Commit
•
0588142
1
Parent(s):
de6a112
Training in progress, epoch 2
Browse files- checkpoint-40000/config.json +28 -0
- checkpoint-40000/merges.txt +0 -0
- checkpoint-40000/optimizer.pt +3 -0
- checkpoint-40000/pytorch_model.bin +3 -0
- checkpoint-40000/rng_state.pth +3 -0
- checkpoint-40000/scaler.pt +3 -0
- checkpoint-40000/scheduler.pt +3 -0
- checkpoint-40000/special_tokens_map.json +15 -0
- checkpoint-40000/tokenizer.json +0 -0
- checkpoint-40000/tokenizer_config.json +15 -0
- checkpoint-40000/trainer_state.json +516 -0
- checkpoint-40000/training_args.bin +3 -0
- checkpoint-40000/vocab.json +0 -0
- pytorch_model.bin +1 -1
- runs/Apr02_03-12-09_201fb07c756b/events.out.tfevents.1680405142.201fb07c756b.23.0 +2 -2
checkpoint-40000/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.27.3",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
checkpoint-40000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-40000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2712a5bd321dae31f035c40c35a458194b77d2fc5be4b77704826f7055745013
|
| 3 |
+
size 997295237
|
checkpoint-40000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a978bd6a7acdb2bf44f9f6eec23890411e4c50847cc57ec14ce2b4cf1dd2e344
|
| 3 |
+
size 498662069
|
checkpoint-40000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8539a12d70e9610986a83b0bff19ffcb4752b5ab0b0609382a41fd8378852283
|
| 3 |
+
size 14575
|
checkpoint-40000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51673bf8c99292a9f7fe2c855780624e02c25ff4e676e36893825c5baef99f8a
|
| 3 |
+
size 557
|
checkpoint-40000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a19e109c66261b30a0a1ed5f9482674f6a52e03a404f6fef1c3518b74edb84b3
|
| 3 |
+
size 627
|
checkpoint-40000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-40000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-40000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "<pad>",
|
| 10 |
+
"sep_token": "</s>",
|
| 11 |
+
"special_tokens_map_file": null,
|
| 12 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 13 |
+
"trim_offsets": true,
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-40000/trainer_state.json
ADDED
|
@@ -0,0 +1,516 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7626183364552219,
|
| 3 |
+
"best_model_checkpoint": "robertabase-subjectivity-1-actual/checkpoint-40000",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 40000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 9.875750000000001e-06,
|
| 13 |
+
"loss": 0.6845,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 9.751250000000001e-06,
|
| 19 |
+
"loss": 0.6182,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 9.6265e-06,
|
| 25 |
+
"loss": 0.6045,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 9.501500000000002e-06,
|
| 31 |
+
"loss": 0.6057,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 9.3765e-06,
|
| 37 |
+
"loss": 0.5845,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15,
|
| 42 |
+
"learning_rate": 9.251500000000001e-06,
|
| 43 |
+
"loss": 0.5819,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17,
|
| 48 |
+
"learning_rate": 9.1265e-06,
|
| 49 |
+
"loss": 0.6158,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.2,
|
| 54 |
+
"learning_rate": 9.00175e-06,
|
| 55 |
+
"loss": 0.5941,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.23,
|
| 60 |
+
"learning_rate": 8.876750000000001e-06,
|
| 61 |
+
"loss": 0.5953,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.25,
|
| 66 |
+
"learning_rate": 8.751750000000001e-06,
|
| 67 |
+
"loss": 0.5965,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.28,
|
| 72 |
+
"learning_rate": 8.62675e-06,
|
| 73 |
+
"loss": 0.6077,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.3,
|
| 78 |
+
"learning_rate": 8.50175e-06,
|
| 79 |
+
"loss": 0.5663,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.33,
