Training in progress, step 3500, checkpoint
Browse files- checkpoint-3500/config.json +107 -0
- checkpoint-3500/model.safetensors +3 -0
- checkpoint-3500/optimizer.pt +3 -0
- checkpoint-3500/preprocessor_config.json +9 -0
- checkpoint-3500/rng_state.pth +3 -0
- checkpoint-3500/scaler.pt +3 -0
- checkpoint-3500/scheduler.pt +3 -0
- checkpoint-3500/trainer_state.json +594 -0
- checkpoint-3500/training_args.bin +3 -0
checkpoint-3500/config.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.05,
|
| 3 |
+
"adapter_attn_dim": 16,
|
| 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": 0.0,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 1024,
|
| 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": 0.05,
|
| 55 |
+
"hidden_act": "gelu",
|
| 56 |
+
"hidden_dropout": 0.0,
|
| 57 |
+
"hidden_size": 1280,
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 5120,
|
| 60 |
+
"layer_norm_eps": 1e-05,
|
| 61 |
+
"layerdrop": 0.0,
|
| 62 |
+
"mask_feature_length": 10,
|
| 63 |
+
"mask_feature_min_masks": 0,
|
| 64 |
+
"mask_feature_prob": 0.0,
|
| 65 |
+
"mask_time_length": 10,
|
| 66 |
+
"mask_time_min_masks": 2,
|
| 67 |
+
"mask_time_prob": 0.05,
|
| 68 |
+
"model_type": "wav2vec2",
|
| 69 |
+
"num_adapter_layers": 3,
|
| 70 |
+
"num_attention_heads": 16,
|
| 71 |
+
"num_codevector_groups": 2,
|
| 72 |
+
"num_codevectors_per_group": 320,
|
| 73 |
+
"num_conv_pos_embedding_groups": 16,
|
| 74 |
+
"num_conv_pos_embeddings": 128,
|
| 75 |
+
"num_feat_extract_layers": 7,
|
| 76 |
+
"num_hidden_layers": 48,
|
| 77 |
+
"num_negatives": 100,
|
| 78 |
+
"output_hidden_size": 1280,
|
| 79 |
+
"pad_token_id": 65,
|
| 80 |
+
"proj_codevector_dim": 1024,
|
| 81 |
+
"tdnn_dilation": [
|
| 82 |
+
1,
|
| 83 |
+
2,
|
| 84 |
+
3,
|
| 85 |
+
1,
|
| 86 |
+
1
|
| 87 |
+
],
|
| 88 |
+
"tdnn_dim": [
|
| 89 |
+
512,
|
| 90 |
+
512,
|
| 91 |
+
512,
|
| 92 |
+
512,
|
| 93 |
+
1500
|
| 94 |
+
],
|
| 95 |
+
"tdnn_kernel": [
|
| 96 |
+
5,
|
| 97 |
+
3,
|
| 98 |
+
3,
|
| 99 |
+
1,
|
| 100 |
+
1
|
| 101 |
+
],
|
| 102 |
+
"torch_dtype": "float32",
|
| 103 |
+
"transformers_version": "4.52.0.dev0",
|
| 104 |
+
"use_weighted_layer_sum": false,
|
| 105 |
+
"vocab_size": 68,
|
| 106 |
+
"xvector_output_dim": 512
|
| 107 |
+
}
|
checkpoint-3500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eda98e9b49db2ac388c5836d8fb4a9da5ddc322ba3a4aba98fd05d2569ab824e
|
| 3 |
+
size 3859080512
|
checkpoint-3500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03ed61938a15171415b59e6caf2c789dcc731936988c9c922f5be555c2176a12
|
| 3 |
+
size 18147578
|
checkpoint-3500/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-3500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dae87ec77530ee6cb17bdf13846a88e178ce734f74df61e92457cb12afde4ea
|
| 3 |
+
size 14244
|
checkpoint-3500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aea95074e2b131abfaea7cc7accba1369e6fa216f4c65cdec4bcf667f322ba6
|
| 3 |
+
size 988
|
checkpoint-3500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eba76c971046d967c7147184b89adfa77e3831b27c04a648557361c1dab7d5be
|
| 3 |
+
size 1064
|
checkpoint-3500/trainer_state.json
ADDED
|
@@ -0,0 +1,594 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.516443361753959,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 3500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.243605359317905,
