Commit
·
e3717e2
1
Parent(s):
9d1188a
yashcode00/wav2vec2-large-xlsr-indian-language-classification-featureExtractor
Browse files- README.md +62 -0
- all_results.json +15 -0
- config.json +146 -0
- eval_results.json +9 -0
- preprocessor_config.json +10 -0
- pytorch_model.bin +3 -0
- train_results.json +9 -0
- trainer_state.json +1180 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-large-xlsr-53
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: wav2vec2-large-xlsr-indian-language-classification-featureExtractor
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# wav2vec2-large-xlsr-indian-language-classification-featureExtractor
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.5192
|
| 21 |
+
- Accuracy: 0.7529
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 64
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 100
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 54 |
+
| 0.1136 | 52.81 | 10000 | 1.4509 | 0.7108 |
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
### Framework versions
|
| 58 |
+
|
| 59 |
+
- Transformers 4.32.1
|
| 60 |
+
- Pytorch 2.0.0
|
| 61 |
+
- Datasets 2.11.0
|
| 62 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 99.8,
|
| 3 |
+
"eval_accuracy": 0.7528877854347229,
|
| 4 |
+
"eval_loss": 1.519213080406189,
|
| 5 |
+
"eval_runtime": 48.7307,
|
| 6 |
+
"eval_samples": 2424,
|
| 7 |
+
"eval_samples_per_second": 49.743,
|
| 8 |
+
"eval_steps_per_second": 6.218,
|
| 9 |
+
"total_flos": 3.6752439370752e+19,
|
| 10 |
+
"train_loss": 0.3331463608035335,
|
| 11 |
+
"train_runtime": 40683.5838,
|
| 12 |
+
"train_samples": 12120,
|
| 13 |
+
"train_samples_per_second": 29.791,
|
| 14 |
+
"train_steps_per_second": 0.465
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForSpeechClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 768,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": true,
|
| 18 |
+
"conv_dim": [
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
3,
|
| 33 |
+
2,
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"conv_stride": [
|
| 37 |
+
5,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2
|
| 44 |
+
],
|
| 45 |
+
"ctc_loss_reduction": "sum",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": true,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "layer",
|
| 53 |
+
"feat_proj_dropout": 0.1,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.0,
|
| 56 |
+
"finetuning_task": "wav2vec2_clf",
|
| 57 |
+
"gradient_checkpointing": false,
|
| 58 |
+
"hidden_act": "gelu",
|
| 59 |
+
"hidden_dropout": 0.1,
|
| 60 |
+
"hidden_size": 1024,
|
| 61 |
+
"id2label": {
|
| 62 |
+
"0": "asm",
|
| 63 |
+
"1": "ben",
|
| 64 |
+
"2": "eng",
|
| 65 |
+
"3": "guj",
|
| 66 |
+
"4": "hin",
|
| 67 |
+
"5": "kan",
|
| 68 |
+
"6": "mal",
|
| 69 |
+
"7": "mar",
|
| 70 |
+
"8": "odi",
|
| 71 |
+
"9": "tam",
|
| 72 |
+
"10": "tel"
|
| 73 |
+
},
|
| 74 |
+
"initializer_range": 0.02,
|
| 75 |
+
"intermediate_size": 4096,
|
| 76 |
+
"label2id": {
|
| 77 |
+
"asm": 0,
|
| 78 |
+
"ben": 1,
|
| 79 |
+
"eng": 2,
|
| 80 |
+
"guj": 3,
|
| 81 |
+
"hin": 4,
|
| 82 |
+
"kan": 5,
|
| 83 |
+
"mal": 6,
|
| 84 |
+
"mar": 7,
|
| 85 |
+
"odi": 8,
|
| 86 |
+
"tam": 9,
|
| 87 |
+
"tel": 10
|
| 88 |
+
},
|
| 89 |
+
"layer_norm_eps": 1e-05,
|
| 90 |
+
"layerdrop": 0.1,
|
| 91 |
+
"mask_channel_length": 10,
|
| 92 |
+
"mask_channel_min_space": 1,
|
| 93 |
+
"mask_channel_other": 0.0,
|
| 94 |
+
"mask_channel_prob": 0.0,
|
| 95 |
+
"mask_channel_selection": "static",
|
| 96 |
+
"mask_feature_length": 10,
|
| 97 |
+
"mask_feature_min_masks": 0,
|
| 98 |
+
"mask_feature_prob": 0.0,
|
| 99 |
+
"mask_time_length": 10,
|
| 100 |
+
"mask_time_min_masks": 2,
|
| 101 |
+
"mask_time_min_space": 1,
|
| 102 |
+
"mask_time_other": 0.0,
|
| 103 |
+
"mask_time_prob": 0.075,
|
| 104 |
+
"mask_time_selection": "static",
|
| 105 |
+
"model_type": "wav2vec2",
|
| 106 |
+
"num_adapter_layers": 3,
|
| 107 |
+
"num_attention_heads": 16,
|
| 108 |
+
"num_codevector_groups": 2,
|
| 109 |
+
"num_codevectors_per_group": 320,
|
| 110 |
+
"num_conv_pos_embedding_groups": 16,
|
| 111 |
+
"num_conv_pos_embeddings": 128,
|
| 112 |
+
"num_feat_extract_layers": 7,
|
| 113 |
+
"num_hidden_layers": 24,
|
| 114 |
+
"num_negatives": 100,
|
| 115 |
+
"output_hidden_size": 1024,
|
| 116 |
+
"pad_token_id": 0,
|
| 117 |
+
"pooling_mode": "mean",
|
| 118 |
+
"problem_type": "single_label_classification",
|
| 119 |
+
"proj_codevector_dim": 768,
|
| 120 |
+
"tdnn_dilation": [
|
| 121 |
+
1,
|
| 122 |
+
2,
|
| 123 |
+
3,
|
| 124 |
+
1,
|
| 125 |
+
1
|
| 126 |
+
],
|
| 127 |
+
"tdnn_dim": [
|
| 128 |
+
512,
|
| 129 |
+
512,
|
| 130 |
+
512,
|
| 131 |
+
512,
|
| 132 |
+
1500
|
| 133 |
+
],
|
| 134 |
+
"tdnn_kernel": [
|
| 135 |
+
5,
|
| 136 |
+
3,
|
| 137 |
+
3,
|
| 138 |
+
1,
|
| 139 |
+
1
|
| 140 |
+
],
|
| 141 |
+
"torch_dtype": "float32",
