Hugging Face's logo

minmingzhu02
/
Mistral-7B-v0.1-habana-lora

PEFT
TensorBoard
Safetensors
Habana
Model card Files Metrics Community
minmingzhu02 commited on
Commit
1156297
·
verified ·
1 Parent(s): 8c2b929

Upload folder using huggingface_hub

Browse files
Files changed (30) hide show
  1. README.md +1 -0
  2. adapter_config.json +3 -1
  3. adapter_model.safetensors +2 -2
  4. all_results.json +13 -13
  5. checkpoint-1000/README.md +9 -0
  6. checkpoint-1000/adapter_config.json +23 -0
  7. checkpoint-1000/adapter_model.safetensors +3 -0
  8. checkpoint-1000/gaudi_config.json +10 -0
  9. checkpoint-1000/optimizer.pt +3 -0
  10. checkpoint-1000/rng_state_0.pth +3 -0
  11. checkpoint-1000/rng_state_1.pth +3 -0
  12. checkpoint-1000/rng_state_2.pth +3 -0
  13. checkpoint-1000/rng_state_3.pth +3 -0
  14. checkpoint-1000/rng_state_4.pth +3 -0
  15. checkpoint-1000/rng_state_5.pth +3 -0
  16. checkpoint-1000/rng_state_6.pth +3 -0
  17. checkpoint-1000/rng_state_7.pth +3 -0
  18. checkpoint-1000/scheduler.pt +3 -0
  19. checkpoint-1000/special_tokens_map.json +12 -0
  20. checkpoint-1000/tokenizer.json +0 -0
  21. checkpoint-1000/tokenizer.model +3 -0
  22. checkpoint-1000/tokenizer_config.json +42 -0
  23. checkpoint-1000/trainer_state.json +1021 -0
  24. checkpoint-1000/training_args.bin +3 -0
  25. eval_results.json +9 -9
  26. runs/Jun05_02-37-29_9d340316bc35/events.out.tfevents.1717556360.9d340316bc35.1970.0 +3 -0
  27. runs/Jun05_03-27-04_9d340316bc35/events.out.tfevents.1717559330.9d340316bc35.8193.0 +3 -0
  28. runs/Jun05_03-27-04_9d340316bc35/events.out.tfevents.1717565888.9d340316bc35.8193.1 +3 -0
  29. train_results.json +7 -7
  30. training_args.bin +1 -1
README.md CHANGED
@@ -5,5 +5,6 @@ library_name: peft
5
 
6
  ### Framework versions
7
 
 
8
 
9
  - PEFT 0.4.0
 
5
 
6
  ### Framework versions
7
 
8
+ - PEFT 0.4.0
9
 
10
  - PEFT 0.4.0
adapter_config.json CHANGED
@@ -15,7 +15,9 @@
15
  "revision": null,
16
  "target_modules": [
17
  "q_proj",
18
- "v_proj"
 
 
19
  ],
20
  "task_type": "CAUSAL_LM"
21
  }
 
15
  "revision": null,
16
  "target_modules": [
17
  "q_proj",
18
+ "v_proj",
19
+ "o_proj",
20
+ "k_proj"
21
  ],
22
  "task_type": "CAUSAL_LM"
23
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e5e6f12137445a7824c154a682d97f46030c9f7bb5987a97293f75617cc5b7b
3
- size 6832728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae2baae2caa1c84747f772e81443c4650e7672c82fd76636f3126afa569f83f
3
+ size 13665592
all_results.json CHANGED
@@ -1,17 +1,17 @@
1
  {
2
- "epoch": 3.0,
3
- "eval_accuracy": 0.4639155611944004,
4
- "eval_loss": 1.0861796140670776,
5
- "eval_runtime": 144.8,
6
  "eval_samples": 25899,
7
- "eval_samples_per_second": 183.416,
8
- "eval_steps_per_second": 2.868,
9
- "max_memory_allocated (GB)": 91.29,
10
- "memory_allocated (GB)": 20.51,
11
- "perplexity": 2.96293287540469,
12
  "total_memory_available (GB)": 94.62,
13
- "train_loss": 1.0007781735929895,
14
- "train_runtime": 10023.6622,
15
- "train_samples_per_second": 148.487,
16
- "train_steps_per_second": 1.16
17
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "eval_accuracy": 0.45881899043469254,
4
+ "eval_loss": 1.125322937965393,
5
+ "eval_runtime": 146.7119,
6
  "eval_samples": 25899,
7
+ "eval_samples_per_second": 181.966,
8
+ "eval_steps_per_second": 2.846,
9
+ "max_memory_allocated (GB)": 92.9,
10
+ "memory_allocated (GB)": 20.53,
11
+ "perplexity": 3.08121172851374,
12
  "total_memory_available (GB)": 94.62,
13
+ "train_loss": 1.0511445318126778,
14
+ "train_runtime": 6406.9638,
15
+ "train_samples_per_second": 157.111,
16
+ "train_steps_per_second": 0.307
17
  }
checkpoint-1000/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
checkpoint-1000/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
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,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj",
19
+ "o_proj",
20
+ "k_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-1000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4509af98b4f6e2b60b6f6fd928f4d0ae5c324b97b94c0a79ea7f5cdef43c1e
3
+ size 13665592
checkpoint-1000/gaudi_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "autocast_bf16_ops": null,
3
+ "autocast_fp32_ops": null,
4
+ "optimum_version": "1.20.0",
5
+ "transformers_version": "4.38.2",
6
+ "use_dynamic_shapes": false,
7
+ "use_fused_adam": true,
8
+ "use_fused_clip_norm": true,
9
+ "use_torch_autocast": false
10
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b55b396bfded23346ea3fb31116105e6b11cd9db3fd2061f92418263bac939eb
3
+ size 27390650
