Upload with huggingface_hub
Browse files- config.json +129 -0
- optimizer.pt +3 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +493 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
+
"apply_spec_augment": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"Wav2Vec2ForSequenceClassification"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.1,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 256,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": false,
|
| 17 |
+
"conv_dim": [
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512
|
| 25 |
+
],
|
| 26 |
+
"conv_kernel": [
|
| 27 |
+
10,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2
|
| 34 |
+
],
|
| 35 |
+
"conv_stride": [
|
| 36 |
+
5,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"ctc_loss_reduction": "sum",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": false,
|
| 48 |
+
"eos_token_id": 2,
|
| 49 |
+
"feat_extract_activation": "gelu",
|
| 50 |
+
"feat_extract_norm": "group",
|
| 51 |
+
"feat_proj_dropout": 0.1,
|
| 52 |
+
"feat_quantizer_dropout": 0.0,
|
| 53 |
+
"final_dropout": 0.0,
|
| 54 |
+
"freeze_feat_extract_train": true,
|
| 55 |
+
"hidden_act": "gelu",
|
| 56 |
+
"hidden_dropout": 0.1,
|
| 57 |
+
"hidden_size": 768,
|
| 58 |
+
"id2label": {
|
| 59 |
+
"0": "door_close",
|
| 60 |
+
"1": "door_open",
|
| 61 |
+
"2": "door_stop",
|
| 62 |
+
"3": "unknown"
|
| 63 |
+
},
|
| 64 |
+
"initializer_range": 0.02,
|
| 65 |
+
"intermediate_size": 3072,
|
| 66 |
+
"label2id": {
|
| 67 |
+
"door_close": "0",
|
| 68 |
+
"door_open": "1",
|
| 69 |
+
"door_stop": "2",
|
| 70 |
+
"unknown": "3"
|
| 71 |
+
},
|
| 72 |
+
"layer_norm_eps": 1e-05,
|
| 73 |
+
"layerdrop": 0.0,
|
| 74 |
+
"mask_channel_length": 10,
|
| 75 |
+
"mask_channel_min_space": 1,
|
| 76 |
+
"mask_channel_other": 0.0,
|
| 77 |
+
"mask_channel_prob": 0.0,
|
| 78 |
+
"mask_channel_selection": "static",
|
| 79 |
+
"mask_feature_length": 10,
|
| 80 |
+
"mask_feature_min_masks": 0,
|
| 81 |
+
"mask_feature_prob": 0.0,
|
| 82 |
+
"mask_time_length": 10,
|
| 83 |
+
"mask_time_min_masks": 2,
|
| 84 |
+
"mask_time_min_space": 1,
|
| 85 |
+
"mask_time_other": 0.0,
|
| 86 |
+
"mask_time_prob": 0.05,
|
| 87 |
+
"mask_time_selection": "static",
|
| 88 |
+
"model_type": "wav2vec2",
|
| 89 |
+
"no_mask_channel_overlap": false,
|
| 90 |
+
"no_mask_time_overlap": false,
|
| 91 |
+
"num_adapter_layers": 3,
|
| 92 |
+
"num_attention_heads": 12,
|
| 93 |
+
"num_codevector_groups": 2,
|
| 94 |
+
"num_codevectors_per_group": 320,
|
| 95 |
+
"num_conv_pos_embedding_groups": 16,
|
| 96 |
+
"num_conv_pos_embeddings": 128,
|
| 97 |
+
"num_feat_extract_layers": 7,
|
| 98 |
+
"num_hidden_layers": 12,
|
| 99 |
+
"num_negatives": 100,
|
| 100 |
+
"output_hidden_size": 768,
|
| 101 |
+
"pad_token_id": 0,
|
| 102 |
+
"proj_codevector_dim": 256,
|
| 103 |
+
"tdnn_dilation": [
|
| 104 |
+
1,
|
| 105 |
+
2,
|
| 106 |
+
3,
|
| 107 |
+
1,
|
| 108 |
+
1
|
| 109 |
+
],
|
| 110 |
+
"tdnn_dim": [
|
| 111 |
+
512,
|
| 112 |
+
512,
|
| 113 |
+
512,
|
| 114 |
+
512,
|
| 115 |
+
1500
|
| 116 |
+
],
|
| 117 |
+
"tdnn_kernel": [
|
| 118 |
+
5,
|
| 119 |
+
3,
|
| 120 |
+
3,
|
| 121 |
+
1,
|
| 122 |
+
1
|
| 123 |
+
],
|
| 124 |
+
"torch_dtype": "float32",
|
| 125 |
+
"transformers_version": "4.27.4",
|
| 126 |
+
"use_weighted_layer_sum": false,
|
| 127 |
+
"vocab_size": 32,
|
| 128 |
+
"xvector_output_dim": 512
|