|
| 142 |
+
"transformers_version": "4.32.1",
|
| 143 |
+
"use_weighted_layer_sum": false,
|
| 144 |
+
"vocab_size": 32,
|
| 145 |
+
"xvector_output_dim": 512
|
| 146 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 99.8,
|
| 3 |
+
"eval_accuracy": 0.7528877854347229,
|
| 4 |
+
"eval_loss": 1.519213080406189,
|
| 5 |
+
"eval_runtime": 48.7307,
|
| 6 |
+
"eval_samples": 2424,
|
| 7 |
+
"eval_samples_per_second": 49.743,
|
| 8 |
+
"eval_steps_per_second": 6.218
|
| 9 |
+
}
|
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": false,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:891bea4361102bde3e80265f97be89f91a22bb4eb116a7b395690848cd130186
|
| 3 |
+
size 1266146037
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 99.8,
|
| 3 |
+
"total_flos": 3.6752439370752e+19,
|
| 4 |
+
"train_loss": 0.3331463608035335,
|
| 5 |
+
"train_runtime": 40683.5838,
|
| 6 |
+
"train_samples": 12120,
|
| 7 |
+
"train_samples_per_second": 29.791,
|
| 8 |
+
"train_steps_per_second": 0.465
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1180 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 99.8019801980198,
|
| 5 |
+
"eval_steps": 10000,
|
| 6 |
+
"global_step": 18900,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.53,
|
| 13 |
+
"learning_rate": 4.974074074074074e-05,
|
| 14 |
+
"loss": 2.3707,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.06,
|
| 19 |
+
"learning_rate": 4.947883597883598e-05,
|
| 20 |
+
"loss": 2.3317,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.58,
|
| 25 |
+
"learning_rate": 4.9216931216931214e-05,
|
| 26 |
+
"loss": 2.2586,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.11,
|
| 31 |
+
"learning_rate": 4.895238095238096e-05,
|
| 32 |
+
"loss": 2.1762,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.64,
|
| 37 |
+
"learning_rate": 4.8690476190476194e-05,
|
| 38 |
+
"loss": 2.0583,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.17,
|
| 43 |
+
"learning_rate": 4.842592592592593e-05,
|
| 44 |
+
"loss": 1.9666,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.7,
|
| 49 |
+
"learning_rate": 4.8161375661375666e-05,
|
| 50 |
+
"loss": 1.8805,
|
| 51 |
+
"step": 700
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.22,
|
| 55 |
+
"learning_rate": 4.78968253968254e-05,
|
| 56 |
+
"loss": 1.7925,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.75,
|
| 61 |
+
"learning_rate": 4.763227513227513e-05,
|
| 62 |
+
"loss": 1.668,
|
| 63 |
+
"step": 900
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 5.28,
|
| 67 |
+
"learning_rate": 4.7367724867724874e-05,
|
| 68 |
+
"loss": 1.582,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.81,
|
| 73 |
+
"learning_rate": 4.71031746031746e-05,
|
| 74 |
+
"loss": 1.517,
|
| 75 |
+
"step": 1100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 6.34,
|
| 79 |
+
"learning_rate": 4.6838624338624346e-05,
|
| 80 |
+
"loss": 1.4208,
|
| 81 |
+
"step": 1200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 6.86,
|
| 85 |
+
"learning_rate": 4.6574074074074076e-05,
|
| 86 |
+
"loss": 1.3843,
|
| 87 |
+
"step": 1300
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 7.39,
|
| 91 |
+
"learning_rate": 4.630952380952381e-05,
|
| 92 |
+
"loss": 1.2794,
|
| 93 |
+
"step": 1400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.92,
|
| 97 |
+
"learning_rate": 4.604497354497355e-05,
|
| 98 |
+
"loss": 1.2562,
|
| 99 |
+
"step": 1500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 8.45,
|
| 103 |
+
"learning_rate": 4.5780423280423284e-05,
|
| 104 |
+
"loss": 1.1514,
|
| 105 |
+
"step": 1600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 8.98,
|
| 109 |
+
"learning_rate": 4.551587301587302e-05,
|
| 110 |
+
"loss": 1.1387,
|
| 111 |
+
"step": 1700
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 9.5,
|
| 115 |
+
"learning_rate": 4.5251322751322756e-05,
|
| 116 |
+
"loss": 1.0741,
|
| 117 |
+
"step": 1800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 10.03,
|
| 121 |
+
"learning_rate": 4.4986772486772485e-05,
|
| 122 |
+
"loss": 1.0015,
|
| 123 |
+
"step": 1900
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 10.56,
|
| 127 |
+
"learning_rate": 4.472222222222223e-05,
|
| 128 |
+
"loss": 0.9665,
|
| 129 |
+
"step": 2000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 11.09,
|
| 133 |
+
"learning_rate": 4.445767195767196e-05,
|
| 134 |
+
"loss": 0.902,
|
| 135 |
+
"step": 2100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 11.62,
|
| 139 |
+
"learning_rate": 4.41931216931217e-05,
|
| 140 |
+
"loss": 0.8938,
|
| 141 |
+
"step": 2200
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 12.15,
|
| 145 |
+
"learning_rate": 4.392857142857143e-05,
|
| 146 |
+
"loss": 0.8334,
|
| 147 |
+
"step": 2300
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 12.67,
|
| 151 |
+
"learning_rate": 4.3664021164021166e-05,
