Training in progress, epoch 3, checkpoint
Browse files- checkpoint-735/config.json +130 -0
- checkpoint-735/model.safetensors +3 -0
- checkpoint-735/optimizer.pt +3 -0
- checkpoint-735/preprocessor_config.json +10 -0
- checkpoint-735/rng_state.pth +3 -0
- checkpoint-735/scheduler.pt +3 -0
- checkpoint-735/trainer_state.json +553 -0
- checkpoint-735/training_args.bin +3 -0
checkpoint-735/config.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nguyenvulebinh/wav2vec2-base-vi",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 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 |
+
"Wav2Vec2ForViSpeechClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 256,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": false,
|
| 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": "sum",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": false,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "group",
|
| 53 |
+
"feat_proj_dropout": 0.1,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.1,
|
| 56 |
+
"gradient_checkpointing": false,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.1,
|
| 59 |
+
"hidden_dropout_prob": 0.1,
|
| 60 |
+
"hidden_size": 768,
|
| 61 |
+
"id2label": {
|
| 62 |
+
"0": "male, northern dialect",
|
| 63 |
+
"1": "male, central dialect",
|
| 64 |
+
"2": "male, highland central dialect",
|
| 65 |
+
"3": "male, southern dialect",
|
| 66 |
+
"4": "female, northern dialect",
|
| 67 |
+
"5": "female, central dialect",
|
| 68 |
+
"6": "female, highland central dialect",
|
| 69 |
+
"7": "female, southern dialect"
|
| 70 |
+
},
|
| 71 |
+
"initializer_range": 0.02,
|
| 72 |
+
"intermediate_size": 3072,
|
| 73 |
+
"label2id": {
|
| 74 |
+
"female, central dialect": "5",
|
| 75 |
+
"female, highland central dialect": "6",
|
| 76 |
+
"female, northern dialect": "4",
|
| 77 |
+
"female, southern dialect": "7",
|
| 78 |
+
"male, central dialect": "1",
|
| 79 |
+
"male, highland central dialect": "2",
|
| 80 |
+
"male, northern dialect": "0",
|
| 81 |
+
"male, southern dialect": "3"
|
| 82 |
+
},
|
| 83 |
+
"layer_norm_eps": 1e-05,
|
| 84 |
+
"layerdrop": 0.1,
|
| 85 |
+
"mask_feature_length": 10,
|
| 86 |
+
"mask_feature_min_masks": 0,
|
| 87 |
+
"mask_feature_prob": 0.0,
|
| 88 |
+
"mask_time_length": 10,
|
| 89 |
+
"mask_time_min_masks": 2,
|
| 90 |
+
"mask_time_prob": 0.05,
|
| 91 |
+
"model_type": "wav2vec2",
|
| 92 |
+
"num_adapter_layers": 3,
|
| 93 |
+
"num_attention_heads": 12,
|
| 94 |
+
"num_codevector_groups": 2,
|
| 95 |
+
"num_codevectors_per_group": 320,
|
| 96 |
+
"num_conv_pos_embedding_groups": 16,
|
| 97 |
+
"num_conv_pos_embeddings": 128,
|
| 98 |
+
"num_feat_extract_layers": 7,
|
| 99 |
+
"num_hidden_layers": 12,
|
| 100 |
+
"num_negatives": 100,
|
| 101 |
+
"output_hidden_size": 768,
|
| 102 |
+
"pad_token_id": 0,
|
| 103 |
+
"proj_codevector_dim": 256,
|
| 104 |
+
"tdnn_dilation": [
|
| 105 |
+
1,
|
| 106 |
+
2,
|
| 107 |
+
3,
|
| 108 |
+
1,
|
| 109 |
+
1
|
| 110 |
+
],
|
| 111 |
+
"tdnn_dim": [
|
| 112 |
+
512,
|
| 113 |
+
512,
|
| 114 |
+
512,
|
| 115 |
+
512,
|
| 116 |
+
1500
|
| 117 |
+
],
|
| 118 |
+
"tdnn_kernel": [
|
| 119 |
+
5,
|
| 120 |
+
3,
|
| 121 |
+
3,
|
| 122 |
+
1,
|
| 123 |
+
1
|
| 124 |
+
],
|
| 125 |
+
"torch_dtype": "float32",
|
| 126 |
+
"transformers_version": "4.41.2",
|
| 127 |
+
"use_weighted_layer_sum": false,
|
| 128 |
+
"vocab_size": 96,
|
| 129 |
+
"xvector_output_dim": 512
|
| 130 |
+
}
|
checkpoint-735/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef686465dde18fe9a27bbdd5b791acc6cda371a9ad242da59cded93988cfb685
|
| 3 |
+
size 383295784
|
checkpoint-735/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6595ce0f0a7d2f98f487d9eedac5d512388c87c1e056342b968695e6cbbddb88
|
| 3 |
+
size 2929542
|
checkpoint-735/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-735/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6440097b06112b5b65ed863d8e90caadd94c4f1dddbbf8c1e1ff2aa76a85df2a
|
| 3 |
