Training in progress, epoch 1, checkpoint
Browse files- last-checkpoint/config.json +125 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/preprocessor_config.json +9 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +386 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/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 |
+
"Wav2Vec2ForSequenceClassification"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.1,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 256,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": false,
|
| 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": false,
|
| 48 |
+
"dtype": "float32",
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_norm": "group",
|
| 52 |
+
"feat_proj_dropout": 0.1,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"freeze_feat_extract_train": true,
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.1,
|
| 58 |
+
"hidden_size": 768,
|
| 59 |
+
"id2label": {
|
| 60 |
+
"0": "fake",
|
| 61 |
+
"1": "real"
|
| 62 |
+
},
|
| 63 |
+
"initializer_range": 0.02,
|
| 64 |
+
"intermediate_size": 3072,
|
| 65 |
+
"label2id": {
|
| 66 |
+
"fake": "0",
|
| 67 |
+
"real": "1"
|
| 68 |
+
},
|
| 69 |
+
"layer_norm_eps": 1e-05,
|
| 70 |
+
"layerdrop": 0.0,
|
| 71 |
+
"mask_channel_length": 10,
|
| 72 |
+
"mask_channel_min_space": 1,
|
| 73 |
+
"mask_channel_other": 0.0,
|
| 74 |
+
"mask_channel_prob": 0.0,
|
| 75 |
+
"mask_channel_selection": "static",
|
| 76 |
+
"mask_feature_length": 10,
|
| 77 |
+
"mask_feature_min_masks": 0,
|
| 78 |
+
"mask_feature_prob": 0.0,
|
| 79 |
+
"mask_time_length": 10,
|
| 80 |
+
"mask_time_min_masks": 2,
|
| 81 |
+
"mask_time_min_space": 1,
|
| 82 |
+
"mask_time_other": 0.0,
|
| 83 |
+
"mask_time_prob": 0.05,
|
| 84 |
+
"mask_time_selection": "static",
|
| 85 |
+
"model_type": "wav2vec2",
|
| 86 |
+
"no_mask_channel_overlap": false,
|
| 87 |
+
"no_mask_time_overlap": false,
|
| 88 |
+
"num_adapter_layers": 3,
|
| 89 |
+
"num_attention_heads": 12,
|
| 90 |
+
"num_codevector_groups": 2,
|
| 91 |
+
"num_codevectors_per_group": 320,
|
| 92 |
+
"num_conv_pos_embedding_groups": 16,
|
| 93 |
+
"num_conv_pos_embeddings": 128,
|
| 94 |
+
"num_feat_extract_layers": 7,
|
| 95 |
+
"num_hidden_layers": 12,
|
| 96 |
+
"num_negatives": 100,
|
| 97 |
+
"output_hidden_size": 768,
|
| 98 |
+
"pad_token_id": 0,
|
| 99 |
+
"proj_codevector_dim": 256,
|
| 100 |
+
"tdnn_dilation": [
|
| 101 |
+
1,
|
| 102 |
+
2,
|
| 103 |
+
3,
|
| 104 |
+
1,
|
| 105 |
+
1
|
| 106 |
+
],
|
| 107 |
+
"tdnn_dim": [
|
| 108 |
+
512,
|
| 109 |
+
512,
|
| 110 |
+
512,
|
| 111 |
+
512,
|
| 112 |
+
1500
|
| 113 |
+
],
|
| 114 |
+
"tdnn_kernel": [
|
| 115 |
+
5,
|
| 116 |
+
3,
|
| 117 |
+
3,
|
| 118 |
+
1,
|
| 119 |
+
1
|
| 120 |
+
],
|
| 121 |
+
"transformers_version": "4.57.3",
|
| 122 |
+
"use_weighted_layer_sum": false,
|
| 123 |
+
"vocab_size": 32,
|
| 124 |
+
"xvector_output_dim": 512
|
| 125 |
+
}
|
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61f046095e067203694eb7ac3b56101f802c222508ff36c0e8a4fbc1f72d4125
|
| 3 |
+
size 378302360
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3789a0f05d3e97624e349985237e00b70832481cd75b893e1d50304972007da2
|
| 3 |
+
size 756732602
|
last-checkpoint/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": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca69c562ea24f9a8a4e249ce778e6aa3dd1db2c84993f5499e5f9500d2edad8e
|
| 3 |
+
size 14308
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5699a0932df3dd97f15fcfcceb2d361d521d7117e842cbdb8f8aaaa5ca19c383
|
| 3 |
+
size 1064
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,386 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 496,