| 129 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7587ffff1dfe24aa849f7eeb0c52aaf3dfbacbbc3f6602e8c55195a6717d1538
|
| 3 |
+
size 756681573
|
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 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:256a577ac8c6f7f70b6a4c6d33bd866f83728f944e2d8e3e2c681a970ccba294
|
| 3 |
+
size 378350611
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf446337cb7e8c908e927cd6898981bf25871364c58e8cb1d6de5544592f9d8e
|
| 3 |
+
size 14567
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ee1f7050eaf838661ad94fdb4437c7f87c549b7fc38e49c89bd120f7dea84f0
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,493 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9901107169730194,
|
| 3 |
+
"best_model_checkpoint": "wav2vec2-base-finetuned-doorbot/checkpoint-725",
|
| 4 |
+
"epoch": 4.982817869415808,
|
| 5 |
+
"global_step": 725,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 4.10958904109589e-06,
|
| 13 |
+
"loss": 1.369,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.14,
|
| 18 |
+
"learning_rate": 8.21917808219178e-06,
|
| 19 |
+
"loss": 1.3239,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.21,
|
| 24 |
+
"learning_rate": 1.2328767123287671e-05,
|
| 25 |
+
"loss": 1.2559,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.27,
|
| 30 |
+
"learning_rate": 1.643835616438356e-05,
|
| 31 |
+
"loss": 1.1835,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.34,
|
| 36 |
+
"learning_rate": 2.0547945205479453e-05,
|
| 37 |
+
"loss": 1.0583,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.41,
|
| 42 |
+
"learning_rate": 2.4657534246575342e-05,
|
| 43 |
+
"loss": 1.0132,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.48,
|
| 48 |
+
"learning_rate": 2.876712328767123e-05,
|
| 49 |
+
"loss": 0.8901,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.55,
|
| 54 |
+
"learning_rate": 2.9677914110429448e-05,
|
| 55 |
+
"loss": 0.7815,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.62,
|
| 60 |
+
"learning_rate": 2.9217791411042947e-05,
|
| 61 |
+
"loss": 0.6855,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.69,
|
| 66 |
+
"learning_rate": 2.8757668711656442e-05,
|
| 67 |
+
"loss": 0.5417,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.76,
|
| 72 |
+
"learning_rate": 2.829754601226994e-05,
|
| 73 |
+
"loss": 0.4626,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.82,
|
| 78 |
+
"learning_rate": 2.7837423312883435e-05,
|
| 79 |
+
"loss": 0.4475,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.89,
|
| 84 |
+
"learning_rate": 2.737730061349693e-05,
|
| 85 |
+
"loss": 0.375,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.96,
|
| 90 |
+
"learning_rate": 2.6917177914110432e-05,
|
| 91 |
+
"loss": 0.3422,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.0,
|
| 96 |
+
"eval_accuracy": 0.9508760614855423,
|
| 97 |
+
"eval_loss": 0.2727504074573517,
|
| 98 |
+
"eval_runtime": 101.1131,
|
| 99 |
+
"eval_samples_per_second": 92.006,
|
| 100 |
+
"eval_steps_per_second": 2.878,
|
| 101 |
+
"step": 145
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.03,
|
| 105 |
+
"learning_rate": 2.6457055214723928e-05,
|
| 106 |
+
"loss": 0.3256,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.1,
|
| 111 |
+
"learning_rate": 2.5996932515337423e-05,
|
| 112 |
+
"loss": 0.2889,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.17,
|
| 117 |
+
"learning_rate": 2.553680981595092e-05,