|
| 14 |
+
"grad_norm": 33.11063766479492,
|
| 15 |
+
"learning_rate": 4.8844282238442824e-05,
|
| 16 |
+
"loss": 10.7343,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.243605359317905,
|
| 21 |
+
"eval_loss": 4.385446548461914,
|
| 22 |
+
"eval_runtime": 206.0799,
|
| 23 |
+
"eval_samples_per_second": 7.992,
|
| 24 |
+
"eval_steps_per_second": 1.0,
|
| 25 |
+
"eval_wer": 1.0,
|
| 26 |
+
"step": 100
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.48721071863581,
|
| 30 |
+
"grad_norm": 2.508547067642212,
|
| 31 |
+
"learning_rate": 4.762773722627738e-05,
|
| 32 |
+
"loss": 3.1325,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.48721071863581,
|
| 37 |
+
"eval_loss": 2.1581695079803467,
|
| 38 |
+
"eval_runtime": 206.4525,
|
| 39 |
+
"eval_samples_per_second": 7.978,
|
| 40 |
+
"eval_steps_per_second": 0.998,
|
| 41 |
+
"eval_wer": 0.9690996270644646,
|
| 42 |
+
"step": 200
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.730816077953715,
|
| 46 |
+
"grad_norm": 1.2504737377166748,
|
| 47 |
+
"learning_rate": 4.641119221411192e-05,
|
| 48 |
+
"loss": 1.6166,
|
| 49 |
+
"step": 300
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.730816077953715,
|
| 53 |
+
"eval_loss": 1.1347323656082153,
|
| 54 |
+
"eval_runtime": 206.3117,
|
| 55 |
+
"eval_samples_per_second": 7.983,
|
| 56 |
+
"eval_steps_per_second": 0.998,
|
| 57 |
+
"eval_wer": 0.7188184455099745,
|
| 58 |
+
"step": 300
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.97442143727162,
|
| 62 |
+
"grad_norm": 1.3984403610229492,
|
| 63 |
+
"learning_rate": 4.520681265206813e-05,
|
| 64 |
+
"loss": 1.1808,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.97442143727162,
|
| 69 |
+
"eval_loss": 0.9792075157165527,
|
| 70 |
+
"eval_runtime": 206.2345,
|
| 71 |
+
"eval_samples_per_second": 7.986,
|
| 72 |
+
"eval_steps_per_second": 0.999,
|
| 73 |
+
"eval_wer": 0.6746581424258569,
|
| 74 |
+
"step": 400
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.2168087697929355,
|
| 78 |
+
"grad_norm": 10.769020080566406,
|
| 79 |
+
"learning_rate": 4.3990267639902676e-05,
|
| 80 |
+
"loss": 1.0459,
|
| 81 |
+
"step": 500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.2168087697929355,
|
| 85 |
+
"eval_loss": 0.9049620032310486,
|
| 86 |
+
"eval_runtime": 208.2322,
|
| 87 |
+
"eval_samples_per_second": 7.909,
|
| 88 |
+
"eval_steps_per_second": 0.989,
|
| 89 |
+
"eval_wer": 0.6494405966968567,
|
| 90 |
+
"step": 500
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.4604141291108403,
|
| 94 |
+
"grad_norm": 0.8941505551338196,
|
| 95 |
+
"learning_rate": 4.277372262773723e-05,
|
| 96 |
+
"loss": 1.0317,
|
| 97 |
+
"step": 600
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.4604141291108403,
|
| 101 |
+
"eval_loss": 0.8543379306793213,
|
| 102 |
+
"eval_runtime": 205.6459,
|
| 103 |
+
"eval_samples_per_second": 8.009,
|
| 104 |
+
"eval_steps_per_second": 1.002,
|
| 105 |
+
"eval_wer": 0.6338128218788848,
|
| 106 |
+
"step": 600
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.7040194884287454,
|
| 110 |
+
"grad_norm": 0.9768113493919373,
|
| 111 |
+
"learning_rate": 4.1569343065693435e-05,
|
