Commit
•
2317ca0
1
Parent(s):
f299ae0
Training in progress, step 1100
Browse files- checkpoint-1000/config.json +115 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/preprocessor_config.json +10 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +226 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1100/config.json +115 -0
- checkpoint-1100/optimizer.pt +3 -0
- checkpoint-1100/preprocessor_config.json +10 -0
- checkpoint-1100/pytorch_model.bin +3 -0
- checkpoint-1100/rng_state.pth +3 -0
- checkpoint-1100/scaler.pt +3 -0
- checkpoint-1100/scheduler.pt +3 -0
- checkpoint-1100/trainer_state.json +247 -0
- checkpoint-1100/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
| 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 |
+
"Wav2Vec2ForCTC"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.1,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 768,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": true,
|
| 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": "mean",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": true,
|
| 48 |
+
"eos_token_id": 2,
|
| 49 |
+
"feat_extract_activation": "gelu",
|
| 50 |
+
"feat_extract_dropout": 0.0,
|
| 51 |
+
"feat_extract_norm": "layer",
|
| 52 |
+
"feat_proj_dropout": 0.0,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"hidden_act": "gelu",
|
| 56 |
+
"hidden_dropout": 0.1,
|
| 57 |
+
"hidden_size": 1024,
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 4096,
|
| 60 |
+
"layer_norm_eps": 1e-05,
|
| 61 |
+
"layerdrop": 0.1,
|
| 62 |
+
"mask_channel_length": 10,
|
| 63 |
+
"mask_channel_min_space": 1,
|
| 64 |
+
"mask_channel_other": 0.0,
|
| 65 |
+
"mask_channel_prob": 0.0,
|
| 66 |
+
"mask_channel_selection": "static",
|
| 67 |
+
"mask_feature_length": 10,
|
| 68 |
+
"mask_feature_min_masks": 0,
|
| 69 |
+
"mask_feature_prob": 0.0,
|
| 70 |
+
"mask_time_length": 10,
|
| 71 |
+
"mask_time_min_masks": 2,
|
| 72 |
+
"mask_time_min_space": 1,
|
| 73 |
+
"mask_time_other": 0.0,
|
| 74 |
+
"mask_time_prob": 0.05,
|
| 75 |
+
"mask_time_selection": "static",
|
| 76 |
+
"model_type": "wav2vec2",
|
| 77 |
+
"num_adapter_layers": 3,
|
| 78 |
+
"num_attention_heads": 16,
|
| 79 |
+
"num_codevector_groups": 2,
|
| 80 |
+
"num_codevectors_per_group": 320,
|
| 81 |
+
"num_conv_pos_embedding_groups": 16,
|
| 82 |
+
"num_conv_pos_embeddings": 128,
|
| 83 |
+
"num_feat_extract_layers": 7,
|
| 84 |
+
"num_hidden_layers": 24,
|
| 85 |
+
"num_negatives": 100,
|
| 86 |
+
"output_hidden_size": 1024,
|
| 87 |
+
"pad_token_id": 107,
|
| 88 |
+
"proj_codevector_dim": 768,
|
| 89 |
+
"tdnn_dilation": [
|
| 90 |
+
1,
|
| 91 |
+
2,
|
| 92 |
+
3,
|
| 93 |
+
1,
|
| 94 |
+
1
|
| 95 |
+
],
|
| 96 |
+
"tdnn_dim": [
|
| 97 |
+
512,
|
| 98 |
+
512,
|
| 99 |
+
512,
|
| 100 |
+
512,
|
| 101 |
+
1500
|
| 102 |
+
],
|
| 103 |
+
"tdnn_kernel": [
|
| 104 |
+
5,
|
| 105 |
+
3,
|
| 106 |
+
3,
|
| 107 |
+
1,
|
| 108 |
+
1
|
| 109 |
+
],
|
| 110 |
+
"torch_dtype": "float32",
|
| 111 |
+
"transformers_version": "4.29.2",
|
| 112 |
+
"use_weighted_layer_sum": false,
|
| 113 |
+
"vocab_size": 108,
|
| 114 |
+
"xvector_output_dim": 512
|
| 115 |
+
}
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9047a1dbb440cc38970a45319a5646304b15ba0a0843ebcec9895bbdda0ce321
|
| 3 |
+
size 2490946501
|
checkpoint-1000/preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
checkpoint-1000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f063532b60c9d8ebea8e407d99824e1467e0ec25d6e28485f2e79240c5f3e9e9
|
| 3 |
+
size 1262344621