|
| 152 |
+
"loss": 0.787,
|
| 153 |
+
"step": 2400
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 13.2,
|
| 157 |
+
"learning_rate": 4.33994708994709e-05,
|
| 158 |
+
"loss": 0.7729,
|
| 159 |
+
"step": 2500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 13.73,
|
| 163 |
+
"learning_rate": 4.313492063492064e-05,
|
| 164 |
+
"loss": 0.7254,
|
| 165 |
+
"step": 2600
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 14.26,
|
| 169 |
+
"learning_rate": 4.2870370370370374e-05,
|
| 170 |
+
"loss": 0.6632,
|
| 171 |
+
"step": 2700
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 14.79,
|
| 175 |
+
"learning_rate": 4.260582010582011e-05,
|
| 176 |
+
"loss": 0.6737,
|
| 177 |
+
"step": 2800
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 15.31,
|
| 181 |
+
"learning_rate": 4.2341269841269846e-05,
|
| 182 |
+
"loss": 0.6641,
|
| 183 |
+
"step": 2900
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 15.84,
|
| 187 |
+
"learning_rate": 4.207671957671958e-05,
|
| 188 |
+
"loss": 0.5873,
|
| 189 |
+
"step": 3000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 16.37,
|
| 193 |
+
"learning_rate": 4.181216931216931e-05,
|
| 194 |
+
"loss": 0.5618,
|
| 195 |
+
"step": 3100
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 16.9,
|
| 199 |
+
"learning_rate": 4.1547619047619054e-05,
|
| 200 |
+
"loss": 0.5628,
|
| 201 |
+
"step": 3200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 17.43,
|
| 205 |
+
"learning_rate": 4.1283068783068784e-05,
|
| 206 |
+
"loss": 0.5301,
|
| 207 |
+
"step": 3300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 17.95,
|
| 211 |
+
"learning_rate": 4.101851851851852e-05,
|
| 212 |
+
"loss": 0.533,
|
| 213 |
+
"step": 3400
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 18.48,
|
| 217 |
+
"learning_rate": 4.0753968253968256e-05,
|
| 218 |
+
"loss": 0.4929,
|
| 219 |
+
"step": 3500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 19.01,
|
| 223 |
+
"learning_rate": 4.048941798941799e-05,
|
| 224 |
+
"loss": 0.4758,
|
| 225 |
+
"step": 3600
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 19.54,
|
| 229 |
+
"learning_rate": 4.022486772486773e-05,
|
| 230 |
+
"loss": 0.4542,
|
| 231 |
+
"step": 3700
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 20.07,
|
| 235 |
+
"learning_rate": 3.9960317460317464e-05,
|
| 236 |
+
"loss": 0.4134,
|
| 237 |
+
"step": 3800
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 20.59,
|
| 241 |
+
"learning_rate": 3.96984126984127e-05,
|
| 242 |
+
"loss": 0.4194,
|
| 243 |
+
"step": 3900
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 21.12,
|
| 247 |
+
"learning_rate": 3.943386243386244e-05,
|
| 248 |
+
"loss": 0.4098,
|
| 249 |
+
"step": 4000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 21.65,
|
| 253 |
+
"learning_rate": 3.916931216931217e-05,
|
| 254 |
+
"loss": 0.3907,
|
| 255 |
+
"step": 4100
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 22.18,
|
| 259 |
+
"learning_rate": 3.89047619047619e-05,
|
| 260 |
+
"loss": 0.4125,
|
| 261 |
+
"step": 4200
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 22.71,
|
| 265 |
+
"learning_rate": 3.8640211640211645e-05,
|
| 266 |
+
"loss": 0.3631,
|
| 267 |
+
"step": 4300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 23.23,
|
| 271 |
+
"learning_rate": 3.8375661375661375e-05,
|
| 272 |
+
"loss": 0.3434,
|
| 273 |
+
"step": 4400
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 23.76,
|
| 277 |
+
"learning_rate": 3.811111111111112e-05,
|
| 278 |
+
"loss": 0.3318,
|
| 279 |
+
"step": 4500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 24.29,
|
| 283 |
+
"learning_rate": 3.784656084656085e-05,
|
| 284 |
+
"loss": 0.3506,
|
| 285 |
+
"step": 4600
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 24.82,
|
| 289 |
+
"learning_rate": 3.758201058201058e-05,
|
| 290 |
+
"loss": 0.3299,
|
| 291 |
+
"step": 4700
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 25.35,
|
| 295 |
+
"learning_rate": 3.731746031746032e-05,
|
| 296 |
+
"loss": 0.2909,
|
| 297 |
+
"step": 4800
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 25.87,
|
| 301 |
+
"learning_rate": 3.7052910052910055e-05,
|
| 302 |
+
"loss": 0.312,
|
| 303 |
+
"step": 4900
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 26.4,
|
| 307 |
+
"learning_rate": 3.678835978835979e-05,
|
| 308 |
+
"loss": 0.2961,
|
| 309 |
+
"step": 5000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 26.93,
|
| 313 |
+
"learning_rate": 3.652380952380953e-05,
|
| 314 |
+
"loss": 0.311,
|
| 315 |
+
"step": 5100
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 27.46,
|
| 319 |
+
"learning_rate": 3.6259259259259256e-05,
|
| 320 |
+
"loss": 0.288,
|
| 321 |
+
"step": 5200
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 27.99,
|
| 325 |
+
"learning_rate": 3.5994708994709e-05,
|
| 326 |
+
"loss": 0.2783,