| 112 |
+
"loss": 0.9836,
|
| 113 |
+
"step": 700
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.7040194884287454,
|
| 117 |
+
"eval_loss": 0.8191400766372681,
|
| 118 |
+
"eval_runtime": 207.1525,
|
| 119 |
+
"eval_samples_per_second": 7.951,
|
| 120 |
+
"eval_steps_per_second": 0.994,
|
| 121 |
+
"eval_wer": 0.6251701888356124,
|
| 122 |
+
"step": 700
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.9476248477466505,
|
| 126 |
+
"grad_norm": 0.9090480208396912,
|
| 127 |
+
"learning_rate": 4.035279805352798e-05,
|
| 128 |
+
"loss": 0.9567,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.9476248477466505,
|
| 133 |
+
"eval_loss": 0.7955169081687927,
|
| 134 |
+
"eval_runtime": 206.8205,
|
| 135 |
+
"eval_samples_per_second": 7.963,
|
| 136 |
+
"eval_steps_per_second": 0.996,
|
| 137 |
+
"eval_wer": 0.6124430237376428,
|
| 138 |
+
"step": 800
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.1900121802679657,
|
| 142 |
+
"grad_norm": 0.6563196778297424,
|
| 143 |
+
"learning_rate": 3.913625304136253e-05,
|
| 144 |
+
"loss": 0.9354,
|
| 145 |
+
"step": 900
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.1900121802679657,
|
| 149 |
+
"eval_loss": 0.7705180644989014,
|
| 150 |
+
"eval_runtime": 206.4429,
|
| 151 |
+
"eval_samples_per_second": 7.978,
|
| 152 |
+
"eval_steps_per_second": 0.998,
|
| 153 |
+
"eval_wer": 0.6046291363286569,
|
| 154 |
+
"step": 900
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.433617539585871,
|
| 158 |
+
"grad_norm": 0.8123560547828674,
|
| 159 |
+
"learning_rate": 3.791970802919708e-05,
|
| 160 |
+
"loss": 0.9037,
|
| 161 |
+
"step": 1000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.433617539585871,
|
| 165 |
+
"eval_loss": 0.75263512134552,
|
| 166 |
+
"eval_runtime": 206.6571,
|
| 167 |
+
"eval_samples_per_second": 7.97,
|
| 168 |
+
"eval_steps_per_second": 0.997,
|
| 169 |
+
"eval_wer": 0.5982359557213047,
|
| 170 |
+
"step": 1000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.677222898903776,
|
| 174 |
+
"grad_norm": 0.8349791169166565,
|
| 175 |
+
"learning_rate": 3.6703163017031634e-05,
|
| 176 |
+
"loss": 0.901,
|
| 177 |
+
"step": 1100
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.677222898903776,
|
| 181 |
+
"eval_loss": 0.7370020747184753,
|
| 182 |
+
"eval_runtime": 207.9183,
|
| 183 |
+
"eval_samples_per_second": 7.921,
|
| 184 |
+
"eval_steps_per_second": 0.991,
|
| 185 |
+
"eval_wer": 0.5959865032853845,
|
| 186 |
+
"step": 1100
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.9208282582216807,
|
| 190 |
+
"grad_norm": 2.0188732147216797,
|
| 191 |
+
"learning_rate": 3.549878345498784e-05,
|
| 192 |
+
"loss": 0.8888,
|
| 193 |
+
"step": 1200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.9208282582216807,
|
| 197 |
+
"eval_loss": 0.7251046895980835,
|
| 198 |
+
"eval_runtime": 208.4027,
|
| 199 |
+
"eval_samples_per_second": 7.903,
|
| 200 |
+
"eval_steps_per_second": 0.988,
|
| 201 |
+
"eval_wer": 0.58781743917599,
|
| 202 |
+
"step": 1200
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 3.1632155907429964,
|
| 206 |
+
"grad_norm": 0.4746805429458618,
|
| 207 |
+
"learning_rate": 3.4282238442822386e-05,
|
| 208 |
+
"loss": 0.8686,
|
| 209 |
+
"step": 1300