checkpoint-1000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da3853db45e30a134bde6283db65f4d2e12b4f06b534a780433dd598db8504cb
3
+ size 18032
checkpoint-1000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0664a5f5d0f31c8412dfa2b9c211689c20cc952d4ce4660ee1761e2ec10776d
3
+ size 18032
checkpoint-1000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8418b1622ae3a1586b0d267b3c8c1d9d5d403a56cc73434016d717b501b2c0fd
3
+ size 18032
checkpoint-1000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d300bdb34d5407f13acbfb278589f1a2907891fba4e020420c6053746cf8e2
3
+ size 18032
checkpoint-1000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d597fad31002fa89ec1fd8aefe8f76311a32275c74a84439354f630b9b001a4
3
+ size 18032
checkpoint-1000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbf5d648175322bc9d62f67af45fa2e710bdc93b49adb768d8df629d2b0347f
3
+ size 18032
checkpoint-1000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcfd1907de0ce290b15c0e3cda02ca34b46efde1a255be0c9b8e383cbf93e363
3
+ size 18032
checkpoint-1000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a4d45767ae6a4db5ed86b012add567287d0976c731678dabe7dedeb253ea63b
3
+ size 18032
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb125488ec048d326b467028b2637f3a517fd69860afde5a492fab4e9b1be668
3
+ size 1000
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ }
12
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,1021 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0404473923787227,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 0.9921875,
14
+ "learning_rate": 1.7241379310344828e-05,
15
+ "loss": 1.8089,
16
+ "max_memory_allocated (GB)": 92.84,
17
+ "memory_allocated (GB)": 20.53,
18
+ "step": 10,
19
+ "total_memory_available (GB)": 94.62
20
+ },
21
+ {
22
+ "epoch": 0.02,
23
+ "grad_norm": 0.7890625,
24
+ "learning_rate": 3.4482758620689657e-05,
25
+ "loss": 1.7328,
26
+ "max_memory_allocated (GB)": 92.85,
27
+ "memory_allocated (GB)": 20.53,
28
+ "step": 20,
29
+ "total_memory_available (GB)": 94.62
30
+ },
31
+ {
32
+ "epoch": 0.03,
33
+ "grad_norm": 0.66015625,
34
+ "learning_rate": 5.172413793103449e-05,
35
+ "loss": 1.5707,
36
+ "max_memory_allocated (GB)": 92.87,
37
+ "memory_allocated (GB)": 20.53,
38
+ "step": 30,
39
+ "total_memory_available (GB)": 94.62
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "grad_norm": 0.57421875,
44
+ "learning_rate": 6.896551724137931e-05,
45
+ "loss": 1.3808,
46
+ "max_memory_allocated (GB)": 92.87,
47
+ "memory_allocated (GB)": 20.53,
48
+ "step": 40,
49
+ "total_memory_available (GB)": 94.62
50
+ },
51
+ {
52
+ "epoch": 0.05,
53
+ "grad_norm": 0.37890625,
54
+ "learning_rate": 8.620689655172413e-05,
55
+ "loss": 1.3155,
56
+ "max_memory_allocated (GB)": 92.87,
57
+ "memory_allocated (GB)": 20.53,
58
+ "step": 50,
59
+ "total_memory_available (GB)": 94.62
60
+ },
61
+ {
62
+ "epoch": 0.06,
63
+ "grad_norm": 0.23046875,
64
+ "learning_rate": 9.999971594167742e-05,
65
+ "loss": 1.2608,
66
+ "max_memory_allocated (GB)": 92.87,
67
+ "memory_allocated (GB)": 20.53,
68
+ "step": 60,
69
+ "total_memory_available (GB)": 94.62
70
+ },
71
+ {
72
+ "epoch": 0.07,
73
+ "grad_norm": 0.41015625,
74
+ "learning_rate": 9.998977423927714e-05,
75
+ "loss": 1.2335,
76
+ "max_memory_allocated (GB)": 92.88,
77
+ "memory_allocated (GB)": 20.53,
78
+ "step": 70,
79
+ "total_memory_available (GB)": 94.62
80
+ },
81
+ {
82
+ "epoch": 0.08,
83
+ "grad_norm": 0.373046875,
84
+ "learning_rate": 9.996563284814788e-05,
85
+ "loss": 1.1979,
86
+ "max_memory_allocated (GB)": 92.88,
87
+ "memory_allocated (GB)": 20.53,
88
+ "step": 80,
89
+ "total_memory_available (GB)": 94.62
90
+ },
91
+ {
92
+ "epoch": 0.09,
93
+ "grad_norm": 0.34375,
94
+ "learning_rate": 9.992729862569695e-05,
95
+ "loss": 1.1849,
96
+ "max_memory_allocated (GB)": 92.88,
97
+ "memory_allocated (GB)": 20.53,
98
+ "step": 90,
99
+ "total_memory_available (GB)": 94.62
100
+ },
101
+ {
102
+ "epoch": 0.1,
103
+ "grad_norm": 0.291015625,
104
+ "learning_rate": 9.987478246083175e-05,
105
+ "loss": 1.1664,
106
+ "max_memory_allocated (GB)": 92.88,
107
+ "memory_allocated (GB)": 20.53,
108
+ "step": 100,
109
+ "total_memory_available (GB)": 94.62
110
+ },
111
+ {
112
+ "epoch": 0.11,
113
+ "grad_norm": 0.41015625,
114
+ "learning_rate": 9.980809927086704e-05,
115
+ "loss": 1.1494,
116
+ "max_memory_allocated (GB)": 92.88,
117
+ "memory_allocated (GB)": 20.53,
118
+ "step": 110,
119
+ "total_memory_available (GB)": 94.62
120
+ },
121
+ {
122
+ "epoch": 0.12,
123
+ "grad_norm": 0.421875,
124
+ "learning_rate": 9.972726799728744e-05,
125
