Upload folder using huggingface_hub
Browse files- checkpoint-2619/config.json +26 -0
- checkpoint-2619/model.safetensors +3 -0
- checkpoint-2619/optimizer.pt +3 -0
- checkpoint-2619/rng_state.pth +3 -0
- checkpoint-2619/scheduler.pt +3 -0
- checkpoint-2619/special_tokens_map.json +7 -0
- checkpoint-2619/tokenizer.json +0 -0
- checkpoint-2619/tokenizer_config.json +56 -0
- checkpoint-2619/trainer_state.json +427 -0
- checkpoint-2619/training_args.bin +3 -0
- checkpoint-2619/vocab.txt +0 -0
- model.safetensors +1 -1
checkpoint-2619/config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert/distilbert-base-multilingual-cased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"output_past": true,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"problem_type": "single_label_classification",
|
| 19 |
+
"qa_dropout": 0.1,
|
| 20 |
+
"seq_classif_dropout": 0.2,
|
| 21 |
+
"sinusoidal_pos_embds": false,
|
| 22 |
+
"tie_weights_": true,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.48.3",
|
| 25 |
+
"vocab_size": 119547
|
| 26 |
+
}
|
checkpoint-2619/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d5dc69ddbb8668b38815b274b7fa286936063915ed21ba4e61d8cb8f145e5b0
|
| 3 |
+
size 541317368
|
checkpoint-2619/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0de209748c1c3ca7bb580ccc6cde82004dbc4ae26261060038d62ea3b437e124
|
| 3 |
+
size 1082696890
|
checkpoint-2619/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a5ca7efd4a375d77d25ddac2e8b35b94147dddd92d2588ea9d9b654bc545a69
|
| 3 |
+
size 14244
|
checkpoint-2619/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db3fb0b03f25d427366074ae87640f63f368dd48e0fdf8e02a497643a0ca23f2
|
| 3 |
+
size 1064
|
checkpoint-2619/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 |
+
}
|
checkpoint-2619/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2619/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
checkpoint-2619/trainer_state.json
ADDED
|
@@ -0,0 +1,427 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2619,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0572737686139748,
|
| 13 |
+
"grad_norm": 1.6889350414276123,
|
| 14 |
+
"learning_rate": 4.904543718976709e-05,
|
| 15 |
+
"loss": 0.6367,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1145475372279496,
|
| 20 |
+
"grad_norm": 1.8329870700836182,
|
| 21 |
+
"learning_rate": 4.809087437953417e-05,
|
| 22 |
+
"loss": 0.5759,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1718213058419244,
|
| 27 |
+
"grad_norm": 1.3400354385375977,
|
| 28 |
+
"learning_rate": 4.713631156930126e-05,
|
| 29 |
+
"loss": 0.5711,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2290950744558992,
|
| 34 |
+
"grad_norm": 1.22416090965271,
|
| 35 |
+
"learning_rate": 4.618174875906835e-05,
|
| 36 |
+
"loss": 0.5597,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.286368843069874,
|
| 41 |
+
"grad_norm": 1.6629807949066162,
|
| 42 |
+
"learning_rate": 4.522718594883544e-05,
|
| 43 |
+
"loss": 0.5442,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3436426116838488,
|
| 48 |
+
"grad_norm": 1.5647610425949097,
|
| 49 |
+
"learning_rate": 4.427262313860252e-05,
|
| 50 |
+
"loss": 0.5287,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4009163802978236,
|
| 55 |
+
"grad_norm": 1.5147887468338013,
|
| 56 |
+
"learning_rate": 4.331806032836961e-05,
|
| 57 |
+
"loss": 0.5362,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4581901489117984,
|
| 62 |
+
"grad_norm": 1.2945597171783447,
|
| 63 |
+
"learning_rate": 4.2363497518136695e-05,
|
| 64 |
+
"loss": 0.5235,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5154639175257731,
|
| 69 |
+
"grad_norm": 1.9351801872253418,
|
| 70 |
+
"learning_rate": 4.140893470790378e-05,
|
| 71 |
+
"loss": 0.5196,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.572737686139748,