+
size 14244
|
checkpoint-735/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9445168de11e5d693f00276204432476aa068cab82693bd429c3e71ff005744d
|
| 3 |
+
size 1064
|
checkpoint-735/trainer_state.json
ADDED
|
@@ -0,0 +1,553 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 735,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04081632653061224,
|
| 13 |
+
"grad_norm": 20286.314453125,
|
| 14 |
+
"learning_rate": 1.2244897959183673e-06,
|
| 15 |
+
"loss": 2.0797,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08163265306122448,
|
| 20 |
+
"grad_norm": 21226.833984375,
|
| 21 |
+
"learning_rate": 2.4489795918367347e-06,
|
| 22 |
+
"loss": 2.0794,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12244897959183673,
|
| 27 |
+
"grad_norm": 20473.34375,
|
| 28 |
+
"learning_rate": 3.673469387755102e-06,
|
| 29 |
+
"loss": 2.0791,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16326530612244897,
|
| 34 |
+
"grad_norm": 21295.623046875,
|
| 35 |
+
"learning_rate": 4.897959183673469e-06,
|
| 36 |
+
"loss": 2.0786,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.20408163265306123,
|
| 41 |
+
"grad_norm": 22374.26953125,
|
| 42 |
+
"learning_rate": 6.122448979591837e-06,
|
| 43 |
+
"loss": 2.0775,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24489795918367346,
|
| 48 |
+
"grad_norm": 27922.837890625,
|
| 49 |
+
"learning_rate": 7.346938775510204e-06,
|
| 50 |
+
"loss": 2.0762,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2857142857142857,
|
| 55 |
+
"grad_norm": 21962.65625,
|
| 56 |
+
"learning_rate": 8.571428571428571e-06,
|
| 57 |
+
"loss": 2.0751,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.32653061224489793,
|
| 62 |
+
"grad_norm": 25949.669921875,
|
| 63 |
+
"learning_rate": 9.795918367346939e-06,
|
| 64 |
+
"loss": 2.073,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3673469387755102,
|
| 69 |
+
"grad_norm": 21337.779296875,
|
| 70 |
+
"learning_rate": 1.1020408163265306e-05,
|
| 71 |
+
"loss": 2.0711,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.40816326530612246,
|
| 76 |
+
"grad_norm": 21139.53125,
|
| 77 |
+
"learning_rate": 1.2244897959183674e-05,
|
| 78 |
+
"loss": 2.068,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4489795918367347,
|
| 83 |
+
"grad_norm": 18687.326171875,
|
| 84 |
+
"learning_rate": 1.3469387755102042e-05,
|
| 85 |
+
"loss": 2.0621,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.4897959183673469,
|
| 90 |
+
"grad_norm": 23997.892578125,
|
| 91 |
+
"learning_rate": 1.4693877551020408e-05,
|
| 92 |
+
"loss": 2.0557,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5306122448979592,
|
| 97 |
+
"grad_norm": 25094.125,
|
| 98 |
+
"learning_rate": 1.5918367346938776e-05,
|
| 99 |
+
"loss": 2.0436,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5714285714285714,
|
| 104 |
+
"grad_norm": 35127.62890625,
|
| 105 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 106 |
+
"loss": 2.0313,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6122448979591837,
|
| 111 |
+
"grad_norm": 38480.73046875,
|
| 112 |
+
"learning_rate": 1.836734693877551e-05,
|
| 113 |
+
"loss": 2.0124,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6530612244897959,
|
| 118 |
+
"grad_norm": 37025.25390625,
|
| 119 |
+
"learning_rate": 1.9591836734693877e-05,
|
| 120 |
+
"loss": 1.9832,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6938775510204082,
|
| 125 |
+
"grad_norm": 47326.75390625,
|
| 126 |
+
"learning_rate": 2.0816326530612247e-05,
|
| 127 |
+
"loss": 1.9503,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.7346938775510204,
|
| 132 |
+
"grad_norm": 44386.79296875,
|
| 133 |
+
"learning_rate": 2.2040816326530613e-05,
|
| 134 |
+
"loss": 1.9033,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7755102040816326,
|
| 139 |
+
"grad_norm": 60427.28515625,
|
| 140 |
+
"learning_rate": 2.326530612244898e-05,
|
| 141 |
+
"loss": 1.8548,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8163265306122449,