+ "loss": 1.1468,
126
+ "max_memory_allocated (GB)": 92.88,
127
+ "memory_allocated (GB)": 20.53,
128
+ "step": 120,
129
+ "total_memory_available (GB)": 94.62
130
+ },
131
+ {
132
+ "epoch": 0.14,
133
+ "grad_norm": 0.337890625,
134
+ "learning_rate": 9.963231160036714e-05,
135
+ "loss": 1.1467,
136
+ "max_memory_allocated (GB)": 92.88,
137
+ "memory_allocated (GB)": 20.53,
138
+ "step": 130,
139
+ "total_memory_available (GB)": 94.62
140
+ },
141
+ {
142
+ "epoch": 0.15,
143
+ "grad_norm": 0.36328125,
144
+ "learning_rate": 9.952325705264806e-05,
145
+ "loss": 1.1432,
146
+ "max_memory_allocated (GB)": 92.88,
147
+ "memory_allocated (GB)": 20.53,
148
+ "step": 140,
149
+ "total_memory_available (GB)": 94.62
150
+ },
151
+ {
152
+ "epoch": 0.16,
153
+ "grad_norm": 0.384765625,
154
+ "learning_rate": 9.940013533127812e-05,
155
+ "loss": 1.1268,
156
+ "max_memory_allocated (GB)": 92.88,
157
+ "memory_allocated (GB)": 20.53,
158
+ "step": 150,
159
+ "total_memory_available (GB)": 94.62
160
+ },
161
+ {
162
+ "epoch": 0.17,
163
+ "grad_norm": 0.3515625,
164
+ "learning_rate": 9.926298140921221e-05,
165
+ "loss": 1.1197,
166
+ "max_memory_allocated (GB)": 92.88,
167
+ "memory_allocated (GB)": 20.53,
168
+ "step": 160,
169
+ "total_memory_available (GB)": 94.62
170
+ },
171
+ {
172
+ "epoch": 0.18,
173
+ "grad_norm": 0.365234375,
174
+ "learning_rate": 9.911183424527801e-05,
175
+ "loss": 1.1022,
176
+ "max_memory_allocated (GB)": 92.88,
177
+ "memory_allocated (GB)": 20.53,
178
+ "step": 170,
179
+ "total_memory_available (GB)": 94.62
180
+ },
181
+ {
182
+ "epoch": 0.19,
183
+ "grad_norm": 0.421875,
184
+ "learning_rate": 9.894673677310972e-05,
185
+ "loss": 1.0934,
186
+ "max_memory_allocated (GB)": 92.88,
187
+ "memory_allocated (GB)": 20.53,
188
+ "step": 180,
189
+ "total_memory_available (GB)": 94.62
190
+ },
191
+ {
192
+ "epoch": 0.2,
193
+ "grad_norm": 0.439453125,
194
+ "learning_rate": 9.876773588895265e-05,
195
+ "loss": 1.0925,
196
+ "max_memory_allocated (GB)": 92.88,
197
+ "memory_allocated (GB)": 20.53,
198
+ "step": 190,
199
+ "total_memory_available (GB)": 94.62
200
+ },
201
+ {
202
+ "epoch": 0.21,
203
+ "grad_norm": 0.478515625,
204
+ "learning_rate": 9.857488243834219e-05,
205
+ "loss": 1.1038,
206
+ "max_memory_allocated (GB)": 92.88,
207
+ "memory_allocated (GB)": 20.53,
208
+ "step": 200,
209
+ "total_memory_available (GB)": 94.62
210
+ },
211
+ {
212
+ "epoch": 0.22,
213
+ "grad_norm": 0.404296875,
214
+ "learning_rate": 9.836823120166116e-05,
215
+ "loss": 1.0926,
216
+ "max_memory_allocated (GB)": 92.88,
217
+ "memory_allocated (GB)": 20.53,
218
+ "step": 210,
219
+ "total_memory_available (GB)": 94.62
220
+ },
221
+ {
222
+ "epoch": 0.23,
223
+ "grad_norm": 0.5,
224
+ "learning_rate": 9.814784087857927e-05,
225
+ "loss": 1.0955,
226
+ "max_memory_allocated (GB)": 92.88,
227
+ "memory_allocated (GB)": 20.53,
228
+ "step": 220,
229
+ "total_memory_available (GB)": 94.62
230
+ },
231
+ {
232
+ "epoch": 0.24,
233
+ "grad_norm": 0.515625,
234
+ "learning_rate": 9.791377407137936e-05,
235
+ "loss": 1.084,
236
+ "max_memory_allocated (GB)": 92.88,
237
+ "memory_allocated (GB)": 20.53,
238
+ "step": 230,
239
+ "total_memory_available (GB)": 94.62
240
+ },
241
+ {
242
+ "epoch": 0.25,
243
+ "grad_norm": 0.33203125,
244
+ "learning_rate": 9.766609726717515e-05,
245
+ "loss": 1.0855,
246
+ "max_memory_allocated (GB)": 92.88,
247
+ "memory_allocated (GB)": 20.53,
248
+ "step": 240,
249
+ "total_memory_available (GB)": 94.62
250
+ },
251
+ {
252
+ "epoch": 0.26,
253
+ "grad_norm": 0.333984375,
254
+ "learning_rate": 9.740488081902539e-05,
255
+ "loss": 1.0755,
256
+ "max_memory_allocated (GB)": 92.88,
257
+ "memory_allocated (GB)": 20.53,
258
+ "step": 250,
259
+ "total_memory_available (GB)": 94.62
260
+ },
261
+ {
262
+ "epoch": 0.27,
263
+ "grad_norm": 0.376953125,
264
+ "learning_rate": 9.713019892595003e-05,
265
+ "loss": 1.0788,
266
+ "max_memory_allocated (GB)": 92.88,
267
+ "memory_allocated (GB)": 20.53,
268
+ "step": 260,
269
+ "total_memory_available (GB)": 94.62
270
+ },
271
+ {
272
+ "epoch": 0.28,
273
+ "grad_norm": 0.365234375,
274
+ "learning_rate": 9.684212961185374e-05,
275
+ "loss": 1.0705,
276
+ "max_memory_allocated (GB)": 92.88,
277
+ "memory_allocated (GB)": 20.53,
278
+ "step": 270,
279
+ "total_memory_available (GB)": 94.62
280
+ },
281
+ {
282
+ "epoch": 0.29,
283
+ "grad_norm": 0.4609375,
284
+ "learning_rate": 9.654075470336317e-05,
285
+ "loss": 1.0776,
286
+ "max_memory_allocated (GB)": 92.88,
287
+ "memory_allocated (GB)": 20.53,
288
+ "step": 280,
289