|
| 76 |
+
"grad_norm": 1.9045623540878296,
|
| 77 |
+
"learning_rate": 4.0454371897670865e-05,
|
| 78 |
+
"loss": 0.5093,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6300114547537228,
|
| 83 |
+
"grad_norm": 1.5518434047698975,
|
| 84 |
+
"learning_rate": 3.949980908743795e-05,
|
| 85 |
+
"loss": 0.5106,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6872852233676976,
|
| 90 |
+
"grad_norm": 1.466840386390686,
|
| 91 |
+
"learning_rate": 3.854524627720504e-05,
|
| 92 |
+
"loss": 0.5121,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7445589919816724,
|
| 97 |
+
"grad_norm": 1.359466791152954,
|
| 98 |
+
"learning_rate": 3.759068346697213e-05,
|
| 99 |
+
"loss": 0.507,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.8018327605956472,
|
| 104 |
+
"grad_norm": 1.9663983583450317,
|
| 105 |
+
"learning_rate": 3.663612065673922e-05,
|
| 106 |
+
"loss": 0.5028,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8591065292096219,
|
| 111 |
+
"grad_norm": 1.6117963790893555,
|
| 112 |
+
"learning_rate": 3.5681557846506306e-05,
|
| 113 |
+
"loss": 0.4896,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.9163802978235968,
|
| 118 |
+
"grad_norm": 1.4263460636138916,
|
| 119 |
+
"learning_rate": 3.4726995036273394e-05,
|
| 120 |
+
"loss": 0.4917,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9736540664375716,
|
| 125 |
+
"grad_norm": 1.079898715019226,
|
| 126 |
+
"learning_rate": 3.3772432226040476e-05,
|
| 127 |
+
"loss": 0.5124,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0,
|
| 132 |
+
"eval_accuracy": 0.738814878479683,
|
| 133 |
+
"eval_f1": 0.728374217896514,
|
| 134 |
+
"eval_loss": 0.4868564307689667,
|
| 135 |
+
"eval_runtime": 56.2275,
|
| 136 |
+
"eval_samples_per_second": 372.469,
|
| 137 |
+
"eval_steps_per_second": 3.895,
|
| 138 |
+
"step": 873
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.0309278350515463,
|
| 142 |
+
"grad_norm": 1.4357503652572632,
|
| 143 |
+
"learning_rate": 3.2817869415807564e-05,
|
| 144 |
+
"loss": 0.4585,
|
| 145 |
+
"step": 900
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.088201603665521,
|
| 149 |
+
"grad_norm": 2.1344144344329834,
|
| 150 |
+
"learning_rate": 3.186330660557465e-05,
|
| 151 |
+
"loss": 0.4482,
|
| 152 |
+
"step": 950
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.145475372279496,
|
| 156 |
+
"grad_norm": 1.5237584114074707,
|
| 157 |
+
"learning_rate": 3.0908743795341734e-05,
|
| 158 |
+
"loss": 0.445,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.2027491408934707,
|
| 163 |
+
"grad_norm": 2.1996545791625977,
|
| 164 |
+
"learning_rate": 2.9954180985108822e-05,
|
| 165 |
+
"loss": 0.4414,
|
| 166 |
+
"step": 1050
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.2600229095074456,
|
| 170 |
+
"grad_norm": 1.8122806549072266,
|
| 171 |
+
"learning_rate": 2.899961817487591e-05,
|
| 172 |
+
"loss": 0.4379,
|
| 173 |
+
"step": 1100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.3172966781214204,
|
| 177 |
+
"grad_norm": 1.9378130435943604,
|
| 178 |
+
"learning_rate": 2.8045055364643e-05,
|
| 179 |
+
"loss": 0.4358,
|
| 180 |
+
"step": 1150
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.3745704467353952,
|
| 184 |
+
"grad_norm": 2.2606778144836426,
|
| 185 |
+
"learning_rate": 2.709049255441008e-05,
|
| 186 |
+
"loss": 0.4321,
|
| 187 |
+
"step": 1200
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 1.43184421534937,
|
| 191 |
+
"grad_norm": 1.9233603477478027,
|
| 192 |
+
"learning_rate": 2.6135929744177168e-05,
|
| 193 |
+
"loss": 0.4191,
|
| 194 |
+
"step": 1250
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.4891179839633448,
|
| 198 |
+
"grad_norm": 2.874886989593506,
|
| 199 |
+
"learning_rate": 2.5181366933944256e-05,
|
| 200 |
