mrpc task
Browse files- mrpc/{config.json → checkpoint-10000/config.json} +1 -1
- mrpc/{model.safetensors → checkpoint-10000/model.safetensors} +1 -1
- mrpc/checkpoint-10000/rng_state.pth +3 -0
- mrpc/checkpoint-10000/scheduler.pt +3 -0
- mrpc/{special_tokens_map.json → checkpoint-10000/special_tokens_map.json} +0 -0
- mrpc/{tokenizer_config.json → checkpoint-10000/tokenizer_config.json} +0 -0
- mrpc/checkpoint-10000/trainer_state.json +796 -0
- mrpc/checkpoint-10000/training_args.bin +3 -0
- mrpc/{vocab.txt → checkpoint-10000/vocab.txt} +0 -0
- mrpc/checkpoint-2000/config.json +27 -0
- mrpc/checkpoint-2000/model.safetensors +3 -0
- mrpc/checkpoint-2000/rng_state.pth +3 -0
- mrpc/checkpoint-2000/scheduler.pt +3 -0
- mrpc/checkpoint-2000/special_tokens_map.json +7 -0
- mrpc/checkpoint-2000/tokenizer_config.json +57 -0
- mrpc/checkpoint-2000/trainer_state.json +176 -0
- mrpc/checkpoint-2000/training_args.bin +3 -0
- mrpc/checkpoint-2000/vocab.txt +0 -0
- mrpc/checkpoint-4000/config.json +27 -0
- mrpc/checkpoint-4000/model.safetensors +3 -0
- mrpc/checkpoint-4000/rng_state.pth +3 -0
- mrpc/checkpoint-4000/scheduler.pt +3 -0
- mrpc/checkpoint-4000/special_tokens_map.json +7 -0
- mrpc/checkpoint-4000/tokenizer_config.json +57 -0
- mrpc/checkpoint-4000/trainer_state.json +331 -0
- mrpc/checkpoint-4000/training_args.bin +3 -0
- mrpc/checkpoint-4000/vocab.txt +0 -0
- mrpc/checkpoint-6000/config.json +27 -0
- mrpc/checkpoint-6000/model.safetensors +3 -0
- mrpc/checkpoint-6000/rng_state.pth +3 -0
- mrpc/checkpoint-6000/scheduler.pt +3 -0
- mrpc/checkpoint-6000/special_tokens_map.json +7 -0
- mrpc/checkpoint-6000/tokenizer_config.json +57 -0
- mrpc/checkpoint-6000/trainer_state.json +486 -0
- mrpc/checkpoint-6000/training_args.bin +3 -0
- mrpc/checkpoint-6000/vocab.txt +0 -0
- mrpc/checkpoint-8000/config.json +27 -0
- mrpc/checkpoint-8000/model.safetensors +3 -0
- mrpc/checkpoint-8000/rng_state.pth +3 -0
- mrpc/checkpoint-8000/scheduler.pt +3 -0
- mrpc/checkpoint-8000/special_tokens_map.json +7 -0
- mrpc/checkpoint-8000/tokenizer_config.json +57 -0
- mrpc/checkpoint-8000/trainer_state.json +641 -0
- mrpc/checkpoint-8000/training_args.bin +3 -0
- mrpc/checkpoint-8000/vocab.txt +0 -0
mrpc/{config.json → checkpoint-10000/config.json}
RENAMED
|
@@ -20,7 +20,7 @@
|
|
| 20 |
"position_embedding_type": "absolute",
|
| 21 |
"problem_type": "single_label_classification",
|
| 22 |
"torch_dtype": "float32",
|
| 23 |
-
"transformers_version": "4.
|
| 24 |
"type_vocab_size": 2,
|
| 25 |
"use_cache": true,
|
| 26 |
"vocab_size": 30522
|
|
|
|
| 20 |
"position_embedding_type": "absolute",
|
| 21 |
"problem_type": "single_label_classification",
|
| 22 |
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.38.2",
|
| 24 |
"type_vocab_size": 2,
|
| 25 |
"use_cache": true,
|
| 26 |
"vocab_size": 30522
|
mrpc/{model.safetensors → checkpoint-10000/model.safetensors}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437958648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e4f65a7dc25db16eed6785af62623d34ffba14f96fbd55b441bf5ae9d673936
|
| 3 |
size 437958648
|
mrpc/checkpoint-10000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:703622daa608ad0bc0522d956e3a02e84baefcd25522e7459a586c3a686efe25
|
| 3 |
+
size 14244
|
mrpc/checkpoint-10000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04c72869181363c7c0dcffb7a71857fd6a7c81a93e70aff2985fc26363295969
|
| 3 |
+
size 1064
|
mrpc/{special_tokens_map.json → checkpoint-10000/special_tokens_map.json}
RENAMED
|
File without changes
|
mrpc/{tokenizer_config.json → checkpoint-10000/tokenizer_config.json}
RENAMED
|
File without changes
|
mrpc/checkpoint-10000/trainer_state.json
ADDED
|
@@ -0,0 +1,796 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 86.95652173913044,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 10000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.87,
|
| 13 |
+
"grad_norm": 4.196278095245361,
|
| 14 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 15 |
+
"loss": 0.5435,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.74,
|
| 20 |
+
"grad_norm": 8.441207885742188,
|
| 21 |
+
"learning_rate": 4.9e-05,
|
| 22 |
+
"loss": 0.2564,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.61,
|
| 27 |
+
"grad_norm": 8.456403732299805,
|
| 28 |
+
"learning_rate": 4.85e-05,
|
| 29 |
+
"loss": 0.1488,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 3.48,
|
| 34 |
+
"grad_norm": 0.8015245795249939,
|
| 35 |
+
"learning_rate": 4.8e-05,
|
| 36 |
+
"loss": 0.0688,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 4.35,
|
| 41 |
+
"grad_norm": 0.2079729586839676,
|
| 42 |
+
"learning_rate": 4.75e-05,
|
| 43 |
+
"loss": 0.0622,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.22,
|
| 48 |
+
"grad_norm": 0.10826250910758972,
|
| 49 |
+
"learning_rate": 4.7e-05,
|
| 50 |
+
"loss": 0.0491,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.09,
|
| 55 |
+
"grad_norm": 15.216827392578125,
|
| 56 |
+
"learning_rate": 4.6500000000000005e-05,
|
| 57 |
+
"loss": 0.0328,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 6.96,
|
| 62 |
+
"grad_norm": 15.634430885314941,
|
| 63 |
+
"learning_rate": 4.600000000000001e-05,
|
| 64 |
+
"loss": 0.0306,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 7.83,
|
| 69 |
+
"grad_norm": 31.188247680664062,
|
| 70 |
+
"learning_rate": 4.55e-05,
|
| 71 |
+
"loss": 0.0182,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.7,
|
| 76 |
+
"grad_norm": 0.016402140259742737,
|
| 77 |
+
"learning_rate": 4.5e-05,
|
| 78 |
+
"loss": 0.0222,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 9.57,
|
| 83 |
+
"grad_norm": 31.216285705566406,
|
| 84 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 85 |
+
"loss": 0.0181,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 10.43,
|
| 90 |
+
"grad_norm": 0.2328696846961975,
|
| 91 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 92 |
+
"loss": 0.0121,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 11.3,
|
| 97 |
+
"grad_norm": 0.007173949386924505,
|
| 98 |
+
"learning_rate": 4.35e-05,
|
| 99 |
+
"loss": 0.0253,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 12.17,
|
| 104 |
+
"grad_norm": 0.003974032588303089,
|
| 105 |
+
"learning_rate": 4.3e-05,
|
| 106 |
+
"loss": 0.0099,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 13.04,
|
| 111 |
+
"grad_norm": 0.3920653164386749,
|
| 112 |
+
"learning_rate": 4.25e-05,
|
| 113 |
+
"loss": 0.0172,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 13.91,
|
| 118 |
+
"grad_norm": 1.2646549940109253,
|
| 119 |
+
"learning_rate": 4.2e-05,
|
| 120 |
+
"loss": 0.0295,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 14.78,
|
| 125 |
+
"grad_norm": 0.07062631100416183,
|
| 126 |
+
"learning_rate": 4.15e-05,
|
| 127 |
+
"loss": 0.0181,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 15.65,
|
| 132 |
+
"grad_norm": 0.005436008796095848,
|
| 133 |
+
"learning_rate": 4.1e-05,
|
| 134 |
+
"loss": 0.0067,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 16.52,
|
| 139 |
+
"grad_norm": 0.004679691046476364,
|
| 140 |
+
"learning_rate": 4.05e-05,
|
| 141 |
+
"loss": 0.02,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 17.39,
|
| 146 |
+
"grad_norm": 0.01030748151242733,
|
| 147 |
+
"learning_rate": 4e-05,
|
| 148 |
+
"loss": 0.0197,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 17.39,
|
| 153 |
+
"eval_accuracy": 0.9387254901960784,
|
| 154 |
+
"eval_brier_score": 0.05757000434820965,
|
| 155 |
+
"eval_ece": 0.05797517591831729,
|
| 156 |
+
"eval_f1": 0.9382506413699704,
|
| 157 |
+
"eval_loss": 0.40406298637390137,
|
| 158 |
+
"eval_nll": 6.776806058077595,
|
| 159 |
+
"eval_precision": 0.9384196444828075,
|
| 160 |
+
"eval_recall": 0.9387254901960784,
|
| 161 |
+
"eval_runtime": 1.9112,
|
| 162 |
+
"eval_samples_per_second": 213.478,
|
| 163 |
+
"eval_steps_per_second": 6.802,
|
| 164 |
+
"step": 2000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 18.26,
|
| 168 |
+
"grad_norm": 0.004601624328643084,
|
| 169 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 170 |
+
"loss": 0.0158,
|
| 171 |
+
"step": 2100
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 19.13,
|
| 175 |
+
"grad_norm": 0.012901573441922665,
|
| 176 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 177 |
+
"loss": 0.0092,
|
| 178 |
+
"step": 2200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 20.0,
|
| 182 |
+
"grad_norm": 0.00762163195759058,
|
| 183 |
+
"learning_rate": 3.85e-05,
|
| 184 |
+
"loss": 0.0082,
|
| 185 |
+
"step": 2300
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 20.87,
|
| 189 |
+
"grad_norm": 0.154510959982872,
|
| 190 |
+
"learning_rate": 3.8e-05,
|
| 191 |
+
"loss": 0.0131,
|
| 192 |
+
"step": 2400
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 21.74,
|
| 196 |
+
"grad_norm": 0.003832124872133136,
|
| 197 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 198 |
+
"loss": 0.0201,
|
| 199 |
+
"step": 2500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 22.61,
|
| 203 |
+
"grad_norm": 0.0029927650466561317,
|
| 204 |
+
"learning_rate": 3.7e-05,
|
| 205 |
+
"loss": 0.019,
|
| 206 |
+
"step": 2600
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 23.48,
|
| 210 |
+
"grad_norm": 0.0018748922739177942,
|
| 211 |
+
"learning_rate": 3.65e-05,
|
| 212 |
+
"loss": 0.0086,
|
| 213 |
+
"step": 2700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 24.35,
|
| 217 |
+
"grad_norm": 0.14622557163238525,
|
| 218 |
+
"learning_rate": 3.6e-05,
|
| 219 |
+
"loss": 0.01,
|
| 220 |
+
"step": 2800
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 25.22,
|
| 224 |
+
"grad_norm": 0.03812519088387489,
|
| 225 |
+
"learning_rate": 3.55e-05,
|
| 226 |
+
"loss": 0.0234,
|
| 227 |
+
"step": 2900