+ "total_memory_available (GB)": 94.62
290
+ },
291
+ {
292
+ "epoch": 0.3,
293
+ "grad_norm": 0.365234375,
294
+ "learning_rate": 9.622615980658391e-05,
295
+ "loss": 1.0759,
296
+ "max_memory_allocated (GB)": 92.88,
297
+ "memory_allocated (GB)": 20.53,
298
+ "step": 290,
299
+ "total_memory_available (GB)": 94.62
300
+ },
301
+ {
302
+ "epoch": 0.31,
303
+ "grad_norm": 0.36328125,
304
+ "learning_rate": 9.589843428278388e-05,
305
+ "loss": 1.0685,
306
+ "max_memory_allocated (GB)": 92.88,
307
+ "memory_allocated (GB)": 20.53,
308
+ "step": 300,
309
+ "total_memory_available (GB)": 94.62
310
+ },
311
+ {
312
+ "epoch": 0.32,
313
+ "grad_norm": 0.333984375,
314
+ "learning_rate": 9.555767122301016e-05,
315
+ "loss": 1.0794,
316
+ "max_memory_allocated (GB)": 92.88,
317
+ "memory_allocated (GB)": 20.53,
318
+ "step": 310,
319
+ "total_memory_available (GB)": 94.62
320
+ },
321
+ {
322
+ "epoch": 0.33,
323
+ "grad_norm": 0.326171875,
324
+ "learning_rate": 9.520396742164624e-05,
325
+ "loss": 1.0648,
326
+ "max_memory_allocated (GB)": 92.88,
327
+ "memory_allocated (GB)": 20.53,
328
+ "step": 320,
329
+ "total_memory_available (GB)": 94.62
330
+ },
331
+ {
332
+ "epoch": 0.34,
333
+ "grad_norm": 0.361328125,
334
+ "learning_rate": 9.483742334891746e-05,
335
+ "loss": 1.0656,
336
+ "max_memory_allocated (GB)": 92.88,
337
+ "memory_allocated (GB)": 20.53,
338
+ "step": 330,
339
+ "total_memory_available (GB)": 94.62
340
+ },
341
+ {
342
+ "epoch": 0.35,
343
+ "grad_norm": 0.384765625,
344
+ "learning_rate": 9.44581431223522e-05,
345
+ "loss": 1.0547,
346
+ "max_memory_allocated (GB)": 92.88,
347
+ "memory_allocated (GB)": 20.53,
348
+ "step": 340,
349
+ "total_memory_available (GB)": 94.62
350
+ },
351
+ {
352
+ "epoch": 0.36,
353
+ "grad_norm": 0.38671875,
354
+ "learning_rate": 9.40662344772071e-05,
355
+ "loss": 1.0675,
356
+ "max_memory_allocated (GB)": 92.88,
357
+ "memory_allocated (GB)": 20.53,
358
+ "step": 350,
359
+ "total_memory_available (GB)": 94.62
360
+ },
361
+ {
362
+ "epoch": 0.37,
363
+ "grad_norm": 0.361328125,
364
+ "learning_rate": 9.366180873586475e-05,
365
+ "loss": 1.0626,
366
+ "max_memory_allocated (GB)": 92.88,
367
+ "memory_allocated (GB)": 20.53,
368
+ "step": 360,
369
+ "total_memory_available (GB)": 94.62
370
+ },
371
+ {
372
+ "epoch": 0.38,
373
+ "grad_norm": 0.306640625,
374
+ "learning_rate": 9.32449807762122e-05,
375
+ "loss": 1.0587,
376
+ "max_memory_allocated (GB)": 92.88,
377
+ "memory_allocated (GB)": 20.53,
378
+ "step": 370,
379
+ "total_memory_available (GB)": 94.62
380
+ },
381
+ {
382
+ "epoch": 0.4,
383
+ "grad_norm": 0.333984375,
384
+ "learning_rate": 9.281586899900985e-05,
385
+ "loss": 1.0601,
386
+ "max_memory_allocated (GB)": 92.88,
387
+ "memory_allocated (GB)": 20.53,
388
+ "step": 380,
389
+ "total_memory_available (GB)": 94.62
390
+ },
391
+ {
392
+ "epoch": 0.41,
393
+ "grad_norm": 0.380859375,
394
+ "learning_rate": 9.237459529425938e-05,
395
+ "loss": 1.0606,
396
+ "max_memory_allocated (GB)": 92.88,
397
+ "memory_allocated (GB)": 20.53,
398
+ "step": 390,
399
+ "total_memory_available (GB)": 94.62
400
+ },
401
+ {
402
+ "epoch": 0.42,
403
+ "grad_norm": 0.31640625,
404
+ "learning_rate": 9.192128500658068e-05,
405
+ "loss": 1.0568,
406
+ "max_memory_allocated (GB)": 92.88,
407
+ "memory_allocated (GB)": 20.53,
408
+ "step": 400,
409
+ "total_memory_available (GB)": 94.62
410
+ },
411
+ {
412
+ "epoch": 0.43,
413
+ "grad_norm": 0.34375,
414
+ "learning_rate": 9.145606689960756e-05,
415
+ "loss": 1.0591,
416
+ "max_memory_allocated (GB)": 92.88,
417
+ "memory_allocated (GB)": 20.53,
418
+ "step": 410,
419
+ "total_memory_available (GB)": 94.62
420
+ },
421
+ {
422
+ "epoch": 0.44,
423
+ "grad_norm": 0.333984375,
424
+ "learning_rate": 9.097907311941208e-05,
425
+ "loss": 1.0533,
426
+ "max_memory_allocated (GB)": 92.88,
427
+ "memory_allocated (GB)": 20.53,
428
+ "step": 420,
429
+ "total_memory_available (GB)": 94.62
430
+ },
431
+ {
432
+ "epoch": 0.45,
433
+ "grad_norm": 0.326171875,
434
+ "learning_rate": 9.049043915696831e-05,
435
+ "loss": 1.0483,
436
+ "max_memory_allocated (GB)": 92.88,
437
+ "memory_allocated (GB)": 20.53,
438
+ "step": 430,
439
+ "total_memory_available (GB)": 94.62
440
+ },
441
+ {
442
+ "epoch": 0.46,
443
+ "grad_norm": 0.326171875,
444
+ "learning_rate": 8.99903038096658e-05,
445
+ "loss": 1.0501,
446
+ "max_memory_allocated (GB)": 92.88,
447
+ "memory_allocated (GB)": 20.53,
448
+ "step": 440,
449
+ "total_memory_available (GB)": 94.62
450
+ },
451
+ {
452
+ "epoch": 0.47,
453
+ "grad_norm": 0.326171875,
454