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a57d9d544f974865071e68a80b84de5de664a230baeb249be510db0a0d96d04
|
| 3 |
+
size 14639
|
checkpoint-1000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31f7c33f7d4b3d298a27a7dc6b22c035e0393e714287cc7d69f421614213cb75
|
| 3 |
+
size 557
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e835e668d21436e5880ed5cc917e1d91cd36b1736933800a6be8ba358688f2ff
|
| 3 |
+
size 627
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.802721088435375,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.34,
|
| 12 |
+
"learning_rate": 2.8199999999999998e-05,
|
| 13 |
+
"loss": 14.6495,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.68,
|
| 18 |
+
"learning_rate": 5.82e-05,
|
| 19 |
+
"loss": 8.9314,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.68,
|
| 24 |
+
"eval_cer": 0.9940322843632806,
|
| 25 |
+
"eval_loss": 4.78579044342041,
|
| 26 |
+
"eval_runtime": 24.1442,
|
| 27 |
+
"eval_samples_per_second": 24.354,
|
| 28 |
+
"eval_steps_per_second": 3.065,
|
| 29 |
+
"step": 100
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.02,
|
| 33 |
+
"learning_rate": 8.819999999999999e-05,
|
| 34 |
+
"loss": 4.2225,
|
| 35 |
+
"step": 150
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.36,
|
| 39 |
+
"learning_rate": 0.0001182,
|
| 40 |
+
"loss": 3.2937,
|
| 41 |
+
"step": 200
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.36,
|
| 45 |
+
"eval_cer": 0.9940322843632806,
|
| 46 |
+
"eval_loss": 3.2489850521087646,
|
| 47 |
+
"eval_runtime": 24.3318,
|
| 48 |
+
"eval_samples_per_second": 24.166,
|
| 49 |
+
"eval_steps_per_second": 3.041,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.7,
|
| 54 |
+
"learning_rate": 0.0001482,
|
| 55 |
+
"loss": 3.2508,
|
| 56 |
+
"step": 250
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.04,
|
| 60 |
+
"learning_rate": 0.00017819999999999997,
|
| 61 |
+
"loss": 3.2412,
|
| 62 |
+
"step": 300
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.04,
|
| 66 |
+
"eval_cer": 0.9940322843632806,
|
| 67 |
+
"eval_loss": 3.222844123840332,
|
| 68 |
+
"eval_runtime": 24.3579,
|
| 69 |
+
"eval_samples_per_second": 24.14,
|
| 70 |
+
"eval_steps_per_second": 3.038,
|
| 71 |
+
"step": 300
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.38,
|
| 75 |
+
"learning_rate": 0.00020819999999999996,
|
| 76 |
+
"loss": 3.1855,
|
| 77 |
+
"step": 350
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 2.72,
|
| 81 |
+
"learning_rate": 0.0002382,
|
| 82 |
+
"loss": 3.0985,
|
| 83 |
+
"step": 400
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.72,
|
| 87 |
+
"eval_cer": 0.9940322843632806,
|
| 88 |
+
"eval_loss": 3.1458029747009277,
|
| 89 |
+
"eval_runtime": 24.7673,
|
| 90 |
+
"eval_samples_per_second": 23.741,
|
| 91 |
+
"eval_steps_per_second": 2.988,
|
| 92 |
+
"step": 400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.06,
|
| 96 |
+
"learning_rate": 0.00026819999999999996,
|
| 97 |
+
"loss": 3.0739,
|
| 98 |
+
"step": 450
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.4,
|
| 102 |
+
"learning_rate": 0.0002982,
|
| 103 |
+
"loss": 3.0209,
|
| 104 |
+
"step": 500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.4,
|
| 108 |
+
"eval_cer": 0.9938692320234795,
|
| 109 |
+
"eval_loss": 3.004169225692749,
|
| 110 |
+
"eval_runtime": 24.3542,
|
| 111 |
+
"eval_samples_per_second": 24.144,
|
| 112 |
+
"eval_steps_per_second": 3.038,
|
| 113 |
+
"step": 500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.74,
|
| 117 |
+
"learning_rate": 0.0002955590551181102,
|
| 118 |
+
"loss": 2.9536,
|
| 119 |