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 26.09,
|
| 231 |
+
"grad_norm": 24.803911209106445,
|
| 232 |
+
"learning_rate": 3.5e-05,
|
| 233 |
+
"loss": 0.0119,
|
| 234 |
+
"step": 3000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 26.96,
|
| 238 |
+
"grad_norm": 0.00613383948802948,
|
| 239 |
+
"learning_rate": 3.45e-05,
|
| 240 |
+
"loss": 0.0129,
|
| 241 |
+
"step": 3100
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 27.83,
|
| 245 |
+
"grad_norm": 0.005301126278936863,
|
| 246 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 247 |
+
"loss": 0.0086,
|
| 248 |
+
"step": 3200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 28.7,
|
| 252 |
+
"grad_norm": 0.0037701462861150503,
|
| 253 |
+
"learning_rate": 3.35e-05,
|
| 254 |
+
"loss": 0.0104,
|
| 255 |
+
"step": 3300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 29.57,
|
| 259 |
+
"grad_norm": 0.03656579554080963,
|
| 260 |
+
"learning_rate": 3.3e-05,
|
| 261 |
+
"loss": 0.0065,
|
| 262 |
+
"step": 3400
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 30.43,
|
| 266 |
+
"grad_norm": 0.1510837972164154,
|
| 267 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 268 |
+
"loss": 0.0093,
|
| 269 |
+
"step": 3500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 31.3,
|
| 273 |
+
"grad_norm": 0.0025348912458866835,
|
| 274 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 275 |
+
"loss": 0.009,
|
| 276 |
+
"step": 3600
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 32.17,
|
| 280 |
+
"grad_norm": 0.002163603436201811,
|
| 281 |
+
"learning_rate": 3.15e-05,
|
| 282 |
+
"loss": 0.0077,
|
| 283 |
+
"step": 3700
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 33.04,
|
| 287 |
+
"grad_norm": 0.0018990840762853622,
|
| 288 |
+
"learning_rate": 3.1e-05,
|
| 289 |
+
"loss": 0.0041,
|
| 290 |
+
"step": 3800
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 33.91,
|
| 294 |
+
"grad_norm": 0.0013024972286075354,
|
| 295 |
+
"learning_rate": 3.05e-05,
|
| 296 |
+
"loss": 0.0073,
|
| 297 |
+
"step": 3900
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 34.78,
|
| 301 |
+
"grad_norm": 0.001054937718436122,
|
| 302 |
+
"learning_rate": 3e-05,
|
| 303 |
+
"loss": 0.0004,
|
| 304 |
+
"step": 4000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 34.78,
|
| 308 |
+
"eval_accuracy": 0.928921568627451,
|
| 309 |
+
"eval_brier_score": 0.0675812841670148,
|
| 310 |
+
"eval_ece": 0.06654327976353025,
|
| 311 |
+
"eval_f1": 0.9280259003838475,
|
| 312 |
+
"eval_loss": 0.5349375605583191,
|
| 313 |
+
"eval_nll": 7.384143338090662,
|
| 314 |
+
"eval_precision": 0.9287246020559013,
|
| 315 |
+
"eval_recall": 0.928921568627451,
|
| 316 |
+
"eval_runtime": 1.8817,
|
| 317 |
+
"eval_samples_per_second": 216.828,
|
| 318 |
+
"eval_steps_per_second": 6.909,
|
| 319 |
+
"step": 4000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 35.65,
|
| 323 |
+
"grad_norm": 0.0011927990708500147,
|
| 324 |
+
"learning_rate": 2.95e-05,
|
| 325 |
+
"loss": 0.0003,
|
| 326 |
+
"step": 4100
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 36.52,
|
| 330 |
+
"grad_norm": 0.0007499050698243082,
|
| 331 |
+
"learning_rate": 2.9e-05,
|
| 332 |
+
"loss": 0.0013,
|
| 333 |
+
"step": 4200
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 37.39,
|
| 337 |
+
"grad_norm": 0.0024869628250598907,
|
| 338 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 339 |
+
"loss": 0.0001,
|
| 340 |
+
"step": 4300
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 38.26,
|
| 344 |
+
"grad_norm": 0.018704690039157867,
|
| 345 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 346 |
+
"loss": 0.0099,
|
| 347 |
+
"step": 4400
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 39.13,
|
| 351 |
+
"grad_norm": 0.00480309734120965,
|
| 352 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 353 |
+
"loss": 0.0064,
|
| 354 |
+
"step": 4500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 40.0,
|
| 358 |
+
"grad_norm": 0.016563115641474724,
|
| 359 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 360 |
+
"loss": 0.0085,
|
| 361 |
+
"step": 4600
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 40.87,
|
| 365 |
+
"grad_norm": 0.0018221806967630982,
|
| 366 |
+
"learning_rate": 2.6500000000000004e-05,
|
| 367 |
+
"loss": 0.001,
|
| 368 |
+
"step": 4700
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 41.74,
|
| 372 |
+
"grad_norm": 0.0007343711331486702,
|
| 373 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 374 |
+
"loss": 0.0012,
|
| 375 |
+
"step": 4800
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 42.61,
|
| 379 |
+
"grad_norm": 0.008326762355864048,
|
| 380 |
+
"learning_rate": 2.5500000000000003e-05,
|
| 381 |
+
"loss": 0.0029,
|
| 382 |
+
"step": 4900
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 43.48,
|
| 386 |
+
"grad_norm": 0.004561099223792553,
|
| 387 |
+
"learning_rate": 2.5e-05,
|
| 388 |
+
"loss": 0.0004,
|
| 389 |
+
"step": 5000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 44.35,
|
| 393 |
+
"grad_norm": 0.0013891893904656172,
|
| 394 |
+
"learning_rate": 2.45e-05,
|
| 395 |
+
"loss": 0.0074,
|
| 396 |
+
"step": 5100
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 45.22,
|
| 400 |
+
"grad_norm": 0.013074066489934921,
|
| 401 |
+
"learning_rate": 2.4e-05,
|
| 402 |
+
"loss": 0.0018,
|
| 403 |
+
"step": 5200
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 46.09,
|
| 407 |
+
"grad_norm": 0.0006578834727406502,
|
| 408 |
+
"learning_rate": 2.35e-05,
|
| 409 |
+
"loss": 0.0,
|
| 410 |
+
"step": 5300
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 46.96,
|
| 414 |
+
"grad_norm": 0.0006401424179784954,
|
| 415 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 416 |
+
"loss": 0.0,
|
| 417 |
+
"step": 5400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 47.83,
|
| 421 |
+
"grad_norm": 0.000561197055503726,
|
| 422 |
+
"learning_rate": 2.25e-05,
|
| 423 |
+
"loss": 0.0024,
|
| 424 |
+
"step": 5500
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 48.7,
|
| 428 |
+
"grad_norm": 0.0004986047861166298,
|
| 429 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 430 |
+
"loss": 0.0,
|
| 431 |
+
"step": 5600
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 49.57,
|
| 435 |
+
"grad_norm": 0.0004820087051484734,
|
| 436 |
+
"learning_rate": 2.15e-05,
|
| 437 |
+
"loss": 0.0,
|
| 438 |
+
"step": 5700
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 50.43,
|
| 442 |
+
"grad_norm": 0.00033787055872380733,
|
| 443 |
+
"learning_rate": 2.1e-05,
|
| 444 |
+
"loss": 0.0,
|
| 445 |
+
"step": 5800
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 51.3,
|
| 449 |
+
"grad_norm": 0.00030797443469054997,
|
| 450 |
+
"learning_rate": 2.05e-05,
|
| 451 |
+
"loss": 0.0,
|
| 452 |
+
"step": 5900
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 52.17,
|
| 456 |
+
"grad_norm": 0.0003839946002699435,
|
| 457 |
+
"learning_rate": 2e-05,
|
| 458 |
+
"loss": 0.0,
|
| 459 |
+
"step": 6000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 52.17,
|
| 463 |
+
"eval_accuracy": 0.9191176470588235,
|
| 464 |
+
"eval_brier_score": 0.0754212002677414,
|
| 465 |
+
"eval_ece": 0.0762045159935951,
|
| 466 |
+
"eval_f1": 0.9180984383678263,
|
| 467 |
+
"eval_loss": 0.6726267337799072,
|
| 468 |
+
"eval_nll": 8.413597393856437,
|
| 469 |
+
"eval_precision": 0.9186496544848213,
|
| 470 |
+
"eval_recall": 0.9191176470588235,
|
| 471 |
+
"eval_runtime": 1.8842,
|
| 472 |
+
"eval_samples_per_second": 216.536,
|
| 473 |
+
"eval_steps_per_second": 6.899,
|
| 474 |
+
"step": 6000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 53.04,
|
| 478 |
+
"grad_norm": 0.00035972893238067627,
|
| 479 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 480 |
+
"loss": 0.0,
|
| 481 |
+
"step": 6100
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 53.91,
|
| 485 |
+
"grad_norm": 0.0002692355774343014,
|
| 486 |
+
"learning_rate": 1.9e-05,
|
| 487 |
+
"loss": 0.0,
|
| 488 |
+
"step": 6200
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 54.78,
|
| 492 |
+
"grad_norm": 0.0003426405892241746,
|
| 493 |
+
"learning_rate": 1.85e-05,
|
| 494 |
+
"loss": 0.0,
|
| 495 |
+
"step": 6300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 55.65,
|
| 499 |
+
"grad_norm": 0.00027685274835675955,
|
| 500 |
+
"learning_rate": 1.8e-05,
|
| 501 |
+
"loss": 0.0,
|
| 502 |
+
"step": 6400
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 56.52,
|
| 506 |
+
"grad_norm": 0.00028565863613039255,
|
| 507 |
+
"learning_rate": 1.75e-05,
|
| 508 |
+
"loss": 0.0,
|
| 509 |
+
"step": 6500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 57.39,
|
| 513 |
+
"grad_norm": 0.0002044347784249112,
|
| 514 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 515 |
+
"loss": 0.0,
|
| 516 |
+
"step": 6600
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 58.26,
|
| 520 |
+
"grad_norm": 0.00019555067410692573,
|
| 521 |
+
"learning_rate": 1.65e-05,
|
| 522 |
+
"loss": 0.0,
|
| 523 |
+
"step": 6700
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 59.13,
|
| 527 |
+
"grad_norm": 13.264129638671875,
|
| 528 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 529 |
+
"loss": 0.0001,
|
| 530 |
+
"step": 6800
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 60.0,
|
| 534 |
+
"grad_norm": 0.00021661369828507304,
|
| 535 |
+
"learning_rate": 1.55e-05,
|
| 536 |
+
"loss": 0.0071,
|
| 537 |
+
"step": 6900
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 60.87,
|
| 541 |
+
"grad_norm": 0.0025544350501149893,
|
| 542 |
+
"learning_rate": 1.5e-05,
|
| 543 |
+
"loss": 0.0047,
|
| 544 |
+
"step": 7000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 61.74,
|
| 548 |
+
"grad_norm": 0.00023375553428195417,
|
| 549 |
+
"learning_rate": 1.45e-05,
|
| 550 |
+