+ "learning_rate": 8.947880914188397e-05,
455
+ "loss": 1.053,
456
+ "max_memory_allocated (GB)": 92.88,
457
+ "memory_allocated (GB)": 20.53,
458
+ "step": 450,
459
+ "total_memory_available (GB)": 94.62
460
+ },
461
+ {
462
+ "epoch": 0.48,
463
+ "grad_norm": 0.357421875,
464
+ "learning_rate": 8.89561004446384e-05,
465
+ "loss": 1.0441,
466
+ "max_memory_allocated (GB)": 92.88,
467
+ "memory_allocated (GB)": 20.53,
468
+ "step": 460,
469
+ "total_memory_available (GB)": 94.62
470
+ },
471
+ {
472
+ "epoch": 0.49,
473
+ "grad_norm": 0.306640625,
474
+ "learning_rate": 8.842232619431074e-05,
475
+ "loss": 1.0575,
476
+ "max_memory_allocated (GB)": 92.88,
477
+ "memory_allocated (GB)": 20.53,
478
+ "step": 470,
479
+ "total_memory_available (GB)": 94.62
480
+ },
481
+ {
482
+ "epoch": 0.5,
483
+ "grad_norm": 0.326171875,
484
+ "learning_rate": 8.78776380104736e-05,
485
+ "loss": 1.0639,
486
+ "max_memory_allocated (GB)": 92.89,
487
+ "memory_allocated (GB)": 20.53,
488
+ "step": 480,
489
+ "total_memory_available (GB)": 94.62
490
+ },
491
+ {
492
+ "epoch": 0.51,
493
+ "grad_norm": 0.38671875,
494
+ "learning_rate": 8.732219061282278e-05,
495
+ "loss": 1.0463,
496
+ "max_memory_allocated (GB)": 92.89,
497
+ "memory_allocated (GB)": 20.53,
498
+ "step": 490,
499
+ "total_memory_available (GB)": 94.62
500
+ },
501
+ {
502
+ "epoch": 0.52,
503
+ "grad_norm": 0.3203125,
504
+ "learning_rate": 8.675614177722895e-05,
505
+ "loss": 1.0483,
506
+ "max_memory_allocated (GB)": 92.89,
507
+ "memory_allocated (GB)": 20.53,
508
+ "step": 500,
509
+ "total_memory_available (GB)": 94.62
510
+ },
511
+ {
512
+ "epoch": 0.53,
513
+ "grad_norm": 0.31640625,
514
+ "learning_rate": 8.61796522909209e-05,
515
+ "loss": 1.044,
516
+ "max_memory_allocated (GB)": 92.89,
517
+ "memory_allocated (GB)": 20.53,
518
+ "step": 510,
519
+ "total_memory_available (GB)": 94.62
520
+ },
521
+ {
522
+ "epoch": 0.54,
523
+ "grad_norm": 0.326171875,
524
+ "learning_rate": 8.559288590681387e-05,
525
+ "loss": 1.0478,
526
+ "max_memory_allocated (GB)": 92.89,
527
+ "memory_allocated (GB)": 20.53,
528
+ "step": 520,
529
+ "total_memory_available (GB)": 94.62
530
+ },
531
+ {
532
+ "epoch": 0.55,
533
+ "grad_norm": 0.349609375,
534
+ "learning_rate": 8.4996009296995e-05,
535
+ "loss": 1.0426,
536
+ "max_memory_allocated (GB)": 92.89,
537
+ "memory_allocated (GB)": 20.53,
538
+ "step": 530,
539
+ "total_memory_available (GB)": 94.62
540
+ },
541
+ {
542
+ "epoch": 0.56,
543
+ "grad_norm": 0.353515625,
544
+ "learning_rate": 8.438919200538003e-05,
545
+ "loss": 1.0488,
546
+ "max_memory_allocated (GB)": 92.89,
547
+ "memory_allocated (GB)": 20.53,
548
+ "step": 540,
549
+ "total_memory_available (GB)": 94.62
550
+ },
551
+ {
552
+ "epoch": 0.57,
553
+ "grad_norm": 0.3125,
554
+ "learning_rate": 8.377260639955385e-05,
555
+ "loss": 1.0434,
556
+ "max_memory_allocated (GB)": 92.89,
557
+ "memory_allocated (GB)": 20.53,
558
+ "step": 550,
559
+ "total_memory_available (GB)": 94.62
560
+ },
561
+ {
562
+ "epoch": 0.58,
563
+ "grad_norm": 0.38671875,
564
+ "learning_rate": 8.314642762180927e-05,
565
+ "loss": 1.04,
566
+ "max_memory_allocated (GB)": 92.89,
567
+ "memory_allocated (GB)": 20.53,
568
+ "step": 560,
569
+ "total_memory_available (GB)": 94.62
570
+ },
571
+ {
572
+ "epoch": 0.59,
573
+ "grad_norm": 0.294921875,
574
+ "learning_rate": 8.251083353939752e-05,
575
+ "loss": 1.0406,
576
+ "max_memory_allocated (GB)": 92.89,
577
+ "memory_allocated (GB)": 20.53,
578
+ "step": 570,
579
+ "total_memory_available (GB)": 94.62
580
+ },
581
+ {
582
+ "epoch": 0.6,
583
+ "grad_norm": 0.318359375,
584
+ "learning_rate": 8.186600469400467e-05,
585
+ "loss": 1.0537,
586
+ "max_memory_allocated (GB)": 92.89,
587
+ "memory_allocated (GB)": 20.53,
588
+ "step": 580,
589
+ "total_memory_available (GB)": 94.62
590
+ },
591
+ {
592
+ "epoch": 0.61,
593
+ "grad_norm": 0.302734375,
594
+ "learning_rate": 8.12121242504685e-05,
595
+ "loss": 1.038,
596
+ "max_memory_allocated (GB)": 92.89,
597
+ "memory_allocated (GB)": 20.53,
598
+ "step": 590,
599
+ "total_memory_available (GB)": 94.62
600
+ },
601
+ {
602
+ "epoch": 0.62,
603
+ "grad_norm": 0.302734375,
604
+ "learning_rate": 8.05493779447501e-05,
605
+ "loss": 1.0425,
606
+ "max_memory_allocated (GB)": 92.89,
607
+ "memory_allocated (GB)": 20.53,
608
+ "step": 600,
609
+ "total_memory_available (GB)": 94.62
610
+ },
611
+ {
612
+ "epoch": 0.63,
613
+ "grad_norm": 0.306640625,
614
+ "learning_rate": 7.987795403117529e-05,
615
+ "loss": 1.0336,
616
+ "max_memory_allocated (GB)": 92.89,
617
+ "memory_allocated (GB)": 20.53,