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.1632155907429964,
|
| 213 |
+
"eval_loss": 0.7125080823898315,
|
| 214 |
+
"eval_runtime": 206.121,
|
| 215 |
+
"eval_samples_per_second": 7.99,
|
| 216 |
+
"eval_steps_per_second": 0.999,
|
| 217 |
+
"eval_wer": 0.5834369265376191,
|
| 218 |
+
"step": 1300
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.4068209500609012,
|
| 222 |
+
"grad_norm": 1.0152044296264648,
|
| 223 |
+
"learning_rate": 3.306569343065693e-05,
|
| 224 |
+
"loss": 0.8681,
|
| 225 |
+
"step": 1400
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.4068209500609012,
|
| 229 |
+
"eval_loss": 0.7029690742492676,
|
| 230 |
+
"eval_runtime": 206.1729,
|
| 231 |
+
"eval_samples_per_second": 7.988,
|
| 232 |
+
"eval_steps_per_second": 0.999,
|
| 233 |
+
"eval_wer": 0.577043745930267,
|
| 234 |
+
"step": 1400
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 3.6504263093788065,
|
| 238 |
+
"grad_norm": 0.5681760907173157,
|
| 239 |
+
"learning_rate": 3.1849148418491486e-05,
|
| 240 |
+
"loss": 0.8428,
|
| 241 |
+
"step": 1500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 3.6504263093788065,
|
| 245 |
+
"eval_loss": 0.6939159035682678,
|
| 246 |
+
"eval_runtime": 206.9126,
|
| 247 |
+
"eval_samples_per_second": 7.96,
|
| 248 |
+
"eval_steps_per_second": 0.996,
|
| 249 |
+
"eval_wer": 0.572900017758835,
|
| 250 |
+
"step": 1500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 3.8940316686967114,
|
| 254 |
+
"grad_norm": 0.535625159740448,
|
| 255 |
+
"learning_rate": 3.064476885644769e-05,
|
| 256 |
+
"loss": 0.8372,
|
| 257 |
+
"step": 1600
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.8940316686967114,
|
| 261 |
+
"eval_loss": 0.6848719716072083,
|
| 262 |
+
"eval_runtime": 206.7992,
|
| 263 |
+
"eval_samples_per_second": 7.964,
|
| 264 |
+
"eval_steps_per_second": 0.996,
|
| 265 |
+
"eval_wer": 0.5706505653229148,
|
| 266 |
+
"step": 1600
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.136419001218027,
|
| 270 |
+
"grad_norm": 1.2212234735488892,
|
| 271 |
+
"learning_rate": 2.942822384428224e-05,
|
| 272 |
+
"loss": 0.8388,
|
| 273 |
+
"step": 1700
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 4.136419001218027,
|
| 277 |
+
"eval_loss": 0.6779345870018005,
|
| 278 |
+
"eval_runtime": 206.7198,
|
| 279 |
+
"eval_samples_per_second": 7.967,
|
| 280 |
+
"eval_steps_per_second": 0.997,
|
| 281 |
+
"eval_wer": 0.5667436216184218,
|
| 282 |
+
"step": 1700
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 4.3800243605359315,
|
| 286 |
+
"grad_norm": 0.515786349773407,
|
| 287 |
+
"learning_rate": 2.8211678832116788e-05,
|
| 288 |
+
"loss": 0.8222,
|
| 289 |
+
"step": 1800
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 4.3800243605359315,
|
| 293 |
+
"eval_loss": 0.6726759672164917,
|
| 294 |
+
"eval_runtime": 206.3937,
|
| 295 |
+
"eval_samples_per_second": 7.98,
|
| 296 |
+
"eval_steps_per_second": 0.998,
|
| 297 |
+
"eval_wer": 0.5620671283963772,
|
| 298 |
+
"step": 1800
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 4.623629719853836,
|
| 302 |
+
"grad_norm": 2.3206946849823,
|
| 303 |
+
"learning_rate": 2.699513381995134e-05,
|
| 304 |
+
"loss": 0.8289,
|
| 305 |
+
"step": 1900
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.623629719853836,
