Upload with huggingface_hub
Browse files- config.json +142 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +299 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/hubert-base-ls960",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"HubertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"conv_kernel": [
|
| 22 |
+
10,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
2,
|
| 28 |
+
2
|
| 29 |
+
],
|
| 30 |
+
"conv_stride": [
|
| 31 |
+
5,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2
|
| 38 |
+
],
|
| 39 |
+
"ctc_loss_reduction": "sum",
|
| 40 |
+
"ctc_zero_infinity": false,
|
| 41 |
+
"do_stable_layer_norm": false,
|
| 42 |
+
"eos_token_id": 2,
|
| 43 |
+
"feat_extract_activation": "gelu",
|
| 44 |
+
"feat_extract_dropout": 0.0,
|
| 45 |
+
"feat_extract_norm": "group",
|
| 46 |
+
"feat_proj_dropout": 0.1,
|
| 47 |
+
"feat_proj_layer_norm": true,
|
| 48 |
+
"final_dropout": 0.1,
|
| 49 |
+
"gradient_checkpointing": false,
|
| 50 |
+
"hidden_act": "gelu",
|
| 51 |
+
"hidden_dropout": 0.1,
|
| 52 |
+
"hidden_dropout_prob": 0.1,
|
| 53 |
+
"hidden_size": 768,
|
| 54 |
+
"id2label": {
|
| 55 |
+
"0": "change languagenonenone",
|
| 56 |
+
"1": "activatemusicnone",
|
| 57 |
+
"10": "deactivatelampnone",
|
| 58 |
+
"11": "activatelightskitchen",
|
| 59 |
+
"12": "activatelightsbedroom",
|
| 60 |
+
"13": "activatelightswashroom",
|
| 61 |
+
"14": "deactivatelightskitchen",
|
| 62 |
+
"15": "deactivatelightsbedroom",
|
| 63 |
+
"16": "deactivatelightswashroom",
|
| 64 |
+
"17": "increaseheatkitchen",
|
| 65 |
+
"18": "increaseheatbedroom",
|
| 66 |
+
"19": "increaseheatwashroom",
|
| 67 |
+
"2": "activatelightsnone",
|
| 68 |
+
"20": "decreaseheatkitchen",
|
| 69 |
+
"21": "decreaseheatbedroom",
|
| 70 |
+
"22": "decreaseheatwashroom",
|
| 71 |
+
"23": "bringnewspapernone",
|
| 72 |
+
"24": "bringjuicenone",
|
| 73 |
+
"25": "bringsocksnone",
|
| 74 |
+
"26": "change languageChinesenone",
|
| 75 |
+
"27": "change languageKoreannone",
|
| 76 |
+
"28": "change languageEnglishnone",
|
| 77 |
+
"29": "change languageGermannone",
|
| 78 |
+
"3": "deactivatelightsnone",
|
| 79 |
+
"30": "bringshoesnone",
|
| 80 |
+
"4": "increasevolumenone",
|
| 81 |
+
"5": "decreasevolumenone",
|
| 82 |
+
"6": "increaseheatnone",
|
| 83 |
+
"7": "decreaseheatnone",
|
| 84 |
+
"8": "deactivatemusicnone",
|
| 85 |
+
"9": "activatelampnone"
|
| 86 |
+
},
|
| 87 |
+
"initializer_range": 0.02,
|
| 88 |
+
"intermediate_size": 3072,
|
| 89 |
+
"label2id": {
|
| 90 |
+
"activatelampnone": "9",
|
| 91 |
+
"activatelightsbedroom": "12",
|
| 92 |
+
"activatelightskitchen": "11",
|
| 93 |
+
"activatelightsnone": "2",
|
| 94 |
+
"activatelightswashroom": "13",
|
| 95 |
+
"activatemusicnone": "1",
|
| 96 |
+
"bringjuicenone": "24",
|
| 97 |
+
"bringnewspapernone": "23",
|
| 98 |
+
"bringshoesnone": "30",
|
| 99 |
+
"bringsocksnone": "25",
|
| 100 |
+
"change languageChinesenone": "26",
|
| 101 |
+
"change languageEnglishnone": "28",
|
| 102 |
+
"change languageGermannone": "29",
|
| 103 |
+
"change languageKoreannone": "27",
|
| 104 |
+
"change languagenonenone": "0",
|
| 105 |
+
"deactivatelampnone": "10",
|
| 106 |
+
"deactivatelightsbedroom": "15",
|
| 107 |
+
"deactivatelightskitchen": "14",
|
| 108 |
+
"deactivatelightsnone": "3",
|
| 109 |
+
"deactivatelightswashroom": "16",
|
| 110 |
+
"deactivatemusicnone": "8",
|
| 111 |
+
"decreaseheatbedroom": "21",
|
| 112 |
+
"decreaseheatkitchen": "20",
|
| 113 |
+
"decreaseheatnone": "7",
|
| 114 |
+
"decreaseheatwashroom": "22",
|
| 115 |
+
"decreasevolumenone": "5",
|
| 116 |
+
"increaseheatbedroom": "18",
|
| 117 |
+
"increaseheatkitchen": "17",
|
| 118 |
+
"increaseheatnone": "6",
|
| 119 |
+
"increaseheatwashroom": "19",