|
| 327 |
+
"step": 5300
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 28.51,
|
| 331 |
+
"learning_rate": 3.573015873015873e-05,
|
| 332 |
+
"loss": 0.2649,
|
| 333 |
+
"step": 5400
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 29.04,
|
| 337 |
+
"learning_rate": 3.546560846560847e-05,
|
| 338 |
+
"loss": 0.2573,
|
| 339 |
+
"step": 5500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 29.57,
|
| 343 |
+
"learning_rate": 3.52010582010582e-05,
|
| 344 |
+
"loss": 0.2536,
|
| 345 |
+
"step": 5600
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 30.1,
|
| 349 |
+
"learning_rate": 3.493650793650794e-05,
|
| 350 |
+
"loss": 0.2528,
|
| 351 |
+
"step": 5700
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 30.63,
|
| 355 |
+
"learning_rate": 3.467195767195767e-05,
|
| 356 |
+
"loss": 0.232,
|
| 357 |
+
"step": 5800
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 31.16,
|
| 361 |
+
"learning_rate": 3.440740740740741e-05,
|
| 362 |
+
"loss": 0.2334,
|
| 363 |
+
"step": 5900
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 31.68,
|
| 367 |
+
"learning_rate": 3.4142857142857145e-05,
|
| 368 |
+
"loss": 0.2231,
|
| 369 |
+
"step": 6000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 32.21,
|
| 373 |
+
"learning_rate": 3.387830687830688e-05,
|
| 374 |
+
"loss": 0.2201,
|
| 375 |
+
"step": 6100
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 32.74,
|
| 379 |
+
"learning_rate": 3.361375661375662e-05,
|
| 380 |
+
"loss": 0.2045,
|
| 381 |
+
"step": 6200
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 33.27,
|
| 385 |
+
"learning_rate": 3.334920634920635e-05,
|
| 386 |
+
"loss": 0.2221,
|
| 387 |
+
"step": 6300
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 33.8,
|
| 391 |
+
"learning_rate": 3.308465608465608e-05,
|
| 392 |
+
"loss": 0.2086,
|
| 393 |
+
"step": 6400
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 34.32,
|
| 397 |
+
"learning_rate": 3.2820105820105826e-05,
|
| 398 |
+
"loss": 0.2108,
|
| 399 |
+
"step": 6500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 34.85,
|
| 403 |
+
"learning_rate": 3.2555555555555555e-05,
|
| 404 |
+
"loss": 0.209,
|
| 405 |
+
"step": 6600
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 35.38,
|
| 409 |
+
"learning_rate": 3.229100529100529e-05,
|
| 410 |
+
"loss": 0.1968,
|
| 411 |
+
"step": 6700
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 35.91,
|
| 415 |
+
"learning_rate": 3.202645502645503e-05,
|
| 416 |
+
"loss": 0.2068,
|
| 417 |
+
"step": 6800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 36.44,
|
| 421 |
+
"learning_rate": 3.176190476190476e-05,
|
| 422 |
+
"loss": 0.1827,
|
| 423 |
+
"step": 6900
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 36.96,
|
| 427 |
+
"learning_rate": 3.14973544973545e-05,
|
| 428 |
+
"loss": 0.1966,
|
| 429 |
+
"step": 7000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 37.49,
|
| 433 |
+
"learning_rate": 3.1232804232804235e-05,
|
| 434 |
+
"loss": 0.1794,
|
| 435 |
+
"step": 7100
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 38.02,
|
| 439 |
+
"learning_rate": 3.096825396825397e-05,
|
| 440 |
+
"loss": 0.1737,
|
| 441 |
+
"step": 7200
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 38.55,
|
| 445 |
+
"learning_rate": 3.070370370370371e-05,
|
| 446 |
+
"loss": 0.1721,
|
| 447 |
+
"step": 7300
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 39.08,
|
| 451 |
+
"learning_rate": 3.043915343915344e-05,
|
| 452 |
+
"loss": 0.1928,
|
| 453 |
+
"step": 7400
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 39.6,
|
| 457 |
+
"learning_rate": 3.0174603174603176e-05,
|
| 458 |
+
"loss": 0.164,
|
| 459 |
+
"step": 7500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 40.13,
|
| 463 |
+
"learning_rate": 2.991005291005291e-05,
|
| 464 |
+
"loss": 0.1651,
|
| 465 |
+
"step": 7600
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 40.66,
|
| 469 |
+
"learning_rate": 2.964550264550265e-05,
|
| 470 |
+
"loss": 0.1533,
|
| 471 |
+
"step": 7700
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 41.19,
|
| 475 |
+
"learning_rate": 2.938095238095238e-05,
|
| 476 |
+
"loss": 0.1663,
|
| 477 |
+
"step": 7800
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 41.72,
|
| 481 |
+
"learning_rate": 2.911640211640212e-05,
|
| 482 |
+
"loss": 0.1473,
|
| 483 |
+
"step": 7900
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 42.24,
|
| 487 |
+
"learning_rate": 2.8851851851851853e-05,
|
| 488 |
+
"loss": 0.1562,
|
| 489 |
+
"step": 8000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 42.77,
|
| 493 |
+
"learning_rate": 2.858730158730159e-05,
|
| 494 |
+
"loss": 0.1372,
|
| 495 |
+
"step": 8100
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 43.3,
|
| 499 |
+
"learning_rate": 2.8322751322751322e-05,
|
| 500 |
+
"loss": 0.1479,
|
| 501 |
+
"step": 8200