"loss": 0.0028,
|
| 551 |
+
"step": 7100
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 62.61,
|
| 555 |
+
"grad_norm": 0.00046280986862257123,
|
| 556 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 557 |
+
"loss": 0.0001,
|
| 558 |
+
"step": 7200
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 63.48,
|
| 562 |
+
"grad_norm": 0.0054445345886051655,
|
| 563 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 564 |
+
"loss": 0.0061,
|
| 565 |
+
"step": 7300
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 64.35,
|
| 569 |
+
"grad_norm": 0.0021262529771775007,
|
| 570 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 571 |
+
"loss": 0.0001,
|
| 572 |
+
"step": 7400
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 65.22,
|
| 576 |
+
"grad_norm": 0.0005580468568950891,
|
| 577 |
+
"learning_rate": 1.25e-05,
|
| 578 |
+
"loss": 0.0031,
|
| 579 |
+
"step": 7500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 66.09,
|
| 583 |
+
"grad_norm": 0.0004650899500120431,
|
| 584 |
+
"learning_rate": 1.2e-05,
|
| 585 |
+
"loss": 0.0001,
|
| 586 |
+
"step": 7600
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 66.96,
|
| 590 |
+
"grad_norm": 0.0006638153572566807,
|
| 591 |
+
"learning_rate": 1.1500000000000002e-05,
|
| 592 |
+
"loss": 0.0,
|
| 593 |
+
"step": 7700
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 67.83,
|
| 597 |
+
"grad_norm": 0.0004998428630642593,
|
| 598 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 599 |
+
"loss": 0.0,
|
| 600 |
+
"step": 7800
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 68.7,
|
| 604 |
+
"grad_norm": 0.00034490320831537247,
|
| 605 |
+
"learning_rate": 1.05e-05,
|
| 606 |
+
"loss": 0.0,
|
| 607 |
+
"step": 7900
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 69.57,
|
| 611 |
+
"grad_norm": 0.000332407042151317,
|
| 612 |
+
"learning_rate": 1e-05,
|
| 613 |
+
"loss": 0.0008,
|
| 614 |
+
"step": 8000
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 69.57,
|
| 618 |
+
"eval_accuracy": 0.9093137254901961,
|
| 619 |
+
"eval_brier_score": 0.08612374447215236,
|
| 620 |
+
"eval_ece": 0.08567111121088852,
|
| 621 |
+
"eval_f1": 0.9088203082186265,
|
| 622 |
+
"eval_loss": 0.7547056078910828,
|
| 623 |
+
"eval_nll": 8.256409546928781,
|
| 624 |
+
"eval_precision": 0.908638620145923,
|
| 625 |
+
"eval_recall": 0.9093137254901961,
|
| 626 |
+
"eval_runtime": 1.8815,
|
| 627 |
+
"eval_samples_per_second": 216.849,
|
| 628 |
+
"eval_steps_per_second": 6.909,
|
| 629 |
+
"step": 8000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 70.43,
|
| 633 |
+
"grad_norm": 0.00023413883172906935,
|
| 634 |
+
"learning_rate": 9.5e-06,
|
| 635 |
+
"loss": 0.0002,
|
| 636 |
+
"step": 8100
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 71.3,
|
| 640 |
+
"grad_norm": 23.99155616760254,
|
| 641 |
+
"learning_rate": 9e-06,
|
| 642 |
+
"loss": 0.0063,
|
| 643 |
+
"step": 8200
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 72.17,
|
| 647 |
+
"grad_norm": 0.0003871929075103253,
|
| 648 |
+
"learning_rate": 8.500000000000002e-06,
|
| 649 |
+
"loss": 0.0005,
|
| 650 |
+
"step": 8300
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 73.04,
|
| 654 |
+
"grad_norm": 0.00042980830767191947,
|
| 655 |
+
"learning_rate": 8.000000000000001e-06,
|
| 656 |
+
"loss": 0.0,
|
| 657 |
+
"step": 8400
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 73.91,
|
| 661 |
+
"grad_norm": 0.0013252117205411196,
|
| 662 |
+
"learning_rate": 7.5e-06,
|
| 663 |
+
"loss": 0.0019,
|
| 664 |
+
"step": 8500
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 74.78,
|
| 668 |
+
"grad_norm": 0.00030255893943831325,
|
| 669 |
+
"learning_rate": 7.000000000000001e-06,
|
| 670 |
+
"loss": 0.0001,
|
| 671 |
+
"step": 8600
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 75.65,
|
| 675 |
+
"grad_norm": 0.000279304978903383,
|
| 676 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 677 |
+
"loss": 0.0,
|
| 678 |
+
"step": 8700
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 76.52,
|
| 682 |
+
"grad_norm": 0.00023628314374946058,
|
| 683 |
+
"learning_rate": 6e-06,
|
| 684 |
+
"loss": 0.0,
|
| 685 |
+
"step": 8800
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 77.39,
|
| 689 |
+
"grad_norm": 0.00026065990095958114,
|
| 690 |
+
"learning_rate": 5.500000000000001e-06,
|
| 691 |
+
"loss": 0.0,
|
| 692 |
+
"step": 8900
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 78.26,
|
| 696 |
+
"grad_norm": 0.0002733684959821403,
|
| 697 |
+
"learning_rate": 5e-06,
|
| 698 |
+
"loss": 0.0,
|
| 699 |
+
"step": 9000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 79.13,
|
| 703 |
+
"grad_norm": 0.000217767694266513,
|
| 704 |
+
"learning_rate": 4.5e-06,
|
| 705 |
+
"loss": 0.0,
|
| 706 |
+
"step": 9100
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 80.0,
|
| 710 |
+
"grad_norm": 0.00022373067622538656,
|
| 711 |
+
"learning_rate": 4.000000000000001e-06,
|
| 712 |
+
"loss": 0.0001,
|
| 713 |
+
"step": 9200
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 80.87,
|
| 717 |
+
"grad_norm": 0.00025432344409637153,
|
| 718 |
+
"learning_rate": 3.5000000000000004e-06,
|
| 719 |
+
"loss": 0.0,
|
| 720 |
+
"step": 9300
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 81.74,
|
| 724 |
+
"grad_norm": 0.00020336911256890744,
|
| 725 |
+
"learning_rate": 3e-06,
|
| 726 |
+
"loss": 0.0,
|
| 727 |
+
"step": 9400
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 82.61,
|
| 731 |
+
"grad_norm": 0.00014633308455813676,
|
| 732 |
+
"learning_rate": 2.5e-06,
|
| 733 |
+
"loss": 0.0,
|
| 734 |
+
"step": 9500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 83.48,
|
| 738 |
+
"grad_norm": 0.0003040888987015933,
|
| 739 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 740 |
+
"loss": 0.0,
|
| 741 |
+
"step": 9600
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 84.35,
|
| 745 |
+
"grad_norm": 0.00023693699040450156,
|
| 746 |
+
"learning_rate": 1.5e-06,
|
| 747 |
+
"loss": 0.0,
|
| 748 |
+
"step": 9700
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 85.22,
|
| 752 |
+
"grad_norm": 0.00015578049351461232,
|
| 753 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 754 |
+
"loss": 0.0,
|
| 755 |
+
"step": 9800
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 86.09,
|
| 759 |
+
"grad_norm": 0.00019774572865571827,
|
| 760 |
+
"learning_rate": 5.000000000000001e-07,
|
| 761 |
+
"loss": 0.0,
|
| 762 |
+
"step": 9900
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 86.96,
|
| 766 |
+
"grad_norm": 0.00021942751482129097,
|
| 767 |
+
"learning_rate": 0.0,
|
| 768 |
+
"loss": 0.0,
|
| 769 |
+
"step": 10000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 86.96,
|
| 773 |
+
"eval_accuracy": 0.9240196078431373,
|
| 774 |
+
"eval_brier_score": 0.07567827359639122,
|
| 775 |
+
"eval_ece": 0.07723997489494433,
|
| 776 |
+
"eval_f1": 0.9226690417618795,
|
| 777 |
+
"eval_loss": 0.6729016900062561,
|
| 778 |
+
"eval_nll": 8.918727569637431,
|
| 779 |
+
"eval_precision": 0.9243157789431563,
|
| 780 |
+
"eval_recall": 0.9240196078431373,
|
| 781 |
+
"eval_runtime": 1.8795,
|
| 782 |
+
"eval_samples_per_second": 217.075,
|
| 783 |
+
"eval_steps_per_second": 6.917,
|
| 784 |
+
"step": 10000
|
| 785 |
+
}
|
| 786 |
+
],
|
| 787 |
+
"logging_steps": 100,
|
| 788 |
+
"max_steps": 10000,
|
| 789 |
+
"num_input_tokens_seen": 0,
|
| 790 |
+
"num_train_epochs": 87,
|
| 791 |
+
"save_steps": 2000,
|
| 792 |
+
"total_flos": 1.309401561437256e+16,
|
| 793 |
+
"train_batch_size": 32,
|
| 794 |
+
"trial_name": null,
|
| 795 |
+
"trial_params": null
|
| 796 |
+
}
|
mrpc/checkpoint-10000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45b5ff4c6acb47d0ce7d42bf9d0586515d220366e0d122459e5c18115cd14676
|
| 3 |
+
size 4856
|
mrpc/{vocab.txt → checkpoint-10000/vocab.txt}
RENAMED
|
File without changes
|
mrpc/checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.38.2",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
+
}
|
mrpc/checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:057ad95edf9c0585f999dbc22f3910bbd8b7a7c79ac071dc7f1054dacad98b36
|
| 3 |
+
size 437958648
|
mrpc/checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0169d13508ae576728ae5babd5fdf36d946cd4c2cebd6408e664928fe7f1def1
|
| 3 |
+
size 14244
|
mrpc/checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18c16bda23fbf1fb322914b976482d4c125418dca6a7d13ef911e96abca76529
|
| 3 |
+
size 1064
|
mrpc/checkpoint-2000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
mrpc/checkpoint-2000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
mrpc/checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 17.391304347826086,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.87,
|
| 13 |
+
"grad_norm": 4.196278095245361,
|
| 14 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 15 |
+
"loss": 0.5435,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.74,
|
| 20 |
+
"grad_norm": 8.441207885742188,
|
| 21 |
+
"learning_rate": 4.9e-05,
|
| 22 |
+
"loss": 0.2564,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.61,
|
| 27 |
+
"grad_norm": 8.456403732299805,
|
| 28 |
+
"learning_rate": 4.85e-05,
|
| 29 |
+
"loss": 0.1488,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 3.48,
|
| 34 |
+
"grad_norm": 0.8015245795249939,
|
| 35 |
+
"learning_rate": 4.8e-05,
|
| 36 |
+
"loss": 0.0688,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 4.35,
|
| 41 |
+
"grad_norm": 0.2079729586839676,
|
| 42 |
+
"learning_rate": 4.75e-05,
|
| 43 |
+
"loss": 0.0622,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.22,
|
| 48 |
+
"grad_norm": 0.10826250910758972,
|
| 49 |
+
"learning_rate": 4.7e-05,
|
| 50 |
+
"loss": 0.0491,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.09,
|
| 55 |
+
"grad_norm": 15.216827392578125,