+
"loss": 0.4399,
|
| 201 |
+
"step": 1300
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.5463917525773194,
|
| 205 |
+
"grad_norm": 2.801513671875,
|
| 206 |
+
"learning_rate": 2.422680412371134e-05,
|
| 207 |
+
"loss": 0.4263,
|
| 208 |
+
"step": 1350
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.6036655211912945,
|
| 212 |
+
"grad_norm": 2.149822950363159,
|
| 213 |
+
"learning_rate": 2.3272241313478426e-05,
|
| 214 |
+
"loss": 0.4294,
|
| 215 |
+
"step": 1400
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.660939289805269,
|
| 219 |
+
"grad_norm": 1.6502012014389038,
|
| 220 |
+
"learning_rate": 2.2317678503245514e-05,
|
| 221 |
+
"loss": 0.4293,
|
| 222 |
+
"step": 1450
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.718213058419244,
|
| 226 |
+
"grad_norm": 3.247627019882202,
|
| 227 |
+
"learning_rate": 2.13631156930126e-05,
|
| 228 |
+
"loss": 0.4325,
|
| 229 |
+
"step": 1500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.7754868270332187,
|
| 233 |
+
"grad_norm": 2.349097967147827,
|
| 234 |
+
"learning_rate": 2.0408552882779688e-05,
|
| 235 |
+
"loss": 0.4328,
|
| 236 |
+
"step": 1550
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.8327605956471937,
|
| 240 |
+
"grad_norm": 2.392411708831787,
|
| 241 |
+
"learning_rate": 1.9453990072546772e-05,
|
| 242 |
+
"loss": 0.4273,
|
| 243 |
+
"step": 1600
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.8900343642611683,
|
| 247 |
+
"grad_norm": 1.5783507823944092,
|
| 248 |
+
"learning_rate": 1.849942726231386e-05,
|
| 249 |
+
"loss": 0.4228,
|
| 250 |
+
"step": 1650
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.9473081328751431,
|
| 254 |
+
"grad_norm": 2.832991600036621,
|
| 255 |
+
"learning_rate": 1.754486445208095e-05,
|
| 256 |
+
"loss": 0.4246,
|
| 257 |
+
"step": 1700
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.0,
|
| 261 |
+
"eval_accuracy": 0.752041254834551,
|
| 262 |
+
"eval_f1": 0.7557499647241428,
|
| 263 |
+
"eval_loss": 0.47728216648101807,
|
| 264 |
+
"eval_runtime": 55.7924,
|
| 265 |
+
"eval_samples_per_second": 375.373,
|
| 266 |
+
"eval_steps_per_second": 3.925,
|
| 267 |
+
"step": 1746
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.004581901489118,
|
| 271 |
+
"grad_norm": 1.2103527784347534,
|
| 272 |
+
"learning_rate": 1.6590301641848037e-05,
|
| 273 |
+
"loss": 0.4277,
|
| 274 |
+
"step": 1750
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.0618556701030926,
|
| 278 |
+
"grad_norm": 2.3143885135650635,
|
| 279 |
+
"learning_rate": 1.5635738831615122e-05,
|
| 280 |
+
"loss": 0.3644,
|
| 281 |
+
"step": 1800
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.1191294387170676,
|
| 285 |
+
"grad_norm": 1.9333767890930176,
|
| 286 |
+
"learning_rate": 1.4681176021382207e-05,
|
| 287 |
+
"loss": 0.3809,
|
| 288 |
+
"step": 1850
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.176403207331042,
|
| 292 |
+
"grad_norm": 1.8364256620407104,
|
| 293 |
+
"learning_rate": 1.3726613211149295e-05,
|
| 294 |
+
"loss": 0.3638,
|
| 295 |
+
"step": 1900
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.2336769759450172,
|
| 299 |
+
"grad_norm": 2.7426836490631104,
|
| 300 |
+
"learning_rate": 1.277205040091638e-05,
|
| 301 |
+
"loss": 0.3711,
|
| 302 |
+
"step": 1950
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.290950744558992,
|
| 306 |
+
"grad_norm": 2.5422801971435547,
|
| 307 |
+
"learning_rate": 1.1817487590683468e-05,
|
| 308 |
+
"loss": 0.3711,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.348224513172967,
|
| 313 |
+
"grad_norm": 3.0044119358062744,
|
| 314 |
+
"learning_rate": 1.0862924780450553e-05,
|
| 315 |
+
"loss": 0.372,
|
| 316 |
+
"step": 2050
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.4054982817869415,
|
| 320 |
+