|
| 118 |
+
"loss": 0.2608,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.24,
|
| 123 |
+
"learning_rate": 2.5076687116564416e-05,
|
| 124 |
+
"loss": 0.2261,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.31,
|
| 129 |
+
"learning_rate": 2.4616564417177915e-05,
|
| 130 |
+
"loss": 0.1831,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.37,
|
| 135 |
+
"learning_rate": 2.4156441717791413e-05,
|
| 136 |
+
"loss": 0.178,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.44,
|
| 141 |
+
"learning_rate": 2.369631901840491e-05,
|
| 142 |
+
"loss": 0.1697,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.51,
|
| 147 |
+
"learning_rate": 2.3236196319018404e-05,
|
| 148 |
+
"loss": 0.1918,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.58,
|
| 153 |
+
"learning_rate": 2.2776073619631902e-05,
|
| 154 |
+
"loss": 0.1838,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.65,
|
| 159 |
+
"learning_rate": 2.23159509202454e-05,
|
| 160 |
+
"loss": 0.1839,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.72,
|
| 165 |
+
"learning_rate": 2.1855828220858896e-05,
|
| 166 |
+
"loss": 0.1522,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.79,
|
| 171 |
+
"learning_rate": 2.1395705521472395e-05,
|
| 172 |
+
"loss": 0.1487,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.86,
|
| 177 |
+
"learning_rate": 2.093558282208589e-05,
|
| 178 |
+
"loss": 0.1389,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.92,
|
| 183 |
+
"learning_rate": 2.0475460122699385e-05,
|
| 184 |
+
"loss": 0.1334,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.99,
|
| 189 |
+
"learning_rate": 2.0015337423312883e-05,
|
| 190 |
+
"loss": 0.1201,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.0,
|
| 195 |
+
"eval_accuracy": 0.9834462001504891,
|
| 196 |
+
"eval_loss": 0.09842008352279663,
|
| 197 |
+
"eval_runtime": 100.3887,
|
| 198 |
+
"eval_samples_per_second": 92.67,
|
| 199 |
+
"eval_steps_per_second": 2.899,
|
| 200 |
+
"step": 291
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.06,
|
| 204 |
+
"learning_rate": 1.9555214723926382e-05,
|
| 205 |
+
"loss": 0.1195,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.13,
|
| 210 |
+
"learning_rate": 1.9095092024539877e-05,
|
| 211 |
+
"loss": 0.1137,
|
| 212 |
+
"step": 310
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.2,
|
| 216 |
+
"learning_rate": 1.8634969325153372e-05,
|
| 217 |
+
"loss": 0.1058,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.27,
|
| 222 |
+
"learning_rate": 1.8174846625766874e-05,
|
| 223 |
+
"loss": 0.1208,
|
| 224 |
+
"step": 330
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.34,
|
| 228 |
+
"learning_rate": 1.771472392638037e-05,
|
| 229 |
+
"loss": 0.1067,
|
| 230 |
+
"step": 340
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.41,
|
| 234 |
+
"learning_rate": 1.7254601226993864e-05,
|
| 235 |
+
"loss": 0.0979,
|
| 236 |
+
"step": 350
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.47,
|
| 240 |
+
"learning_rate": 1.6794478527607363e-05,
|
| 241 |
+
"loss": 0.1151,
|
| 242 |
+
"step": 360
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.54,
|
| 246 |
+
"learning_rate": 1.6334355828220858e-05,
|
| 247 |
+
"loss": 0.1143,
|
| 248 |
+
"step": 370
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.61,
|
| 252 |
+
"learning_rate": 1.5874233128834357e-05,
|
| 253 |
+
"loss": 0.1025,
|
| 254 |
+
"step": 380
