Training in progress, epoch 7, checkpoint
Browse files- checkpoint-5103/config.json +108 -0
- checkpoint-5103/optimizer.pt +3 -0
- checkpoint-5103/preprocessor_config.json +9 -0
- checkpoint-5103/pytorch_model.bin +3 -0
- checkpoint-5103/rng_state.pth +3 -0
- checkpoint-5103/scheduler.pt +3 -0
- checkpoint-5103/trainer_state.json +415 -0
- checkpoint-5103/training_args.bin +3 -0
checkpoint-5103/config.json
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/mms-1b-all",
|
| 3 |
+
"activation_dropout": 0.05,
|
| 4 |
+
"adapter_attn_dim": 16,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForCTC"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 1024,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": true,
|
| 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": "mean",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": true,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "layer",
|
| 53 |
+
"feat_proj_dropout": 0.0,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.05,
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.0,
|
| 58 |
+
"hidden_size": 1280,
|
| 59 |
+
"initializer_range": 0.02,
|
| 60 |
+
"intermediate_size": 5120,
|
| 61 |
+
"layer_norm_eps": 1e-05,
|
| 62 |
+
"layerdrop": 0.0,
|
| 63 |
+
"mask_feature_length": 10,
|
| 64 |
+
"mask_feature_min_masks": 0,
|
| 65 |
+
"mask_feature_prob": 0.0,
|
| 66 |
+
"mask_time_length": 10,
|
| 67 |
+
"mask_time_min_masks": 2,
|
| 68 |
+
"mask_time_prob": 0.05,
|
| 69 |
+
"model_type": "wav2vec2",
|
| 70 |
+
"num_adapter_layers": 3,
|
| 71 |
+
"num_attention_heads": 16,
|
| 72 |
+
"num_codevector_groups": 2,
|
| 73 |
+
"num_codevectors_per_group": 320,
|
| 74 |
+
"num_conv_pos_embedding_groups": 16,
|
| 75 |
+
"num_conv_pos_embeddings": 128,
|
| 76 |
+
"num_feat_extract_layers": 7,
|
| 77 |
+
"num_hidden_layers": 48,
|
| 78 |
+
"num_negatives": 100,
|
| 79 |
+
"output_hidden_size": 1280,
|
| 80 |
+
"pad_token_id": 92,
|
| 81 |
+
"proj_codevector_dim": 1024,
|
| 82 |
+
"tdnn_dilation": [
|
| 83 |
+
1,
|
| 84 |
+
2,
|
| 85 |
+
3,
|
| 86 |
+
1,
|
| 87 |
+
1
|
| 88 |
+
],
|
| 89 |
+
"tdnn_dim": [
|
| 90 |
+
512,
|
| 91 |
+
512,
|
| 92 |
+
512,
|
| 93 |
+
512,
|
| 94 |
+
1500
|
| 95 |
+
],
|
| 96 |
+
"tdnn_kernel": [
|
| 97 |
+
5,
|
| 98 |
+
3,
|
| 99 |
+
3,
|
| 100 |
+
1,
|
| 101 |
+
1
|
| 102 |
+
],
|
| 103 |
+
"torch_dtype": "float32",
|
| 104 |
+
"transformers_version": "4.34.1",
|
| 105 |
+
"use_weighted_layer_sum": false,
|
| 106 |
+
"vocab_size": 95,
|
| 107 |
+
"xvector_output_dim": 512
|
| 108 |
+
}
|
checkpoint-5103/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41358eacddc741ba8faf78fcf607af6e9c16395b78bac0cbe4a2043bd16be27c
|
| 3 |
+
size 18424186
|
checkpoint-5103/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": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
checkpoint-5103/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:518f9f3198d5a6b84daa9490dff7d865a9349d8a884c1fd6922834162450b7b0
|
| 3 |
+
size 3859463050
|
checkpoint-5103/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbc876e06ead5628f8960e773c168eacff67fe91f826aa649d5aad804289794b
|
| 3 |
+
size 14308
|
checkpoint-5103/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9b6864031891c1a12f9cf8e6e913a6142a9ad35e17347779c04c4dac0c7d9cd
|
| 3 |
+
size 1064
|
checkpoint-5103/trainer_state.json
ADDED
|
@@ -0,0 +1,415 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5103,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14,
|
| 13 |
+
"learning_rate": 0.00048,
|
| 14 |
+
"loss": 7.0366,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.27,
|
| 19 |
+
"learning_rate": 0.0004933240611961058,
|
| 20 |
+
"loss": 0.4467,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.41,
|
| 25 |
+