+
"step": 550
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.08,
|
| 123 |
+
"learning_rate": 0.0002908346456692913,
|
| 124 |
+
"loss": 2.518,
|
| 125 |
+
"step": 600
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.08,
|
| 129 |
+
"eval_cer": 0.5400945703570846,
|
| 130 |
+
"eval_loss": 1.770609736442566,
|
| 131 |
+
"eval_runtime": 24.8378,
|
| 132 |
+
"eval_samples_per_second": 23.674,
|
| 133 |
+
"eval_steps_per_second": 2.979,
|
| 134 |
+
"step": 600
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.42,
|
| 138 |
+
"learning_rate": 0.00028611023622047245,
|
| 139 |
+
"loss": 1.6291,
|
| 140 |
+
"step": 650
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.76,
|
| 144 |
+
"learning_rate": 0.0002813858267716535,
|
| 145 |
+
"loss": 1.2291,
|
| 146 |
+
"step": 700
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.76,
|
| 150 |
+
"eval_cer": 0.30572313712701776,
|
| 151 |
+
"eval_loss": 0.8816090226173401,
|
| 152 |
+
"eval_runtime": 24.4305,
|
| 153 |
+
"eval_samples_per_second": 24.068,
|
| 154 |
+
"eval_steps_per_second": 3.029,
|
| 155 |
+
"step": 700
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 5.1,
|
| 159 |
+
"learning_rate": 0.0002766614173228346,
|
| 160 |
+
"loss": 1.0153,
|
| 161 |
+
"step": 750
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.44,
|
| 165 |
+
"learning_rate": 0.0002719370078740157,
|
| 166 |
+
"loss": 0.8879,
|
| 167 |
+
"step": 800
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 5.44,
|
| 171 |
+
"eval_cer": 0.23668677645524214,
|
| 172 |
+
"eval_loss": 0.6693652868270874,
|
| 173 |
+
"eval_runtime": 24.5154,
|
| 174 |
+
"eval_samples_per_second": 23.985,
|
| 175 |
+
"eval_steps_per_second": 3.019,
|
| 176 |
+
"step": 800
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 5.78,
|
| 180 |
+
"learning_rate": 0.00026721259842519684,
|
| 181 |
+
"loss": 0.8337,
|
| 182 |
+
"step": 850
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 6.12,
|
| 186 |
+
"learning_rate": 0.00026248818897637796,
|
| 187 |
+
"loss": 0.7717,
|
| 188 |
+
"step": 900
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 6.12,
|
| 192 |
+
"eval_cer": 0.20955486711234306,
|
| 193 |
+
"eval_loss": 0.5637524127960205,
|
| 194 |
+
"eval_runtime": 24.5794,
|
| 195 |
+
"eval_samples_per_second": 23.922,
|
| 196 |
+
"eval_steps_per_second": 3.011,
|
| 197 |
+
"step": 900
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 6.46,
|
| 201 |
+
"learning_rate": 0.00025776377952755903,
|
| 202 |
+
"loss": 0.6711,
|
| 203 |
+
"step": 950
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 6.8,
|
| 207 |
+
"learning_rate": 0.00025303937007874016,
|
| 208 |
+
"loss": 0.7003,
|
| 209 |
+
"step": 1000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 6.8,
|
| 213 |
+
"eval_cer": 0.19279308658079244,
|
| 214 |
+
"eval_loss": 0.5100580453872681,
|
| 215 |
+
"eval_runtime": 24.6049,
|
| 216 |
+
"eval_samples_per_second": 23.898,
|
| 217 |
+
"eval_steps_per_second": 3.008,
|
| 218 |
+
"step": 1000
|
| 219 |
+
}
|
| 220 |
+
],
|
| 221 |
+
"max_steps": 3675,
|
| 222 |
+
"num_train_epochs": 25,
|
| 223 |
+
"total_flos": 3.8998743326073446e+18,
|
| 224 |
+
"trial_name": null,
|
| 225 |
+
"trial_params": null
|
| 226 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6818a2e9b105d4d459b9ef327417424b7dc79e7c93157b85684e997060ce05b5
|
| 3 |
+
size 3899
|
checkpoint-1100/config.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
| 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 |
+