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 43.83,
|
| 505 |
+
"learning_rate": 2.805820105820106e-05,
|
| 506 |
+
"loss": 0.1496,
|
| 507 |
+
"step": 8300
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 44.36,
|
| 511 |
+
"learning_rate": 2.7793650793650794e-05,
|
| 512 |
+
"loss": 0.1373,
|
| 513 |
+
"step": 8400
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 44.88,
|
| 517 |
+
"learning_rate": 2.7529100529100534e-05,
|
| 518 |
+
"loss": 0.1414,
|
| 519 |
+
"step": 8500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 45.41,
|
| 523 |
+
"learning_rate": 2.7264550264550266e-05,
|
| 524 |
+
"loss": 0.1411,
|
| 525 |
+
"step": 8600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 45.94,
|
| 529 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 530 |
+
"loss": 0.1349,
|
| 531 |
+
"step": 8700
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 46.47,
|
| 535 |
+
"learning_rate": 2.673809523809524e-05,
|
| 536 |
+
"loss": 0.1248,
|
| 537 |
+
"step": 8800
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 47.0,
|
| 541 |
+
"learning_rate": 2.6473544973544972e-05,
|
| 542 |
+
"loss": 0.1489,
|
| 543 |
+
"step": 8900
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 47.52,
|
| 547 |
+
"learning_rate": 2.620899470899471e-05,
|
| 548 |
+
"loss": 0.1311,
|
| 549 |
+
"step": 9000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 48.05,
|
| 553 |
+
"learning_rate": 2.5944444444444444e-05,
|
| 554 |
+
"loss": 0.1282,
|
| 555 |
+
"step": 9100
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 48.58,
|
| 559 |
+
"learning_rate": 2.567989417989418e-05,
|
| 560 |
+
"loss": 0.1367,
|
| 561 |
+
"step": 9200
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 49.11,
|
| 565 |
+
"learning_rate": 2.5415343915343913e-05,
|
| 566 |
+
"loss": 0.1209,
|
| 567 |
+
"step": 9300
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 49.64,
|
| 571 |
+
"learning_rate": 2.5150793650793652e-05,
|
| 572 |
+
"loss": 0.1416,
|
| 573 |
+
"step": 9400
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 50.17,
|
| 577 |
+
"learning_rate": 2.488624338624339e-05,
|
| 578 |
+
"loss": 0.132,
|
| 579 |
+
"step": 9500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 50.69,
|
| 583 |
+
"learning_rate": 2.4621693121693125e-05,
|
| 584 |
+
"loss": 0.111,
|
| 585 |
+
"step": 9600
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 51.22,
|
| 589 |
+
"learning_rate": 2.4357142857142857e-05,
|
| 590 |
+
"loss": 0.1004,
|
| 591 |
+
"step": 9700
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 51.75,
|
| 595 |
+
"learning_rate": 2.4092592592592593e-05,
|
| 596 |
+
"loss": 0.1118,
|
| 597 |
+
"step": 9800
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 52.28,
|
| 601 |
+
"learning_rate": 2.382804232804233e-05,
|
| 602 |
+
"loss": 0.1309,
|
| 603 |
+
"step": 9900
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 52.81,
|
| 607 |
+
"learning_rate": 2.3563492063492065e-05,
|
| 608 |
+
"loss": 0.1136,
|
| 609 |
+
"step": 10000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 52.81,
|
| 613 |
+
"eval_accuracy": 0.7108085751533508,
|
| 614 |
+
"eval_loss": 1.4509037733078003,
|
| 615 |
+
"eval_runtime": 49.9625,
|
| 616 |
+
"eval_samples_per_second": 48.516,
|
| 617 |
+
"eval_steps_per_second": 6.065,
|
| 618 |
+
"step": 10000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 53.33,
|
| 622 |
+
"learning_rate": 2.32989417989418e-05,
|
| 623 |
+
"loss": 0.1023,
|
| 624 |
+
"step": 10100
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 53.86,
|
| 628 |
+
"learning_rate": 2.3034391534391538e-05,
|
| 629 |
+
"loss": 0.1242,
|
| 630 |
+
"step": 10200
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 54.39,
|
| 634 |
+
"learning_rate": 2.276984126984127e-05,
|
| 635 |
+
"loss": 0.1162,
|
| 636 |
+
"step": 10300
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 54.92,
|
| 640 |
+
"learning_rate": 2.2505291005291006e-05,
|
| 641 |
+
"loss": 0.1228,
|
| 642 |
+
"step": 10400
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 55.45,
|
| 646 |
+
"learning_rate": 2.2240740740740743e-05,
|
| 647 |
+
"loss": 0.1087,
|
| 648 |
+
"step": 10500
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 55.97,
|
| 652 |
+
"learning_rate": 2.197619047619048e-05,
|
| 653 |
+
"loss": 0.1039,
|
| 654 |
+
"step": 10600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 56.5,
|
| 658 |
+
"learning_rate": 2.1711640211640215e-05,
|
| 659 |
+
"loss": 0.1059,
|
| 660 |
+
"step": 10700
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 57.03,
|
| 664 |
+
"learning_rate": 2.1447089947089947e-05,
|
| 665 |
+
"loss": 0.0999,
|
| 666 |
+
"step": 10800
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 57.56,
|
| 670 |
+
"learning_rate": 2.1182539682539683e-05,
|
| 671 |
+
"loss": 0.0937,
|
| 672 |
+
"step": 10900