618
+ "step": 610,
619
+ "total_memory_available (GB)": 94.62
620
+ },
621
+ {
622
+ "epoch": 0.65,
623
+ "grad_norm": 0.3046875,
624
+ "learning_rate": 7.919804322896062e-05,
625
+ "loss": 1.0397,
626
+ "max_memory_allocated (GB)": 92.89,
627
+ "memory_allocated (GB)": 20.53,
628
+ "step": 620,
629
+ "total_memory_available (GB)": 94.62
630
+ },
631
+ {
632
+ "epoch": 0.66,
633
+ "grad_norm": 0.322265625,
634
+ "learning_rate": 7.850983866803922e-05,
635
+ "loss": 1.0388,
636
+ "max_memory_allocated (GB)": 92.89,
637
+ "memory_allocated (GB)": 20.53,
638
+ "step": 630,
639
+ "total_memory_available (GB)": 94.62
640
+ },
641
+ {
642
+ "epoch": 0.67,
643
+ "grad_norm": 0.314453125,
644
+ "learning_rate": 7.78135358342018e-05,
645
+ "loss": 1.0301,
646
+ "max_memory_allocated (GB)": 92.89,
647
+ "memory_allocated (GB)": 20.53,
648
+ "step": 640,
649
+ "total_memory_available (GB)": 94.62
650
+ },
651
+ {
652
+ "epoch": 0.68,
653
+ "grad_norm": 0.283203125,
654
+ "learning_rate": 7.71093325135687e-05,
655
+ "loss": 1.0341,
656
+ "max_memory_allocated (GB)": 92.89,
657
+ "memory_allocated (GB)": 20.53,
658
+ "step": 650,
659
+ "total_memory_available (GB)": 94.62
660
+ },
661
+ {
662
+ "epoch": 0.69,
663
+ "grad_norm": 0.30859375,
664
+ "learning_rate": 7.639742873640825e-05,
665
+ "loss": 1.0348,
666
+ "max_memory_allocated (GB)": 92.89,
667
+ "memory_allocated (GB)": 20.53,
668
+ "step": 660,
669
+ "total_memory_available (GB)": 94.62
670
+ },
671
+ {
672
+ "epoch": 0.7,
673
+ "grad_norm": 0.357421875,
674
+ "learning_rate": 7.56780267203178e-05,
675
+ "loss": 1.036,
676
+ "max_memory_allocated (GB)": 92.89,
677
+ "memory_allocated (GB)": 20.53,
678
+ "step": 670,
679
+ "total_memory_available (GB)": 94.62
680
+ },
681
+ {
682
+ "epoch": 0.71,
683
+ "grad_norm": 0.314453125,
684
+ "learning_rate": 7.495133081278356e-05,
685
+ "loss": 1.0322,
686
+ "max_memory_allocated (GB)": 92.89,
687
+ "memory_allocated (GB)": 20.53,
688
+ "step": 680,
689
+ "total_memory_available (GB)": 94.62
690
+ },
691
+ {
692
+ "epoch": 0.72,
693
+ "grad_norm": 0.357421875,
694
+ "learning_rate": 7.421754743313514e-05,
695
+ "loss": 1.039,
696
+ "max_memory_allocated (GB)": 92.89,
697
+ "memory_allocated (GB)": 20.53,
698
+ "step": 690,
699
+ "total_memory_available (GB)": 94.62
700
+ },
701
+ {
702
+ "epoch": 0.73,
703
+ "grad_norm": 0.314453125,
704
+ "learning_rate": 7.347688501391187e-05,
705
+ "loss": 1.0402,
706
+ "max_memory_allocated (GB)": 92.89,
707
+ "memory_allocated (GB)": 20.53,
708
+ "step": 700,
709
+ "total_memory_available (GB)": 94.62
710
+ },
711
+ {
712
+ "epoch": 0.74,
713
+ "grad_norm": 0.3203125,
714
+ "learning_rate": 7.272955394165717e-05,
715
+ "loss": 1.0326,
716
+ "max_memory_allocated (GB)": 92.89,
717
+ "memory_allocated (GB)": 20.53,
718
+ "step": 710,
719
+ "total_memory_available (GB)": 94.62
720
+ },
721
+ {
722
+ "epoch": 0.75,
723
+ "grad_norm": 0.328125,
724
+ "learning_rate": 7.197576649715771e-05,
725
+ "loss": 1.0304,
726
+ "max_memory_allocated (GB)": 92.89,
727
+ "memory_allocated (GB)": 20.53,
728
+ "step": 720,
729
+ "total_memory_available (GB)": 94.62
730
+ },
731
+ {
732
+ "epoch": 0.76,
733
+ "grad_norm": 0.33984375,
734
+ "learning_rate": 7.121573679514484e-05,
735
+ "loss": 1.0314,
736
+ "max_memory_allocated (GB)": 92.89,
737
+ "memory_allocated (GB)": 20.53,
738
+ "step": 730,
739
+ "total_memory_available (GB)": 94.62
740
+ },
741
+ {
742
+ "epoch": 0.77,
743
+ "grad_norm": 0.283203125,
744
+ "learning_rate": 7.044968072347473e-05,
745
+ "loss": 1.0427,
746
+ "max_memory_allocated (GB)": 92.89,
747
+ "memory_allocated (GB)": 20.53,
748
+ "step": 740,
749
+ "total_memory_available (GB)": 94.62
750
+ },
751
+ {
752
+ "epoch": 0.78,
753
+ "grad_norm": 0.3515625,
754
+ "learning_rate": 6.967781588180521e-05,
755
+ "loss": 1.0365,
756
+ "max_memory_allocated (GB)": 92.89,
757
+ "memory_allocated (GB)": 20.53,
758
+ "step": 750,
759
+ "total_memory_available (GB)": 94.62
760
+ },
761
+ {
762
+ "epoch": 0.79,
763
+ "grad_norm": 0.3125,
764
+ "learning_rate": 6.890036151978598e-05,
765
+ "loss": 1.026,
766
+ "max_memory_allocated (GB)": 92.89,
767
+ "memory_allocated (GB)": 20.53,
768
+ "step": 760,
769
+ "total_memory_available (GB)": 94.62
770
+ },
771
+ {
772
+ "epoch": 0.8,
773
+ "grad_norm": 0.326171875,
774
+ "learning_rate": 6.811753847478051e-05,
775
+ "loss": 1.0243,
776
+ "max_memory_allocated (GB)": 92.89,
777
+ "memory_allocated (GB)": 20.53,
778
+ "step": 770,
779
+ "total_memory_available (GB)": 94.62
780
+ },
781
+ {
782
+ "epoch": 0.81,
783
+ "grad_norm": 0.3203125,