|
| 120 |
+
"increasevolumenone": "4"
|
| 121 |
+
},
|
| 122 |
+
"layer_norm_eps": 1e-05,
|
| 123 |
+
"layerdrop": 0.1,
|
| 124 |
+
"mask_feature_length": 10,
|
| 125 |
+
"mask_feature_min_masks": 0,
|
| 126 |
+
"mask_feature_prob": 0.0,
|
| 127 |
+
"mask_time_length": 10,
|
| 128 |
+
"mask_time_min_masks": 2,
|
| 129 |
+
"mask_time_prob": 0.05,
|
| 130 |
+
"model_type": "hubert",
|
| 131 |
+
"num_attention_heads": 12,
|
| 132 |
+
"num_conv_pos_embedding_groups": 16,
|
| 133 |
+
"num_conv_pos_embeddings": 128,
|
| 134 |
+
"num_feat_extract_layers": 7,
|
| 135 |
+
"num_hidden_layers": 12,
|
| 136 |
+
"pad_token_id": 0,
|
| 137 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 138 |
+
"torch_dtype": "float32",
|
| 139 |
+
"transformers_version": "4.47.0",
|
| 140 |
+
"use_weighted_layer_sum": false,
|
| 141 |
+
"vocab_size": 32
|
| 142 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edc7c9103f8b6114e39558c04832d63ff0a3d6d66caddb9771948c9fc219ee8e
|
| 3 |
+
size 378331764
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d03345785797b9f0c448917b0ba4a48bc975a33a0f7fbb78a43d8ae3fd9c3fed
|
| 3 |
+
size 756792122
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0e6d5b10ace79f32a5c6a89b0272b55190635f3a6a274ee8e25a5ca69560dd3
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ab44e7477902ea1b1faa0367c963428b2c71cf2acf64863d0f8adfb88d0b2ec
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,299 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9329698524695318,
|
| 3 |
+
"best_model_checkpoint": "results/facebook/hubert-base-ls960/42/_retain/checkpoint-2800",
|
| 4 |
+
"epoch": 4.017216642754663,
|
| 5 |
+
"eval_steps": 400,
|
| 6 |
+
"global_step": 2800,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14347202295552366,
|
| 13 |
+
"grad_norm": 7.395946025848389,
|
| 14 |
+
"learning_rate": 0.00017857142857142857,
|
| 15 |
+
"loss": 3.276,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.28694404591104733,
|
| 20 |
+
"grad_norm": 64.37727355957031,
|
| 21 |
+
"learning_rate": 0.00035714285714285714,
|
| 22 |
+
"loss": 2.5895,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.430416068866571,
|
| 27 |
+
"grad_norm": 37.723262786865234,
|
| 28 |
+
"learning_rate": 0.000496031746031746,
|
| 29 |
+
"loss": 2.0702,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5738880918220947,
|
| 34 |
+
"grad_norm": 34.24871826171875,
|
| 35 |
+
"learning_rate": 0.0004761904761904762,
|
| 36 |
+
"loss": 1.9753,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5738880918220947,
|
| 41 |
+
"eval_accuracy": 0.39191789608723543,
|
| 42 |
+
"eval_f1_macro": 0.2435662437168276,
|
| 43 |
+
"eval_loss": 1.6742650270462036,
|
| 44 |
+
"eval_runtime": 12.5972,
|
| 45 |
+
"eval_samples_per_second": 247.516,
|
| 46 |
+
"eval_steps_per_second": 30.959,
|
| 47 |
+
"step": 400
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.7173601147776184,
|
| 51 |
+
"grad_norm": 54.40435791015625,
|
| 52 |
+
"learning_rate": 0.0004563492063492063,
|
| 53 |
+
"loss": 1.8347,
|
| 54 |
+
"step": 500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.860832137733142,
|
| 58 |
+
"grad_norm": 95.11190795898438,
|
| 59 |
+
"learning_rate": 0.0004365079365079365,
|
| 60 |
+
"loss": 1.6797,
|
| 61 |
+
"step": 600
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.0043041606886658,
|
| 65 |
+
"grad_norm": 57.426300048828125,
|
| 66 |
+
"learning_rate": 0.0004166666666666667,
|
| 67 |
+
"loss": 1.5546,
|
| 68 |
+
"step": 700
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.1477761836441893,
|
| 72 |
+
"grad_norm": 26.83301544189453,
|
| 73 |
+
"learning_rate": 0.0003968253968253968,
|
| 74 |
+
"loss": 1.4852,
|
| 75 |
+
"step": 800