|
| 56 |
+
"learning_rate": 4.6500000000000005e-05,
|
| 57 |
+
"loss": 0.0328,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 6.96,
|
| 62 |
+
"grad_norm": 15.634430885314941,
|
| 63 |
+
"learning_rate": 4.600000000000001e-05,
|
| 64 |
+
"loss": 0.0306,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 7.83,
|
| 69 |
+
"grad_norm": 31.188247680664062,
|
| 70 |
+
"learning_rate": 4.55e-05,
|
| 71 |
+
"loss": 0.0182,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.7,
|
| 76 |
+
"grad_norm": 0.016402140259742737,
|
| 77 |
+
"learning_rate": 4.5e-05,
|
| 78 |
+
"loss": 0.0222,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 9.57,
|
| 83 |
+
"grad_norm": 31.216285705566406,
|
| 84 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 85 |
+
"loss": 0.0181,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 10.43,
|
| 90 |
+
"grad_norm": 0.2328696846961975,
|
| 91 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 92 |
+
"loss": 0.0121,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 11.3,
|
| 97 |
+
"grad_norm": 0.007173949386924505,
|
| 98 |
+
"learning_rate": 4.35e-05,
|
| 99 |
+
"loss": 0.0253,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 12.17,
|
| 104 |
+
"grad_norm": 0.003974032588303089,
|
| 105 |
+
"learning_rate": 4.3e-05,
|
| 106 |
+
"loss": 0.0099,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 13.04,
|
| 111 |
+
"grad_norm": 0.3920653164386749,
|
| 112 |
+
"learning_rate": 4.25e-05,
|
| 113 |
+
"loss": 0.0172,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 13.91,
|
| 118 |
+
"grad_norm": 1.2646549940109253,
|
| 119 |
+
"learning_rate": 4.2e-05,
|
| 120 |
+
"loss": 0.0295,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 14.78,
|
| 125 |
+
"grad_norm": 0.07062631100416183,
|
| 126 |
+
"learning_rate": 4.15e-05,
|
| 127 |
+
"loss": 0.0181,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 15.65,
|
| 132 |
+
"grad_norm": 0.005436008796095848,
|
| 133 |
+
"learning_rate": 4.1e-05,
|
| 134 |
+
"loss": 0.0067,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 16.52,
|
| 139 |
+
"grad_norm": 0.004679691046476364,
|
| 140 |
+
"learning_rate": 4.05e-05,
|
| 141 |
+
"loss": 0.02,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 17.39,
|
| 146 |
+
"grad_norm": 0.01030748151242733,
|
| 147 |
+
"learning_rate": 4e-05,
|
| 148 |
+
"loss": 0.0197,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 17.39,
|
| 153 |
+
"eval_accuracy": 0.9387254901960784,
|
| 154 |
+
"eval_brier_score": 0.05757000434820965,
|
| 155 |
+
"eval_ece": 0.05797517591831729,
|
| 156 |
+
"eval_f1": 0.9382506413699704,
|
| 157 |
+
"eval_loss": 0.40406298637390137,
|
| 158 |
+
"eval_nll": 6.776806058077595,
|
| 159 |
+
"eval_precision": 0.9384196444828075,
|
| 160 |
+
"eval_recall": 0.9387254901960784,
|
| 161 |
+
"eval_runtime": 1.9112,
|
| 162 |
+
"eval_samples_per_second": 213.478,
|
| 163 |
+
"eval_steps_per_second": 6.802,
|
| 164 |
+
"step": 2000
|
| 165 |
+
}
|
| 166 |
+
],
|
| 167 |
+
"logging_steps": 100,
|
| 168 |
+
"max_steps": 10000,
|
| 169 |
+
"num_input_tokens_seen": 0,
|
| 170 |
+
"num_train_epochs": 87,
|
| 171 |
+
"save_steps": 2000,
|
| 172 |
+
"total_flos": 2619132833915760.0,
|
| 173 |
+
"train_batch_size": 32,
|
| 174 |
+
"trial_name": null,
|
| 175 |
+
"trial_params": null
|
| 176 |
+
}
|
mrpc/checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45b5ff4c6acb47d0ce7d42bf9d0586515d220366e0d122459e5c18115cd14676
|
| 3 |
+
size 4856
|
mrpc/checkpoint-2000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mrpc/checkpoint-4000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.38.2",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
+
}
|
mrpc/checkpoint-4000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b22537fc80682a69f39a3bd686681e6af04c67781d6de9d3bc2fc7043970fe80
|
| 3 |
+
size 437958648
|
mrpc/checkpoint-4000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc52e99503fdbf70503643accbc25a705f4a4638b8401a83723befaee70f554d
|
| 3 |
+
size 14244
|
mrpc/checkpoint-4000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:762a291429a0f63ee6b6218939182d9a927a5c2da96c23ee68a024d92a257f72
|
| 3 |
+
size 1064
|
mrpc/checkpoint-4000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
mrpc/checkpoint-4000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
mrpc/checkpoint-4000/trainer_state.json
ADDED
|
@@ -0,0 +1,331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 34.78260869565217,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 4000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.87,
|
| 13 |
+
"grad_norm": 4.196278095245361,
|
| 14 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 15 |
+
"loss": 0.5435,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.74,
|
| 20 |
+
"grad_norm": 8.441207885742188,
|
| 21 |
+
"learning_rate": 4.9e-05,
|
| 22 |
+
"loss": 0.2564,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.61,
|
| 27 |
+
"grad_norm": 8.456403732299805,
|
| 28 |
+
"learning_rate": 4.85e-05,
|
| 29 |
+
"loss": 0.1488,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 3.48,
|
| 34 |
+
"grad_norm": 0.8015245795249939,
|
| 35 |
+
"learning_rate": 4.8e-05,
|
| 36 |
+
"loss": 0.0688,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 4.35,
|
| 41 |
+
"grad_norm": 0.2079729586839676,
|
| 42 |
+
"learning_rate": 4.75e-05,
|
| 43 |
+
"loss": 0.0622,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.22,
|
| 48 |
+
"grad_norm": 0.10826250910758972,
|
| 49 |
+
"learning_rate": 4.7e-05,
|
| 50 |
+
"loss": 0.0491,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.09,
|
| 55 |
+
"grad_norm": 15.216827392578125,
|
| 56 |
+
"learning_rate": 4.6500000000000005e-05,
|
| 57 |
+
"loss": 0.0328,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 6.96,
|
| 62 |
+
"grad_norm": 15.634430885314941,
|
| 63 |
+
"learning_rate": 4.600000000000001e-05,
|
| 64 |
+
"loss": 0.0306,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 7.83,
|
| 69 |
+
"grad_norm": 31.188247680664062,
|
| 70 |
+
"learning_rate": 4.55e-05,
|
| 71 |
+
"loss": 0.0182,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.7,
|
| 76 |
+
"grad_norm": 0.016402140259742737,
|
| 77 |
+
"learning_rate": 4.5e-05,
|
| 78 |
+
"loss": 0.0222,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 9.57,
|
| 83 |
+
"grad_norm": 31.216285705566406,
|
| 84 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 85 |
+
"loss": 0.0181,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 10.43,
|
| 90 |
+
"grad_norm": 0.2328696846961975,
|
| 91 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 92 |
+
"loss": 0.0121,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 11.3,
|
| 97 |
+
"grad_norm": 0.007173949386924505,
|
| 98 |
+
"learning_rate": 4.35e-05,
|
| 99 |
+
"loss": 0.0253,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 12.17,
|
| 104 |
+
"grad_norm": 0.003974032588303089,
|
| 105 |
+
"learning_rate": 4.3e-05,
|
| 106 |
+
"loss": 0.0099,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 13.04,
|
| 111 |
+
"grad_norm": 0.3920653164386749,
|
| 112 |
+
"learning_rate": 4.25e-05,
|
| 113 |
+
"loss": 0.0172,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 13.91,
|
| 118 |
+
"grad_norm": 1.2646549940109253,
|
| 119 |
+
"learning_rate": 4.2e-05,
|
| 120 |
+
"loss": 0.0295,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 14.78,
|
| 125 |
+
"grad_norm": 0.07062631100416183,
|
| 126 |
+
"learning_rate": 4.15e-05,
|
| 127 |
+
"loss": 0.0181,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 15.65,
|
| 132 |
+
"grad_norm": 0.005436008796095848,
|
| 133 |
+
"learning_rate": 4.1e-05,
|
| 134 |
+
"loss": 0.0067,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 16.52,
|
| 139 |
+
"grad_norm": 0.004679691046476364,
|
| 140 |
+
"learning_rate": 4.05e-05,
|
| 141 |
+
"loss": 0.02,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 17.39,
|
| 146 |
+
"grad_norm": 0.01030748151242733,
|
| 147 |
+
"learning_rate": 4e-05,
|
| 148 |
+
"loss": 0.0197,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 17.39,
|
| 153 |
+
"eval_accuracy": 0.9387254901960784,
|
| 154 |
+
"eval_brier_score": 0.05757000434820965,
|
| 155 |
+
"eval_ece": 0.05797517591831729,
|
| 156 |
+
"eval_f1": 0.9382506413699704,
|
| 157 |
+
"eval_loss": 0.40406298637390137,
|
| 158 |
+
"eval_nll": 6.776806058077595,
|
| 159 |
+
"eval_precision": 0.9384196444828075,
|
| 160 |
+
"eval_recall": 0.9387254901960784,
|
| 161 |
+
"eval_runtime": 1.9112,
|
| 162 |
+
"eval_samples_per_second": 213.478,
|
| 163 |
+
"eval_steps_per_second": 6.802,
|
| 164 |
+
"step": 2000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 18.26,
|
| 168 |
+
"grad_norm": 0.004601624328643084,
|
| 169 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 170 |
+
"loss": 0.0158,
|
| 171 |
+
"step": 2100
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 19.13,
|
| 175 |
+
"grad_norm": 0.012901573441922665,
|
| 176 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 177 |
+
"loss": 0.0092,
|
| 178 |
+
"step": 2200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 20.0,
|
| 182 |
+
"grad_norm": 0.00762163195759058,
|
| 183 |
+
"learning_rate": 3.85e-05,
|
| 184 |
+
"loss": 0.0082,
|
| 185 |
+
"step": 2300
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 20.87,
|
| 189 |
+
"grad_norm": 0.154510959982872,
|
| 190 |
+
"learning_rate": 3.8e-05,
|
| 191 |
+
"loss": 0.0131,
|
| 192 |
+
"step": 2400
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 21.74,
|
| 196 |
+
"grad_norm": 0.003832124872133136,
|
| 197 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 198 |
+
"loss": 0.0201,
|
| 199 |
+
"step": 2500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 22.61,
|
| 203 |
+
"grad_norm": 0.0029927650466561317,
|
| 204 |
+
"learning_rate": 3.7e-05,
