Upload folder using huggingface_hub
Browse files- config.json +125 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +466 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"adapter_attn_dim": null,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
+
"apply_spec_augment": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"Wav2Vec2ForAudioRegression"
|
| 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": "sum",
|
| 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": 0.1,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"finetuning_task": "wav2vec2_regression",
|
| 56 |
+
"gradient_checkpointing": false,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.1,
|
| 59 |
+
"hidden_size": 1024,
|
| 60 |
+
"id2label": {
|
| 61 |
+
"0": "LABEL_0"
|
| 62 |
+
},
|
| 63 |
+
"initializer_range": 0.02,
|
| 64 |
+
"intermediate_size": 4096,
|
| 65 |
+
"label2id": {
|
| 66 |
+
"LABEL_0": 0
|
| 67 |
+
},
|
| 68 |
+
"layer_norm_eps": 1e-05,
|
| 69 |
+
"layerdrop": 0.1,
|
| 70 |
+
"mask_channel_length": 10,
|
| 71 |
+
"mask_channel_min_space": 1,
|
| 72 |
+
"mask_channel_other": 0.0,
|
| 73 |
+
"mask_channel_prob": 0.0,
|
| 74 |
+
"mask_channel_selection": "static",
|
| 75 |
+
"mask_feature_length": 10,
|
| 76 |
+
"mask_feature_min_masks": 0,
|
| 77 |
+
"mask_feature_prob": 0.0,
|
| 78 |
+
"mask_time_length": 10,
|
| 79 |
+
"mask_time_min_masks": 2,
|
| 80 |
+
"mask_time_min_space": 1,
|
| 81 |
+
"mask_time_other": 0.0,
|
| 82 |
+
"mask_time_prob": 0.075,
|
| 83 |
+
"mask_time_selection": "static",
|
| 84 |
+
"model_type": "wav2vec2",
|
| 85 |
+
"num_adapter_layers": 3,
|
| 86 |
+
"num_attention_heads": 16,
|
| 87 |
+
"num_codevector_groups": 2,
|
| 88 |
+
"num_codevectors_per_group": 320,
|
| 89 |
+
"num_conv_pos_embedding_groups": 16,
|
| 90 |
+
"num_conv_pos_embeddings": 128,
|
| 91 |
+
"num_feat_extract_layers": 7,
|
| 92 |
+
"num_hidden_layers": 24,
|
| 93 |
+
"num_negatives": 100,
|
| 94 |
+
"output_hidden_size": 1024,
|
| 95 |
+
"pad_token_id": 0,
|
| 96 |
+
"pooling_mode": "mean",
|
| 97 |
+
"problem_type": "regression",
|
| 98 |
+
"proj_codevector_dim": 768,
|
| 99 |
+
"tdnn_dilation": [
|
| 100 |
+
1,
|
| 101 |
+
2,
|
| 102 |
+
3,
|
| 103 |
+
1,
|
| 104 |
+
1
|
| 105 |
+
],
|
| 106 |
+
"tdnn_dim": [
|
| 107 |
+
512,
|
| 108 |
+
512,
|
| 109 |
+
512,
|
| 110 |
+
512,
|
| 111 |
+
1500
|
| 112 |
+
],
|
| 113 |
+
"tdnn_kernel": [
|
| 114 |
+
5,
|
| 115 |
+
3,
|
| 116 |
+
3,
|
| 117 |
+
1,
|
| 118 |
+
1
|
| 119 |
+
],
|
| 120 |
+
"torch_dtype": "float32",
|
| 121 |
+
"transformers_version": "4.50.3",
|
| 122 |
+
"use_weighted_layer_sum": false,
|
| 123 |
+
"vocab_size": 32,
|
| 124 |
+
"xvector_output_dim": 512
|
| 125 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:beee9cad6447f1e9a6410044e00d0fe0568b2cc4a9356460241ab34066ed29cf
|
| 3 |
+
size 1266010204
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce7a8a06b9778a121f398462ad16ceca30c56dc97f39fb648557576f820cb63c
|
| 3 |
+
size 2532271440
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b152b9f7d7b48829a1b2299a92270be44656a04d72273f4b0c3578ffcd1b99f1
|
| 3 |
+
size 14244