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.1477761836441893,
|
| 79 |
+
"eval_accuracy": 0.43585631815266196,
|
| 80 |
+
"eval_f1_macro": 0.35693788277668864,
|
| 81 |
+
"eval_loss": 1.400166392326355,
|
| 82 |
+
"eval_runtime": 12.5264,
|
| 83 |
+
"eval_samples_per_second": 248.914,
|
| 84 |
+
"eval_steps_per_second": 31.134,
|
| 85 |
+
"step": 800
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.291248206599713,
|
| 89 |
+
"grad_norm": 110.81356048583984,
|
| 90 |
+
"learning_rate": 0.000376984126984127,
|
| 91 |
+
"loss": 1.3436,
|
| 92 |
+
"step": 900
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.4347202295552366,
|
| 96 |
+
"grad_norm": 32.543121337890625,
|
| 97 |
+
"learning_rate": 0.00035714285714285714,
|
| 98 |
+
"loss": 1.2294,
|
| 99 |
+
"step": 1000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.5781922525107603,
|
| 103 |
+
"grad_norm": 56.1235237121582,
|
| 104 |
+
"learning_rate": 0.00033730158730158733,
|
| 105 |
+
"loss": 1.2193,
|
| 106 |
+
"step": 1100
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.721664275466284,
|
| 110 |
+
"grad_norm": 45.8999137878418,
|
| 111 |
+
"learning_rate": 0.00031746031746031746,
|
| 112 |
+
"loss": 1.1012,
|
| 113 |
+
"step": 1200
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.721664275466284,
|
| 117 |
+
"eval_accuracy": 0.5,
|
| 118 |
+
"eval_f1_macro": 0.40820204518718034,
|
| 119 |
+
"eval_loss": 1.1420663595199585,
|
| 120 |
+
"eval_runtime": 12.5482,
|
| 121 |
+
"eval_samples_per_second": 248.481,
|
| 122 |
+
"eval_steps_per_second": 31.08,
|
| 123 |
+
"step": 1200
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.8651362984218078,
|
| 127 |
+
"grad_norm": 61.26133728027344,
|
| 128 |
+
"learning_rate": 0.00029761904761904765,
|
| 129 |
+
"loss": 1.0592,
|
| 130 |
+
"step": 1300
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.0086083213773316,
|
| 134 |
+
"grad_norm": 14.982177734375,
|
| 135 |
+
"learning_rate": 0.0002777777777777778,
|
| 136 |
+
"loss": 0.9699,
|
| 137 |
+
"step": 1400
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 2.152080344332855,
|
| 141 |
+
"grad_norm": 81.27915954589844,
|
| 142 |
+
"learning_rate": 0.00025793650793650796,
|
| 143 |
+
"loss": 0.8729,
|
| 144 |
+
"step": 1500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.2955523672883786,
|
| 148 |
+
"grad_norm": 20.86075210571289,
|
| 149 |
+
"learning_rate": 0.0002380952380952381,
|
| 150 |
+
"loss": 0.8175,
|
| 151 |
+
"step": 1600
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 2.2955523672883786,
|
| 155 |
+
"eval_accuracy": 0.7113534316869788,
|
| 156 |
+
"eval_f1_macro": 0.7266787228808548,
|
| 157 |
+
"eval_loss": 0.9044921398162842,
|
| 158 |
+
"eval_runtime": 12.5282,
|
| 159 |
+
"eval_samples_per_second": 248.878,
|
| 160 |
+
"eval_steps_per_second": 31.13,
|
| 161 |
+
"step": 1600
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.4390243902439024,
|
| 165 |
+
"grad_norm": 25.487239837646484,
|
| 166 |
+
"learning_rate": 0.00021825396825396825,
|
| 167 |
+
"loss": 0.7922,
|
| 168 |
+
"step": 1700
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.582496413199426,
|
| 172 |
+
"grad_norm": 63.39326477050781,
|
| 173 |
+
"learning_rate": 0.0001984126984126984,
|
| 174 |
+
"loss": 0.6825,
|
| 175 |
+
"step": 1800
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 2.72596843615495,
|
| 179 |
+
"grad_norm": 28.30609893798828,
|
| 180 |
+
"learning_rate": 0.00017857142857142857,
|
| 181 |
+
"loss": 0.6263,
|
| 182 |
+
"step": 1900
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.869440459110473,
|
| 186 |
+
"grad_norm": 20.287073135375977,
|
| 187 |
+
"learning_rate": 0.00015873015873015873,
|
| 188 |
+
"loss": 0.5372,
|
| 189 |
+