|
| 205 |
+
"loss": 0.019,
|
| 206 |
+
"step": 2600
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 23.48,
|
| 210 |
+
"grad_norm": 0.0018748922739177942,
|
| 211 |
+
"learning_rate": 3.65e-05,
|
| 212 |
+
"loss": 0.0086,
|
| 213 |
+
"step": 2700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 24.35,
|
| 217 |
+
"grad_norm": 0.14622557163238525,
|
| 218 |
+
"learning_rate": 3.6e-05,
|
| 219 |
+
"loss": 0.01,
|
| 220 |
+
"step": 2800
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 25.22,
|
| 224 |
+
"grad_norm": 0.03812519088387489,
|
| 225 |
+
"learning_rate": 3.55e-05,
|
| 226 |
+
"loss": 0.0234,
|
| 227 |
+
"step": 2900
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 26.09,
|
| 231 |
+
"grad_norm": 24.803911209106445,
|
| 232 |
+
"learning_rate": 3.5e-05,
|
| 233 |
+
"loss": 0.0119,
|
| 234 |
+
"step": 3000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 26.96,
|
| 238 |
+
"grad_norm": 0.00613383948802948,
|
| 239 |
+
"learning_rate": 3.45e-05,
|
| 240 |
+
"loss": 0.0129,
|
| 241 |
+
"step": 3100
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 27.83,
|
| 245 |
+
"grad_norm": 0.005301126278936863,
|
| 246 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 247 |
+
"loss": 0.0086,
|
| 248 |
+
"step": 3200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 28.7,
|
| 252 |
+
"grad_norm": 0.0037701462861150503,
|
| 253 |
+
"learning_rate": 3.35e-05,
|
| 254 |
+
"loss": 0.0104,
|
| 255 |
+
"step": 3300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 29.57,
|
| 259 |
+
"grad_norm": 0.03656579554080963,
|
| 260 |
+
"learning_rate": 3.3e-05,
|
| 261 |
+
"loss": 0.0065,
|
| 262 |
+
"step": 3400
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 30.43,
|
| 266 |
+
"grad_norm": 0.1510837972164154,
|
| 267 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 268 |
+
"loss": 0.0093,
|
| 269 |
+
"step": 3500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 31.3,
|
| 273 |
+
"grad_norm": 0.0025348912458866835,
|
| 274 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 275 |
+
"loss": 0.009,
|
| 276 |
+
"step": 3600
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 32.17,
|
| 280 |
+
"grad_norm": 0.002163603436201811,
|
| 281 |
+
"learning_rate": 3.15e-05,
|
| 282 |
+
"loss": 0.0077,
|
| 283 |
+
"step": 3700
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 33.04,
|
| 287 |
+
"grad_norm": 0.0018990840762853622,
|
| 288 |
+
"learning_rate": 3.1e-05,
|
| 289 |
+
"loss": 0.0041,
|
| 290 |
+
"step": 3800
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 33.91,
|
| 294 |
+
"grad_norm": 0.0013024972286075354,
|
| 295 |
+
"learning_rate": 3.05e-05,
|
| 296 |
+
"loss": 0.0073,
|
| 297 |
+
"step": 3900
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 34.78,
|
| 301 |
+
"grad_norm": 0.001054937718436122,
|
| 302 |
+
"learning_rate": 3e-05,
|
| 303 |
+
"loss": 0.0004,
|
| 304 |
+
"step": 4000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 34.78,
|
| 308 |
+
"eval_accuracy": 0.928921568627451,
|
| 309 |
+
"eval_brier_score": 0.0675812841670148,
|
| 310 |
+
"eval_ece": 0.06654327976353025,
|
| 311 |
+
"eval_f1": 0.9280259003838475,
|
| 312 |
+
"eval_loss": 0.5349375605583191,
|
| 313 |
+
"eval_nll": 7.384143338090662,
|
| 314 |
+
"eval_precision": 0.9287246020559013,
|
| 315 |
+
"eval_recall": 0.928921568627451,
|
| 316 |
+
"eval_runtime": 1.8817,
|
| 317 |
+
"eval_samples_per_second": 216.828,
|
| 318 |
+
"eval_steps_per_second": 6.909,
|
| 319 |
+
"step": 4000
|
| 320 |
+
}
|
| 321 |
+
],
|
| 322 |
+
"logging_steps": 100,
|
| 323 |
+
"max_steps": 10000,
|
| 324 |
+
"num_input_tokens_seen": 0,
|
| 325 |
+
"num_train_epochs": 87,
|
| 326 |
+
"save_steps": 2000,
|
| 327 |
+
"total_flos": 5238097112311680.0,
|
| 328 |
+
"train_batch_size": 32,
|
| 329 |
+
"trial_name": null,
|
| 330 |
+
"trial_params": null
|
| 331 |
+
}
|
mrpc/checkpoint-4000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45b5ff4c6acb47d0ce7d42bf9d0586515d220366e0d122459e5c18115cd14676
|
| 3 |
+
size 4856
|
mrpc/checkpoint-4000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mrpc/checkpoint-6000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.38.2",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
+
}
|
mrpc/checkpoint-6000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4edfda67a5199ee8af0db9977118268aafe607781583003f5fef6d653fb9fa02
|
| 3 |
+
size 437958648
|
mrpc/checkpoint-6000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d317567d04062c1441078a17c798abea95f9da99ef8fd11326fc7a13753e7d4a
|
| 3 |
+
size 14244
|
mrpc/checkpoint-6000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d39394b88b23cb5c76f884a0327727196168ba1cf0c4264a8ef3e18494b8591
|
| 3 |
+
size 1064
|
mrpc/checkpoint-6000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
mrpc/checkpoint-6000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
mrpc/checkpoint-6000/trainer_state.json
ADDED
|
@@ -0,0 +1,486 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 52.17391304347826,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 6000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.87,
|
| 13 |
+
"grad_norm": 4.196278095245361,
|
| 14 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 15 |
+
"loss": 0.5435,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.74,
|
| 20 |
+
"grad_norm": 8.441207885742188,
|
| 21 |
+
"learning_rate": 4.9e-05,
|
| 22 |
+
"loss": 0.2564,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.61,
|
| 27 |
+
"grad_norm": 8.456403732299805,
|
| 28 |
+
"learning_rate": 4.85e-05,
|
| 29 |
+
"loss": 0.1488,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 3.48,
|
| 34 |
+
"grad_norm": 0.8015245795249939,
|
| 35 |
+
"learning_rate": 4.8e-05,
|
| 36 |
+
"loss": 0.0688,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 4.35,
|
| 41 |
+
"grad_norm": 0.2079729586839676,
|
| 42 |
+
"learning_rate": 4.75e-05,
|
| 43 |
+
"loss": 0.0622,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.22,
|
| 48 |
+
"grad_norm": 0.10826250910758972,
|
| 49 |
+
"learning_rate": 4.7e-05,
|
| 50 |
+
"loss": 0.0491,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.09,
|
| 55 |
+
"grad_norm": 15.216827392578125,
|
| 56 |
+
"learning_rate": 4.6500000000000005e-05,
|
| 57 |
+
"loss": 0.0328,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 6.96,
|
| 62 |
+
"grad_norm": 15.634430885314941,
|
| 63 |
+
"learning_rate": 4.600000000000001e-05,
|
| 64 |
+
"loss": 0.0306,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 7.83,
|
| 69 |
+
"grad_norm": 31.188247680664062,
|
| 70 |
+
"learning_rate": 4.55e-05,
|
| 71 |
+
"loss": 0.0182,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.7,
|
| 76 |
+
"grad_norm": 0.016402140259742737,
|
| 77 |
+
"learning_rate": 4.5e-05,
|
| 78 |
+
"loss": 0.0222,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 9.57,
|
| 83 |
+
"grad_norm": 31.216285705566406,
|
| 84 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 85 |
+
"loss": 0.0181,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 10.43,
|
| 90 |
+
"grad_norm": 0.2328696846961975,
|
| 91 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 92 |
+
"loss": 0.0121,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 11.3,
|
| 97 |
+
"grad_norm": 0.007173949386924505,
|
| 98 |
+
"learning_rate": 4.35e-05,
|
| 99 |
+
"loss": 0.0253,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 12.17,
|
| 104 |
+
"grad_norm": 0.003974032588303089,
|
| 105 |
+
"learning_rate": 4.3e-05,
|
| 106 |
+
"loss": 0.0099,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 13.04,
|
| 111 |
+
"grad_norm": 0.3920653164386749,
|
| 112 |
+
"learning_rate": 4.25e-05,
|
| 113 |
+
"loss": 0.0172,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 13.91,
|
| 118 |
+
"grad_norm": 1.2646549940109253,
|
| 119 |
+
"learning_rate": 4.2e-05,
|
| 120 |
+
"loss": 0.0295,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 14.78,
|
| 125 |
+
"grad_norm": 0.07062631100416183,
|
| 126 |
+
"learning_rate": 4.15e-05,
|
| 127 |
+
"loss": 0.0181,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 15.65,
|
| 132 |
+
"grad_norm": 0.005436008796095848,
|
| 133 |
+
"learning_rate": 4.1e-05,
|
| 134 |
+
"loss": 0.0067,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 16.52,
|
| 139 |
+
"grad_norm": 0.004679691046476364,
|
| 140 |
+
"learning_rate": 4.05e-05,
|
| 141 |
+
"loss": 0.02,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 17.39,
|
| 146 |
+
"grad_norm": 0.01030748151242733,
|
| 147 |
+
"learning_rate": 4e-05,
|
| 148 |
+
"loss": 0.0197,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 17.39,
|
| 153 |
+
"eval_accuracy": 0.9387254901960784,
|
| 154 |
+
"eval_brier_score": 0.05757000434820965,
|
| 155 |
+
"eval_ece": 0.05797517591831729,
|
| 156 |
+
"eval_f1": 0.9382506413699704,
|
| 157 |
+
"eval_loss": 0.40406298637390137,
|
| 158 |
+
"eval_nll": 6.776806058077595,
|
| 159 |
+
"eval_precision": 0.9384196444828075,
|
| 160 |
+
"eval_recall": 0.9387254901960784,
|
| 161 |
+
"eval_runtime": 1.9112,
|
| 162 |
+
"eval_samples_per_second": 213.478,
|
| 163 |
+
"eval_steps_per_second": 6.802,
|
| 164 |
+
"step": 2000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 18.26,
|
| 168 |
+
"grad_norm": 0.004601624328643084,
|
| 169 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 170 |
+
"loss": 0.0158,
|
| 171 |
+
"step": 2100
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 19.13,
|
| 175 |
+
"grad_norm": 0.012901573441922665,
|
| 176 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 177 |
+
"loss": 0.0092,
|
| 178 |
+
"step": 2200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 20.0,
|
| 182 |
+
"grad_norm": 0.00762163195759058,
|
| 183 |
+
"learning_rate": 3.85e-05,
|
| 184 |
+
"loss": 0.0082,
|
| 185 |
+
"step": 2300