"learning_rate": 0.00048643949930458967,
|
| 26 |
+
"loss": 0.3946,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.55,
|
| 31 |
+
"learning_rate": 0.0004794853963838665,
|
| 32 |
+
"loss": 0.399,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.69,
|
| 37 |
+
"learning_rate": 0.0004726008344923505,
|
| 38 |
+
"loss": 0.3696,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.69,
|
| 43 |
+
"eval_loss": 0.3043254017829895,
|
| 44 |
+
"eval_runtime": 65.1553,
|
| 45 |
+
"eval_samples_per_second": 11.664,
|
| 46 |
+
"eval_steps_per_second": 1.458,
|
| 47 |
+
"eval_wer": 0.265993265993266,
|
| 48 |
+
"step": 500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.82,
|
| 52 |
+
"learning_rate": 0.0004656467315716273,
|
| 53 |
+
"loss": 0.3677,
|
| 54 |
+
"step": 600
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.96,
|
| 58 |
+
"learning_rate": 0.00045869262865090403,
|
| 59 |
+
"loss": 0.3534,
|
| 60 |
+
"step": 700
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.1,
|
| 64 |
+
"learning_rate": 0.00045173852573018083,
|
| 65 |
+
"loss": 0.34,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.23,
|
| 70 |
+
"learning_rate": 0.0004447844228094576,
|
| 71 |
+
"loss": 0.3428,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.37,
|
| 76 |
+
"learning_rate": 0.0004378998609179416,
|
| 77 |
+
"loss": 0.3533,
|
| 78 |
+
"step": 1000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.37,
|
| 82 |
+
"eval_loss": 0.27337372303009033,
|
| 83 |
+
"eval_runtime": 65.7997,
|
| 84 |
+
"eval_samples_per_second": 11.55,
|
| 85 |
+
"eval_steps_per_second": 1.444,
|
| 86 |
+
"eval_wer": 0.23931623931623933,
|
| 87 |
+
"step": 1000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.51,
|
| 91 |
+
"learning_rate": 0.00043094575799721834,
|
| 92 |
+
"loss": 0.336,
|
| 93 |
+
"step": 1100
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.65,
|
| 97 |
+
"learning_rate": 0.00042399165507649514,
|
| 98 |
+
"loss": 0.3453,
|
| 99 |
+
"step": 1200
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.78,
|
| 103 |
+
"learning_rate": 0.00041703755215577194,
|
| 104 |
+
"loss": 0.342,
|
| 105 |
+
"step": 1300
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.92,
|
| 109 |
+
"learning_rate": 0.0004100834492350487,
|
| 110 |
+
"loss": 0.3232,
|
| 111 |
+
"step": 1400
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.06,
|
| 115 |
+
"learning_rate": 0.0004031293463143255,
|
| 116 |
+
"loss": 0.3419,
|
| 117 |
+
"step": 1500
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.06,
|
| 121 |
+
"eval_loss": 0.2687598764896393,
|
| 122 |
+
"eval_runtime": 66.7716,
|
| 123 |
+
"eval_samples_per_second": 11.382,
|
| 124 |
+
"eval_steps_per_second": 1.423,
|
| 125 |
+
"eval_wer": 0.23776223776223776,
|
| 126 |
+
"step": 1500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.19,
|
| 130 |
+
"learning_rate": 0.0003961752433936022,
|
| 131 |
+
"loss": 0.3045,
|
| 132 |
+
"step": 1600
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.33,
|
| 136 |
+
"learning_rate": 0.00038922114047287897,
|
| 137 |
+
"loss": 0.327,
|
| 138 |
+
"step": 1700
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.47,
|
| 142 |
+
"learning_rate": 0.0003822670375521558,
|
| 143 |
+
"loss": 0.3162,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.61,
|
| 148 |
+
"learning_rate": 0.00037531293463143256,
|
| 149 |
+
"loss": 0.3111,
|
| 150 |
+
"step": 1900
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.74,
|
| 154 |
+
"learning_rate": 0.0003684283727399166,
|
| 155 |
+
"loss": 0.3399,
|
| 156 |
+
"step": 2000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.74,
|
| 160 |
+
"eval_loss": 0.2612040042877197,
|
| 161 |
+
"eval_runtime": 66.305,
|
| 162 |
+
"eval_samples_per_second": 11.462,
