Upload 8 files
Browse files- config.json +126 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +9 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +336 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForSequenceClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 256,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": false,
|
| 18 |
+
"conv_dim": [
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
3,
|
| 33 |
+
2,
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"conv_stride": [
|
| 37 |
+
5,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2
|
| 44 |
+
],
|
| 45 |
+
"ctc_loss_reduction": "sum",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": false,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_norm": "group",
|
| 52 |
+
"feat_proj_dropout": 0.1,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"freeze_feat_extract_train": true,
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.1,
|
| 58 |
+
"hidden_size": 768,
|
| 59 |
+
"id2label": {
|
| 60 |
+
"0": "fake",
|
| 61 |
+
"1": "real"
|
| 62 |
+
},
|
| 63 |
+
"initializer_range": 0.02,
|
| 64 |
+
"intermediate_size": 3072,
|
| 65 |
+
"label2id": {
|
| 66 |
+
"fake": "0",
|
| 67 |
+
"real": "1"
|
| 68 |
+
},
|
| 69 |
+
"layer_norm_eps": 1e-05,
|
| 70 |
+
"layerdrop": 0.0,
|
| 71 |
+
"mask_channel_length": 10,
|
| 72 |
+
"mask_channel_min_space": 1,
|
| 73 |
+
"mask_channel_other": 0.0,
|
| 74 |
+
"mask_channel_prob": 0.0,
|
| 75 |
+
"mask_channel_selection": "static",
|
| 76 |
+
"mask_feature_length": 10,
|
| 77 |
+
"mask_feature_min_masks": 0,
|
| 78 |
+
"mask_feature_prob": 0.0,
|
| 79 |
+
"mask_time_length": 10,
|
| 80 |
+
"mask_time_min_masks": 2,
|
| 81 |
+
"mask_time_min_space": 1,
|
| 82 |
+
"mask_time_other": 0.0,
|
| 83 |
+
"mask_time_prob": 0.05,
|
| 84 |
+
"mask_time_selection": "static",
|
| 85 |
+
"model_type": "wav2vec2",
|
| 86 |
+
"no_mask_channel_overlap": false,
|
| 87 |
+
"no_mask_time_overlap": false,
|
| 88 |
+
"num_adapter_layers": 3,
|
| 89 |
+
"num_attention_heads": 12,
|
| 90 |
+
"num_codevector_groups": 2,
|
| 91 |
+
"num_codevectors_per_group": 320,
|
| 92 |
+
"num_conv_pos_embedding_groups": 16,
|
| 93 |
+
"num_conv_pos_embeddings": 128,
|
| 94 |
+
"num_feat_extract_layers": 7,
|
| 95 |
+
"num_hidden_layers": 12,
|
| 96 |
+
"num_negatives": 100,
|
| 97 |
+
"output_hidden_size": 768,
|
| 98 |
+
"pad_token_id": 0,
|
| 99 |
+
"proj_codevector_dim": 256,
|
| 100 |
+
"tdnn_dilation": [
|
| 101 |
+
1,
|
| 102 |
+
2,
|
| 103 |
+
3,
|
| 104 |
+
1,
|
| 105 |
+
1
|
| 106 |
+
],
|
| 107 |
+
"tdnn_dim": [
|
| 108 |
+
512,
|
| 109 |
+
512,
|
| 110 |
+
512,
|
| 111 |
+
512,
|
| 112 |
+
1500
|
| 113 |
+
],
|
| 114 |
+
"tdnn_kernel": [
|
| 115 |
+
5,
|
| 116 |
+
3,
|
| 117 |
+
3,
|
| 118 |
+
1,
|
| 119 |
+
1
|
| 120 |
+
],
|
| 121 |
+
"torch_dtype": "float32",
|
| 122 |
+
"transformers_version": "4.46.3",
|
| 123 |
+
"use_weighted_layer_sum": false,
|
| 124 |
+
"vocab_size": 32,
|
| 125 |
+
"xvector_output_dim": 512
|
| 126 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:114a5b357b1017c2e4b2cccf614488fd30e8134835732074e12d1e787c0f1fd1
|
| 3 |
+
size 378302360
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:574978391563ae05403d9031e8e860cf63882ea6ddc25239018934471833d11b
|
| 3 |
+
size 756732602
