Training in progress, step 400, checkpoint
Browse files- .gitattributes +1 -0
- checkpoint-400/config.json +117 -0
- checkpoint-400/model.safetensors +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/preprocessor_config.json +9 -0
- checkpoint-400/rng_state.pth +0 -0
- checkpoint-400/scheduler.pt +0 -0
- checkpoint-400/trainer_state.json +295 -0
- checkpoint-400/training_args.bin +0 -0
.gitattributes
CHANGED
|
@@ -1,2 +1,3 @@
|
|
| 1 |
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 2 |
checkpoint-200/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 1 |
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 2 |
checkpoint-200/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
checkpoint-400/optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
checkpoint-400/config.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
| 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 |
+
"Wav2Vec2ForCTC"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 768,
|
| 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": 0.0,
|
| 56 |
+
"gradient_checkpointing": false,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.1,
|
| 59 |
+
"hidden_size": 1024,
|
| 60 |
+
"initializer_range": 0.02,
|
| 61 |
+
"intermediate_size": 4096,
|
| 62 |
+
"layer_norm_eps": 1e-05,
|
| 63 |
+
"layerdrop": 0.1,
|
| 64 |
+
"mask_channel_length": 10,
|
| 65 |
+
"mask_channel_min_space": 1,
|
| 66 |
+
"mask_channel_other": 0.0,
|
| 67 |
+
"mask_channel_prob": 0.0,
|
| 68 |
+
"mask_channel_selection": "static",
|
| 69 |
+
"mask_feature_length": 10,
|
| 70 |
+
"mask_feature_min_masks": 0,
|
| 71 |
+
"mask_feature_prob": 0.0,
|
| 72 |
+
"mask_time_length": 10,
|
| 73 |
+
"mask_time_min_masks": 2,
|
| 74 |
+
"mask_time_min_space": 1,
|
| 75 |
+
"mask_time_other": 0.0,
|
| 76 |
+
"mask_time_prob": 0.05,
|
| 77 |
+
"mask_time_selection": "static",
|
| 78 |
+
"model_type": "wav2vec2",
|
| 79 |
+
"num_adapter_layers": 3,
|
| 80 |
+
"num_attention_heads": 16,
|
| 81 |
+
"num_codevector_groups": 2,
|
| 82 |
+
"num_codevectors_per_group": 320,
|
| 83 |
+
"num_conv_pos_embedding_groups": 16,
|
| 84 |
+
"num_conv_pos_embeddings": 128,
|
| 85 |
+
"num_feat_extract_layers": 7,
|
| 86 |
+
"num_hidden_layers": 24,
|
| 87 |
+
"num_negatives": 100,
|
| 88 |
+
"output_hidden_size": 1024,
|
| 89 |
+
"pad_token_id": 38,
|
| 90 |
+
"proj_codevector_dim": 768,
|
| 91 |
+
"tdnn_dilation": [
|
| 92 |
+
1,
|
| 93 |
+
2,
|
| 94 |
+
3,
|
| 95 |
+
1,
|
| 96 |
+
1
|
| 97 |
+
],
|
| 98 |
+
"tdnn_dim": [
|
| 99 |
+
512,
|
| 100 |
+
512,
|
| 101 |
+
512,
|
| 102 |
+
512,
|
| 103 |
+
1500
|
| 104 |
+
],
|
| 105 |
+
"tdnn_kernel": [
|
| 106 |
+
5,
|
| 107 |
+
3,
|
| 108 |
+
3,
|
| 109 |
+
1,
|
| 110 |
+
1
|
| 111 |
+
],
|
| 112 |
+
"torch_dtype": "float32",
|
| 113 |
+
"transformers_version": "4.35.2",
|
| 114 |
+
"use_weighted_layer_sum": false,
|
| 115 |
+
"vocab_size": 41,
|
| 116 |
+
"xvector_output_dim": 512
|
| 117 |
+
}
|
checkpoint-400/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20c99c4c03ab837c28822370865d69027e6545cfac6d8bd17be4fce043a18cb8
|
| 3 |
+
size 1261975580
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92838f71270aa5414c9307e05e1ad49b23ac9a0cd6457ab82b32d17b397de4d6
|
| 3 |
+
size 2490495926
|
checkpoint-400/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-400/rng_state.pth
ADDED
|
Binary file (14.2 kB). View file
|
|
|
checkpoint-400/scheduler.pt
ADDED
|
Binary file (1.06 kB). View file
|
|
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,295 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.6509357200976403,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 1.4999999999999999e-05,