"step": 2000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.869440459110473,
|
| 193 |
+
"eval_accuracy": 0.8787684413085312,
|
| 194 |
+
"eval_f1_macro": 0.8885767692084414,
|
| 195 |
+
"eval_loss": 0.48355233669281006,
|
| 196 |
+
"eval_runtime": 12.5225,
|
| 197 |
+
"eval_samples_per_second": 248.991,
|
| 198 |
+
"eval_steps_per_second": 31.144,
|
| 199 |
+
"step": 2000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 3.012912482065997,
|
| 203 |
+
"grad_norm": 23.214784622192383,
|
| 204 |
+
"learning_rate": 0.0001388888888888889,
|
| 205 |
+
"loss": 0.4395,
|
| 206 |
+
"step": 2100
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.1563845050215207,
|
| 210 |
+
"grad_norm": 60.17699432373047,
|
| 211 |
+
"learning_rate": 0.00011904761904761905,
|
| 212 |
+
"loss": 0.3497,
|
| 213 |
+
"step": 2200
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 3.2998565279770444,
|
| 217 |
+
"grad_norm": 1.4547343254089355,
|
| 218 |
+
"learning_rate": 9.92063492063492e-05,
|
| 219 |
+
"loss": 0.3281,
|
| 220 |
+
"step": 2300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.443328550932568,
|
| 224 |
+
"grad_norm": 8.235297203063965,
|
| 225 |
+
"learning_rate": 7.936507936507937e-05,
|
| 226 |
+
"loss": 0.3182,
|
| 227 |
+
"step": 2400
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.443328550932568,
|
| 231 |
+
"eval_accuracy": 0.9153303399615138,
|
| 232 |
+
"eval_f1_macro": 0.916711729246869,
|
| 233 |
+
"eval_loss": 0.41809144616127014,
|
| 234 |
+
"eval_runtime": 12.7913,
|
| 235 |
+
"eval_samples_per_second": 243.759,
|
| 236 |
+
"eval_steps_per_second": 30.489,
|
| 237 |
+
"step": 2400
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 3.586800573888092,
|
| 241 |
+
"grad_norm": 24.18486213684082,
|
| 242 |
+
"learning_rate": 5.9523809523809524e-05,
|
| 243 |
+
"loss": 0.2798,
|
| 244 |
+
"step": 2500
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 3.7302725968436157,
|
| 248 |
+
"grad_norm": 12.47843074798584,
|
| 249 |
+
"learning_rate": 3.968253968253968e-05,
|
| 250 |
+
"loss": 0.2553,
|
| 251 |
+
"step": 2600
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 3.8737446197991394,
|
| 255 |
+
"grad_norm": 24.14739990234375,
|
| 256 |
+
"learning_rate": 1.984126984126984e-05,
|
| 257 |
+
"loss": 0.231,
|
| 258 |
+
"step": 2700
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 4.017216642754663,
|
| 262 |
+
"grad_norm": 4.063531398773193,
|
| 263 |
+
"learning_rate": 0.0,
|
| 264 |
+
"loss": 0.2035,
|
| 265 |
+
"step": 2800
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 4.017216642754663,
|
| 269 |
+
"eval_accuracy": 0.9329698524695318,
|
| 270 |
+
"eval_f1_macro": 0.9320770657825714,
|
| 271 |
+
"eval_loss": 0.33222800493240356,
|
| 272 |
+
"eval_runtime": 12.7416,
|
| 273 |
+
"eval_samples_per_second": 244.711,
|
| 274 |
+
"eval_steps_per_second": 30.608,
|
| 275 |
+
"step": 2800
|
| 276 |
+
}
|
| 277 |
+
],
|
| 278 |
+
"logging_steps": 100,
|
| 279 |
+
"max_steps": 2800,
|
| 280 |
+
"num_input_tokens_seen": 0,
|
| 281 |
+
"num_train_epochs": 5,
|
| 282 |
+
"save_steps": 2800,
|
| 283 |
+
"stateful_callbacks": {
|
| 284 |
+
"TrainerControl": {
|
| 285 |
+
"args": {
|
| 286 |
+
"should_epoch_stop": false,
|
| 287 |
+
"should_evaluate": false,
|
| 288 |
+
"should_log": false,
|
| 289 |
+
"should_save": true,
|
| 290 |
+
"should_training_stop": true
|
| 291 |
+
},
|
| 292 |
+
"attributes": {}
|
| 293 |
+
}
|
| 294 |
+
},
|
| 295 |
+
"total_flos": 3.2540383690752e+18,
|
| 296 |
+
"train_batch_size": 8,
|
| 297 |
+
"trial_name": null,
|
| 298 |
+
"trial_params": null
|
| 299 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c17e6666fb7c04a4ec127301f26c8fa15de4c9a06abf35a824e4c414489961ff
|
| 3 |
+
size 5368
|