|
| 84 |
+
"learning_rate": 8.37675e-06,
|
| 85 |
+
"loss": 0.5649,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.35,
|
| 90 |
+
"learning_rate": 8.251750000000001e-06,
|
| 91 |
+
"loss": 0.6021,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.38,
|
| 96 |
+
"learning_rate": 8.126750000000001e-06,
|
| 97 |
+
"loss": 0.5803,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.4,
|
| 102 |
+
"learning_rate": 8.00175e-06,
|
| 103 |
+
"loss": 0.5851,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.42,
|
| 108 |
+
"learning_rate": 7.877000000000001e-06,
|
| 109 |
+
"loss": 0.5872,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.45,
|
| 114 |
+
"learning_rate": 7.752000000000001e-06,
|
| 115 |
+
"loss": 0.5597,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.47,
|
| 120 |
+
"learning_rate": 7.6272500000000005e-06,
|
| 121 |
+
"loss": 0.5764,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5,
|
| 126 |
+
"learning_rate": 7.502250000000001e-06,
|
| 127 |
+
"loss": 0.5588,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.53,
|
| 132 |
+
"learning_rate": 7.37725e-06,
|
| 133 |
+
"loss": 0.5993,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.55,
|
| 138 |
+
"learning_rate": 7.252250000000001e-06,
|
| 139 |
+
"loss": 0.5873,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.57,
|
| 144 |
+
"learning_rate": 7.127250000000001e-06,
|
| 145 |
+
"loss": 0.5928,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.6,
|
| 150 |
+
"learning_rate": 7.002500000000001e-06,
|
| 151 |
+
"loss": 0.5655,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.62,
|
| 156 |
+
"learning_rate": 6.877500000000001e-06,
|
| 157 |
+
"loss": 0.5705,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.65,
|
| 162 |
+
"learning_rate": 6.752500000000001e-06,
|
| 163 |
+
"loss": 0.5528,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.68,
|
| 168 |
+
"learning_rate": 6.6275e-06,
|
| 169 |
+
"loss": 0.59,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7,
|
| 174 |
+
"learning_rate": 6.502500000000001e-06,
|
| 175 |
+
"loss": 0.5587,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.72,
|
| 180 |
+
"learning_rate": 6.377500000000001e-06,
|
| 181 |
+
"loss": 0.5601,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.75,
|
| 186 |
+
"learning_rate": 6.2525e-06,
|
| 187 |
+
"loss": 0.5804,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.78,
|
| 192 |
+
"learning_rate": 6.127500000000001e-06,
|
| 193 |
+
"loss": 0.5639,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.8,
|
| 198 |
+
"learning_rate": 6.0025e-06,
|
| 199 |
+
"loss": 0.5722,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.82,
|
| 204 |
+
"learning_rate": 5.8775e-06,
|
| 205 |
+
"loss": 0.5601,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.85,
|
| 210 |
+
"learning_rate": 5.752500000000001e-06,
|
| 211 |
+
"loss": 0.5758,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.88,
|
| 216 |
+
"learning_rate": 5.6275e-06,
|
| 217 |
+
"loss": 0.5648,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.9,
|
| 222 |
+
"learning_rate": 5.5025e-06,
|
| 223 |
+
"loss": 0.5723,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.93,
|
| 228 |
+
"learning_rate": 5.37775e-06,
|
| 229 |
+
"loss": 0.5714,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.95,
|
| 234 |
+
"learning_rate": 5.252750000000001e-06,
|
| 235 |
+
"loss": 0.5639,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.97,
|
| 240 |
+
"learning_rate": 5.128000000000001e-06,
|
| 241 |
+
"loss": 0.5499,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.0,
|
| 246 |
+
"learning_rate": 5.003e-06,
|
| 247 |
+
"loss": 0.5463,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.0,
|
| 252 |
+
"eval_accuracy": 0.7495,
|
| 253 |
+
"eval_f1": 0.7516359309934564,
|
| 254 |
+