|
| 14 |
+
"loss": 11.8163,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 20 |
+
"loss": 11.8929,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.05,
|
| 25 |
+
"learning_rate": 4.3499999999999993e-05,
|
| 26 |
+
"loss": 12.0064,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.07,
|
| 31 |
+
"learning_rate": 5.6999999999999996e-05,
|
| 32 |
+
"loss": 10.5132,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.08,
|
| 37 |
+
"learning_rate": 7.199999999999999e-05,
|
| 38 |
+
"loss": 7.9699,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.1,
|
| 43 |
+
"learning_rate": 8.699999999999999e-05,
|
| 44 |
+
"loss": 4.7703,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11,
|
| 49 |
+
"learning_rate": 0.000102,
|
| 50 |
+
"loss": 3.7982,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.13,
|
| 55 |
+
"learning_rate": 0.000117,
|
| 56 |
+
"loss": 3.436,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.15,
|
| 61 |
+
"learning_rate": 0.00013199999999999998,
|
| 62 |
+
"loss": 3.2573,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.16,
|
| 67 |
+
"learning_rate": 0.000147,
|
| 68 |
+
"loss": 3.1412,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.16,
|
| 73 |
+
"eval_loss": 3.0855324268341064,
|
| 74 |
+
"eval_runtime": 1038.5545,
|
| 75 |
+
"eval_samples_per_second": 11.178,
|
| 76 |
+
"eval_steps_per_second": 0.699,
|
| 77 |
+
"eval_wer": 1.0,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.18,
|
| 82 |
+
"learning_rate": 0.000162,
|
| 83 |
+
"loss": 3.0577,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.2,
|
| 88 |
+
"learning_rate": 0.00017699999999999997,
|
| 89 |
+
"loss": 3.0443,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.21,
|
| 94 |
+
"learning_rate": 0.00019199999999999998,
|
| 95 |
+
"loss": 3.0597,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.23,
|
| 100 |
+
"learning_rate": 0.00020699999999999996,
|
| 101 |
+
"loss": 3.061,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.24,
|
| 106 |
+
"learning_rate": 0.00022199999999999998,
|
| 107 |
+
"loss": 3.0717,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.26,
|
| 112 |
+
"learning_rate": 0.000237,
|
| 113 |
+
"loss": 3.0299,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.28,
|
| 118 |
+
"learning_rate": 0.00025199999999999995,
|
| 119 |
+
"loss": 3.0295,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.29,
|
| 124 |
+
"learning_rate": 0.000267,
|
| 125 |
+
"loss": 3.0423,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.31,
|
| 130 |
+
"learning_rate": 0.00028199999999999997,
|
| 131 |
+
"loss": 3.0437,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.33,
|
| 136 |
+
"learning_rate": 0.00029699999999999996,
|
| 137 |
+
"loss": 3.0569,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.33,
|
| 142 |
+
"eval_loss": 3.036912679672241,
|
| 143 |
+
"eval_runtime": 1030.0275,
|
| 144 |
+
"eval_samples_per_second": 11.271,
|
| 145 |
+
"eval_steps_per_second": 0.705,
|
| 146 |
+
"eval_wer": 1.0,
|
| 147 |
+
"step": 200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.34,
|
| 151 |
+
"learning_rate": 0.00029973362930077685,
|
| 152 |
+
"loss": 3.0243,
|
| 153 |
+
"step": 210
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.36,
|
| 157 |
+
"learning_rate": 0.000299400665926748,
|
| 158 |
+
"loss": 3.0236,
|
| 159 |
+
"step": 220
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.37,
|
| 163 |
+
"learning_rate": 0.0002990677025527192,
|
| 164 |
+
"loss": 3.0316,
|
| 165 |
+
"step": 230
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.39,
|
| 169 |
+
"learning_rate": 0.0002987347391786903,