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 20.87,
|
| 189 |
+
"grad_norm": 0.154510959982872,
|
| 190 |
+
"learning_rate": 3.8e-05,
|
| 191 |
+
"loss": 0.0131,
|
| 192 |
+
"step": 2400
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 21.74,
|
| 196 |
+
"grad_norm": 0.003832124872133136,
|
| 197 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 198 |
+
"loss": 0.0201,
|
| 199 |
+
"step": 2500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 22.61,
|
| 203 |
+
"grad_norm": 0.0029927650466561317,
|
| 204 |
+
"learning_rate": 3.7e-05,
|
| 205 |
+
"loss": 0.019,
|
| 206 |
+
"step": 2600
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 23.48,
|
| 210 |
+
"grad_norm": 0.0018748922739177942,
|
| 211 |
+
"learning_rate": 3.65e-05,
|
| 212 |
+
"loss": 0.0086,
|
| 213 |
+
"step": 2700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 24.35,
|
| 217 |
+
"grad_norm": 0.14622557163238525,
|
| 218 |
+
"learning_rate": 3.6e-05,
|
| 219 |
+
"loss": 0.01,
|
| 220 |
+
"step": 2800
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 25.22,
|
| 224 |
+
"grad_norm": 0.03812519088387489,
|
| 225 |
+
"learning_rate": 3.55e-05,
|
| 226 |
+
"loss": 0.0234,
|
| 227 |
+
"step": 2900
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 26.09,
|
| 231 |
+
"grad_norm": 24.803911209106445,
|
| 232 |
+
"learning_rate": 3.5e-05,
|
| 233 |
+
"loss": 0.0119,
|
| 234 |
+
"step": 3000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 26.96,
|
| 238 |
+
"grad_norm": 0.00613383948802948,
|
| 239 |
+
"learning_rate": 3.45e-05,
|
| 240 |
+
"loss": 0.0129,
|
| 241 |
+
"step": 3100
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 27.83,
|
| 245 |
+
"grad_norm": 0.005301126278936863,
|
| 246 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 247 |
+
"loss": 0.0086,
|
| 248 |
+
"step": 3200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 28.7,
|
| 252 |
+
"grad_norm": 0.0037701462861150503,
|
| 253 |
+
"learning_rate": 3.35e-05,
|
| 254 |
+
"loss": 0.0104,
|
| 255 |
+
"step": 3300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 29.57,
|
| 259 |
+
"grad_norm": 0.03656579554080963,
|
| 260 |
+
"learning_rate": 3.3e-05,
|
| 261 |
+
"loss": 0.0065,
|
| 262 |
+
"step": 3400
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 30.43,
|
| 266 |
+
"grad_norm": 0.1510837972164154,
|
| 267 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 268 |
+
"loss": 0.0093,
|
| 269 |
+
"step": 3500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 31.3,
|
| 273 |
+
"grad_norm": 0.0025348912458866835,
|
| 274 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 275 |
+
"loss": 0.009,
|
| 276 |
+
"step": 3600
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 32.17,
|
| 280 |
+
"grad_norm": 0.002163603436201811,
|
| 281 |
+
"learning_rate": 3.15e-05,
|
| 282 |
+
"loss": 0.0077,
|
| 283 |
+
"step": 3700
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 33.04,
|
| 287 |
+
"grad_norm": 0.0018990840762853622,
|
| 288 |
+
"learning_rate": 3.1e-05,
|
| 289 |
+
"loss": 0.0041,
|
| 290 |
+
"step": 3800
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 33.91,
|
| 294 |
+
"grad_norm": 0.0013024972286075354,
|
| 295 |
+
"learning_rate": 3.05e-05,
|
| 296 |
+
"loss": 0.0073,
|
| 297 |
+
"step": 3900
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 34.78,
|
| 301 |
+
"grad_norm": 0.001054937718436122,
|
| 302 |
+
"learning_rate": 3e-05,
|
| 303 |
+
"loss": 0.0004,
|
| 304 |
+
"step": 4000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 34.78,
|
| 308 |
+
"eval_accuracy": 0.928921568627451,
|
| 309 |
+
"eval_brier_score": 0.0675812841670148,
|
| 310 |
+
"eval_ece": 0.06654327976353025,
|
| 311 |
+
"eval_f1": 0.9280259003838475,
|
| 312 |
+
"eval_loss": 0.5349375605583191,
|
| 313 |
+
"eval_nll": 7.384143338090662,
|
| 314 |
+
"eval_precision": 0.9287246020559013,
|
| 315 |
+
"eval_recall": 0.928921568627451,
|
| 316 |
+
"eval_runtime": 1.8817,
|
| 317 |
+
"eval_samples_per_second": 216.828,
|
| 318 |
+
"eval_steps_per_second": 6.909,
|
| 319 |
+
"step": 4000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 35.65,
|
| 323 |
+
"grad_norm": 0.0011927990708500147,
|
| 324 |
+
"learning_rate": 2.95e-05,
|
| 325 |
+
"loss": 0.0003,
|
| 326 |
+
"step": 4100
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 36.52,
|
| 330 |
+
"grad_norm": 0.0007499050698243082,
|
| 331 |
+
"learning_rate": 2.9e-05,
|
| 332 |
+
"loss": 0.0013,
|
| 333 |
+
"step": 4200
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 37.39,
|
| 337 |
+
"grad_norm": 0.0024869628250598907,
|
| 338 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 339 |
+
"loss": 0.0001,
|
| 340 |
+
"step": 4300
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 38.26,
|
| 344 |
+
"grad_norm": 0.018704690039157867,
|
| 345 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 346 |
+
"loss": 0.0099,
|
| 347 |
+
"step": 4400
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 39.13,
|
| 351 |
+
"grad_norm": 0.00480309734120965,
|
| 352 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 353 |
+
"loss": 0.0064,
|
| 354 |
+
"step": 4500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 40.0,
|
| 358 |
+
"grad_norm": 0.016563115641474724,
|
| 359 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 360 |
+
"loss": 0.0085,
|
| 361 |
+
"step": 4600
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 40.87,
|
| 365 |
+
"grad_norm": 0.0018221806967630982,
|
| 366 |
+
"learning_rate": 2.6500000000000004e-05,
|
| 367 |
+
"loss": 0.001,
|
| 368 |
+
"step": 4700
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 41.74,
|
| 372 |
+
"grad_norm": 0.0007343711331486702,
|
| 373 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 374 |
+
"loss": 0.0012,
|
| 375 |
+
"step": 4800
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 42.61,
|
| 379 |
+
"grad_norm": 0.008326762355864048,
|
| 380 |
+
"learning_rate": 2.5500000000000003e-05,
|
| 381 |
+
"loss": 0.0029,
|
| 382 |
+
"step": 4900
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 43.48,
|
| 386 |
+
"grad_norm": 0.004561099223792553,
|
| 387 |
+
"learning_rate": 2.5e-05,
|
| 388 |
+
"loss": 0.0004,
|
| 389 |
+
"step": 5000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 44.35,
|
| 393 |
+
"grad_norm": 0.0013891893904656172,
|
| 394 |
+
"learning_rate": 2.45e-05,
|
| 395 |
+
"loss": 0.0074,
|
| 396 |
+
"step": 5100
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 45.22,
|
| 400 |
+
"grad_norm": 0.013074066489934921,
|
| 401 |
+
"learning_rate": 2.4e-05,
|
| 402 |
+
"loss": 0.0018,
|
| 403 |
+
"step": 5200
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 46.09,
|
| 407 |
+
"grad_norm": 0.0006578834727406502,
|
| 408 |
+
"learning_rate": 2.35e-05,
|
| 409 |
+
"loss": 0.0,
|
| 410 |
+
"step": 5300
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 46.96,
|
| 414 |
+
"grad_norm": 0.0006401424179784954,
|
| 415 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 416 |
+
"loss": 0.0,
|
| 417 |
+
"step": 5400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 47.83,
|
| 421 |
+
"grad_norm": 0.000561197055503726,
|
| 422 |
+
"learning_rate": 2.25e-05,
|
| 423 |
+
"loss": 0.0024,
|
| 424 |
+
"step": 5500
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 48.7,
|
| 428 |
+
"grad_norm": 0.0004986047861166298,
|
| 429 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 430 |
+
"loss": 0.0,
|
| 431 |
+
"step": 5600
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 49.57,
|
| 435 |
+
"grad_norm": 0.0004820087051484734,
|
| 436 |
+
"learning_rate": 2.15e-05,
|
| 437 |
+
"loss": 0.0,
|
| 438 |
+
"step": 5700
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 50.43,
|
| 442 |
+
"grad_norm": 0.00033787055872380733,
|
| 443 |
+
"learning_rate": 2.1e-05,
|
| 444 |
+
"loss": 0.0,
|
| 445 |
+
"step": 5800
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 51.3,
|
| 449 |
+
"grad_norm": 0.00030797443469054997,
|
| 450 |
+
"learning_rate": 2.05e-05,
|
| 451 |
+
"loss": 0.0,
|
| 452 |
+
"step": 5900
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 52.17,
|
| 456 |
+
"grad_norm": 0.0003839946002699435,
|
| 457 |
+
"learning_rate": 2e-05,
|
| 458 |
+
"loss": 0.0,
|
| 459 |
+
"step": 6000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 52.17,
|
| 463 |
+
"eval_accuracy": 0.9191176470588235,
|
| 464 |
+
"eval_brier_score": 0.0754212002677414,
|
| 465 |
+
"eval_ece": 0.0762045159935951,
|
| 466 |
+
"eval_f1": 0.9180984383678263,
|
| 467 |
+
"eval_loss": 0.6726267337799072,
|
| 468 |
+
"eval_nll": 8.413597393856437,
|
| 469 |
+
"eval_precision": 0.9186496544848213,
|
| 470 |
+
"eval_recall": 0.9191176470588235,
|
| 471 |
+
"eval_runtime": 1.8842,
|
| 472 |
+
"eval_samples_per_second": 216.536,
|
| 473 |
+
"eval_steps_per_second": 6.899,
|
| 474 |
+
"step": 6000
|
| 475 |
+
}
|
| 476 |
+
],
|
| 477 |
+
"logging_steps": 100,
|
| 478 |
+
"max_steps": 10000,
|
| 479 |
+
"num_input_tokens_seen": 0,
|
| 480 |
+
"num_train_epochs": 87,
|
| 481 |
+
"save_steps": 2000,
|
| 482 |
+
"total_flos": 7856884612967280.0,
|
| 483 |
+
"train_batch_size": 32,
|
| 484 |
+
"trial_name": null,
|
| 485 |
+
"trial_params": null
|
| 486 |
+
}
|
mrpc/checkpoint-6000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45b5ff4c6acb47d0ce7d42bf9d0586515d220366e0d122459e5c18115cd14676
|
| 3 |
+
size 4856
|
mrpc/checkpoint-6000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mrpc/checkpoint-8000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"problem_type": "single_label_classification",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.38.2",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 30522
|
| 27 |
+
}
|
mrpc/checkpoint-8000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58e9babfeacdc78d4c4a7e57bc895a6263d23d8a086d8c4411b9b62d86639704