|
| 163 |
+
"eval_steps_per_second": 1.433,
|
| 164 |
+
"eval_wer": 0.22895622895622897,
|
| 165 |
+
"step": 2000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.88,
|
| 169 |
+
"learning_rate": 0.00036147426981919333,
|
| 170 |
+
"loss": 0.3113,
|
| 171 |
+
"step": 2100
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 3.02,
|
| 175 |
+
"learning_rate": 0.00035452016689847013,
|
| 176 |
+
"loss": 0.307,
|
| 177 |
+
"step": 2200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.16,
|
| 181 |
+
"learning_rate": 0.0003475660639777469,
|
| 182 |
+
"loss": 0.3061,
|
| 183 |
+
"step": 2300
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.29,
|
| 187 |
+
"learning_rate": 0.0003406119610570236,
|
| 188 |
+
"loss": 0.2974,
|
| 189 |
+
"step": 2400
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.43,
|
| 193 |
+
"learning_rate": 0.00033365785813630047,
|
| 194 |
+
"loss": 0.3087,
|
| 195 |
+
"step": 2500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.43,
|
| 199 |
+
"eval_loss": 0.26245519518852234,
|
| 200 |
+
"eval_runtime": 66.092,
|
| 201 |
+
"eval_samples_per_second": 11.499,
|
| 202 |
+
"eval_steps_per_second": 1.437,
|
| 203 |
+
"eval_wer": 0.22986272986272988,
|
| 204 |
+
"step": 2500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.57,
|
| 208 |
+
"learning_rate": 0.0003267037552155772,
|
| 209 |
+
"loss": 0.3007,
|
| 210 |
+
"step": 2600
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.7,
|
| 214 |
+
"learning_rate": 0.00031974965229485396,
|
| 215 |
+
"loss": 0.3073,
|
| 216 |
+
"step": 2700
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 3.84,
|
| 220 |
+
"learning_rate": 0.00031279554937413076,
|
| 221 |
+
"loss": 0.314,
|
| 222 |
+
"step": 2800
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 3.98,
|
| 226 |
+
"learning_rate": 0.0003059109874826148,
|
| 227 |
+
"loss": 0.2944,
|
| 228 |
+
"step": 2900
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 4.12,
|
| 232 |
+
"learning_rate": 0.00029902642559109875,
|
| 233 |
+
"loss": 0.2908,
|
| 234 |
+
"step": 3000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.12,
|
| 238 |
+
"eval_loss": 0.254683256149292,
|
| 239 |
+
"eval_runtime": 65.5917,
|
| 240 |
+
"eval_samples_per_second": 11.587,
|
| 241 |
+
"eval_steps_per_second": 1.448,
|
| 242 |
+
"eval_wer": 0.2220927220927221,
|
| 243 |
+
"step": 3000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 4.25,
|
| 247 |
+
"learning_rate": 0.00029207232267037554,
|
| 248 |
+
"loss": 0.2906,
|
| 249 |
+
"step": 3100
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 4.39,
|
| 253 |
+
"learning_rate": 0.0002851182197496523,
|
| 254 |
+
"loss": 0.296,
|
| 255 |
+
"step": 3200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.53,
|
| 259 |
+
"learning_rate": 0.00027816411682892903,
|
| 260 |
+
"loss": 0.2826,
|
| 261 |
+
"step": 3300
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 4.66,
|
| 265 |
+
"learning_rate": 0.00027121001390820583,
|
| 266 |
+
"loss": 0.2866,
|
| 267 |
+
"step": 3400
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 4.8,
|
| 271 |
+
"learning_rate": 0.00026425591098748263,
|
| 272 |
+
"loss": 0.2938,
|
| 273 |
+
"step": 3500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 4.8,
|
| 277 |
+
"eval_loss": 0.24941803514957428,
|
| 278 |
+
"eval_runtime": 65.3746,
|
| 279 |
+
"eval_samples_per_second": 11.625,
|
| 280 |
+
"eval_steps_per_second": 1.453,
|
| 281 |
+
"eval_wer": 0.21561771561771562,
|
| 282 |
+
"step": 3500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 4.94,
|
| 286 |
+
"learning_rate": 0.0002573018080667594,
|
| 287 |
+
"loss": 0.2953,
|
| 288 |
+
"step": 3600
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 5.08,
|
| 292 |
+