|
| 3 |
+
"best_metric": 0.5052976791120081,
|
| 4 |
+
"best_model_checkpoint": "Deeepfake-audio-Recognition/checkpoint-496",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 496,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.020181634712411706,
|
| 14 |
+
"grad_norm": 0.6100882291793823,
|
| 15 |
+
"learning_rate": 5.399999999999999e-05,
|
| 16 |
+
"loss": 0.6925,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.04036326942482341,
|
| 21 |
+
"grad_norm": 4.445184230804443,
|
| 22 |
+
"learning_rate": 0.00011399999999999999,
|
| 23 |
+
"loss": 0.6948,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.060544904137235116,
|
| 28 |
+
"grad_norm": 2.134990692138672,
|
| 29 |
+
"learning_rate": 0.00017399999999999997,
|
| 30 |
+
"loss": 0.6859,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08072653884964683,
|
| 35 |
+
"grad_norm": 0.7902814149856567,
|
| 36 |
+
"learning_rate": 0.000234,
|
| 37 |
+
"loss": 0.7172,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.10090817356205853,
|
| 42 |
+
"grad_norm": 0.5187829732894897,
|
| 43 |
+
"learning_rate": 0.000294,
|
| 44 |
+
"loss": 0.698,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.12108980827447023,
|
| 49 |
+
"grad_norm": 0.06201840192079544,
|
| 50 |
+
"learning_rate": 0.00029394618834080715,
|
| 51 |
+
"loss": 0.6939,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.14127144298688193,
|
| 56 |
+
"grad_norm": 0.3845376968383789,
|
| 57 |
+
"learning_rate": 0.000287219730941704,
|
| 58 |
+
"loss": 0.6893,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.16145307769929365,
|
| 63 |
+
"grad_norm": 0.10666169226169586,
|
| 64 |
+
"learning_rate": 0.0002804932735426009,
|
| 65 |
+
"loss": 0.6989,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.18163471241170534,
|
| 70 |
+
"grad_norm": 0.0453961119055748,
|
| 71 |
+
"learning_rate": 0.0002737668161434977,
|
| 72 |
+
"loss": 0.6962,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.20181634712411706,
|
| 77 |
+
"grad_norm": 0.3139711320400238,
|
| 78 |
+
"learning_rate": 0.0002670403587443946,
|
| 79 |
+
"loss": 0.6969,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.22199798183652875,
|
| 84 |
+
"grad_norm": 0.08844541013240814,
|
| 85 |
+
"learning_rate": 0.00026031390134529145,
|
| 86 |
+
"loss": 0.6895,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.24217961654894046,
|
| 91 |
+
"grad_norm": 0.21342194080352783,
|
| 92 |
+
"learning_rate": 0.0002535874439461883,
|
| 93 |
+
"loss": 0.6964,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.2623612512613522,
|
| 98 |
+
"grad_norm": 0.21850763261318207,
|
| 99 |
+
"learning_rate": 0.0002468609865470852,
|
| 100 |
+
"loss": 0.6946,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.28254288597376387,
|
| 105 |
+
"grad_norm": 0.3530184328556061,
|
| 106 |
+
"learning_rate": 0.00024013452914798202,
|
| 107 |
+
"loss": 0.6928,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.30272452068617556,
|
| 112 |
+
"grad_norm": 0.11930827051401138,
|
| 113 |
+
"learning_rate": 0.00023340807174887892,
|
| 114 |
+
"loss": 0.6951,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.3229061553985873,
|
| 119 |
+
"grad_norm": 0.25173401832580566,
|
| 120 |
+
"learning_rate": 0.00022668161434977576,
|
| 121 |
+
"loss": 0.6934,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.343087790110999,
|
| 126 |
+
"grad_norm": 0.25978365540504456,
|
| 127 |
+
"learning_rate": 0.00021995515695067262,
|
| 128 |
+
"loss": 0.6947,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3632694248234107,
|
| 133 |
+
"grad_norm": 0.07770789414644241,
|
| 134 |
+
"learning_rate": 0.00021322869955156952,