"Wav2Vec2ForCTC"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.1,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 768,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": true,
|
| 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": "mean",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": true,
|
| 48 |
+
"eos_token_id": 2,
|
| 49 |
+
"feat_extract_activation": "gelu",
|
| 50 |
+
"feat_extract_dropout": 0.0,
|
| 51 |
+
"feat_extract_norm": "layer",
|
| 52 |
+
"feat_proj_dropout": 0.0,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"hidden_act": "gelu",
|
| 56 |
+
"hidden_dropout": 0.1,
|
| 57 |
+
"hidden_size": 1024,
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 4096,
|
| 60 |
+
"layer_norm_eps": 1e-05,
|
| 61 |
+
"layerdrop": 0.1,
|
| 62 |
+
"mask_channel_length": 10,
|
| 63 |
+
"mask_channel_min_space": 1,
|
| 64 |
+
"mask_channel_other": 0.0,
|
| 65 |
+
"mask_channel_prob": 0.0,
|
| 66 |
+
"mask_channel_selection": "static",
|
| 67 |
+
"mask_feature_length": 10,
|
| 68 |
+
"mask_feature_min_masks": 0,
|
| 69 |
+
"mask_feature_prob": 0.0,
|
| 70 |
+
"mask_time_length": 10,
|
| 71 |
+
"mask_time_min_masks": 2,
|
| 72 |
+
"mask_time_min_space": 1,
|
| 73 |
+
"mask_time_other": 0.0,
|
| 74 |
+
"mask_time_prob": 0.05,
|
| 75 |
+
"mask_time_selection": "static",
|
| 76 |
+
"model_type": "wav2vec2",
|
| 77 |
+
"num_adapter_layers": 3,
|
| 78 |
+
"num_attention_heads": 16,
|
| 79 |
+
"num_codevector_groups": 2,
|
| 80 |
+
"num_codevectors_per_group": 320,
|
| 81 |
+
"num_conv_pos_embedding_groups": 16,
|
| 82 |
+
"num_conv_pos_embeddings": 128,
|
| 83 |
+
"num_feat_extract_layers": 7,
|
| 84 |
+
"num_hidden_layers": 24,
|
| 85 |
+
"num_negatives": 100,
|
| 86 |
+
"output_hidden_size": 1024,
|
| 87 |
+
"pad_token_id": 107,
|
| 88 |
+
"proj_codevector_dim": 768,
|
| 89 |
+
"tdnn_dilation": [
|
| 90 |
+
1,
|
| 91 |
+
2,
|
| 92 |
+
3,
|
| 93 |
+
1,
|
| 94 |
+
1
|
| 95 |
+
],
|
| 96 |
+
"tdnn_dim": [
|
| 97 |
+
512,
|
| 98 |
+
512,
|
| 99 |
+
512,
|
| 100 |
+
512,
|
| 101 |
+
1500
|
| 102 |
+
],
|
| 103 |
+
"tdnn_kernel": [
|
| 104 |
+
5,
|
| 105 |
+
3,
|
| 106 |
+
3,
|
| 107 |
+
1,
|
| 108 |
+
1
|
| 109 |
+
],
|
| 110 |
+
"torch_dtype": "float32",
|
| 111 |
+
"transformers_version": "4.29.2",
|
| 112 |
+
"use_weighted_layer_sum": false,
|
| 113 |
+
"vocab_size": 108,
|
| 114 |
+
"xvector_output_dim": 512
|
| 115 |
+
}
|
checkpoint-1100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d84baa683ae59251136ef1213c546834d2423e442bc33b4caaff7eb445c3b093
|
| 3 |
+
size 2490946501
|
checkpoint-1100/preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
checkpoint-1100/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af184981e8ebee592f6c98b0af779168b14638479433458e7cf2a4106c245b93
|
| 3 |
+
size 1262344621
|
checkpoint-1100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56070c3210ed2169fdd0a61946fcfae018aacbed2f7fe3a075289958e78f6dae
|
| 3 |
+
size 14639
|
checkpoint-1100/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d098e7e4684807ea12185fa4d9f1ac316f808ba5578f67d7703063c52ee64348
|
| 3 |
+
size 557
|
checkpoint-1100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4b41b33b0360e96f29e54c993bc6c3f6a7fa15994da61400c12094f94bb4a86
|
| 3 |
+
size 627
|
checkpoint-1100/trainer_state.json
ADDED
|
@@ -0,0 +1,247 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.482993197278912,
|
| 5 |
+
"global_step": 1100,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.34,
|
| 12 |
+
"learning_rate": 2.8199999999999998e-05,
|
| 13 |
+
"loss": 14.6495,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.68,