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bad94cdb8f0a0743f0ec0580dcedaed421685aa69bfe25e22370b770eba75961
|
| 3 |
+
size 14180
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3b95b9c4d93cb1990e760105ca28b3a84d08994ab7de5bc650dffb313ef227c
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,336 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.996666049268383,
|
| 3 |
+
"best_model_checkpoint": "wav2vec2-base-finetuned-ks/checkpoint-421",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 421,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.023752969121140142,
|
| 13 |
+
"grad_norm": 3.1579225063323975,
|
| 14 |
+
"learning_rate": 1.4218009478672985e-06,
|
| 15 |
+
"loss": 0.69,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.047505938242280284,
|
| 20 |
+
"grad_norm": 3.6760764122009277,
|
| 21 |
+
"learning_rate": 2.843601895734597e-06,
|
| 22 |
+
"loss": 0.6769,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07125890736342043,
|
| 27 |
+
"grad_norm": 4.035228729248047,
|
| 28 |
+
"learning_rate": 4.265402843601896e-06,
|
| 29 |
+
"loss": 0.6482,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09501187648456057,
|
| 34 |
+
"grad_norm": 5.847353458404541,
|
| 35 |
+
"learning_rate": 5.687203791469194e-06,
|
| 36 |
+
"loss": 0.6134,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1187648456057007,
|
| 41 |
+
"grad_norm": 6.475171089172363,
|
| 42 |
+
"learning_rate": 7.1090047393364935e-06,
|
| 43 |
+
"loss": 0.5474,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.14251781472684086,
|
| 48 |
+
"grad_norm": 7.511197566986084,
|
| 49 |
+
"learning_rate": 8.530805687203792e-06,
|
| 50 |
+
"loss": 0.4575,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.166270783847981,
|
| 55 |
+
"grad_norm": 12.910219192504883,
|
| 56 |
+
"learning_rate": 9.95260663507109e-06,
|
| 57 |
+
"loss": 0.3523,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.19002375296912113,
|
| 62 |
+
"grad_norm": 7.936448574066162,
|
| 63 |
+
"learning_rate": 1.1374407582938388e-05,
|
| 64 |
+
"loss": 0.2608,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.21377672209026127,
|
| 69 |
+
"grad_norm": 22.39988899230957,
|
| 70 |
+
"learning_rate": 1.2796208530805688e-05,
|
| 71 |
+
"loss": 0.2022,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2375296912114014,
|
| 76 |
+
"grad_norm": 74.65003967285156,
|
| 77 |
+
"learning_rate": 1.4218009478672987e-05,
|
| 78 |
+
"loss": 0.162,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.26128266033254155,
|
| 83 |
+
"grad_norm": 2.993229389190674,
|
| 84 |
+
"learning_rate": 1.5639810426540286e-05,
|
| 85 |
+
"loss": 0.1456,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2850356294536817,
|
| 90 |
+
"grad_norm": 5.789615154266357,
|
| 91 |
+
"learning_rate": 1.7061611374407583e-05,
|
| 92 |
+
"loss": 0.0996,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.3087885985748218,
|
| 97 |
+
"grad_norm": 49.30809020996094,
|
| 98 |
+
"learning_rate": 1.8483412322274884e-05,
|
| 99 |
+
"loss": 0.0696,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.332541567695962,
|
| 104 |
+
"grad_norm": 1.4047824144363403,
|
| 105 |
+
"learning_rate": 1.990521327014218e-05,
|
| 106 |
+
"loss": 0.074,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.35629453681710216,
|