"eval_loss": 0.564261257648468,
|
| 255 |
+
"eval_runtime": 133.9593,
|
| 256 |
+
"eval_samples_per_second": 149.299,
|
| 257 |
+
"eval_steps_per_second": 37.325,
|
| 258 |
+
"step": 20000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.02,
|
| 262 |
+
"learning_rate": 4.8780000000000006e-06,
|
| 263 |
+
"loss": 0.5198,
|
| 264 |
+
"step": 20500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.05,
|
| 268 |
+
"learning_rate": 4.753e-06,
|
| 269 |
+
"loss": 0.566,
|
| 270 |
+
"step": 21000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.07,
|
| 274 |
+
"learning_rate": 4.62825e-06,
|
| 275 |
+
"loss": 0.5717,
|
| 276 |
+
"step": 21500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.1,
|
| 280 |
+
"learning_rate": 4.5035e-06,
|
| 281 |
+
"loss": 0.5588,
|
| 282 |
+
"step": 22000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.12,
|
| 286 |
+
"learning_rate": 4.3785000000000005e-06,
|
| 287 |
+
"loss": 0.5626,
|
| 288 |
+
"step": 22500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.15,
|
| 292 |
+
"learning_rate": 4.2535e-06,
|
| 293 |
+
"loss": 0.5428,
|
| 294 |
+
"step": 23000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.18,
|
| 298 |
+
"learning_rate": 4.1285e-06,
|
| 299 |
+
"loss": 0.575,
|
| 300 |
+
"step": 23500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.2,
|
| 304 |
+
"learning_rate": 4.0035e-06,
|
| 305 |
+
"loss": 0.5605,
|
| 306 |
+
"step": 24000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.23,
|
| 310 |
+
"learning_rate": 3.8785e-06,
|
| 311 |
+
"loss": 0.5632,
|
| 312 |
+
"step": 24500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.25,
|
| 316 |
+
"learning_rate": 3.7535000000000006e-06,
|
| 317 |
+
"loss": 0.6156,
|
| 318 |
+
"step": 25000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.27,
|
| 322 |
+
"learning_rate": 3.6285000000000005e-06,
|
| 323 |
+
"loss": 0.5611,
|
| 324 |
+
"step": 25500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.3,
|
| 328 |
+
"learning_rate": 3.5035000000000004e-06,
|
| 329 |
+
"loss": 0.564,
|
| 330 |
+
"step": 26000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.32,
|
| 334 |
+
"learning_rate": 3.37875e-06,
|
| 335 |
+
"loss": 0.6065,
|
| 336 |
+
"step": 26500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.35,
|
| 340 |
+
"learning_rate": 3.2537500000000004e-06,
|
| 341 |
+
"loss": 0.593,
|
| 342 |
+
"step": 27000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.38,
|
| 346 |
+
"learning_rate": 3.1287500000000003e-06,
|
| 347 |
+
"loss": 0.6235,
|
| 348 |
+
"step": 27500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.4,
|
| 352 |
+
"learning_rate": 3.0037500000000003e-06,
|
| 353 |
+
"loss": 0.5948,
|
| 354 |
+
"step": 28000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.43,
|
| 358 |
+
"learning_rate": 2.87875e-06,
|
| 359 |
+
"loss": 0.5809,
|
| 360 |
+
"step": 28500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.45,
|
| 364 |
+
"learning_rate": 2.754e-06,
|
| 365 |
+
"loss": 0.5674,
|
| 366 |
+
"step": 29000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.48,
|
| 370 |
+
"learning_rate": 2.6292500000000003e-06,
|
| 371 |
+
"loss": 0.6117,
|
| 372 |
+
"step": 29500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.5,
|
| 376 |
+
"learning_rate": 2.50425e-06,
|
| 377 |
+
"loss": 0.6033,
|
| 378 |
+
"step": 30000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.52,
|
| 382 |
+
"learning_rate": 2.3795000000000003e-06,
|
| 383 |
+
"loss": 0.612,
|
| 384 |
+
"step": 30500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.55,
|
| 388 |
+
"learning_rate": 2.2545e-06,
|
| 389 |
+
"loss": 0.616,
|
| 390 |
+
"step": 31000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.57,
|
| 394 |
+
"learning_rate": 2.1295e-06,
|
| 395 |
+
"loss": 0.6101,
|
| 396 |
+
"step": 31500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.6,