784
+ "learning_rate": 6.732956910913661e-05,
785
+ "loss": 1.0348,
786
+ "max_memory_allocated (GB)": 92.89,
787
+ "memory_allocated (GB)": 20.53,
788
+ "step": 780,
789
+ "total_memory_available (GB)": 94.62
790
+ },
791
+ {
792
+ "epoch": 0.82,
793
+ "grad_norm": 0.298828125,
794
+ "learning_rate": 6.653667724702418e-05,
795
+ "loss": 1.0218,
796
+ "max_memory_allocated (GB)": 92.89,
797
+ "memory_allocated (GB)": 20.53,
798
+ "step": 790,
799
+ "total_memory_available (GB)": 94.62
800
+ },
801
+ {
802
+ "epoch": 0.83,
803
+ "grad_norm": 0.33984375,
804
+ "learning_rate": 6.573908811085734e-05,
805
+ "loss": 1.0267,
806
+ "max_memory_allocated (GB)": 92.89,
807
+ "memory_allocated (GB)": 20.53,
808
+ "step": 800,
809
+ "total_memory_available (GB)": 94.62
810
+ },
811
+ {
812
+ "epoch": 0.84,
813
+ "grad_norm": 0.294921875,
814
+ "learning_rate": 6.493702825731976e-05,
815
+ "loss": 1.0316,
816
+ "max_memory_allocated (GB)": 92.89,
817
+ "memory_allocated (GB)": 20.53,
818
+ "step": 810,
819
+ "total_memory_available (GB)": 94.62
820
+ },
821
+ {
822
+ "epoch": 0.85,
823
+ "grad_norm": 0.36328125,
824
+ "learning_rate": 6.41307255130107e-05,
825
+ "loss": 1.0252,
826
+ "max_memory_allocated (GB)": 92.89,
827
+ "memory_allocated (GB)": 20.53,
828
+ "step": 820,
829
+ "total_memory_available (GB)": 94.62
830
+ },
831
+ {
832
+ "epoch": 0.86,
833
+ "grad_norm": 0.310546875,
834
+ "learning_rate": 6.33204089097304e-05,
835
+ "loss": 1.0267,
836
+ "max_memory_allocated (GB)": 92.89,
837
+ "memory_allocated (GB)": 20.53,
838
+ "step": 830,
839
+ "total_memory_available (GB)": 94.62
840
+ },
841
+ {
842
+ "epoch": 0.87,
843
+ "grad_norm": 0.318359375,
844
+ "learning_rate": 6.250630861942333e-05,
845
+ "loss": 1.0194,
846
+ "max_memory_allocated (GB)": 92.89,
847
+ "memory_allocated (GB)": 20.53,
848
+ "step": 840,
849
+ "total_memory_available (GB)": 94.62
850
+ },
851
+ {
852
+ "epoch": 0.88,
853
+ "grad_norm": 0.357421875,
854
+ "learning_rate": 6.16886558887973e-05,
855
+ "loss": 1.0328,
856
+ "max_memory_allocated (GB)": 92.89,
857
+ "memory_allocated (GB)": 20.53,
858
+ "step": 850,
859
+ "total_memory_available (GB)": 94.62
860
+ },
861
+ {
862
+ "epoch": 0.89,
863
+ "grad_norm": 0.283203125,
864
+ "learning_rate": 6.0867682973637394e-05,
865
+ "loss": 1.0136,
866
+ "max_memory_allocated (GB)": 92.89,
867
+ "memory_allocated (GB)": 20.53,
868
+ "step": 860,
869
+ "total_memory_available (GB)": 94.62
870
+ },
871
+ {
872
+ "epoch": 0.91,
873
+ "grad_norm": 0.318359375,
874
+ "learning_rate": 6.004362307283335e-05,
875
+ "loss": 1.037,
876
+ "max_memory_allocated (GB)": 92.89,
877
+ "memory_allocated (GB)": 20.53,
878
+ "step": 870,
879
+ "total_memory_available (GB)": 94.62
880
+ },
881
+ {
882
+ "epoch": 0.92,
883
+ "grad_norm": 0.3046875,
884
+ "learning_rate": 5.921671026213893e-05,
885
+ "loss": 1.0175,
886
+ "max_memory_allocated (GB)": 92.89,
887
+ "memory_allocated (GB)": 20.53,
888
+ "step": 880,
889
+ "total_memory_available (GB)": 94.62
890
+ },
891
+ {
892
+ "epoch": 0.93,
893
+ "grad_norm": 0.32421875,
894
+ "learning_rate": 5.838717942768226e-05,
895
+ "loss": 1.0266,
896
+ "max_memory_allocated (GB)": 92.89,
897
+ "memory_allocated (GB)": 20.53,
898
+ "step": 890,
899
+ "total_memory_available (GB)": 94.62
900
+ },
901
+ {
902
+ "epoch": 0.94,
903
+ "grad_norm": 0.326171875,
904
+ "learning_rate": 5.755526619924605e-05,
905
+ "loss": 1.0358,
906
+ "max_memory_allocated (GB)": 92.89,
907
+ "memory_allocated (GB)": 20.53,
908
+ "step": 900,
909
+ "total_memory_available (GB)": 94.62
910
+ },
911
+ {
912
+ "epoch": 0.95,
913
+ "grad_norm": 0.306640625,
914
+ "learning_rate": 5.672120688333642e-05,
915
+ "loss": 1.0214,
916
+ "max_memory_allocated (GB)": 92.89,
917
+ "memory_allocated (GB)": 20.53,
918
+ "step": 910,
919
+ "total_memory_available (GB)": 94.62
920
+ },
921
+ {
922
+ "epoch": 0.96,
923
+ "grad_norm": 0.337890625,
924
+ "learning_rate": 5.588523839605968e-05,
925
+ "loss": 1.0225,
926
+ "max_memory_allocated (GB)": 92.89,
927
+ "memory_allocated (GB)": 20.53,
928
+ "step": 920,
929
+ "total_memory_available (GB)": 94.62
930
+ },
931
+ {
932
+ "epoch": 0.97,
933
+ "grad_norm": 0.345703125,
934
+ "learning_rate": 5.504759819582581e-05,
935
+ "loss": 1.0307,
936
+ "max_memory_allocated (GB)": 92.89,
937
+ "memory_allocated (GB)": 20.53,
938
+ "step": 930,
939
+ "total_memory_available (GB)": 94.62
940
+ },
941
+ {
942
+ "epoch": 0.98,
943
+ "grad_norm": 0.30859375,
944
+ "learning_rate": 5.4208524215897985e-05,
945
+ "loss": 1.0187,
946
+ "max_memory_allocated (GB)": 92.89,