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.68,
|
| 258 |
+
"learning_rate": 1.5414110429447855e-05,
|
| 259 |
+
"loss": 0.0852,
|
| 260 |
+
"step": 390
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.75,
|
| 264 |
+
"learning_rate": 1.495398773006135e-05,
|
| 265 |
+
"loss": 0.0908,
|
| 266 |
+
"step": 400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.82,
|
| 270 |
+
"learning_rate": 1.4493865030674847e-05,
|
| 271 |
+
"loss": 0.0992,
|
| 272 |
+
"step": 410
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.89,
|
| 276 |
+
"learning_rate": 1.4033742331288344e-05,
|
| 277 |
+
"loss": 0.0869,
|
| 278 |
+
"step": 420
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.96,
|
| 282 |
+
"learning_rate": 1.357361963190184e-05,
|
| 283 |
+
"loss": 0.0867,
|
| 284 |
+
"step": 430
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.0,
|
| 288 |
+
"eval_accuracy": 0.9893582715253144,
|
| 289 |
+
"eval_loss": 0.058089084923267365,
|
| 290 |
+
"eval_runtime": 100.4678,
|
| 291 |
+
"eval_samples_per_second": 92.597,
|
| 292 |
+
"eval_steps_per_second": 2.896,
|
| 293 |
+
"step": 436
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.02,
|
| 297 |
+
"learning_rate": 1.3113496932515338e-05,
|
| 298 |
+
"loss": 0.096,
|
| 299 |
+
"step": 440
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.09,
|
| 303 |
+
"learning_rate": 1.2653374233128834e-05,
|
| 304 |
+
"loss": 0.0985,
|
| 305 |
+
"step": 450
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 3.16,
|
| 309 |
+
"learning_rate": 1.2193251533742331e-05,
|
| 310 |
+
"loss": 0.0964,
|
| 311 |
+
"step": 460
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 3.23,
|
| 315 |
+
"learning_rate": 1.173312883435583e-05,
|
| 316 |
+
"loss": 0.0804,
|
| 317 |
+
"step": 470
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.3,
|
| 321 |
+
"learning_rate": 1.1273006134969325e-05,
|
| 322 |
+
"loss": 0.0762,
|
| 323 |
+
"step": 480
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.37,
|
| 327 |
+
"learning_rate": 1.0812883435582822e-05,
|
| 328 |
+
"loss": 0.0645,
|
| 329 |
+
"step": 490
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.44,
|
| 333 |
+
"learning_rate": 1.035276073619632e-05,
|
| 334 |
+
"loss": 0.0685,
|
| 335 |
+
"step": 500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.51,
|
| 339 |
+
"learning_rate": 9.892638036809815e-06,
|
| 340 |
+
"loss": 0.0703,
|
| 341 |
+
"step": 510
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.57,
|
| 345 |
+
"learning_rate": 9.432515337423314e-06,
|
| 346 |
+
"loss": 0.0753,
|
| 347 |
+
"step": 520
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.64,
|
| 351 |
+
"learning_rate": 8.972392638036809e-06,
|
| 352 |
+
"loss": 0.0652,
|
| 353 |
+
"step": 530
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.71,
|
| 357 |
+
"learning_rate": 8.512269938650308e-06,
|
| 358 |
+
"loss": 0.0571,
|
| 359 |
+
"step": 540
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.78,
|
| 363 |
+
"learning_rate": 8.052147239263804e-06,
|
| 364 |
+
"loss": 0.0707,
|
| 365 |
+
"step": 550
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.85,
|
| 369 |
+
"learning_rate": 7.5920245398773005e-06,
|
| 370 |
+
"loss": 0.0729,
|
| 371 |
+
"step": 560
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.92,
|
| 375 |
+
"learning_rate": 7.131901840490797e-06,
|
| 376 |
+
"loss": 0.0659,
|
| 377 |
+
"step": 570
