0,
2244
+ "learning_rate": 0.0004,
2245
+ "loss": 8.3458,
2246
+ "step": 370
2247
+ },
2248
+ {
2249
+ "epoch": 0.0,
2250
+ "learning_rate": 0.0004,
2251
+ "loss": 8.6254,
2252
+ "step": 371
2253
+ },
2254
+ {
2255
+ "epoch": 0.0,
2256
+ "learning_rate": 0.0004,
2257
+ "loss": 7.8706,
2258
+ "step": 372
2259
+ },
2260
+ {
2261
+ "epoch": 0.0,
2262
+ "learning_rate": 0.0004,
2263
+ "loss": 7.6076,
2264
+ "step": 373
2265
+ },
2266
+ {
2267
+ "epoch": 0.0,
2268
+ "learning_rate": 0.0004,
2269
+ "loss": 3.2912,
2270
+ "step": 374
2271
+ },
2272
+ {
2273
+ "epoch": 0.0,
2274
+ "learning_rate": 0.0004,
2275
+ "loss": 6.3326,
2276
+ "step": 375
2277
+ },
2278
+ {
2279
+ "epoch": 0.0,
2280
+ "learning_rate": 0.0004,
2281
+ "loss": 4.3735,
2282
+ "step": 376
2283
+ },
2284
+ {
2285
+ "epoch": 0.0,
2286
+ "learning_rate": 0.0004,
2287
+ "loss": 5.4916,
2288
+ "step": 377
2289
+ },
2290
+ {
2291
+ "epoch": 0.0,
2292
+ "learning_rate": 0.0004,
2293
+ "loss": 3.5553,
2294
+ "step": 378
2295
+ },
2296
+ {
2297
+ "epoch": 0.0,
2298
+ "learning_rate": 0.0004,
2299
+ "loss": 7.6241,
2300
+ "step": 379
2301
+ },
2302
+ {
2303
+ "epoch": 0.0,
2304
+ "learning_rate": 0.0004,
2305
+ "loss": 6.6106,
2306
+ "step": 380
2307
+ },
2308
+ {
2309
+ "epoch": 0.0,
2310
+ "learning_rate": 0.0004,
2311
+ "loss": 9.266,
2312
+ "step": 381
2313
+ },
2314
+ {
2315
+ "epoch": 0.0,
2316
+ "learning_rate": 0.0004,
2317
+ "loss": 7.7738,
2318
+ "step": 382
2319
+ },
2320
+ {
2321
+ "epoch": 0.0,
2322
+ "learning_rate": 0.0004,
2323
+ "loss": 5.4988,
2324
+ "step": 383
2325
+ },
2326
+ {
2327
+ "epoch": 0.0,
2328
+ "learning_rate": 0.0004,
2329
+ "loss": 7.2968,
2330
+ "step": 384
2331
+ },
2332
+ {
2333
+ "epoch": 0.0,
2334
+ "learning_rate": 0.0004,
2335
+ "loss": 6.8512,
2336
+ "step": 385
2337
+ },
2338
+ {
2339
+ "epoch": 0.0,
2340
+ "learning_rate": 0.0004,
2341
+ "loss": 8.0341,
2342
+ "step": 386
2343
+ },
2344
+ {
2345
+ "epoch": 0.0,
2346
+ "learning_rate": 0.0004,
2347
+ "loss": 4.898,
2348
+ "step": 387
2349
+ },
2350
+ {
2351
+ "epoch": 0.0,
2352
+ "learning_rate": 0.0004,
2353
+ "loss": 5.23,
2354
+ "step": 388
2355
+ },
2356
+ {
2357
+ "epoch": 0.0,
2358
+ "learning_rate": 0.0004,
2359
+ "loss": 4.9608,
2360
+ "step": 389
2361
+ },
2362
+ {
2363
+ "epoch": 0.0,
2364
+ "learning_rate": 0.0004,
2365
+ "loss": 3.3679,
2366
+ "step": 390
2367
+ },
2368
+ {
2369
+ "epoch": 0.0,
2370
+ "learning_rate": 0.0004,
2371
+ "loss": 2.7074,
2372
+ "step": 391
2373
+ },
2374
+ {
2375
+ "epoch": 0.0,
2376
+ "learning_rate": 0.0004,
2377
+ "loss": 8.9903,
2378
+ "step": 392
2379
+ },
2380
+ {
2381
+ "epoch": 0.0,
2382
+ "learning_rate": 0.0004,
2383
+ "loss": 7.5845,
2384
+ "step": 393
2385
+ },
2386
+ {
2387
+ "epoch": 0.0,
2388
+ "learning_rate": 0.0004,
2389
+ "loss": 8.6493,
2390
+ "step": 394
2391
+ },
2392
+ {
2393
+ "epoch": 0.0,
2394
+ "learning_rate": 0.0004,
2395
+ "loss": 7.7962,
2396
+ "step": 395
2397
+ },
2398
+ {
2399
+ "epoch": 0.0,
2400
+ "learning_rate": 0.0004,
2401
+ "loss": 6.4865,
2402
+ "step": 396
2403
+ },
2404
+ {
2405
+ "epoch": 0.0,
2406
+ "learning_rate": 0.0004,
2407
+ "loss": 8.3418,
2408
+ "step": 397
2409
+ },
2410
+ {
2411
+ "epoch": 0.0,
2412
+ "learning_rate": 0.0004,
2413
+ "loss": 8.3942,
2414
+ "step": 398
2415
+ },
2416
+ {
2417
+ "epoch": 0.0,
2418
+ "learning_rate": 0.0004,
2419
+ "loss": 3.4715,
2420
+ "step": 399
2421
+ },
2422
+ {
2423
+ "epoch": 0.0,
2424
+ "learning_rate": 0.0004,
2425
+ "loss": 4.2073,
2426
+ "step": 400
2427
+ },
2428
+ {
2429
+ "epoch": 0.0,
2430
+ "eval_loss": 7.106412410736084,
2431
+ "eval_runtime": 22.5667,
2432
+ "eval_samples_per_second": 2.216,
2433
+ "eval_steps_per_second": 1.108,
2434
+ "step": 400
2435
+ },
2436
+ {
2437
+ "epoch": 0.0,
2438
+ "mmlu_eval_accuracy": 0.2525477994227994,
2439
+ "mmlu_eval_accuracy_abstract_algebra": 0.18181818181818182,
2440
+ "mmlu_eval_accuracy_anatomy": 0.07142857142857142,
2441
+ "mmlu_eval_accuracy_astronomy": 0.3125,
2442
+ "mmlu_eval_accuracy_business_ethics": 0.4444444444444444,
2443
+ "mmlu_loss": 2.9128687667846678,
2444
+ "step": 400
2445
+ }
2446
+ ],
2447
+ "max_steps": 30000,
2448
+ "num_train_epochs": 1,
2449
+ "total_flos": 6768426179887104.0,
2450
+ "trial_name": null,
2451
+ "trial_params": null
2452
+ }
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2493c95326c359fb00f88976162bc7966690beaaca22964b91c1db649a04988f
3
+ size 6011