| 111 |
+
"grad_norm": 12.824111938476562,
|
| 112 |
+
"learning_rate": 2.1327014218009478e-05,
|
| 113 |
+
"loss": 0.0472,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.38004750593824227,
|
| 118 |
+
"grad_norm": 1.3231825828552246,
|
| 119 |
+
"learning_rate": 2.2748815165876775e-05,
|
| 120 |
+
"loss": 0.0228,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.40380047505938244,
|
| 125 |
+
"grad_norm": 0.6064344048500061,
|
| 126 |
+
"learning_rate": 2.4170616113744076e-05,
|
| 127 |
+
"loss": 0.0219,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.42755344418052255,
|
| 132 |
+
"grad_norm": 0.5575058460235596,
|
| 133 |
+
"learning_rate": 2.5592417061611376e-05,
|
| 134 |
+
"loss": 0.0234,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4513064133016627,
|
| 139 |
+
"grad_norm": 0.5436674952507019,
|
| 140 |
+
"learning_rate": 2.7014218009478674e-05,
|
| 141 |
+
"loss": 0.0222,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.4750593824228028,
|
| 146 |
+
"grad_norm": 53.069393157958984,
|
| 147 |
+
"learning_rate": 2.8436018957345974e-05,
|
| 148 |
+
"loss": 0.0291,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.498812351543943,
|
| 153 |
+
"grad_norm": 61.781707763671875,
|
| 154 |
+
"learning_rate": 2.9857819905213268e-05,
|
| 155 |
+
"loss": 0.0629,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5225653206650831,
|
| 160 |
+
"grad_norm": 0.30075332522392273,
|
| 161 |
+
"learning_rate": 2.9857444561774023e-05,
|
| 162 |
+
"loss": 0.0427,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5463182897862233,
|
| 167 |
+
"grad_norm": 0.26658549904823303,
|
| 168 |
+
"learning_rate": 2.969904963041183e-05,
|
| 169 |
+
"loss": 0.0082,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5700712589073634,
|
| 174 |
+
"grad_norm": 29.976423263549805,
|
| 175 |
+
"learning_rate": 2.954065469904963e-05,
|
| 176 |
+
"loss": 0.0328,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5938242280285035,
|
| 181 |
+
"grad_norm": 8.100483894348145,
|
| 182 |
+
"learning_rate": 2.9382259767687437e-05,
|
| 183 |
+
"loss": 0.0257,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6175771971496437,
|
| 188 |
+
"grad_norm": 215.22640991210938,
|
| 189 |
+
"learning_rate": 2.9223864836325236e-05,
|
| 190 |
+
"loss": 0.0236,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6413301662707839,
|
| 195 |
+
"grad_norm": 0.21856270730495453,
|
| 196 |
+
"learning_rate": 2.906546990496304e-05,
|
| 197 |
+
"loss": 0.0073,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.665083135391924,
|
| 202 |
+
"grad_norm": 203.41920471191406,
|
| 203 |
+
"learning_rate": 2.8907074973600844e-05,
|
| 204 |
+
"loss": 0.0214,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6888361045130641,
|
| 209 |
+
"grad_norm": 0.17976981401443481,
|
| 210 |
+
"learning_rate": 2.874868004223865e-05,
|
| 211 |
+
"loss": 0.0179,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7125890736342043,
|
| 216 |
+
"grad_norm": 87.75640106201172,
|
| 217 |
+
"learning_rate": 2.8590285110876456e-05,
|
| 218 |
+
"loss": 0.0127,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7363420427553444,
|
| 223 |
+
"grad_norm": 0.13777469098567963,
|
| 224 |
+
"learning_rate": 2.8431890179514255e-05,
|
| 225 |
+