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 58.09,
|
| 676 |
+
"learning_rate": 2.091798941798942e-05,
|
| 677 |
+
"loss": 0.0996,
|
| 678 |
+
"step": 11000
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 58.61,
|
| 682 |
+
"learning_rate": 2.0653439153439156e-05,
|
| 683 |
+
"loss": 0.0856,
|
| 684 |
+
"step": 11100
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 59.14,
|
| 688 |
+
"learning_rate": 2.0388888888888892e-05,
|
| 689 |
+
"loss": 0.1025,
|
| 690 |
+
"step": 11200
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 59.67,
|
| 694 |
+
"learning_rate": 2.0124338624338628e-05,
|
| 695 |
+
"loss": 0.0908,
|
| 696 |
+
"step": 11300
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 60.2,
|
| 700 |
+
"learning_rate": 1.985978835978836e-05,
|
| 701 |
+
"loss": 0.0873,
|
| 702 |
+
"step": 11400
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 60.73,
|
| 706 |
+
"learning_rate": 1.9595238095238097e-05,
|
| 707 |
+
"loss": 0.0959,
|
| 708 |
+
"step": 11500
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 61.25,
|
| 712 |
+
"learning_rate": 1.9330687830687833e-05,
|
| 713 |
+
"loss": 0.0967,
|
| 714 |
+
"step": 11600
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 61.78,
|
| 718 |
+
"learning_rate": 1.906613756613757e-05,
|
| 719 |
+
"loss": 0.0968,
|
| 720 |
+
"step": 11700
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 62.31,
|
| 724 |
+
"learning_rate": 1.8801587301587305e-05,
|
| 725 |
+
"loss": 0.083,
|
| 726 |
+
"step": 11800
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 62.84,
|
| 730 |
+
"learning_rate": 1.8537037037037037e-05,
|
| 731 |
+
"loss": 0.0831,
|
| 732 |
+
"step": 11900
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 63.37,
|
| 736 |
+
"learning_rate": 1.8272486772486774e-05,
|
| 737 |
+
"loss": 0.0938,
|
| 738 |
+
"step": 12000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 63.89,
|
| 742 |
+
"learning_rate": 1.800793650793651e-05,
|
| 743 |
+
"loss": 0.088,
|
| 744 |
+
"step": 12100
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 64.42,
|
| 748 |
+
"learning_rate": 1.7743386243386246e-05,
|
| 749 |
+
"loss": 0.0741,
|
| 750 |
+
"step": 12200
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 64.95,
|
| 754 |
+
"learning_rate": 1.7478835978835982e-05,
|
| 755 |
+
"loss": 0.0938,
|
| 756 |
+
"step": 12300
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 65.48,
|
| 760 |
+
"learning_rate": 1.7214285714285715e-05,
|
| 761 |
+
"loss": 0.0833,
|
| 762 |
+
"step": 12400
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 66.01,
|
| 766 |
+
"learning_rate": 1.694973544973545e-05,
|
| 767 |
+
"loss": 0.0803,
|
| 768 |
+
"step": 12500
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 66.53,
|
| 772 |
+
"learning_rate": 1.6685185185185187e-05,
|
| 773 |
+
"loss": 0.0702,
|
| 774 |
+
"step": 12600
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 67.06,
|
| 778 |
+
"learning_rate": 1.6420634920634923e-05,
|
| 779 |
+
"loss": 0.0783,
|
| 780 |
+
"step": 12700
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 67.59,
|
| 784 |
+
"learning_rate": 1.615608465608466e-05,
|
| 785 |
+
"loss": 0.0858,
|
| 786 |
+
"step": 12800
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 68.12,
|
| 790 |
+
"learning_rate": 1.5891534391534395e-05,
|
| 791 |
+
"loss": 0.0737,
|
| 792 |
+
"step": 12900
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 68.65,
|
| 796 |
+
"learning_rate": 1.5626984126984128e-05,
|
| 797 |
+
"loss": 0.0751,
|
| 798 |
+
"step": 13000
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 69.17,
|
| 802 |
+
"learning_rate": 1.5362433862433864e-05,
|
| 803 |
+
"loss": 0.0703,
|
| 804 |
+
"step": 13100
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 69.7,
|
| 808 |
+
"learning_rate": 1.51005291005291e-05,
|
| 809 |
+
"loss": 0.0626,
|
| 810 |
+
"step": 13200
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 70.23,
|
| 814 |
+
"learning_rate": 1.4835978835978837e-05,
|
| 815 |
+
"loss": 0.0747,
|
| 816 |
+
"step": 13300
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 70.76,
|
| 820 |
+
"learning_rate": 1.4571428571428573e-05,
|
| 821 |
+
"loss": 0.0763,
|
| 822 |
+
"step": 13400
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 71.29,
|
| 826 |
+
"learning_rate": 1.4309523809523811e-05,
|
| 827 |
+
"loss": 0.0777,
|
| 828 |
+
"step": 13500
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 71.82,
|
| 832 |
+
"learning_rate": 1.4044973544973547e-05,
|
| 833 |
+
"loss": 0.06,
|
| 834 |
+
"step": 13600
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 72.34,
|
| 838 |
+
"learning_rate": 1.3780423280423282e-05,
|
| 839 |
+
"loss": 0.0695,
|
| 840 |
+
"step": 13700
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 72.87,
|
| 844 |
+
"learning_rate": 1.3515873015873018e-05,
|
| 845 |
+
"loss": 0.0619,
|
| 846 |
+
"step": 13800