"grad_norm": 3.1833741664886475,
|
| 321 |
+
"learning_rate": 9.90836197021764e-06,
|
| 322 |
+
"loss": 0.3645,
|
| 323 |
+
"step": 2100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.4627720504009165,
|
| 327 |
+
"grad_norm": 2.613365650177002,
|
| 328 |
+
"learning_rate": 8.953799159984726e-06,
|
| 329 |
+
"loss": 0.3673,
|
| 330 |
+
"step": 2150
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.520045819014891,
|
| 334 |
+
"grad_norm": 2.555938959121704,
|
| 335 |
+
"learning_rate": 7.999236349751815e-06,
|
| 336 |
+
"loss": 0.3718,
|
| 337 |
+
"step": 2200
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.5773195876288657,
|
| 341 |
+
"grad_norm": 2.8468923568725586,
|
| 342 |
+
"learning_rate": 7.0446735395189e-06,
|
| 343 |
+
"loss": 0.3649,
|
| 344 |
+
"step": 2250
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.6345933562428407,
|
| 348 |
+
"grad_norm": 3.8473777770996094,
|
| 349 |
+
"learning_rate": 6.090110729285988e-06,
|
| 350 |
+
"loss": 0.3702,
|
| 351 |
+
"step": 2300
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.691867124856816,
|
| 355 |
+
"grad_norm": 2.7918660640716553,
|
| 356 |
+
"learning_rate": 5.135547919053074e-06,
|
| 357 |
+
"loss": 0.3564,
|
| 358 |
+
"step": 2350
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 2.7491408934707904,
|
| 362 |
+
"grad_norm": 2.7832207679748535,
|
| 363 |
+
"learning_rate": 4.18098510882016e-06,
|
| 364 |
+
"loss": 0.3647,
|
| 365 |
+
"step": 2400
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.806414662084765,
|
| 369 |
+
"grad_norm": 3.194080352783203,
|
| 370 |
+
"learning_rate": 3.226422298587247e-06,
|
| 371 |
+
"loss": 0.3695,
|
| 372 |
+
"step": 2450
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.86368843069874,
|
| 376 |
+
"grad_norm": 4.3022966384887695,
|
| 377 |
+
"learning_rate": 2.271859488354334e-06,
|
| 378 |
+
"loss": 0.358,
|
| 379 |
+
"step": 2500
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.9209621993127146,
|
| 383 |
+
"grad_norm": 1.7924271821975708,
|
| 384 |
+
"learning_rate": 1.3172966781214204e-06,
|
| 385 |
+
"loss": 0.3721,
|
| 386 |
+
"step": 2550
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.9782359679266897,
|
| 390 |
+
"grad_norm": 1.7951252460479736,
|
| 391 |
+
"learning_rate": 3.627338678885071e-07,
|
| 392 |
+
"loss": 0.3626,
|
| 393 |
+
"step": 2600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.0,
|
| 397 |
+
"eval_accuracy": 0.7545241846917825,
|
| 398 |
+
"eval_f1": 0.7647893123484467,
|
| 399 |
+
"eval_loss": 0.4975164234638214,
|
| 400 |
+
"eval_runtime": 55.5446,
|
| 401 |
+
"eval_samples_per_second": 377.048,
|
| 402 |
+
"eval_steps_per_second": 3.943,
|
| 403 |
+
"step": 2619
|
| 404 |
+
}
|
| 405 |
+
],
|
| 406 |
+
"logging_steps": 50,
|
| 407 |
+
"max_steps": 2619,
|
| 408 |
+
"num_input_tokens_seen": 0,
|
| 409 |
+
"num_train_epochs": 3,
|
| 410 |
+
"save_steps": 500,
|
| 411 |
+
"stateful_callbacks": {
|
| 412 |
+
"TrainerControl": {
|
| 413 |
+
"args": {
|
| 414 |
+
"should_epoch_stop": false,
|
| 415 |
+
"should_evaluate": false,
|
| 416 |
+
"should_log": false,
|
| 417 |
+
"should_save": true,
|
| 418 |
+
"should_training_stop": true
|
| 419 |
+
},
|
| 420 |
+
"attributes": {}
|
| 421 |
+
}
|
| 422 |
+
},
|
| 423 |
+
"total_flos": 3.3289189749651456e+16,
|
| 424 |
+
"train_batch_size": 96,
|
| 425 |
+
"trial_name": null,
|
| 426 |
+
"trial_params": null
|
| 427 |
+
}
|
checkpoint-2619/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6146ad1dc98175c3ae7f8a62eacf07a21eecf97d91bd50cf4d4048071a0d9148
|
| 3 |
+
size 5304
|
checkpoint-2619/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 541317368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d5dc69ddbb8668b38815b274b7fa286936063915ed21ba4e61d8cb8f145e5b0
|
| 3 |
size 541317368
|