"loss": 0.0152,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.7600950118764845,
|
| 230 |
+
"grad_norm": 0.15721271932125092,
|
| 231 |
+
"learning_rate": 2.827349524815206e-05,
|
| 232 |
+
"loss": 0.0112,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7838479809976246,
|
| 237 |
+
"grad_norm": 0.11672163009643555,
|
| 238 |
+
"learning_rate": 2.8115100316789863e-05,
|
| 239 |
+
"loss": 0.0064,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8076009501187649,
|
| 244 |
+
"grad_norm": 0.12480423599481583,
|
| 245 |
+
"learning_rate": 2.795670538542767e-05,
|
| 246 |
+
"loss": 0.0134,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.831353919239905,
|
| 251 |
+
"grad_norm": 0.0994909331202507,
|
| 252 |
+
"learning_rate": 2.779831045406547e-05,
|
| 253 |
+
"loss": 0.0335,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8551068883610451,
|
| 258 |
+
"grad_norm": 0.24741250276565552,
|
| 259 |
+
"learning_rate": 2.7639915522703273e-05,
|
| 260 |
+
"loss": 0.0098,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.8788598574821853,
|
| 265 |
+
"grad_norm": 0.086154043674469,
|
| 266 |
+
"learning_rate": 2.7481520591341076e-05,
|
| 267 |
+
"loss": 0.0113,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.9026128266033254,
|
| 272 |
+
"grad_norm": 0.0834391638636589,
|
| 273 |
+
"learning_rate": 2.732312565997888e-05,
|
| 274 |
+
"loss": 0.001,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9263657957244655,
|
| 279 |
+
"grad_norm": 0.07236961275339127,
|
| 280 |
+
"learning_rate": 2.7164730728616687e-05,
|
| 281 |
+
"loss": 0.0033,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9501187648456056,
|
| 286 |
+
"grad_norm": 0.06638740003108978,
|
| 287 |
+
"learning_rate": 2.700633579725449e-05,
|
| 288 |
+
"loss": 0.0008,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9738717339667459,
|
| 293 |
+
"grad_norm": 0.06140037626028061,
|
| 294 |
+
"learning_rate": 2.6847940865892292e-05,
|
| 295 |
+
"loss": 0.0007,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.997624703087886,
|
| 300 |
+
"grad_norm": 0.8051447868347168,
|
| 301 |
+
"learning_rate": 2.6689545934530094e-05,
|
| 302 |
+
"loss": 0.0109,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.0,
|
| 307 |
+
"eval_accuracy": 0.996666049268383,
|
| 308 |
+
"eval_loss": 0.021043801680207253,
|
| 309 |
+
"eval_runtime": 437.9848,
|
| 310 |
+
"eval_samples_per_second": 24.654,
|
| 311 |
+
"eval_steps_per_second": 0.772,
|
| 312 |
+
"step": 421
|
| 313 |
+
}
|
| 314 |
+
],
|
| 315 |
+
"logging_steps": 10,
|
| 316 |
+
"max_steps": 2105,
|
| 317 |
+
"num_input_tokens_seen": 0,
|
| 318 |
+
"num_train_epochs": 5,
|
| 319 |
+
"save_steps": 500,
|
| 320 |
+
"stateful_callbacks": {
|
| 321 |
+
"TrainerControl": {
|
| 322 |
+
"args": {
|
| 323 |
+
"should_epoch_stop": false,
|
| 324 |
+
"should_evaluate": false,
|
| 325 |
+
"should_log": false,
|
| 326 |
+
"should_save": true,
|
| 327 |
+
"should_training_stop": false
|
| 328 |
+
},
|
| 329 |
+
"attributes": {}
|
| 330 |
+
}
|
| 331 |
+
},
|
| 332 |
+
"total_flos": 2.4451992597902285e+18,
|
| 333 |
+
"train_batch_size": 32,
|
| 334 |
+
"trial_name": null,
|
| 335 |
+
"trial_params": null
|
| 336 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7acb1cbf3a5f2b6019ca25dcdd0761a6a46d77812dd91d8a3c5cc8756ecb95ef
|
| 3 |
+
size 5304
|