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 73.4,
|
| 850 |
+
"learning_rate": 1.325132275132275e-05,
|
| 851 |
+
"loss": 0.0689,
|
| 852 |
+
"step": 13900
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 73.93,
|
| 856 |
+
"learning_rate": 1.2986772486772487e-05,
|
| 857 |
+
"loss": 0.06,
|
| 858 |
+
"step": 14000
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 74.46,
|
| 862 |
+
"learning_rate": 1.2722222222222221e-05,
|
| 863 |
+
"loss": 0.0626,
|
| 864 |
+
"step": 14100
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 74.98,
|
| 868 |
+
"learning_rate": 1.2457671957671959e-05,
|
| 869 |
+
"loss": 0.0644,
|
| 870 |
+
"step": 14200
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 75.51,
|
| 874 |
+
"learning_rate": 1.2193121693121693e-05,
|
| 875 |
+
"loss": 0.0591,
|
| 876 |
+
"step": 14300
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 76.04,
|
| 880 |
+
"learning_rate": 1.192857142857143e-05,
|
| 881 |
+
"loss": 0.0584,
|
| 882 |
+
"step": 14400
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 76.57,
|
| 886 |
+
"learning_rate": 1.1664021164021165e-05,
|
| 887 |
+
"loss": 0.0521,
|
| 888 |
+
"step": 14500
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 77.1,
|
| 892 |
+
"learning_rate": 1.13994708994709e-05,
|
| 893 |
+
"loss": 0.0609,
|
| 894 |
+
"step": 14600
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 77.62,
|
| 898 |
+
"learning_rate": 1.1134920634920636e-05,
|
| 899 |
+
"loss": 0.0589,
|
| 900 |
+
"step": 14700
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 78.15,
|
| 904 |
+
"learning_rate": 1.087037037037037e-05,
|
| 905 |
+
"loss": 0.0581,
|
| 906 |
+
"step": 14800
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 78.68,
|
| 910 |
+
"learning_rate": 1.0605820105820106e-05,
|
| 911 |
+
"loss": 0.0714,
|
| 912 |
+
"step": 14900
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 79.21,
|
| 916 |
+
"learning_rate": 1.0341269841269842e-05,
|
| 917 |
+
"loss": 0.0511,
|
| 918 |
+
"step": 15000
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 79.74,
|
| 922 |
+
"learning_rate": 1.0076719576719577e-05,
|
| 923 |
+
"loss": 0.0541,
|
| 924 |
+
"step": 15100
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 80.26,
|
| 928 |
+
"learning_rate": 9.812169312169313e-06,
|
| 929 |
+
"loss": 0.0581,
|
| 930 |
+
"step": 15200
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 80.79,
|
| 934 |
+
"learning_rate": 9.547619047619049e-06,
|
| 935 |
+
"loss": 0.0535,
|
| 936 |
+
"step": 15300
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 81.32,
|
| 940 |
+
"learning_rate": 9.283068783068783e-06,
|
| 941 |
+
"loss": 0.0464,
|
| 942 |
+
"step": 15400
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 81.85,
|
| 946 |
+
"learning_rate": 9.01851851851852e-06,
|
| 947 |
+
"loss": 0.0635,
|
| 948 |
+
"step": 15500
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 82.38,
|
| 952 |
+
"learning_rate": 8.753968253968254e-06,
|
| 953 |
+
"loss": 0.0508,
|
| 954 |
+
"step": 15600
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 82.9,
|
| 958 |
+
"learning_rate": 8.48941798941799e-06,
|
| 959 |
+
"loss": 0.0562,
|
| 960 |
+
"step": 15700
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 83.43,
|
| 964 |
+
"learning_rate": 8.224867724867726e-06,
|
| 965 |
+
"loss": 0.0543,
|
| 966 |
+
"step": 15800
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 83.96,
|
| 970 |
+
"learning_rate": 7.96031746031746e-06,
|
| 971 |
+
"loss": 0.0525,
|
| 972 |
+
"step": 15900
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 84.49,
|
| 976 |
+
"learning_rate": 7.695767195767196e-06,
|
| 977 |
+
"loss": 0.0517,
|
| 978 |
+
"step": 16000
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 85.02,
|
| 982 |
+
"learning_rate": 7.431216931216932e-06,
|
| 983 |
+
"loss": 0.0552,
|
| 984 |
+
"step": 16100
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 85.54,
|
| 988 |
+
"learning_rate": 7.166666666666667e-06,
|
| 989 |
+
"loss": 0.0443,
|
| 990 |
+
"step": 16200
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 86.07,
|
| 994 |
+
"learning_rate": 6.902116402116403e-06,
|
| 995 |
+
"loss": 0.0409,
|
| 996 |
+
"step": 16300
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 86.6,
|
| 1000 |
+
"learning_rate": 6.637566137566138e-06,
|
| 1001 |
+
"loss": 0.0418,
|
| 1002 |
+
"step": 16400
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 87.13,
|
| 1006 |
+
"learning_rate": 6.3730158730158735e-06,
|
| 1007 |
+
"loss": 0.0537,
|
| 1008 |
+
"step": 16500
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 87.66,
|
| 1012 |
+
"learning_rate": 6.108465608465609e-06,
|
| 1013 |
+
"loss": 0.0518,
|
| 1014 |
+
"step": 16600
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 88.18,
|
| 1018 |
+
"learning_rate": 5.843915343915344e-06,
|
| 1019 |
+
"loss": 0.057,
|