"learning_rate": 0.0002503477051460362,
|
| 293 |
+
"loss": 0.2972,
|
| 294 |
+
"step": 3700
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.21,
|
| 298 |
+
"learning_rate": 0.00024339360222531292,
|
| 299 |
+
"loss": 0.2781,
|
| 300 |
+
"step": 3800
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 5.35,
|
| 304 |
+
"learning_rate": 0.00023643949930458972,
|
| 305 |
+
"loss": 0.2803,
|
| 306 |
+
"step": 3900
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 5.49,
|
| 310 |
+
"learning_rate": 0.0002294853963838665,
|
| 311 |
+
"loss": 0.275,
|
| 312 |
+
"step": 4000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 5.49,
|
| 316 |
+
"eval_loss": 0.2497035413980484,
|
| 317 |
+
"eval_runtime": 65.425,
|
| 318 |
+
"eval_samples_per_second": 11.616,
|
| 319 |
+
"eval_steps_per_second": 1.452,
|
| 320 |
+
"eval_wer": 0.21406371406371405,
|
| 321 |
+
"step": 4000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 5.62,
|
| 325 |
+
"learning_rate": 0.00022253129346314326,
|
| 326 |
+
"loss": 0.2751,
|
| 327 |
+
"step": 4100
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 5.76,
|
| 331 |
+
"learning_rate": 0.00021564673157162725,
|
| 332 |
+
"loss": 0.2915,
|
| 333 |
+
"step": 4200
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 5.9,
|
| 337 |
+
"learning_rate": 0.00020869262865090405,
|
| 338 |
+
"loss": 0.2848,
|
| 339 |
+
"step": 4300
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 6.04,
|
| 343 |
+
"learning_rate": 0.00020173852573018082,
|
| 344 |
+
"loss": 0.2846,
|
| 345 |
+
"step": 4400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 6.17,
|
| 349 |
+
"learning_rate": 0.00019485396383866482,
|
| 350 |
+
"loss": 0.2775,
|
| 351 |
+
"step": 4500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 6.17,
|
| 355 |
+
"eval_loss": 0.24489344656467438,
|
| 356 |
+
"eval_runtime": 65.0133,
|
| 357 |
+
"eval_samples_per_second": 11.69,
|
| 358 |
+
"eval_steps_per_second": 1.461,
|
| 359 |
+
"eval_wer": 0.21095571095571095,
|
| 360 |
+
"step": 4500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 6.31,
|
| 364 |
+
"learning_rate": 0.0001878998609179416,
|
| 365 |
+
"loss": 0.2845,
|
| 366 |
+
"step": 4600
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 6.45,
|
| 370 |
+
"learning_rate": 0.00018094575799721836,
|
| 371 |
+
"loss": 0.2754,
|
| 372 |
+
"step": 4700
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 6.58,
|
| 376 |
+
"learning_rate": 0.00017399165507649513,
|
| 377 |
+
"loss": 0.2625,
|
| 378 |
+
"step": 4800
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 6.72,
|
| 382 |
+
"learning_rate": 0.0001670375521557719,
|
| 383 |
+
"loss": 0.2822,
|
| 384 |
+
"step": 4900
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 6.86,
|
| 388 |
+
"learning_rate": 0.0001600834492350487,
|
| 389 |
+
"loss": 0.2639,
|
| 390 |
+
"step": 5000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 6.86,
|
| 394 |
+
"eval_loss": 0.24407874047756195,
|
| 395 |
+
"eval_runtime": 65.6065,
|
| 396 |
+
"eval_samples_per_second": 11.584,
|
| 397 |
+
"eval_steps_per_second": 1.448,
|
| 398 |
+
"eval_wer": 0.2106967106967107,
|
| 399 |
+
"step": 5000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 7.0,
|
| 403 |
+
"learning_rate": 0.00015312934631432545,
|
| 404 |
+
"loss": 0.2771,
|
| 405 |
+
"step": 5100
|
| 406 |
+
}
|
| 407 |
+
],
|
| 408 |
+
"logging_steps": 100,
|
| 409 |
+
"max_steps": 7290,
|
| 410 |
+
"num_train_epochs": 10,
|
| 411 |
+
"save_steps": 500,
|
| 412 |
+
"total_flos": 3.5356221446356038e+19,
|
| 413 |
+
"trial_name": null,
|
| 414 |
+
"trial_params": null
|
| 415 |
+
}
|
checkpoint-5103/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d3aa848da266dd9fcefac1319c4009241b1015d8306bc1c8253b19be17b56d9
|
| 3 |
+
size 4536
|