947
+ "memory_allocated (GB)": 20.53,
948
+ "step": 940,
949
+ "total_memory_available (GB)": 94.62
950
+ },
951
+ {
952
+ "epoch": 0.99,
953
+ "grad_norm": 0.28515625,
954
+ "learning_rate": 5.3368254796807196e-05,
955
+ "loss": 1.0284,
956
+ "max_memory_allocated (GB)": 92.89,
957
+ "memory_allocated (GB)": 20.53,
958
+ "step": 950,
959
+ "total_memory_available (GB)": 94.62
960
+ },
961
+ {
962
+ "epoch": 1.0,
963
+ "grad_norm": 0.296875,
964
+ "learning_rate": 5.2527028618651117e-05,
965
+ "loss": 1.0252,
966
+ "max_memory_allocated (GB)": 92.89,
967
+ "memory_allocated (GB)": 20.53,
968
+ "step": 960,
969
+ "total_memory_available (GB)": 94.62
970
+ },
971
+ {
972
+ "epoch": 1.01,
973
+ "grad_norm": 0.3515625,
974
+ "learning_rate": 5.1685084633296665e-05,
975
+ "loss": 1.0183,
976
+ "max_memory_allocated (GB)": 92.89,
977
+ "memory_allocated (GB)": 20.53,
978
+ "step": 970,
979
+ "total_memory_available (GB)": 94.62
980
+ },
981
+ {
982
+ "epoch": 1.02,
983
+ "grad_norm": 0.322265625,
984
+ "learning_rate": 5.084266199650523e-05,
985
+ "loss": 1.0235,
986
+ "max_memory_allocated (GB)": 92.89,
987
+ "memory_allocated (GB)": 20.53,
988
+ "step": 980,
989
+ "total_memory_available (GB)": 94.62
990
+ },
991
+ {
992
+ "epoch": 1.03,
993
+ "grad_norm": 0.3125,
994
+ "learning_rate": 5e-05,
995
+ "loss": 1.0193,
996
+ "max_memory_allocated (GB)": 92.89,
997
+ "memory_allocated (GB)": 20.53,
998
+ "step": 990,
999
+ "total_memory_available (GB)": 94.62
1000
+ },
1001
+ {
1002
+ "epoch": 1.04,
1003
+ "grad_norm": 0.306640625,
1004
+ "learning_rate": 4.915733800349477e-05,
1005
+ "loss": 1.0199,
1006
+ "max_memory_allocated (GB)": 92.89,
1007
+ "memory_allocated (GB)": 20.53,
1008
+ "step": 1000,
1009
+ "total_memory_available (GB)": 94.62
1010
+ }
1011
+ ],
1012
+ "logging_steps": 10,
1013
+ "max_steps": 1922,
1014
+ "num_input_tokens_seen": 0,
1015
+ "num_train_epochs": 2,
1016
+ "save_steps": 1000,
1017
+ "total_flos": 1.119482194910249e+19,
1018
+ "train_batch_size": 8,
1019
+ "trial_name": null,
1020
+ "trial_params": null
1021
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e256a8ee7ac5ec1d841453d02ab5bf80f5d13ccba4b54ab27d93f992f1385f1
3
+ size 4792
eval_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "epoch": 3.0,
3
- "eval_accuracy": 0.4639155611944004,
4
- "eval_loss": 1.0861796140670776,
5
- "eval_runtime": 144.8,
6
  "eval_samples": 25899,
7
- "eval_samples_per_second": 183.416,
8
- "eval_steps_per_second": 2.868,
9
- "max_memory_allocated (GB)": 91.29,
10
- "memory_allocated (GB)": 20.51,
11
- "perplexity": 2.96293287540469,
12
  "total_memory_available (GB)": 94.62
13
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "eval_accuracy": 0.45881899043469254,
4
+ "eval_loss": 1.125322937965393,
5
+ "eval_runtime": 146.7119,
6
  "eval_samples": 25899,
7
+ "eval_samples_per_second": 181.966,
8
+ "eval_steps_per_second": 2.846,
9
+ "max_memory_allocated (GB)": 92.9,
10
+ "memory_allocated (GB)": 20.53,
11
+ "perplexity": 3.08121172851374,
12
  "total_memory_available (GB)": 94.62
13
  }
runs/Jun05_02-37-29_9d340316bc35/events.out.tfevents.1717556360.9d340316bc35.1970.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b7fa24d7090ed1d69f9f71aff447abb5c1c3f1abb84684c55c95927d297ed6
3
+ size 23960
runs/Jun05_03-27-04_9d340316bc35/events.out.tfevents.1717559330.9d340316bc35.8193.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e27174d1bac97def129e3dd6d0e3846e1ccbe447e3dfe4b861dc835d4d0084
3
+ size 86115
runs/Jun05_03-27-04_9d340316bc35/events.out.tfevents.1717565888.9d340316bc35.8193.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d356c650985f430700689f3f673d05dfa692a2cfce4cefa57746bca0ad1deb
3
+ size 571
train_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "epoch": 3.0,
3
- "max_memory_allocated (GB)": 91.29,
4
- "memory_allocated (GB)": 20.51,
5
  "total_memory_available (GB)": 94.62,
6
- "train_loss": 1.0007781735929895,
7
- "train_runtime": 10023.6622,
8
- "train_samples_per_second": 148.487,
9
- "train_steps_per_second": 1.16
10
  }
 
1
  {
2
+ "epoch": 2.0,
3
+ "max_memory_allocated (GB)": 92.9,
4
+ "memory_allocated (GB)": 20.53,
5
  "total_memory_available (GB)": 94.62,
6
+ "train_loss": 1.0511445318126778,
7
+ "train_runtime": 6406.9638,
8
+ "train_samples_per_second": 157.111,
9
+ "train_steps_per_second": 0.307
10
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49580d318555f90ea2a27a0a15c9bd5e89af013379c376f36a54dec7cb029fce
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e256a8ee7ac5ec1d841453d02ab5bf80f5d13ccba4b54ab27d93f992f1385f1
3
  size 4792