|
| 146 |
+
"grad_norm": 60310.234375,
|
| 147 |
+
"learning_rate": 2.448979591836735e-05,
|
| 148 |
+
"loss": 1.7809,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8571428571428571,
|
| 153 |
+
"grad_norm": 73581.171875,
|
| 154 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 155 |
+
"loss": 1.8435,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8979591836734694,
|
| 160 |
+
"grad_norm": 63305.5,
|
| 161 |
+
"learning_rate": 2.6938775510204084e-05,
|
| 162 |
+
"loss": 1.7222,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.9387755102040817,
|
| 167 |
+
"grad_norm": 78695.546875,
|
| 168 |
+
"learning_rate": 2.816326530612245e-05,
|
| 169 |
+
"loss": 1.7823,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9795918367346939,
|
| 174 |
+
"grad_norm": 118529.84375,
|
| 175 |
+
"learning_rate": 2.9387755102040816e-05,
|
| 176 |
+
"loss": 1.7203,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.0204081632653061,
|
| 181 |
+
"grad_norm": 39453.51953125,
|
| 182 |
+
"learning_rate": 2.9931972789115647e-05,
|
| 183 |
+
"loss": 1.7304,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0612244897959184,
|
| 188 |
+
"grad_norm": 58271.04296875,
|
| 189 |
+
"learning_rate": 2.979591836734694e-05,
|
| 190 |
+
"loss": 1.6894,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.1020408163265305,
|
| 195 |
+
"grad_norm": 66804.171875,
|
| 196 |
+
"learning_rate": 2.9659863945578233e-05,
|
| 197 |
+
"loss": 1.7216,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.1428571428571428,
|
| 202 |
+
"grad_norm": 85323.1328125,
|
| 203 |
+
"learning_rate": 2.9523809523809523e-05,
|
| 204 |
+
"loss": 1.6702,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.183673469387755,
|
| 209 |
+
"grad_norm": 56704.1484375,
|
| 210 |
+
"learning_rate": 2.9387755102040816e-05,
|
| 211 |
+
"loss": 1.7761,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2244897959183674,
|
| 216 |
+
"grad_norm": 26519.884765625,
|
| 217 |
+
"learning_rate": 2.925170068027211e-05,
|
| 218 |
+
"loss": 1.7161,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.2653061224489797,
|
| 223 |
+
"grad_norm": 30323.771484375,
|
| 224 |
+
"learning_rate": 2.9115646258503402e-05,
|
| 225 |
+
"loss": 1.7138,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.306122448979592,
|
| 230 |
+
"grad_norm": 88774.5234375,
|
| 231 |
+
"learning_rate": 2.8979591836734695e-05,
|
| 232 |
+
"loss": 1.7125,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.346938775510204,
|
| 237 |
+
"grad_norm": 81892.703125,
|
| 238 |
+
"learning_rate": 2.8843537414965988e-05,
|
| 239 |
+
"loss": 1.7273,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.3877551020408163,
|
| 244 |
+
"grad_norm": 35876.6171875,
|
| 245 |
+
"learning_rate": 2.870748299319728e-05,
|
| 246 |
+
"loss": 1.7185,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.4285714285714286,
|
| 251 |
+
"grad_norm": 91867.0390625,
|
| 252 |
+
"learning_rate": 2.857142857142857e-05,
|
| 253 |
+
"loss": 1.7057,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.469387755102041,
|
| 258 |
+
"grad_norm": 47658.41796875,
|
| 259 |
+
"learning_rate": 2.8435374149659864e-05,
|
| 260 |
+
"loss": 1.7744,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.510204081632653,
|
| 265 |
+
"grad_norm": 105770.484375,
|
| 266 |
+
"learning_rate": 2.8299319727891157e-05,
|
| 267 |
+
"loss": 1.6898,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.5510204081632653,
|
| 272 |
+
"grad_norm": 104692.265625,
|
| 273 |
+
"learning_rate": 2.816326530612245e-05,
|
| 274 |
+
"loss": 1.7351,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.5918367346938775,
|
| 279 |
+
"grad_norm": 45664.515625,
|
| 280 |
+
"learning_rate": 2.802721088435374e-05,
|
| 281 |
+
"loss": 1.6806,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.6326530612244898,
|
| 286 |
+
"grad_norm": 45678.98828125,
|
| 287 |
+
"learning_rate": 2.7891156462585036e-05,
|
| 288 |
+