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10afc989ad9dd0fec06ec057139942b34d77f6fd53e85d253a1f4f69c016339e
|
| 3 |
+
size 988
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cfb1d7dd89b470d7bbf8ab8a7e5768ce4e98edd22662563aa48ac874be01776
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,466 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.88599348534202,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 2754,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.6514657980456026,
|
| 14 |
+
"grad_norm": 1.2638410329818726,
|
| 15 |
+
"learning_rate": 9.647785039941903e-05,
|
| 16 |
+
"loss": 0.0465,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.6514657980456026,
|
| 21 |
+
"eval_loss": 0.03762375935912132,
|
| 22 |
+
"eval_mse": 0.03703753277659416,
|
| 23 |
+
"eval_runtime": 88.6656,
|
| 24 |
+
"eval_samples_per_second": 1.737,
|
| 25 |
+
"eval_steps_per_second": 0.868,
|
| 26 |
+
"step": 100
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.2996742671009773,
|
| 30 |
+
"grad_norm": 4.225351333618164,
|
| 31 |
+
"learning_rate": 9.284676833696442e-05,
|
| 32 |
+
"loss": 0.0309,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.2996742671009773,
|
| 37 |
+
"eval_loss": 0.02817053347826004,
|
| 38 |
+
"eval_mse": 0.028493033722043037,
|
| 39 |
+
"eval_runtime": 89.1695,
|
| 40 |
+
"eval_samples_per_second": 1.727,
|
| 41 |
+
"eval_steps_per_second": 0.864,
|
| 42 |
+
"step": 200
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.9511400651465798,
|
| 46 |
+
"grad_norm": 0.3467458188533783,
|
| 47 |
+
"learning_rate": 8.921568627450981e-05,
|
| 48 |
+
"loss": 0.0299,
|
| 49 |
+
"step": 300
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.9511400651465798,
|
| 53 |
+
"eval_loss": 0.02852724678814411,
|
| 54 |
+
"eval_mse": 0.028662405908107758,
|
| 55 |
+
"eval_runtime": 89.7708,
|
| 56 |
+
"eval_samples_per_second": 1.715,
|
| 57 |
+
"eval_steps_per_second": 0.858,
|
| 58 |
+
"step": 300
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.5993485342019547,
|
| 62 |
+
"grad_norm": 0.9525694847106934,
|
| 63 |
+
"learning_rate": 8.55846042120552e-05,
|
| 64 |
+
"loss": 0.0294,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.5993485342019547,
|
| 69 |
+
"eval_loss": 0.027554582804441452,
|
| 70 |
+
"eval_mse": 0.02786860242486,
|
| 71 |
+
"eval_runtime": 89.8297,
|
| 72 |
+
"eval_samples_per_second": 1.714,
|
| 73 |
+
"eval_steps_per_second": 0.857,
|
| 74 |
+
"step": 400
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 3.247557003257329,
|
| 78 |
+
"grad_norm": 5.774784564971924,
|
| 79 |
+
"learning_rate": 8.195352214960058e-05,
|
| 80 |
+
"loss": 0.0277,
|
| 81 |
+
"step": 500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 3.247557003257329,
|
| 85 |
+
"eval_loss": 0.02871050126850605,
|
| 86 |
+
"eval_mse": 0.034602127969264984,
|
| 87 |
+
"eval_runtime": 89.8152,
|
| 88 |
+
"eval_samples_per_second": 1.715,
|
| 89 |
+
"eval_steps_per_second": 0.857,
|
| 90 |
+
"step": 500
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 3.8990228013029316,
|
| 94 |
+
"grad_norm": 0.9268798232078552,
|
| 95 |
+
"learning_rate": 7.832244008714598e-05,