|
| 18 |
+
"learning_rate": 5.82e-05,
|
| 19 |
+
"loss": 8.9314,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.68,
|
| 24 |
+
"eval_cer": 0.9940322843632806,
|
| 25 |
+
"eval_loss": 4.78579044342041,
|
| 26 |
+
"eval_runtime": 24.1442,
|
| 27 |
+
"eval_samples_per_second": 24.354,
|
| 28 |
+
"eval_steps_per_second": 3.065,
|
| 29 |
+
"step": 100
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.02,
|
| 33 |
+
"learning_rate": 8.819999999999999e-05,
|
| 34 |
+
"loss": 4.2225,
|
| 35 |
+
"step": 150
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.36,
|
| 39 |
+
"learning_rate": 0.0001182,
|
| 40 |
+
"loss": 3.2937,
|
| 41 |
+
"step": 200
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.36,
|
| 45 |
+
"eval_cer": 0.9940322843632806,
|
| 46 |
+
"eval_loss": 3.2489850521087646,
|
| 47 |
+
"eval_runtime": 24.3318,
|
| 48 |
+
"eval_samples_per_second": 24.166,
|
| 49 |
+
"eval_steps_per_second": 3.041,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.7,
|
| 54 |
+
"learning_rate": 0.0001482,
|
| 55 |
+
"loss": 3.2508,
|
| 56 |
+
"step": 250
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.04,
|
| 60 |
+
"learning_rate": 0.00017819999999999997,
|
| 61 |
+
"loss": 3.2412,
|
| 62 |
+
"step": 300
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.04,
|
| 66 |
+
"eval_cer": 0.9940322843632806,
|
| 67 |
+
"eval_loss": 3.222844123840332,
|
| 68 |
+
"eval_runtime": 24.3579,
|
| 69 |
+
"eval_samples_per_second": 24.14,
|
| 70 |
+
"eval_steps_per_second": 3.038,
|
| 71 |
+
"step": 300
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.38,
|
| 75 |
+
"learning_rate": 0.00020819999999999996,
|
| 76 |
+
"loss": 3.1855,
|
| 77 |
+
"step": 350
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 2.72,
|
| 81 |
+
"learning_rate": 0.0002382,
|
| 82 |
+
"loss": 3.0985,
|
| 83 |
+
"step": 400
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.72,
|
| 87 |
+
"eval_cer": 0.9940322843632806,
|
| 88 |
+
"eval_loss": 3.1458029747009277,
|
| 89 |
+
"eval_runtime": 24.7673,
|
| 90 |
+
"eval_samples_per_second": 23.741,
|
| 91 |
+
"eval_steps_per_second": 2.988,
|
| 92 |
+
"step": 400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.06,
|
| 96 |
+
"learning_rate": 0.00026819999999999996,
|
| 97 |
+
"loss": 3.0739,
|
| 98 |
+
"step": 450
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.4,
|
| 102 |
+
"learning_rate": 0.0002982,
|
| 103 |
+
"loss": 3.0209,
|
| 104 |
+
"step": 500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.4,
|
| 108 |
+
"eval_cer": 0.9938692320234795,
|
| 109 |
+
"eval_loss": 3.004169225692749,
|
| 110 |
+
"eval_runtime": 24.3542,
|
| 111 |
+
"eval_samples_per_second": 24.144,
|
| 112 |
+
"eval_steps_per_second": 3.038,
|
| 113 |
+
"step": 500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.74,
|
| 117 |
+
"learning_rate": 0.0002955590551181102,
|
| 118 |
+
"loss": 2.9536,
|
| 119 |
+
"step": 550
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.08,
|
| 123 |
+
"learning_rate": 0.0002908346456692913,
|
| 124 |
+
"loss": 2.518,
|
| 125 |
+
"step": 600
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.08,
|
| 129 |
+
"eval_cer": 0.5400945703570846,
|
| 130 |
+
"eval_loss": 1.770609736442566,
|
| 131 |
+
"eval_runtime": 24.8378,
|
| 132 |
+
"eval_samples_per_second": 23.674,
|
| 133 |
+
"eval_steps_per_second": 2.979,
|
| 134 |
+
"step": 600
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.42,
|
| 138 |
+
"learning_rate": 0.00028611023622047245,
|
| 139 |
+
"loss": 1.6291,
|
| 140 |
+
"step": 650