|
| 135 |
+
"loss": 0.6936,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3834510595358224,
|
| 140 |
+
"grad_norm": 0.01727680303156376,
|
| 141 |
+
"learning_rate": 0.00020650224215246636,
|
| 142 |
+
"loss": 0.6939,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4036326942482341,
|
| 147 |
+
"grad_norm": 0.11968690156936646,
|
| 148 |
+
"learning_rate": 0.00019977578475336322,
|
| 149 |
+
"loss": 0.6938,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.4238143289606458,
|
| 154 |
+
"grad_norm": 0.21573954820632935,
|
| 155 |
+
"learning_rate": 0.00019304932735426006,
|
| 156 |
+
"loss": 0.6891,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4439959636730575,
|
| 161 |
+
"grad_norm": 0.2965114414691925,
|
| 162 |
+
"learning_rate": 0.00018632286995515693,
|
| 163 |
+
"loss": 0.7002,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.46417759838546924,
|
| 168 |
+
"grad_norm": 0.21291188895702362,
|
| 169 |
+
"learning_rate": 0.0001795964125560538,
|
| 170 |
+
"loss": 0.6933,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.4843592330978809,
|
| 175 |
+
"grad_norm": 0.19937728345394135,
|
| 176 |
+
"learning_rate": 0.00017286995515695066,
|
| 177 |
+
"loss": 0.693,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5045408678102926,
|
| 182 |
+
"grad_norm": 0.13156402111053467,
|
| 183 |
+
"learning_rate": 0.00016614349775784752,
|
| 184 |
+
"loss": 0.6934,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5247225025227044,
|
| 189 |
+
"grad_norm": 0.521071195602417,
|
| 190 |
+
"learning_rate": 0.00015941704035874436,
|
| 191 |
+
"loss": 0.6951,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.544904137235116,
|
| 196 |
+
"grad_norm": 0.09291291236877441,
|
| 197 |
+
"learning_rate": 0.00015269058295964126,
|
| 198 |
+
"loss": 0.6924,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5650857719475277,
|
| 203 |
+
"grad_norm": 0.023215485736727715,
|
| 204 |
+
"learning_rate": 0.0001459641255605381,
|
| 205 |
+
"loss": 0.6983,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.5852674066599395,
|
| 210 |
+
"grad_norm": 0.3948315978050232,
|
| 211 |
+
"learning_rate": 0.00013923766816143496,
|
| 212 |
+
"loss": 0.6927,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.6054490413723511,
|
| 217 |
+
"grad_norm": 0.20814433693885803,
|
| 218 |
+
"learning_rate": 0.00013251121076233183,
|
| 219 |
+
"loss": 0.6944,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.6256306760847629,
|
| 224 |
+
"grad_norm": 0.47286856174468994,
|
| 225 |
+
"learning_rate": 0.0001257847533632287,
|
| 226 |
+
"loss": 0.6932,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.6458123107971746,
|
| 231 |
+
"grad_norm": 0.19758112728595734,
|
| 232 |
+
"learning_rate": 0.00011905829596412555,
|
| 233 |
+
"loss": 0.6933,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.6659939455095862,
|
| 238 |
+
"grad_norm": 0.20121727883815765,
|
| 239 |
+
"learning_rate": 0.00011233183856502243,
|
| 240 |
+
"loss": 0.6933,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.686175580221998,
|
| 245 |
+
"grad_norm": 0.02322172187268734,
|
| 246 |
+
"learning_rate": 0.00010560538116591928,
|
| 247 |
+
"loss": 0.6929,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.7063572149344097,
|
| 252 |
+
"grad_norm": 0.10014554113149643,
|
| 253 |
+
"learning_rate": 9.887892376681613e-05,
|
| 254 |
+
"loss": 0.6923,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.7265388496468214,
|
| 259 |
+
"grad_norm": 0.09777415543794632,
|
| 260 |
+
"learning_rate": 9.2152466367713e-05,
|
| 261 |
+
"loss": 0.6925,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.7467204843592331,