|
| 400 |
+
"learning_rate": 2.0045e-06,
|
| 401 |
+
"loss": 0.5966,
|
| 402 |
+
"step": 32000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.62,
|
| 406 |
+
"learning_rate": 1.8795000000000002e-06,
|
| 407 |
+
"loss": 0.5791,
|
| 408 |
+
"step": 32500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.65,
|
| 412 |
+
"learning_rate": 1.7545e-06,
|
| 413 |
+
"loss": 0.5769,
|
| 414 |
+
"step": 33000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.68,
|
| 418 |
+
"learning_rate": 1.6295000000000002e-06,
|
| 419 |
+
"loss": 0.5649,
|
| 420 |
+
"step": 33500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.7,
|
| 424 |
+
"learning_rate": 1.5045000000000002e-06,
|
| 425 |
+
"loss": 0.569,
|
| 426 |
+
"step": 34000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.73,
|
| 430 |
+
"learning_rate": 1.3795e-06,
|
| 431 |
+
"loss": 0.5982,
|
| 432 |
+
"step": 34500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.75,
|
| 436 |
+
"learning_rate": 1.2545000000000002e-06,
|
| 437 |
+
"loss": 0.5422,
|
| 438 |
+
"step": 35000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.77,
|
| 442 |
+
"learning_rate": 1.1295e-06,
|
| 443 |
+
"loss": 0.5664,
|
| 444 |
+
"step": 35500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.8,
|
| 448 |
+
"learning_rate": 1.0045e-06,
|
| 449 |
+
"loss": 0.6063,
|
| 450 |
+
"step": 36000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.82,
|
| 454 |
+
"learning_rate": 8.795000000000001e-07,
|
| 455 |
+
"loss": 0.5577,
|
| 456 |
+
"step": 36500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.85,
|
| 460 |
+
"learning_rate": 7.545000000000001e-07,
|
| 461 |
+
"loss": 0.5846,
|
| 462 |
+
"step": 37000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.88,
|
| 466 |
+
"learning_rate": 6.297500000000001e-07,
|
| 467 |
+
"loss": 0.5746,
|
| 468 |
+
"step": 37500
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.9,
|
| 472 |
+
"learning_rate": 5.0475e-07,
|
| 473 |
+
"loss": 0.6285,
|
| 474 |
+
"step": 38000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.93,
|
| 478 |
+
"learning_rate": 3.7975000000000005e-07,
|
| 479 |
+
"loss": 0.6408,
|
| 480 |
+
"step": 38500
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.95,
|
| 484 |
+
"learning_rate": 2.5475000000000003e-07,
|
| 485 |
+
"loss": 0.5656,
|
| 486 |
+
"step": 39000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.98,
|
| 490 |
+
"learning_rate": 1.3e-07,
|
| 491 |
+
"loss": 0.622,
|
| 492 |
+
"step": 39500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.0,
|
| 496 |
+
"learning_rate": 5e-09,
|
| 497 |
+
"loss": 0.6327,
|
| 498 |
+
"step": 40000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 2.0,
|
| 502 |
+
"eval_accuracy": 0.76555,
|
| 503 |
+
"eval_f1": 0.7626183364552219,
|
| 504 |
+
"eval_loss": 0.7705514430999756,
|
| 505 |
+
"eval_runtime": 133.8772,
|
| 506 |
+
"eval_samples_per_second": 149.391,
|
| 507 |
+
"eval_steps_per_second": 37.348,
|
| 508 |
+
"step": 40000
|
| 509 |
+
}
|
| 510 |
+
],
|
| 511 |
+
"max_steps": 40000,
|
| 512 |
+
"num_train_epochs": 2,
|
| 513 |
+
"total_flos": 1.289539965645768e+16,
|
| 514 |
+
"trial_name": null,
|
| 515 |
+
"trial_params": null
|
| 516 |
+
}
|
checkpoint-40000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6de3c2ba13ce79e3f44a2647ea8e3f91330a0d13b2a72de1dbbc7e86baf262c
|
| 3 |
+
size 3707
|
checkpoint-40000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498662069
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a978bd6a7acdb2bf44f9f6eec23890411e4c50847cc57ec14ce2b4cf1dd2e344
|
| 3 |
size 498662069
|
runs/Apr02_03-12-09_201fb07c756b/events.out.tfevents.1680405142.201fb07c756b.23.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80d8ae0633b823dd012b9ae64609a5e1c2ecef197bc3a2a3d6297b3eb1157fa9
|
| 3 |
+
size 17434
|