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.76,
|
| 144 |
+
"learning_rate": 0.0002813858267716535,
|
| 145 |
+
"loss": 1.2291,
|
| 146 |
+
"step": 700
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.76,
|
| 150 |
+
"eval_cer": 0.30572313712701776,
|
| 151 |
+
"eval_loss": 0.8816090226173401,
|
| 152 |
+
"eval_runtime": 24.4305,
|
| 153 |
+
"eval_samples_per_second": 24.068,
|
| 154 |
+
"eval_steps_per_second": 3.029,
|
| 155 |
+
"step": 700
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 5.1,
|
| 159 |
+
"learning_rate": 0.0002766614173228346,
|
| 160 |
+
"loss": 1.0153,
|
| 161 |
+
"step": 750
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.44,
|
| 165 |
+
"learning_rate": 0.0002719370078740157,
|
| 166 |
+
"loss": 0.8879,
|
| 167 |
+
"step": 800
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 5.44,
|
| 171 |
+
"eval_cer": 0.23668677645524214,
|
| 172 |
+
"eval_loss": 0.6693652868270874,
|
| 173 |
+
"eval_runtime": 24.5154,
|
| 174 |
+
"eval_samples_per_second": 23.985,
|
| 175 |
+
"eval_steps_per_second": 3.019,
|
| 176 |
+
"step": 800
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 5.78,
|
| 180 |
+
"learning_rate": 0.00026721259842519684,
|
| 181 |
+
"loss": 0.8337,
|
| 182 |
+
"step": 850
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 6.12,
|
| 186 |
+
"learning_rate": 0.00026248818897637796,
|
| 187 |
+
"loss": 0.7717,
|
| 188 |
+
"step": 900
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 6.12,
|
| 192 |
+
"eval_cer": 0.20955486711234306,
|
| 193 |
+
"eval_loss": 0.5637524127960205,
|
| 194 |
+
"eval_runtime": 24.5794,
|
| 195 |
+
"eval_samples_per_second": 23.922,
|
| 196 |
+
"eval_steps_per_second": 3.011,
|
| 197 |
+
"step": 900
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 6.46,
|
| 201 |
+
"learning_rate": 0.00025776377952755903,
|
| 202 |
+
"loss": 0.6711,
|
| 203 |
+
"step": 950
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 6.8,
|
| 207 |
+
"learning_rate": 0.00025303937007874016,
|
| 208 |
+
"loss": 0.7003,
|
| 209 |
+
"step": 1000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 6.8,
|
| 213 |
+
"eval_cer": 0.19279308658079244,
|
| 214 |
+
"eval_loss": 0.5100580453872681,
|
| 215 |
+
"eval_runtime": 24.6049,
|
| 216 |
+
"eval_samples_per_second": 23.898,
|
| 217 |
+
"eval_steps_per_second": 3.008,
|
| 218 |
+
"step": 1000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 7.14,
|
| 222 |
+
"learning_rate": 0.0002483149606299212,
|
| 223 |
+
"loss": 0.6349,
|
| 224 |
+
"step": 1050
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 7.48,
|
| 228 |
+
"learning_rate": 0.00024359055118110235,
|
| 229 |
+
"loss": 0.5935,
|
| 230 |
+
"step": 1100
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 7.48,
|
| 234 |
+
"eval_cer": 0.17746616663949127,
|
| 235 |
+
"eval_loss": 0.46862325072288513,
|
| 236 |
+
"eval_runtime": 24.2024,
|
| 237 |
+
"eval_samples_per_second": 24.295,
|
| 238 |
+
"eval_steps_per_second": 3.058,
|
| 239 |
+
"step": 1100
|
| 240 |
+
}
|
| 241 |
+
],
|
| 242 |
+
"max_steps": 3675,
|
| 243 |
+
"num_train_epochs": 25,
|
| 244 |
+
"total_flos": 4.2702477228389837e+18,
|
| 245 |
+
"trial_name": null,
|
| 246 |
+
"trial_params": null
|
| 247 |
+
}
|
checkpoint-1100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6818a2e9b105d4d459b9ef327417424b7dc79e7c93157b85684e997060ce05b5
|
| 3 |
+
size 3899
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262344621
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af184981e8ebee592f6c98b0af779168b14638479433458e7cf2a4106c245b93
|
| 3 |
size 1262344621
|