|
| 96 |
+
"loss": 0.0292,
|
| 97 |
+
"step": 600
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 3.8990228013029316,
|
| 101 |
+
"eval_loss": 0.03371996432542801,
|
| 102 |
+
"eval_mse": 0.037180185317993164,
|
| 103 |
+
"eval_runtime": 90.195,
|
| 104 |
+
"eval_samples_per_second": 1.707,
|
| 105 |
+
"eval_steps_per_second": 0.854,
|
| 106 |
+
"step": 600
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 4.547231270358306,
|
| 110 |
+
"grad_norm": 0.12350838631391525,
|
| 111 |
+
"learning_rate": 7.469135802469136e-05,
|
| 112 |
+
"loss": 0.0272,
|
| 113 |
+
"step": 700
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 4.547231270358306,
|
| 117 |
+
"eval_loss": 0.025019396096467972,
|
| 118 |
+
"eval_mse": 0.02873270958662033,
|
| 119 |
+
"eval_runtime": 90.451,
|
| 120 |
+
"eval_samples_per_second": 1.703,
|
| 121 |
+
"eval_steps_per_second": 0.851,
|
| 122 |
+
"step": 700
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.195439739413681,
|
| 126 |
+
"grad_norm": 0.3085576593875885,
|
| 127 |
+
"learning_rate": 7.106027596223676e-05,
|
| 128 |
+
"loss": 0.0216,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.195439739413681,
|
| 133 |
+
"eval_loss": 0.023245293647050858,
|
| 134 |
+
"eval_mse": 0.03596530482172966,
|
| 135 |
+
"eval_runtime": 90.2027,
|
| 136 |
+
"eval_samples_per_second": 1.707,
|
| 137 |
+
"eval_steps_per_second": 0.854,
|
| 138 |
+
"step": 800
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 5.846905537459284,
|
| 142 |
+
"grad_norm": 4.71547269821167,
|
| 143 |
+
"learning_rate": 6.742919389978214e-05,
|
| 144 |
+
"loss": 0.02,
|
| 145 |
+
"step": 900
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 5.846905537459284,
|
| 149 |
+
"eval_loss": 0.016941210255026817,
|
| 150 |
+
"eval_mse": 0.032546475529670715,
|
| 151 |
+
"eval_runtime": 90.1386,
|
| 152 |
+
"eval_samples_per_second": 1.708,
|
| 153 |
+
"eval_steps_per_second": 0.854,
|
| 154 |
+
"step": 900
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 6.495114006514658,
|
| 158 |
+
"grad_norm": 0.2343684285879135,
|
| 159 |
+
"learning_rate": 6.379811183732753e-05,
|
| 160 |
+
"loss": 0.0177,
|
| 161 |
+
"step": 1000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 6.495114006514658,
|
| 165 |
+
"eval_loss": 0.021996306255459785,
|
| 166 |
+
"eval_mse": 0.031924955546855927,
|
| 167 |
+
"eval_runtime": 90.9876,
|
| 168 |
+
"eval_samples_per_second": 1.693,
|
| 169 |
+
"eval_steps_per_second": 0.846,
|
| 170 |
+
"step": 1000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 7.143322475570033,
|
| 174 |
+
"grad_norm": 0.37635019421577454,
|
| 175 |
+
"learning_rate": 6.016702977487292e-05,
|
| 176 |
+
"loss": 0.0203,
|
| 177 |
+
"step": 1100
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 7.143322475570033,
|
| 181 |
+
"eval_loss": 0.03620931878685951,
|
| 182 |
+
"eval_mse": 0.05669161304831505,
|
| 183 |
+
"eval_runtime": 90.6862,
|
| 184 |
+
"eval_samples_per_second": 1.698,
|
| 185 |
+
"eval_steps_per_second": 0.849,
|
| 186 |
+
"step": 1100
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 7.7947882736156355,
|
| 190 |
+
"grad_norm": 0.4336552023887634,