|
| 3 |
+
size 437958648
|
mrpc/checkpoint-8000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a91796f34d7399c36cd4ea75d4aefce1faa4f33dbcd163ec3c5699381803386a
|
| 3 |
+
size 14244
|
mrpc/checkpoint-8000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1f8795cd71b0ad726fc421a5a3758672326d602a89558c9fec480df511fbfa0
|
| 3 |
+
size 1064
|
mrpc/checkpoint-8000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
mrpc/checkpoint-8000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
mrpc/checkpoint-8000/trainer_state.json
ADDED
|
@@ -0,0 +1,641 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 69.56521739130434,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 8000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.87,
|
| 13 |
+
"grad_norm": 4.196278095245361,
|
| 14 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 15 |
+
"loss": 0.5435,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.74,
|
| 20 |
+
"grad_norm": 8.441207885742188,
|
| 21 |
+
"learning_rate": 4.9e-05,
|
| 22 |
+
"loss": 0.2564,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.61,
|
| 27 |
+
"grad_norm": 8.456403732299805,
|
| 28 |
+
"learning_rate": 4.85e-05,
|
| 29 |
+
"loss": 0.1488,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 3.48,
|
| 34 |
+
"grad_norm": 0.8015245795249939,
|
| 35 |
+
"learning_rate": 4.8e-05,
|
| 36 |
+
"loss": 0.0688,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 4.35,
|
| 41 |
+
"grad_norm": 0.2079729586839676,
|
| 42 |
+
"learning_rate": 4.75e-05,
|
| 43 |
+
"loss": 0.0622,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.22,
|
| 48 |
+
"grad_norm": 0.10826250910758972,
|
| 49 |
+
"learning_rate": 4.7e-05,
|
| 50 |
+
"loss": 0.0491,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.09,
|
| 55 |
+
"grad_norm": 15.216827392578125,
|
| 56 |
+
"learning_rate": 4.6500000000000005e-05,
|
| 57 |
+
"loss": 0.0328,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 6.96,
|
| 62 |
+
"grad_norm": 15.634430885314941,
|
| 63 |
+
"learning_rate": 4.600000000000001e-05,
|
| 64 |
+
"loss": 0.0306,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 7.83,
|
| 69 |
+
"grad_norm": 31.188247680664062,
|
| 70 |
+
"learning_rate": 4.55e-05,
|
| 71 |
+
"loss": 0.0182,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.7,
|
| 76 |
+
"grad_norm": 0.016402140259742737,
|
| 77 |
+
"learning_rate": 4.5e-05,
|
| 78 |
+
"loss": 0.0222,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 9.57,
|
| 83 |
+
"grad_norm": 31.216285705566406,
|
| 84 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 85 |
+
"loss": 0.0181,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 10.43,
|
| 90 |
+
"grad_norm": 0.2328696846961975,
|
| 91 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 92 |
+
"loss": 0.0121,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 11.3,
|
| 97 |
+
"grad_norm": 0.007173949386924505,
|
| 98 |
+
"learning_rate": 4.35e-05,
|
| 99 |
+
"loss": 0.0253,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 12.17,
|
| 104 |
+
"grad_norm": 0.003974032588303089,
|
| 105 |
+
"learning_rate": 4.3e-05,
|
| 106 |
+
"loss": 0.0099,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 13.04,
|
| 111 |
+
"grad_norm": 0.3920653164386749,
|
| 112 |
+
"learning_rate": 4.25e-05,
|
| 113 |
+
"loss": 0.0172,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 13.91,
|
| 118 |
+
"grad_norm": 1.2646549940109253,
|
| 119 |
+
"learning_rate": 4.2e-05,
|
| 120 |
+
"loss": 0.0295,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 14.78,
|
| 125 |
+
"grad_norm": 0.07062631100416183,
|
| 126 |
+
"learning_rate": 4.15e-05,
|
| 127 |
+
"loss": 0.0181,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 15.65,
|
| 132 |
+
"grad_norm": 0.005436008796095848,
|
| 133 |
+
"learning_rate": 4.1e-05,
|
| 134 |
+
"loss": 0.0067,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 16.52,
|
| 139 |
+
"grad_norm": 0.004679691046476364,
|
| 140 |
+
"learning_rate": 4.05e-05,
|
| 141 |
+
"loss": 0.02,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 17.39,
|
| 146 |
+
"grad_norm": 0.01030748151242733,
|
| 147 |
+
"learning_rate": 4e-05,
|
| 148 |
+
"loss": 0.0197,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 17.39,
|
| 153 |
+
"eval_accuracy": 0.9387254901960784,
|
| 154 |
+
"eval_brier_score": 0.05757000434820965,
|
| 155 |
+
"eval_ece": 0.05797517591831729,
|
| 156 |
+
"eval_f1": 0.9382506413699704,
|
| 157 |
+
"eval_loss": 0.40406298637390137,
|
| 158 |
+
"eval_nll": 6.776806058077595,
|
| 159 |
+
"eval_precision": 0.9384196444828075,
|
| 160 |
+
"eval_recall": 0.9387254901960784,
|
| 161 |
+
"eval_runtime": 1.9112,
|
| 162 |
+
"eval_samples_per_second": 213.478,
|
| 163 |
+
"eval_steps_per_second": 6.802,
|
| 164 |
+
"step": 2000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 18.26,
|
| 168 |
+
"grad_norm": 0.004601624328643084,
|
| 169 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 170 |
+
"loss": 0.0158,
|
| 171 |
+
"step": 2100
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 19.13,
|
| 175 |
+
"grad_norm": 0.012901573441922665,
|
| 176 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 177 |
+
"loss": 0.0092,
|
| 178 |
+
"step": 2200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 20.0,
|
| 182 |
+
"grad_norm": 0.00762163195759058,
|
| 183 |
+
"learning_rate": 3.85e-05,
|
| 184 |
+
"loss": 0.0082,
|
| 185 |
+
"step": 2300
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 20.87,
|
| 189 |
+
"grad_norm": 0.154510959982872,
|
| 190 |
+
"learning_rate": 3.8e-05,
|
| 191 |
+
"loss": 0.0131,
|
| 192 |
+
"step": 2400
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 21.74,
|
| 196 |
+
"grad_norm": 0.003832124872133136,
|
| 197 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 198 |
+
"loss": 0.0201,
|
| 199 |
+
"step": 2500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 22.61,
|
| 203 |
+
"grad_norm": 0.0029927650466561317,
|
| 204 |
+
"learning_rate": 3.7e-05,
|
| 205 |
+
"loss": 0.019,
|
| 206 |
+
"step": 2600
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 23.48,
|
| 210 |
+
"grad_norm": 0.0018748922739177942,
|
| 211 |
+
"learning_rate": 3.65e-05,
|
| 212 |
+
"loss": 0.0086,
|
| 213 |
+
"step": 2700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 24.35,
|
| 217 |
+
"grad_norm": 0.14622557163238525,
|
| 218 |
+
"learning_rate": 3.6e-05,
|
| 219 |
+
"loss": 0.01,
|
| 220 |
+
"step": 2800
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 25.22,
|
| 224 |
+
"grad_norm": 0.03812519088387489,
|
| 225 |
+
"learning_rate": 3.55e-05,
|
| 226 |
+
"loss": 0.0234,
|
| 227 |
+
"step": 2900
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 26.09,
|
| 231 |
+
"grad_norm": 24.803911209106445,
|
| 232 |
+
"learning_rate": 3.5e-05,
|
| 233 |
+
"loss": 0.0119,
|
| 234 |
+
"step": 3000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 26.96,
|
| 238 |
+
"grad_norm": 0.00613383948802948,
|
| 239 |
+
"learning_rate": 3.45e-05,
|
| 240 |
+
"loss": 0.0129,
|
| 241 |
+
"step": 3100
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 27.83,
|
| 245 |
+
"grad_norm": 0.005301126278936863,
|
| 246 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 247 |
+
"loss": 0.0086,
|
| 248 |
+
"step": 3200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 28.7,
|
| 252 |
+
"grad_norm": 0.0037701462861150503,
|
| 253 |
+
"learning_rate": 3.35e-05,
|
| 254 |
+
"loss": 0.0104,
|
| 255 |
+
"step": 3300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 29.57,
|
| 259 |
+
"grad_norm": 0.03656579554080963,
|
| 260 |
+
"learning_rate": 3.3e-05,
|
| 261 |
+
"loss": 0.0065,
|
| 262 |
+
"step": 3400
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 30.43,
|
| 266 |
+
"grad_norm": 0.1510837972164154,
|
| 267 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 268 |
+
"loss": 0.0093,
|
| 269 |
+
"step": 3500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 31.3,
|
| 273 |
+
"grad_norm": 0.0025348912458866835,
|
| 274 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 275 |
+
"loss": 0.009,
|
| 276 |
+
"step": 3600
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 32.17,
|
| 280 |
+
"grad_norm": 0.002163603436201811,
|
| 281 |
+
"learning_rate": 3.15e-05,
|
| 282 |
+
"loss": 0.0077,
|
| 283 |
+
"step": 3700
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 33.04,
|
| 287 |
+
"grad_norm": 0.0018990840762853622,
|
| 288 |
+
"learning_rate": 3.1e-05,
|
| 289 |
+
"loss": 0.0041,
|
| 290 |
+
"step": 3800
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 33.91,
|
| 294 |
+
"grad_norm": 0.0013024972286075354,
|
| 295 |
+
"learning_rate": 3.05e-05,
|
| 296 |
+
"loss": 0.0073,
|
| 297 |
+
"step": 3900
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 34.78,
|
| 301 |
+
"grad_norm": 0.001054937718436122,
|
| 302 |
+
"learning_rate": 3e-05,
|
| 303 |
+
"loss": 0.0004,
|
| 304 |
+
"step": 4000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 34.78,
|
| 308 |
+
"eval_accuracy": 0.928921568627451,
|
| 309 |
+
"eval_brier_score": 0.0675812841670148,
|
| 310 |
+
"eval_ece": 0.06654327976353025,
|
| 311 |
+
"eval_f1": 0.9280259003838475,
|
| 312 |
+
"eval_loss": 0.5349375605583191,
|
| 313 |
+
"eval_nll": 7.384143338090662,
|
| 314 |
+
"eval_precision": 0.9287246020559013,
|
| 315 |
+
"eval_recall": 0.928921568627451,
|
| 316 |
+
"eval_runtime": 1.8817,
|
| 317 |
+
"eval_samples_per_second": 216.828,
|
| 318 |
+
"eval_steps_per_second": 6.909,
|
| 319 |
+
"step": 4000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 35.65,
|
| 323 |
+
"grad_norm": 0.0011927990708500147,
|
| 324 |
+
"learning_rate": 2.95e-05,
|
| 325 |
+
"loss": 0.0003,
|
| 326 |
+
"step": 4100
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 36.52,
|
| 330 |
+
"grad_norm": 0.0007499050698243082,
|