|
| 309 |
+
"eval_loss": 0.6664962768554688,
|
| 310 |
+
"eval_runtime": 206.3925,
|
| 311 |
+
"eval_samples_per_second": 7.98,
|
| 312 |
+
"eval_steps_per_second": 0.998,
|
| 313 |
+
"eval_wer": 0.5570354584739241,
|
| 314 |
+
"step": 1900
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.867235079171742,
|
| 318 |
+
"grad_norm": 2.1069090366363525,
|
| 319 |
+
"learning_rate": 2.5790754257907544e-05,
|
| 320 |
+
"loss": 0.8189,
|
| 321 |
+
"step": 2000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 4.867235079171742,
|
| 325 |
+
"eval_loss": 0.6623280048370361,
|
| 326 |
+
"eval_runtime": 208.1032,
|
| 327 |
+
"eval_samples_per_second": 7.914,
|
| 328 |
+
"eval_steps_per_second": 0.99,
|
| 329 |
+
"eval_wer": 0.5564434973065767,
|
| 330 |
+
"step": 2000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 5.109622411693057,
|
| 334 |
+
"grad_norm": 1.1477903127670288,
|
| 335 |
+
"learning_rate": 2.4574209245742094e-05,
|
| 336 |
+
"loss": 0.8073,
|
| 337 |
+
"step": 2100
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 5.109622411693057,
|
| 341 |
+
"eval_loss": 0.6582257151603699,
|
| 342 |
+
"eval_runtime": 206.4132,
|
| 343 |
+
"eval_samples_per_second": 7.979,
|
| 344 |
+
"eval_steps_per_second": 0.998,
|
| 345 |
+
"eval_wer": 0.5535428875865743,
|
| 346 |
+
"step": 2100
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 5.353227771010962,
|
| 350 |
+
"grad_norm": 1.1735588312149048,
|
| 351 |
+
"learning_rate": 2.3357664233576643e-05,
|
| 352 |
+
"loss": 0.8,
|
| 353 |
+
"step": 2200
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 5.353227771010962,
|
| 357 |
+
"eval_loss": 0.6531500816345215,
|
| 358 |
+
"eval_runtime": 206.8033,
|
| 359 |
+
"eval_samples_per_second": 7.964,
|
| 360 |
+
"eval_steps_per_second": 0.996,
|
| 361 |
+
"eval_wer": 0.5504646895163677,
|
| 362 |
+
"step": 2200
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 5.596833130328867,
|
| 366 |
+
"grad_norm": 0.8227632641792297,
|
| 367 |
+
"learning_rate": 2.2141119221411193e-05,
|
| 368 |
+
"loss": 0.8051,
|
| 369 |
+
"step": 2300
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 5.596833130328867,
|
| 373 |
+
"eval_loss": 0.648690402507782,
|
| 374 |
+
"eval_runtime": 208.3131,
|
| 375 |
+
"eval_samples_per_second": 7.906,
|
| 376 |
+
"eval_steps_per_second": 0.989,
|
| 377 |
+
"eval_wer": 0.5461433729947316,
|
| 378 |
+
"step": 2300
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 5.840438489646772,
|
| 382 |
+
"grad_norm": 1.5486682653427124,
|
| 383 |
+
"learning_rate": 2.0936739659367396e-05,
|
| 384 |
+
"loss": 0.7897,
|
| 385 |
+
"step": 2400
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 5.840438489646772,
|
| 389 |
+
"eval_loss": 0.6454324126243591,
|
| 390 |
+
"eval_runtime": 207.86,
|
| 391 |
+
"eval_samples_per_second": 7.924,
|
| 392 |
+
"eval_steps_per_second": 0.991,
|
| 393 |
+
"eval_wer": 0.5443674894926893,
|
| 394 |
+
"step": 2400
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 6.082825822168088,
|
| 398 |
+
"grad_norm": 0.9000282287597656,
|
| 399 |
+
"learning_rate": 1.972019464720195e-05,
|
| 400 |
+
"loss": 0.7723,
|
| 401 |
+
"step": 2500
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 6.082825822168088,
|