|
| 191 |
+
"learning_rate": 5.65359477124183e-05,
|
| 192 |
+
"loss": 0.0172,
|
| 193 |
+
"step": 1200
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 7.7947882736156355,
|
| 197 |
+
"eval_loss": 0.019503405317664146,
|
| 198 |
+
"eval_mse": 0.04632864147424698,
|
| 199 |
+
"eval_runtime": 90.2807,
|
| 200 |
+
"eval_samples_per_second": 1.706,
|
| 201 |
+
"eval_steps_per_second": 0.853,
|
| 202 |
+
"step": 1200
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 8.44299674267101,
|
| 206 |
+
"grad_norm": 1.6894867420196533,
|
| 207 |
+
"learning_rate": 5.2904865649963685e-05,
|
| 208 |
+
"loss": 0.0159,
|
| 209 |
+
"step": 1300
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 8.44299674267101,
|
| 213 |
+
"eval_loss": 0.018114862963557243,
|
| 214 |
+
"eval_mse": 0.032530076801776886,
|
| 215 |
+
"eval_runtime": 90.5229,
|
| 216 |
+
"eval_samples_per_second": 1.701,
|
| 217 |
+
"eval_steps_per_second": 0.851,
|
| 218 |
+
"step": 1300
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 9.091205211726384,
|
| 222 |
+
"grad_norm": 1.3247390985488892,
|
| 223 |
+
"learning_rate": 4.927378358750908e-05,
|
| 224 |
+
"loss": 0.0183,
|
| 225 |
+
"step": 1400
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 9.091205211726384,
|
| 229 |
+
"eval_loss": 0.023152034729719162,
|
| 230 |
+
"eval_mse": 0.05892067402601242,
|
| 231 |
+
"eval_runtime": 90.2274,
|
| 232 |
+
"eval_samples_per_second": 1.707,
|
| 233 |
+
"eval_steps_per_second": 0.853,
|
| 234 |
+
"step": 1400
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 9.742671009771987,
|
| 238 |
+
"grad_norm": 0.23432166874408722,
|
| 239 |
+
"learning_rate": 4.564270152505447e-05,
|
| 240 |
+
"loss": 0.0167,
|
| 241 |
+
"step": 1500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 9.742671009771987,
|
| 245 |
+
"eval_loss": 0.017632601782679558,
|
| 246 |
+
"eval_mse": 0.04079648479819298,
|
| 247 |
+
"eval_runtime": 90.49,
|
| 248 |
+
"eval_samples_per_second": 1.702,
|
| 249 |
+
"eval_steps_per_second": 0.851,
|
| 250 |
+
"step": 1500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 10.390879478827362,
|
| 254 |
+
"grad_norm": 0.33277449011802673,
|
| 255 |
+
"learning_rate": 4.2011619462599856e-05,
|
| 256 |
+
"loss": 0.0181,
|
| 257 |
+
"step": 1600
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 10.390879478827362,
|
| 261 |
+
"eval_loss": 0.026499085128307343,
|
| 262 |
+
"eval_mse": 0.030374381691217422,
|
| 263 |
+
"eval_runtime": 90.526,
|
| 264 |
+
"eval_samples_per_second": 1.701,
|
| 265 |
+
"eval_steps_per_second": 0.851,
|
| 266 |
+
"step": 1600
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 11.039087947882736,
|
| 270 |
+
"grad_norm": 1.5499602556228638,
|
| 271 |
+
"learning_rate": 3.8380537400145246e-05,
|
| 272 |
+
"loss": 0.0178,
|
| 273 |
+
"step": 1700
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 11.039087947882736,
|
| 277 |
+
"eval_loss": 0.021473562344908714,
|
| 278 |
+
"eval_mse": 0.040922779589891434,
|
| 279 |
+
"eval_runtime": 90.8595,
|
| 280 |
+
"eval_samples_per_second": 1.695,
|
| 281 |
+
"eval_steps_per_second": 0.847,
|
| 282 |
+
"step": 1700