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.99,
|
| 381 |
+
"learning_rate": 6.671779141104294e-06,
|
| 382 |
+
"loss": 0.0569,
|
| 383 |
+
"step": 580
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 4.0,
|
| 387 |
+
"eval_accuracy": 0.9876383962162744,
|
| 388 |
+
"eval_loss": 0.055703163146972656,
|
| 389 |
+
"eval_runtime": 100.1804,
|
| 390 |
+
"eval_samples_per_second": 92.862,
|
| 391 |
+
"eval_steps_per_second": 2.905,
|
| 392 |
+
"step": 582
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.05,
|
| 396 |
+
"learning_rate": 6.211656441717792e-06,
|
| 397 |
+
"loss": 0.0516,
|
| 398 |
+
"step": 590
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.12,
|
| 402 |
+
"learning_rate": 5.751533742331289e-06,
|
| 403 |
+
"loss": 0.0431,
|
| 404 |
+
"step": 600
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.19,
|
| 408 |
+
"learning_rate": 5.2914110429447855e-06,
|
| 409 |
+
"loss": 0.0572,
|
| 410 |
+
"step": 610
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 4.26,
|
| 414 |
+
"learning_rate": 4.8312883435582815e-06,
|
| 415 |
+
"loss": 0.0553,
|
| 416 |
+
"step": 620
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.33,
|
| 420 |
+
"learning_rate": 4.371165644171779e-06,
|
| 421 |
+
"loss": 0.0657,
|
| 422 |
+
"step": 630
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.4,
|
| 426 |
+
"learning_rate": 3.911042944785276e-06,
|
| 427 |
+
"loss": 0.0564,
|
| 428 |
+
"step": 640
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.47,
|
| 432 |
+
"learning_rate": 3.4509202453987733e-06,
|
| 433 |
+
"loss": 0.0397,
|
| 434 |
+
"step": 650
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.54,
|
| 438 |
+
"learning_rate": 2.9907975460122697e-06,
|
| 439 |
+
"loss": 0.0692,
|
| 440 |
+
"step": 660
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 4.6,
|
| 444 |
+
"learning_rate": 2.530674846625767e-06,
|
| 445 |
+
"loss": 0.0514,
|
| 446 |
+
"step": 670
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.67,
|
| 450 |
+
"learning_rate": 2.070552147239264e-06,
|
| 451 |
+
"loss": 0.0573,
|
| 452 |
+
"step": 680
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 4.74,
|
| 456 |
+
"learning_rate": 1.6104294478527609e-06,
|
| 457 |
+
"loss": 0.0495,
|
| 458 |
+
"step": 690
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.81,
|
| 462 |
+
"learning_rate": 1.1503067484662577e-06,
|
| 463 |
+
"loss": 0.0516,
|
| 464 |
+
"step": 700
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.88,
|
| 468 |
+
"learning_rate": 6.901840490797546e-07,
|
| 469 |
+
"loss": 0.0475,
|
| 470 |
+
"step": 710
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 4.95,
|
| 474 |
+
"learning_rate": 2.3006134969325153e-07,
|
| 475 |
+
"loss": 0.0482,
|
| 476 |
+
"step": 720
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.98,
|
| 480 |
+
"eval_accuracy": 0.9901107169730194,
|
| 481 |
+
"eval_loss": 0.045827679336071014,
|
| 482 |
+
"eval_runtime": 100.8088,
|
| 483 |
+
"eval_samples_per_second": 92.284,
|
| 484 |
+
"eval_steps_per_second": 2.887,
|
| 485 |
+
"step": 725
|
| 486 |
+
}
|
| 487 |
+
],
|
| 488 |
+
"max_steps": 725,
|
| 489 |
+
"num_train_epochs": 5,
|
| 490 |
+
"total_flos": 8.41884337740288e+17,
|
| 491 |
+
"trial_name": null,
|
| 492 |
+
"trial_params": null
|
| 493 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:619da0c48946e280f6bb6d4feabe8e0ef5740eb4a2095688deaff22ec38accdb
|
| 3 |
+
size 3567
|