| 405 |
+
"eval_loss": 0.6421072483062744,
|
| 406 |
+
"eval_runtime": 208.0417,
|
| 407 |
+
"eval_samples_per_second": 7.917,
|
| 408 |
+
"eval_steps_per_second": 0.99,
|
| 409 |
+
"eval_wer": 0.5446042739596283,
|
| 410 |
+
"step": 2500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 6.326431181485993,
|
| 414 |
+
"grad_norm": 1.1051301956176758,
|
| 415 |
+
"learning_rate": 1.8515815085158152e-05,
|
| 416 |
+
"loss": 0.7805,
|
| 417 |
+
"step": 2600
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 6.326431181485993,
|
| 421 |
+
"eval_loss": 0.6392606496810913,
|
| 422 |
+
"eval_runtime": 207.7887,
|
| 423 |
+
"eval_samples_per_second": 7.926,
|
| 424 |
+
"eval_steps_per_second": 0.991,
|
| 425 |
+
"eval_wer": 0.5412892914224827,
|
| 426 |
+
"step": 2600
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 6.570036540803898,
|
| 430 |
+
"grad_norm": 0.7573370337486267,
|
| 431 |
+
"learning_rate": 1.7299270072992702e-05,
|
| 432 |
+
"loss": 0.7974,
|
| 433 |
+
"step": 2700
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 6.570036540803898,
|
| 437 |
+
"eval_loss": 0.6364970803260803,
|
| 438 |
+
"eval_runtime": 207.756,
|
| 439 |
+
"eval_samples_per_second": 7.928,
|
| 440 |
+
"eval_steps_per_second": 0.992,
|
| 441 |
+
"eval_wer": 0.5396318001539099,
|
| 442 |
+
"step": 2700
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 6.8136419001218025,
|
| 446 |
+
"grad_norm": 1.2818819284439087,
|
| 447 |
+
"learning_rate": 1.608272506082725e-05,
|
| 448 |
+
"loss": 0.7794,
|
| 449 |
+
"step": 2800
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 6.8136419001218025,
|
| 453 |
+
"eval_loss": 0.6344229578971863,
|
| 454 |
+
"eval_runtime": 207.1477,
|
| 455 |
+
"eval_samples_per_second": 7.951,
|
| 456 |
+
"eval_steps_per_second": 0.994,
|
| 457 |
+
"eval_wer": 0.5391582312200319,
|
| 458 |
+
"step": 2800
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 7.056029232643118,
|
| 462 |
+
"grad_norm": 1.371817708015442,
|
| 463 |
+
"learning_rate": 1.4866180048661801e-05,
|
| 464 |
+
"loss": 0.7676,
|
| 465 |
+
"step": 2900
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 7.056029232643118,
|
| 469 |
+
"eval_loss": 0.6325829029083252,
|
| 470 |
+
"eval_runtime": 207.5164,
|
| 471 |
+
"eval_samples_per_second": 7.937,
|
| 472 |
+
"eval_steps_per_second": 0.993,
|
| 473 |
+
"eval_wer": 0.5388622506363583,
|
| 474 |
+
"step": 2900
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 7.2996345919610235,
|
| 478 |
+
"grad_norm": 0.6480887532234192,
|
| 479 |
+
"learning_rate": 1.364963503649635e-05,
|
| 480 |
+
"loss": 0.7627,
|
| 481 |
+
"step": 3000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 7.2996345919610235,
|
| 485 |
+
"eval_loss": 0.6304593682289124,
|
| 486 |
+
"eval_runtime": 206.7906,
|
| 487 |
+
"eval_samples_per_second": 7.965,
|
| 488 |
+
"eval_steps_per_second": 0.996,
|
| 489 |
+
"eval_wer": 0.5392766234535015,
|
| 490 |
+
"step": 3000
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 7.543239951278928,
|
| 494 |
+
"grad_norm": 0.8857569694519043,
|
| 495 |
+
"learning_rate": 1.2445255474452555e-05,
|
| 496 |
+
"loss": 0.7881,
|
| 497 |
+
"step": 3100
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 7.543239951278928,
|
| 501 |
+