| 1020 |
+
"step": 16700
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 88.71,
|
| 1024 |
+
"learning_rate": 5.579365079365079e-06,
|
| 1025 |
+
"loss": 0.0463,
|
| 1026 |
+
"step": 16800
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 89.24,
|
| 1030 |
+
"learning_rate": 5.3148148148148144e-06,
|
| 1031 |
+
"loss": 0.0384,
|
| 1032 |
+
"step": 16900
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 89.77,
|
| 1036 |
+
"learning_rate": 5.0502645502645505e-06,
|
| 1037 |
+
"loss": 0.0505,
|
| 1038 |
+
"step": 17000
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 90.3,
|
| 1042 |
+
"learning_rate": 4.785714285714286e-06,
|
| 1043 |
+
"loss": 0.0553,
|
| 1044 |
+
"step": 17100
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 90.83,
|
| 1048 |
+
"learning_rate": 4.521164021164021e-06,
|
| 1049 |
+
"loss": 0.049,
|
| 1050 |
+
"step": 17200
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 91.35,
|
| 1054 |
+
"learning_rate": 4.256613756613756e-06,
|
| 1055 |
+
"loss": 0.0443,
|
| 1056 |
+
"step": 17300
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 91.88,
|
| 1060 |
+
"learning_rate": 3.992063492063492e-06,
|
| 1061 |
+
"loss": 0.0453,
|
| 1062 |
+
"step": 17400
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 92.41,
|
| 1066 |
+
"learning_rate": 3.7275132275132275e-06,
|
| 1067 |
+
"loss": 0.0432,
|
| 1068 |
+
"step": 17500
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 92.94,
|
| 1072 |
+
"learning_rate": 3.462962962962963e-06,
|
| 1073 |
+
"loss": 0.0451,
|
| 1074 |
+
"step": 17600
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 93.47,
|
| 1078 |
+
"learning_rate": 3.1984126984126984e-06,
|
| 1079 |
+
"loss": 0.0436,
|
| 1080 |
+
"step": 17700
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 93.99,
|
| 1084 |
+
"learning_rate": 2.933862433862434e-06,
|
| 1085 |
+
"loss": 0.0424,
|
| 1086 |
+
"step": 17800
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 94.52,
|
| 1090 |
+
"learning_rate": 2.6693121693121693e-06,
|
| 1091 |
+
"loss": 0.0456,
|
| 1092 |
+
"step": 17900
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 95.05,
|
| 1096 |
+
"learning_rate": 2.404761904761905e-06,
|
| 1097 |
+
"loss": 0.0426,
|
| 1098 |
+
"step": 18000
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 95.58,
|
| 1102 |
+
"learning_rate": 2.1402116402116402e-06,
|
| 1103 |
+
"loss": 0.0411,
|
| 1104 |
+
"step": 18100
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 96.11,
|
| 1108 |
+
"learning_rate": 1.8756613756613757e-06,
|
| 1109 |
+
"loss": 0.0539,
|
| 1110 |
+
"step": 18200
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 96.63,
|
| 1114 |
+
"learning_rate": 1.6111111111111111e-06,
|
| 1115 |
+
"loss": 0.0451,
|
| 1116 |
+
"step": 18300
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 97.16,
|
| 1120 |
+
"learning_rate": 1.3465608465608466e-06,
|
| 1121 |
+
"loss": 0.0426,
|
| 1122 |
+
"step": 18400
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 97.69,
|
| 1126 |
+
"learning_rate": 1.082010582010582e-06,
|
| 1127 |
+
"loss": 0.0526,
|
| 1128 |
+
"step": 18500
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 98.22,
|
| 1132 |
+
"learning_rate": 8.174603174603175e-07,
|
| 1133 |
+
"loss": 0.0417,
|
| 1134 |
+
"step": 18600
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 98.75,
|
| 1138 |
+
"learning_rate": 5.529100529100529e-07,
|
| 1139 |
+
"loss": 0.0413,
|
| 1140 |
+
"step": 18700
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 99.27,
|
| 1144 |
+
"learning_rate": 2.8835978835978836e-07,
|
| 1145 |
+
"loss": 0.0512,
|
| 1146 |
+
"step": 18800
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 99.8,
|
| 1150 |
+
"learning_rate": 2.380952380952381e-08,
|
| 1151 |
+
"loss": 0.0476,
|
| 1152 |
+
"step": 18900
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 99.8,
|
| 1156 |
+
"step": 18900,
|
| 1157 |
+
"total_flos": 3.6752439370752e+19,
|
| 1158 |
+
"train_loss": 0.3331463608035335,
|
| 1159 |
+
"train_runtime": 40683.5838,
|
| 1160 |
+
"train_samples_per_second": 29.791,
|
| 1161 |
+
"train_steps_per_second": 0.465
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 99.8,
|
| 1165 |
+
"eval_accuracy": 0.7528877854347229,
|
| 1166 |
+
"eval_loss": 1.519213080406189,
|
| 1167 |
+
"eval_runtime": 48.7307,
|
| 1168 |
+
"eval_samples_per_second": 49.743,
|
| 1169 |
+
"eval_steps_per_second": 6.218,
|
| 1170 |
+
"step": 18900
|
| 1171 |
+
}
|
| 1172 |
+
],
|
| 1173 |
+
"logging_steps": 100,
|
| 1174 |
+
"max_steps": 18900,
|
| 1175 |
+
"num_train_epochs": 100,
|
| 1176 |
+
"save_steps": 2000,
|
| 1177 |
+
"total_flos": 3.6752439370752e+19,
|
| 1178 |
+
"trial_name": null,
|
| 1179 |
+
"trial_params": null
|
| 1180 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6973a8ed9ca8e0acde38cd1635af8a78516b15c39a24f84c8d726e2276ded6be
|
| 3 |
+
size 4155
|