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 11.690553745928339,
|
| 286 |
+
"grad_norm": 0.8587289452552795,
|
| 287 |
+
"learning_rate": 3.474945533769064e-05,
|
| 288 |
+
"loss": 0.0164,
|
| 289 |
+
"step": 1800
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 11.690553745928339,
|
| 293 |
+
"eval_loss": 0.015354540199041367,
|
| 294 |
+
"eval_mse": 0.0399436429142952,
|
| 295 |
+
"eval_runtime": 90.1794,
|
| 296 |
+
"eval_samples_per_second": 1.708,
|
| 297 |
+
"eval_steps_per_second": 0.854,
|
| 298 |
+
"step": 1800
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 12.338762214983714,
|
| 302 |
+
"grad_norm": 0.19527116417884827,
|
| 303 |
+
"learning_rate": 3.111837327523602e-05,
|
| 304 |
+
"loss": 0.0144,
|
| 305 |
+
"step": 1900
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 12.338762214983714,
|
| 309 |
+
"eval_loss": 0.018714504316449165,
|
| 310 |
+
"eval_mse": 0.04291320964694023,
|
| 311 |
+
"eval_runtime": 90.7039,
|
| 312 |
+
"eval_samples_per_second": 1.698,
|
| 313 |
+
"eval_steps_per_second": 0.849,
|
| 314 |
+
"step": 1900
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 12.990228013029316,
|
| 318 |
+
"grad_norm": 0.3192684054374695,
|
| 319 |
+
"learning_rate": 2.7487291212781407e-05,
|
| 320 |
+
"loss": 0.015,
|
| 321 |
+
"step": 2000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 12.990228013029316,
|
| 325 |
+
"eval_loss": 0.015104055404663086,
|
| 326 |
+
"eval_mse": 0.04015926271677017,
|
| 327 |
+
"eval_runtime": 90.635,
|
| 328 |
+
"eval_samples_per_second": 1.699,
|
| 329 |
+
"eval_steps_per_second": 0.85,
|
| 330 |
+
"step": 2000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 13.63843648208469,
|
| 334 |
+
"grad_norm": 0.6388863921165466,
|
| 335 |
+
"learning_rate": 2.38562091503268e-05,
|
| 336 |
+
"loss": 0.0139,
|
| 337 |
+
"step": 2100
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 13.63843648208469,
|
| 341 |
+
"eval_loss": 0.016035696491599083,
|
| 342 |
+
"eval_mse": 0.04732033237814903,
|
| 343 |
+
"eval_runtime": 91.5121,
|
| 344 |
+
"eval_samples_per_second": 1.683,
|
| 345 |
+
"eval_steps_per_second": 0.841,
|
| 346 |
+
"step": 2100
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 14.286644951140065,
|
| 350 |
+
"grad_norm": 0.21684342622756958,
|
| 351 |
+
"learning_rate": 2.0225127087872185e-05,
|
| 352 |
+
"loss": 0.0145,
|
| 353 |
+
"step": 2200
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 14.286644951140065,
|
| 357 |
+
"eval_loss": 0.018462415784597397,
|
| 358 |
+
"eval_mse": 0.04823942109942436,
|
| 359 |
+
"eval_runtime": 90.3632,
|
| 360 |
+
"eval_samples_per_second": 1.704,
|
| 361 |
+
"eval_steps_per_second": 0.852,
|
| 362 |
+
"step": 2200
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 14.938110749185668,
|
| 366 |
+
"grad_norm": 1.060388445854187,
|
| 367 |
+
"learning_rate": 1.6594045025417575e-05,
|
| 368 |
+
"loss": 0.0138,
|
| 369 |
+
"step": 2300
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 14.938110749185668,
|
| 373 |
+
"eval_loss": 0.014556349255144596,
|
| 374 |
+
"eval_mse": 0.04120248183608055,
|
| 375 |
+
"eval_runtime": 90.4648,