"loss": 1.7555,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6734693877551021,
|
| 293 |
+
"grad_norm": 108897.0078125,
|
| 294 |
+
"learning_rate": 2.775510204081633e-05,
|
| 295 |
+
"loss": 1.6663,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.7142857142857144,
|
| 300 |
+
"grad_norm": 46971.11328125,
|
| 301 |
+
"learning_rate": 2.761904761904762e-05,
|
| 302 |
+
"loss": 1.7053,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.7551020408163265,
|
| 307 |
+
"grad_norm": 69147.1171875,
|
| 308 |
+
"learning_rate": 2.7482993197278912e-05,
|
| 309 |
+
"loss": 1.7412,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.7959183673469388,
|
| 314 |
+
"grad_norm": 89437.34375,
|
| 315 |
+
"learning_rate": 2.7346938775510205e-05,
|
| 316 |
+
"loss": 1.7245,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.836734693877551,
|
| 321 |
+
"grad_norm": 40401.5625,
|
| 322 |
+
"learning_rate": 2.7210884353741498e-05,
|
| 323 |
+
"loss": 1.7614,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.8775510204081631,
|
| 328 |
+
"grad_norm": 53271.234375,
|
| 329 |
+
"learning_rate": 2.7074829931972787e-05,
|
| 330 |
+
"loss": 1.7179,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.9183673469387754,
|
| 335 |
+
"grad_norm": 69800.3203125,
|
| 336 |
+
"learning_rate": 2.6938775510204084e-05,
|
| 337 |
+
"loss": 1.7467,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.9591836734693877,
|
| 342 |
+
"grad_norm": 86541.828125,
|
| 343 |
+
"learning_rate": 2.6802721088435377e-05,
|
| 344 |
+
"loss": 1.6975,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.0,
|
| 349 |
+
"grad_norm": 100622.125,
|
| 350 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 351 |
+
"loss": 1.6769,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.0408163265306123,
|
| 356 |
+
"grad_norm": 140721.46875,
|
| 357 |
+
"learning_rate": 2.653061224489796e-05,
|
| 358 |
+
"loss": 1.7128,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.0408163265306123,
|
| 363 |
+
"eval_accuracy": 0.1981891348088531,
|
| 364 |
+
"eval_loss": 1.6279175281524658,
|
| 365 |
+
"eval_runtime": 282.7617,
|
| 366 |
+
"eval_samples_per_second": 10.546,
|
| 367 |
+
"eval_steps_per_second": 0.223,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.0816326530612246,
|
| 372 |
+
"grad_norm": 101114.078125,
|
| 373 |
+
"learning_rate": 2.6394557823129253e-05,
|
| 374 |
+
"loss": 1.7745,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.122448979591837,
|
| 379 |
+
"grad_norm": 114329.1640625,
|
| 380 |
+
"learning_rate": 2.6258503401360546e-05,
|
| 381 |
+
"loss": 1.7301,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.163265306122449,
|
| 386 |
+
"grad_norm": 102430.6328125,
|
| 387 |
+
"learning_rate": 2.6122448979591835e-05,
|
| 388 |
+
"loss": 1.7219,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.204081632653061,
|
| 393 |
+
"grad_norm": 92331.4453125,
|
| 394 |
+
"learning_rate": 2.598639455782313e-05,
|
| 395 |
+
"loss": 1.6976,
|
| 396 |
+
"step": 540
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.2448979591836733,
|
| 400 |
+
"grad_norm": 37969.83203125,
|
| 401 |
+
"learning_rate": 2.5850340136054425e-05,
|
| 402 |
+
"loss": 1.6713,
|
| 403 |
+
"step": 550
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 2.2857142857142856,
|
| 407 |
+
"grad_norm": 88346.3046875,
|
| 408 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 409 |
+
"loss": 1.7195,
|
| 410 |
+
"step": 560
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.326530612244898,
|
| 414 |
+
"grad_norm": 85409.15625,
|
| 415 |
+
"learning_rate": 2.5578231292517007e-05,
|
| 416 |
+
"loss": 1.7757,
|
| 417 |
+
"step": 570
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.36734693877551,
|
| 421 |
+
"grad_norm": 26777.841796875,
|
| 422 |
+
"learning_rate": 2.54421768707483e-05,
|
| 423 |
+
"loss": 1.7285,
|
| 424 |
+
"step": 580
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.4081632653061225,
|
| 428 |