| 331 |
+
"learning_rate": 2.9e-05,
|
| 332 |
+
"loss": 0.0013,
|
| 333 |
+
"step": 4200
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 37.39,
|
| 337 |
+
"grad_norm": 0.0024869628250598907,
|
| 338 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 339 |
+
"loss": 0.0001,
|
| 340 |
+
"step": 4300
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 38.26,
|
| 344 |
+
"grad_norm": 0.018704690039157867,
|
| 345 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 346 |
+
"loss": 0.0099,
|
| 347 |
+
"step": 4400
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 39.13,
|
| 351 |
+
"grad_norm": 0.00480309734120965,
|
| 352 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 353 |
+
"loss": 0.0064,
|
| 354 |
+
"step": 4500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 40.0,
|
| 358 |
+
"grad_norm": 0.016563115641474724,
|
| 359 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 360 |
+
"loss": 0.0085,
|
| 361 |
+
"step": 4600
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 40.87,
|
| 365 |
+
"grad_norm": 0.0018221806967630982,
|
| 366 |
+
"learning_rate": 2.6500000000000004e-05,
|
| 367 |
+
"loss": 0.001,
|
| 368 |
+
"step": 4700
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 41.74,
|
| 372 |
+
"grad_norm": 0.0007343711331486702,
|
| 373 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 374 |
+
"loss": 0.0012,
|
| 375 |
+
"step": 4800
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 42.61,
|
| 379 |
+
"grad_norm": 0.008326762355864048,
|
| 380 |
+
"learning_rate": 2.5500000000000003e-05,
|
| 381 |
+
"loss": 0.0029,
|
| 382 |
+
"step": 4900
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 43.48,
|
| 386 |
+
"grad_norm": 0.004561099223792553,
|
| 387 |
+
"learning_rate": 2.5e-05,
|
| 388 |
+
"loss": 0.0004,
|
| 389 |
+
"step": 5000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 44.35,
|
| 393 |
+
"grad_norm": 0.0013891893904656172,
|
| 394 |
+
"learning_rate": 2.45e-05,
|
| 395 |
+
"loss": 0.0074,
|
| 396 |
+
"step": 5100
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 45.22,
|
| 400 |
+
"grad_norm": 0.013074066489934921,
|
| 401 |
+
"learning_rate": 2.4e-05,
|
| 402 |
+
"loss": 0.0018,
|
| 403 |
+
"step": 5200
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 46.09,
|
| 407 |
+
"grad_norm": 0.0006578834727406502,
|
| 408 |
+
"learning_rate": 2.35e-05,
|
| 409 |
+
"loss": 0.0,
|
| 410 |
+
"step": 5300
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 46.96,
|
| 414 |
+
"grad_norm": 0.0006401424179784954,
|
| 415 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 416 |
+
"loss": 0.0,
|
| 417 |
+
"step": 5400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 47.83,
|
| 421 |
+
"grad_norm": 0.000561197055503726,
|
| 422 |
+
"learning_rate": 2.25e-05,
|
| 423 |
+
"loss": 0.0024,
|
| 424 |
+
"step": 5500
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 48.7,
|
| 428 |
+
"grad_norm": 0.0004986047861166298,
|
| 429 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 430 |
+
"loss": 0.0,
|
| 431 |
+
"step": 5600
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 49.57,
|
| 435 |
+
"grad_norm": 0.0004820087051484734,
|
| 436 |
+
"learning_rate": 2.15e-05,
|
| 437 |
+
"loss": 0.0,
|
| 438 |
+
"step": 5700
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 50.43,
|
| 442 |
+
"grad_norm": 0.00033787055872380733,
|
| 443 |
+
"learning_rate": 2.1e-05,
|
| 444 |
+
"loss": 0.0,
|
| 445 |
+
"step": 5800
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 51.3,
|
| 449 |
+
"grad_norm": 0.00030797443469054997,
|
| 450 |
+
"learning_rate": 2.05e-05,
|
| 451 |
+
"loss": 0.0,
|
| 452 |
+
"step": 5900
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 52.17,
|
| 456 |
+
"grad_norm": 0.0003839946002699435,
|
| 457 |
+
"learning_rate": 2e-05,
|
| 458 |
+
"loss": 0.0,
|
| 459 |
+
"step": 6000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 52.17,
|
| 463 |
+
"eval_accuracy": 0.9191176470588235,
|
| 464 |
+
"eval_brier_score": 0.0754212002677414,
|
| 465 |
+
"eval_ece": 0.0762045159935951,
|
| 466 |
+
"eval_f1": 0.9180984383678263,
|
| 467 |
+
"eval_loss": 0.6726267337799072,
|
| 468 |
+
"eval_nll": 8.413597393856437,
|
| 469 |
+
"eval_precision": 0.9186496544848213,
|
| 470 |
+
"eval_recall": 0.9191176470588235,
|
| 471 |
+
"eval_runtime": 1.8842,
|
| 472 |
+
"eval_samples_per_second": 216.536,
|
| 473 |
+
"eval_steps_per_second": 6.899,
|
| 474 |
+
"step": 6000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 53.04,
|
| 478 |
+
"grad_norm": 0.00035972893238067627,
|
| 479 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 480 |
+
"loss": 0.0,
|
| 481 |
+
"step": 6100
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 53.91,
|
| 485 |
+
"grad_norm": 0.0002692355774343014,
|
| 486 |
+
"learning_rate": 1.9e-05,
|
| 487 |
+
"loss": 0.0,
|
| 488 |
+
"step": 6200
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 54.78,
|
| 492 |
+
"grad_norm": 0.0003426405892241746,
|
| 493 |
+
"learning_rate": 1.85e-05,
|
| 494 |
+
"loss": 0.0,
|
| 495 |
+
"step": 6300
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 55.65,
|
| 499 |
+
"grad_norm": 0.00027685274835675955,
|
| 500 |
+
"learning_rate": 1.8e-05,
|
| 501 |
+
"loss": 0.0,
|
| 502 |
+
"step": 6400
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 56.52,
|
| 506 |
+
"grad_norm": 0.00028565863613039255,
|
| 507 |
+
"learning_rate": 1.75e-05,
|
| 508 |
+
"loss": 0.0,
|
| 509 |
+
"step": 6500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 57.39,
|
| 513 |
+
"grad_norm": 0.0002044347784249112,
|
| 514 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 515 |
+
"loss": 0.0,
|
| 516 |
+
"step": 6600
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 58.26,
|
| 520 |
+
"grad_norm": 0.00019555067410692573,
|
| 521 |
+
"learning_rate": 1.65e-05,
|
| 522 |
+
"loss": 0.0,
|
| 523 |
+
"step": 6700
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 59.13,
|
| 527 |
+
"grad_norm": 13.264129638671875,
|
| 528 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 529 |
+
"loss": 0.0001,
|
| 530 |
+
"step": 6800
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 60.0,
|
| 534 |
+
"grad_norm": 0.00021661369828507304,
|
| 535 |
+
"learning_rate": 1.55e-05,
|
| 536 |
+
"loss": 0.0071,
|
| 537 |
+
"step": 6900
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 60.87,
|
| 541 |
+
"grad_norm": 0.0025544350501149893,
|
| 542 |
+
"learning_rate": 1.5e-05,
|
| 543 |
+
"loss": 0.0047,
|
| 544 |
+
"step": 7000
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 61.74,
|
| 548 |
+
"grad_norm": 0.00023375553428195417,
|
| 549 |
+
"learning_rate": 1.45e-05,
|
| 550 |
+
"loss": 0.0028,
|
| 551 |
+
"step": 7100
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 62.61,
|
| 555 |
+
"grad_norm": 0.00046280986862257123,
|
| 556 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 557 |
+
"loss": 0.0001,
|
| 558 |
+
"step": 7200
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 63.48,
|
| 562 |
+
"grad_norm": 0.0054445345886051655,
|
| 563 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 564 |
+
"loss": 0.0061,
|
| 565 |
+
"step": 7300
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 64.35,
|
| 569 |
+
"grad_norm": 0.0021262529771775007,
|
| 570 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 571 |
+
"loss": 0.0001,
|
| 572 |
+
"step": 7400
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 65.22,
|
| 576 |
+
"grad_norm": 0.0005580468568950891,
|
| 577 |
+
"learning_rate": 1.25e-05,
|
| 578 |
+
"loss": 0.0031,
|
| 579 |
+
"step": 7500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 66.09,
|
| 583 |
+
"grad_norm": 0.0004650899500120431,
|
| 584 |
+
"learning_rate": 1.2e-05,
|
| 585 |
+
"loss": 0.0001,
|
| 586 |
+
"step": 7600
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 66.96,
|
| 590 |
+
"grad_norm": 0.0006638153572566807,
|
| 591 |
+
"learning_rate": 1.1500000000000002e-05,
|
| 592 |
+
"loss": 0.0,
|
| 593 |
+
"step": 7700
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 67.83,
|
| 597 |
+
"grad_norm": 0.0004998428630642593,
|
| 598 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 599 |
+
"loss": 0.0,
|
| 600 |
+
"step": 7800
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 68.7,
|
| 604 |
+
"grad_norm": 0.00034490320831537247,
|
| 605 |
+
"learning_rate": 1.05e-05,
|
| 606 |
+
"loss": 0.0,
|
| 607 |
+
"step": 7900
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 69.57,
|
| 611 |
+
"grad_norm": 0.000332407042151317,
|
| 612 |
+
"learning_rate": 1e-05,
|
| 613 |
+
"loss": 0.0008,
|
| 614 |
+
"step": 8000
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 69.57,
|
| 618 |
+
"eval_accuracy": 0.9093137254901961,
|
| 619 |
+
"eval_brier_score": 0.08612374447215236,
|
| 620 |
+
"eval_ece": 0.08567111121088852,
|
| 621 |
+
"eval_f1": 0.9088203082186265,
|
| 622 |
+
"eval_loss": 0.7547056078910828,
|
| 623 |
+
"eval_nll": 8.256409546928781,
|
| 624 |
+
"eval_precision": 0.908638620145923,
|
| 625 |
+
"eval_recall": 0.9093137254901961,
|
| 626 |
+
"eval_runtime": 1.8815,
|
| 627 |
+
"eval_samples_per_second": 216.849,
|
| 628 |
+
"eval_steps_per_second": 6.909,
|
| 629 |
+
"step": 8000
|
| 630 |
+
}
|
| 631 |
+
],
|
| 632 |
+
"logging_steps": 100,
|
| 633 |
+
"max_steps": 10000,
|
| 634 |
+
"num_input_tokens_seen": 0,
|
| 635 |
+
"num_train_epochs": 87,
|
| 636 |
+
"save_steps": 2000,
|
| 637 |
+
"total_flos": 1.047551383587864e+16,
|
| 638 |
+
"train_batch_size": 32,
|
| 639 |
+
"trial_name": null,
|
| 640 |
+
"trial_params": null
|
| 641 |
+
}
|
mrpc/checkpoint-8000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45b5ff4c6acb47d0ce7d42bf9d0586515d220366e0d122459e5c18115cd14676
|
| 3 |
+
size 4856
|
mrpc/checkpoint-8000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|