|
| 376 |
+
"eval_samples_per_second": 1.702,
|
| 377 |
+
"eval_steps_per_second": 0.851,
|
| 378 |
+
"step": 2300
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 15.586319218241043,
|
| 382 |
+
"grad_norm": 0.5649324655532837,
|
| 383 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 384 |
+
"loss": 0.0147,
|
| 385 |
+
"step": 2400
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 15.586319218241043,
|
| 389 |
+
"eval_loss": 0.016257289797067642,
|
| 390 |
+
"eval_mse": 0.04343423992395401,
|
| 391 |
+
"eval_runtime": 90.5146,
|
| 392 |
+
"eval_samples_per_second": 1.701,
|
| 393 |
+
"eval_steps_per_second": 0.851,
|
| 394 |
+
"step": 2400
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 16.234527687296417,
|
| 398 |
+
"grad_norm": 0.2803210914134979,
|
| 399 |
+
"learning_rate": 9.331880900508353e-06,
|
| 400 |
+
"loss": 0.0123,
|
| 401 |
+
"step": 2500
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 16.234527687296417,
|
| 405 |
+
"eval_loss": 0.015808526426553726,
|
| 406 |
+
"eval_mse": 0.0433967150747776,
|
| 407 |
+
"eval_runtime": 90.5827,
|
| 408 |
+
"eval_samples_per_second": 1.7,
|
| 409 |
+
"eval_steps_per_second": 0.85,
|
| 410 |
+
"step": 2500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 16.88599348534202,
|
| 414 |
+
"grad_norm": 0.15071052312850952,
|
| 415 |
+
"learning_rate": 5.700798838053741e-06,
|
| 416 |
+
"loss": 0.0132,
|
| 417 |
+
"step": 2600
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 16.88599348534202,
|
| 421 |
+
"eval_loss": 0.016139788553118706,
|
| 422 |
+
"eval_mse": 0.039463259279727936,
|
| 423 |
+
"eval_runtime": 91.04,
|
| 424 |
+
"eval_samples_per_second": 1.692,
|
| 425 |
+
"eval_steps_per_second": 0.846,
|
| 426 |
+
"step": 2600
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 17.534201954397393,
|
| 430 |
+
"grad_norm": 0.2855733633041382,
|
| 431 |
+
"learning_rate": 2.0697167755991287e-06,
|
| 432 |
+
"loss": 0.0131,
|
| 433 |
+
"step": 2700
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 17.534201954397393,
|
| 437 |
+
"eval_loss": 0.015753401443362236,
|
| 438 |
+
"eval_mse": 0.04061569273471832,
|
| 439 |
+
"eval_runtime": 91.2096,
|
| 440 |
+
"eval_samples_per_second": 1.688,
|
| 441 |
+
"eval_steps_per_second": 0.844,
|
| 442 |
+
"step": 2700
|
| 443 |
+
}
|
| 444 |
+
],
|
| 445 |
+
"logging_steps": 100,
|
| 446 |
+
"max_steps": 2754,
|
| 447 |
+
"num_input_tokens_seen": 0,
|
| 448 |
+
"num_train_epochs": 18,
|
| 449 |
+
"save_steps": 100,
|
| 450 |
+
"stateful_callbacks": {
|
| 451 |
+
"TrainerControl": {
|
| 452 |
+
"args": {
|
| 453 |
+
"should_epoch_stop": false,
|
| 454 |
+
"should_evaluate": false,
|
| 455 |
+
"should_log": false,
|
| 456 |
+
"should_save": true,
|
| 457 |
+
"should_training_stop": true
|
| 458 |
+
},
|
| 459 |
+
"attributes": {}
|
| 460 |
+
}
|
| 461 |
+
},
|
| 462 |
+
"total_flos": 1.5386107538383602e+19,
|
| 463 |
+
"train_batch_size": 2,
|
| 464 |
+
"trial_name": null,
|
| 465 |
+
"trial_params": null
|
| 466 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdcd97e2e6c734a99352d9651d92da44f783a68798e3ea16a7754ecf017e5737
|
| 3 |
+
size 5304
|