+
"grad_norm": 75528.03125,
|
| 429 |
+
"learning_rate": 2.5306122448979594e-05,
|
| 430 |
+
"loss": 1.7239,
|
| 431 |
+
"step": 590
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.4489795918367347,
|
| 435 |
+
"grad_norm": 99135.8515625,
|
| 436 |
+
"learning_rate": 2.5170068027210883e-05,
|
| 437 |
+
"loss": 1.639,
|
| 438 |
+
"step": 600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.489795918367347,
|
| 442 |
+
"grad_norm": 75343.3046875,
|
| 443 |
+
"learning_rate": 2.5034013605442176e-05,
|
| 444 |
+
"loss": 1.7259,
|
| 445 |
+
"step": 610
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.5306122448979593,
|
| 449 |
+
"grad_norm": 118070.5546875,
|
| 450 |
+
"learning_rate": 2.4897959183673473e-05,
|
| 451 |
+
"loss": 1.6815,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.571428571428571,
|
| 456 |
+
"grad_norm": 154820.453125,
|
| 457 |
+
"learning_rate": 2.4761904761904762e-05,
|
| 458 |
+
"loss": 1.6935,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.612244897959184,
|
| 463 |
+
"grad_norm": 95532.75,
|
| 464 |
+
"learning_rate": 2.4625850340136055e-05,
|
| 465 |
+
"loss": 1.6823,
|
| 466 |
+
"step": 640
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.6530612244897958,
|
| 470 |
+
"grad_norm": 86994.4921875,
|
| 471 |
+
"learning_rate": 2.448979591836735e-05,
|
| 472 |
+
"loss": 1.662,
|
| 473 |
+
"step": 650
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.693877551020408,
|
| 477 |
+
"grad_norm": 78671.8359375,
|
| 478 |
+
"learning_rate": 2.435374149659864e-05,
|
| 479 |
+
"loss": 1.6588,
|
| 480 |
+
"step": 660
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.7346938775510203,
|
| 484 |
+
"grad_norm": 96924.7265625,
|
| 485 |
+
"learning_rate": 2.421768707482993e-05,
|
| 486 |
+
"loss": 1.7981,
|
| 487 |
+
"step": 670
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.7755102040816326,
|
| 491 |
+
"grad_norm": 83239.3203125,
|
| 492 |
+
"learning_rate": 2.4081632653061224e-05,
|
| 493 |
+
"loss": 1.7216,
|
| 494 |
+
"step": 680
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.816326530612245,
|
| 498 |
+
"grad_norm": 88283.4765625,
|
| 499 |
+
"learning_rate": 2.3945578231292517e-05,
|
| 500 |
+
"loss": 1.6632,
|
| 501 |
+
"step": 690
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.857142857142857,
|
| 505 |
+
"grad_norm": 57946.15234375,
|
| 506 |
+
"learning_rate": 2.380952380952381e-05,
|
| 507 |
+
"loss": 1.6614,
|
| 508 |
+
"step": 700
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.8979591836734695,
|
| 512 |
+
"grad_norm": 69202.7109375,
|
| 513 |
+
"learning_rate": 2.3673469387755103e-05,
|
| 514 |
+
"loss": 1.753,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.938775510204082,
|
| 519 |
+
"grad_norm": 65562.8046875,
|
| 520 |
+
"learning_rate": 2.3537414965986396e-05,
|
| 521 |
+
"loss": 1.7314,
|
| 522 |
+
"step": 720
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.979591836734694,
|
| 526 |
+
"grad_norm": 114870.2265625,
|
| 527 |
+
"learning_rate": 2.340136054421769e-05,
|
| 528 |
+
"loss": 1.714,
|
| 529 |
+
"step": 730
|
| 530 |
+
}
|
| 531 |
+
],
|
| 532 |
+
"logging_steps": 10,
|
| 533 |
+
"max_steps": 2450,
|
| 534 |
+
"num_input_tokens_seen": 0,
|
| 535 |
+
"num_train_epochs": 10,
|
| 536 |
+
"save_steps": 500,
|
| 537 |
+
"stateful_callbacks": {
|
| 538 |
+
"TrainerControl": {
|
| 539 |
+
"args": {
|
| 540 |
+
"should_epoch_stop": false,
|
| 541 |
+
"should_evaluate": false,
|
| 542 |
+
"should_log": false,
|
| 543 |
+
"should_save": true,
|
| 544 |
+
"should_training_stop": false
|
| 545 |
+
},
|
| 546 |
+
"attributes": {}
|
| 547 |
+
}
|
| 548 |
+
},
|
| 549 |
+
"total_flos": 9.72903329888256e+18,
|
| 550 |
+
"train_batch_size": 48,
|
| 551 |
+
"trial_name": null,
|
| 552 |
+
"trial_params": null
|
| 553 |
+
}
|
checkpoint-735/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff1a5da6b40908735a2131d0c9bb8c41334e1f841f4d5b0727103f09277b756f
|
| 3 |
+
size 5176
|