|
| 170 |
+
"loss": 3.0363,
|
| 171 |
+
"step": 240
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.41,
|
| 175 |
+
"learning_rate": 0.00029840177580466146,
|
| 176 |
+
"loss": 3.0582,
|
| 177 |
+
"step": 250
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.42,
|
| 181 |
+
"learning_rate": 0.0002980688124306326,
|
| 182 |
+
"loss": 3.0144,
|
| 183 |
+
"step": 260
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.44,
|
| 187 |
+
"learning_rate": 0.00029773584905660376,
|
| 188 |
+
"loss": 3.0126,
|
| 189 |
+
"step": 270
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.46,
|
| 193 |
+
"learning_rate": 0.0002974028856825749,
|
| 194 |
+
"loss": 3.0035,
|
| 195 |
+
"step": 280
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.47,
|
| 199 |
+
"learning_rate": 0.000297069922308546,
|
| 200 |
+
"loss": 2.9913,
|
| 201 |
+
"step": 290
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.49,
|
| 205 |
+
"learning_rate": 0.00029673695893451716,
|
| 206 |
+
"loss": 2.9625,
|
| 207 |
+
"step": 300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.49,
|
| 211 |
+
"eval_loss": 2.977771520614624,
|
| 212 |
+
"eval_runtime": 1042.3792,
|
| 213 |
+
"eval_samples_per_second": 11.137,
|
| 214 |
+
"eval_steps_per_second": 0.696,
|
| 215 |
+
"eval_wer": 1.0,
|
| 216 |
+
"step": 300
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.5,
|
| 220 |
+
"learning_rate": 0.0002964039955604883,
|
| 221 |
+
"loss": 2.9686,
|
| 222 |
+
"step": 310
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.52,
|
| 226 |
+
"learning_rate": 0.00029607103218645946,
|
| 227 |
+
"loss": 2.8773,
|
| 228 |
+
"step": 320
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.54,
|
| 232 |
+
"learning_rate": 0.0002957380688124306,
|
| 233 |
+
"loss": 2.726,
|
| 234 |
+
"step": 330
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.55,
|
| 238 |
+
"learning_rate": 0.00029540510543840177,
|
| 239 |
+
"loss": 2.3671,
|
| 240 |
+
"step": 340
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.57,
|
| 244 |
+
"learning_rate": 0.0002950721420643729,
|
| 245 |
+
"loss": 1.9479,
|
| 246 |
+
"step": 350
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.59,
|
| 250 |
+
"learning_rate": 0.000294739178690344,
|
| 251 |
+
"loss": 1.5549,
|
| 252 |
+
"step": 360
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.6,
|
| 256 |
+
"learning_rate": 0.00029440621531631517,
|
| 257 |
+
"loss": 1.1765,
|
| 258 |
+
"step": 370
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.62,
|
| 262 |
+
"learning_rate": 0.0002940732519422863,
|
| 263 |
+
"loss": 0.9155,
|
| 264 |
+
"step": 380
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.63,
|
| 268 |
+
"learning_rate": 0.00029374028856825747,
|
| 269 |
+
"loss": 0.7823,
|
| 270 |
+
"step": 390
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.65,
|
| 274 |
+
"learning_rate": 0.0002934073251942286,
|
| 275 |
+
"loss": 0.7715,
|
| 276 |
+
"step": 400
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.65,
|
| 280 |
+
"eval_loss": 0.5112669467926025,
|
| 281 |
+
"eval_runtime": 1048.8544,
|
| 282 |
+
"eval_samples_per_second": 11.068,
|
| 283 |
+
"eval_steps_per_second": 0.692,
|
| 284 |
+
"eval_wer": 0.718480591159969,
|
| 285 |
+
"step": 400
|
| 286 |
+
}
|
| 287 |
+
],
|
| 288 |
+
"logging_steps": 10,
|
| 289 |
+
"max_steps": 9210,
|
| 290 |
+
"num_train_epochs": 15,
|
| 291 |
+
"save_steps": 200,
|
| 292 |
+
"total_flos": 4.1937122556706406e+18,
|
| 293 |
+
"trial_name": null,
|
| 294 |
+
"trial_params": null
|
| 295 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
Binary file (4.6 kB). View file
|
|
|