"eval_loss": 0.6281934976577759,
|
| 502 |
+
"eval_runtime": 207.7645,
|
| 503 |
+
"eval_samples_per_second": 7.927,
|
| 504 |
+
"eval_steps_per_second": 0.992,
|
| 505 |
+
"eval_wer": 0.5379151127686024,
|
| 506 |
+
"step": 3100
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 7.786845310596833,
|
| 510 |
+
"grad_norm": 3.5432286262512207,
|
| 511 |
+
"learning_rate": 1.1228710462287105e-05,
|
| 512 |
+
"loss": 0.7689,
|
| 513 |
+
"step": 3200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.786845310596833,
|
| 517 |
+
"eval_loss": 0.6266854405403137,
|
| 518 |
+
"eval_runtime": 209.1578,
|
| 519 |
+
"eval_samples_per_second": 7.874,
|
| 520 |
+
"eval_steps_per_second": 0.985,
|
| 521 |
+
"eval_wer": 0.5341857574143136,
|
| 522 |
+
"step": 3200
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 8.02923264311815,
|
| 526 |
+
"grad_norm": 0.5050083994865417,
|
| 527 |
+
"learning_rate": 1.0012165450121655e-05,
|
| 528 |
+
"loss": 0.7784,
|
| 529 |
+
"step": 3300
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 8.02923264311815,
|
| 533 |
+
"eval_loss": 0.6252668499946594,
|
| 534 |
+
"eval_runtime": 208.1091,
|
| 535 |
+
"eval_samples_per_second": 7.914,
|
| 536 |
+
"eval_steps_per_second": 0.99,
|
| 537 |
+
"eval_wer": 0.5369679749008465,
|
| 538 |
+
"step": 3300
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 8.272838002436053,
|
| 542 |
+
"grad_norm": 0.8981237411499023,
|
| 543 |
+
"learning_rate": 8.795620437956204e-06,
|
| 544 |
+
"loss": 0.7643,
|
| 545 |
+
"step": 3400
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 8.272838002436053,
|
| 549 |
+
"eval_loss": 0.6245014667510986,
|
| 550 |
+
"eval_runtime": 208.3764,
|
| 551 |
+
"eval_samples_per_second": 7.904,
|
| 552 |
+
"eval_steps_per_second": 0.989,
|
| 553 |
+
"eval_wer": 0.5344817379979874,
|
| 554 |
+
"step": 3400
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 8.516443361753959,
|
| 558 |
+
"grad_norm": 1.021223783493042,
|
| 559 |
+
"learning_rate": 7.5790754257907545e-06,
|
| 560 |
+
"loss": 0.7817,
|
| 561 |
+
"step": 3500
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 8.516443361753959,
|
| 565 |
+
"eval_loss": 0.6229761838912964,
|
| 566 |
+
"eval_runtime": 208.4474,
|
| 567 |
+
"eval_samples_per_second": 7.901,
|
| 568 |
+
"eval_steps_per_second": 0.988,
|
| 569 |
+
"eval_wer": 0.5351328952820695,
|
| 570 |
+
"step": 3500
|
| 571 |
+
}
|
| 572 |
+
],
|
| 573 |
+
"logging_steps": 100,
|
| 574 |
+
"max_steps": 4110,
|
| 575 |
+
"num_input_tokens_seen": 0,
|
| 576 |
+
"num_train_epochs": 10,
|
| 577 |
+
"save_steps": 100,
|
| 578 |
+
"stateful_callbacks": {
|
| 579 |
+
"TrainerControl": {
|
| 580 |
+
"args": {
|
| 581 |
+
"should_epoch_stop": false,
|
| 582 |
+
"should_evaluate": false,
|
| 583 |
+
"should_log": false,
|
| 584 |
+
"should_save": true,
|
| 585 |
+
"should_training_stop": false
|
| 586 |
+
},
|
| 587 |
+
"attributes": {}
|
| 588 |
+
}
|
| 589 |
+
},
|
| 590 |
+
"total_flos": 4.911928550558042e+19,
|
| 591 |
+
"train_batch_size": 16,
|
| 592 |
+
"trial_name": null,
|
| 593 |
+
"trial_params": null
|
| 594 |
+
}
|
checkpoint-3500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10db31fde7f1e0725d82eac1d448e3bd1e2c86842e5580be4e6cd5c83bfbae42
|
| 3 |
+
size 5240
|