|
| 266 |
+
"grad_norm": 0.1630220115184784,
|
| 267 |
+
"learning_rate": 8.542600896860985e-05,
|
| 268 |
+
"loss": 0.6947,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.7669021190716448,
|
| 273 |
+
"grad_norm": 0.10113658010959625,
|
| 274 |
+
"learning_rate": 7.869955156950672e-05,
|
| 275 |
+
"loss": 0.6911,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.7870837537840565,
|
| 280 |
+
"grad_norm": 0.23644621670246124,
|
| 281 |
+
"learning_rate": 7.197309417040358e-05,
|
| 282 |
+
"loss": 0.6949,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.8072653884964682,
|
| 287 |
+
"grad_norm": 0.0247635617852211,
|
| 288 |
+
"learning_rate": 6.524663677130043e-05,
|
| 289 |
+
"loss": 0.6928,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.82744702320888,
|
| 294 |
+
"grad_norm": 0.04597044363617897,
|
| 295 |
+
"learning_rate": 5.852017937219731e-05,
|
| 296 |
+
"loss": 0.6931,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.8476286579212916,
|
| 301 |
+
"grad_norm": 0.10972382128238678,
|
| 302 |
+
"learning_rate": 5.1793721973094166e-05,
|
| 303 |
+
"loss": 0.6922,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.8678102926337034,
|
| 308 |
+
"grad_norm": 0.026838891208171844,
|
| 309 |
+
"learning_rate": 4.5067264573991026e-05,
|
| 310 |
+
"loss": 0.6933,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.887991927346115,
|
| 315 |
+
"grad_norm": 0.04809186980128288,
|
| 316 |
+
"learning_rate": 3.834080717488789e-05,
|
| 317 |
+
"loss": 0.6934,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.9081735620585267,
|
| 322 |
+
"grad_norm": 0.05220267176628113,
|
| 323 |
+
"learning_rate": 3.161434977578475e-05,
|
| 324 |
+
"loss": 0.6942,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.9283551967709385,
|
| 329 |
+
"grad_norm": 0.0148994205519557,
|
| 330 |
+
"learning_rate": 2.4887892376681614e-05,
|
| 331 |
+
"loss": 0.6936,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.9485368314833501,
|
| 336 |
+
"grad_norm": 0.07287449389696121,
|
| 337 |
+
"learning_rate": 1.8161434977578473e-05,
|
| 338 |
+
"loss": 0.6932,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.9687184661957619,
|
| 343 |
+
"grad_norm": 0.21053215861320496,
|
| 344 |
+
"learning_rate": 1.1434977578475336e-05,
|
| 345 |
+
"loss": 0.6926,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.9889001009081736,
|
| 350 |
+
"grad_norm": 0.1443960815668106,
|
| 351 |
+
"learning_rate": 4.708520179372197e-06,
|
| 352 |
+
"loss": 0.694,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.0,
|
| 357 |
+
"eval_accuracy": 0.5052976791120081,
|
| 358 |
+
"eval_loss": 0.693091094493866,
|
| 359 |
+
"eval_runtime": 89.1283,
|
| 360 |
+
"eval_samples_per_second": 44.475,
|
| 361 |
+
"eval_steps_per_second": 5.565,
|
| 362 |
+
"step": 496
|
| 363 |
+
}
|
| 364 |
+
],
|
| 365 |
+
"logging_steps": 10,
|
| 366 |
+
"max_steps": 496,
|
| 367 |
+
"num_input_tokens_seen": 0,
|
| 368 |
+
"num_train_epochs": 1,
|
| 369 |
+
"save_steps": 500,
|
| 370 |
+
"stateful_callbacks": {
|
| 371 |
+
"TrainerControl": {
|
| 372 |
+
"args": {
|
| 373 |
+
"should_epoch_stop": false,
|
| 374 |
+
"should_evaluate": false,
|
| 375 |
+
"should_log": false,
|
| 376 |
+
"should_save": true,
|
| 377 |
+
"should_training_stop": true
|
| 378 |
+
},
|
| 379 |
+
"attributes": {}
|
| 380 |
+
}
|
| 381 |
+
},
|
| 382 |
+
"total_flos": 1.4392356324192e+17,
|
| 383 |
+
"train_batch_size": 8,
|
| 384 |
+
"trial_name": null,
|
| 385 |
+
"trial_params": null
|
| 386 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0317a4be8305d7c63b70fad14cde7804b597568fd2181ea062cb92553a0917d9
|
| 3 |
+
size 5496
|