Training in progress, epoch 1
Browse files- README.md +83 -0
- all_results.json +16 -0
- config.json +222 -0
- eval_results.json +10 -0
- model.safetensors +3 -0
- preprocessor_config.json +9 -0
- train_results.json +9 -0
- trainer_state.json +873 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/wav2vec2-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: esc50-wav2vec2-attn
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# esc50-wav2vec2-attn
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.6556
|
| 22 |
+
- Accuracy: 0.875
|
| 23 |
+
- F1 Macro: 0.8752
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 3e-05
|
| 43 |
+
- train_batch_size: 8
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 450
|
| 49 |
+
- num_epochs: 20.0
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
| 56 |
+
| 3.7226 | 1.0 | 225 | 3.6235 | 0.205 | 0.1414 |
|
| 57 |
+
| 3.0002 | 2.0 | 450 | 2.8299 | 0.435 | 0.3782 |
|
| 58 |
+
| 2.2889 | 3.0 | 675 | 2.0599 | 0.585 | 0.5339 |
|
| 59 |
+
| 1.6197 | 4.0 | 900 | 1.5775 | 0.7 | 0.66 |
|
| 60 |
+
| 1.1835 | 5.0 | 1125 | 1.3031 | 0.72 | 0.7070 |
|
| 61 |
+
| 0.7858 | 6.0 | 1350 | 1.2474 | 0.7 | 0.6953 |
|
| 62 |
+
| 0.5843 | 7.0 | 1575 | 0.9818 | 0.76 | 0.7385 |
|
| 63 |
+
| 0.4295 | 8.0 | 1800 | 0.8253 | 0.8 | 0.7958 |
|
| 64 |
+
| 0.3041 | 9.0 | 2025 | 0.8176 | 0.8 | 0.7926 |
|
| 65 |
+
| 0.2178 | 10.0 | 2250 | 0.8450 | 0.795 | 0.7861 |
|
| 66 |
+
| 0.1874 | 11.0 | 2475 | 0.7450 | 0.81 | 0.8045 |
|
| 67 |
+
| 0.1225 | 12.0 | 2700 | 0.7663 | 0.845 | 0.8409 |
|
| 68 |
+
| 0.0818 | 13.0 | 2925 | 0.7127 | 0.855 | 0.8531 |
|
| 69 |
+
| 0.0874 | 14.0 | 3150 | 0.7242 | 0.84 | 0.8396 |
|
| 70 |
+
| 0.0469 | 15.0 | 3375 | 0.6220 | 0.855 | 0.8562 |
|
| 71 |
+
| 0.0531 | 16.0 | 3600 | 0.5916 | 0.875 | 0.8743 |
|
| 72 |
+
| 0.0351 | 17.0 | 3825 | 0.6738 | 0.85 | 0.8485 |
|
| 73 |
+
| 0.0205 | 18.0 | 4050 | 0.6656 | 0.865 | 0.8666 |
|
| 74 |
+
| 0.0207 | 19.0 | 4275 | 0.6556 | 0.875 | 0.8752 |
|
| 75 |
+
| 0.0194 | 20.0 | 4500 | 0.6624 | 0.875 | 0.8752 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.56.1
|
| 81 |
+
- Pytorch 2.8.0+cu128
|
| 82 |
+
- Datasets 2.19.0
|
| 83 |
+
- Tokenizers 0.22.0
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.875,
|
| 4 |
+
"eval_f1_macro": 0.8751587301587301,
|
| 5 |
+
"eval_loss": 0.655569851398468,
|
| 6 |
+
"eval_runtime": 2.9004,
|
| 7 |
+
"eval_samples": 200,
|
| 8 |
+
"eval_samples_per_second": 68.957,
|
| 9 |
+
"eval_steps_per_second": 8.62,
|
| 10 |
+
"total_flos": 1.64162630016e+18,
|
| 11 |
+
"train_loss": 0.7825442723168267,
|
| 12 |
+
"train_runtime": 840.5538,
|
| 13 |
+
"train_samples": 1800,
|
| 14 |
+
"train_samples_per_second": 42.829,
|
| 15 |
+
"train_steps_per_second": 5.354
|
| 16 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"finetuning_task": "esc50-audio-classification",
|
| 56 |
+
"freeze_feat_extract_train": true,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.1,
|
| 59 |
+
"hidden_size": 768,
|
| 60 |
+
"id2label": {
|
| 61 |
+
"0": "airplane",
|
| 62 |
+
"1": "breathing",
|
| 63 |
+
"2": "brushing_teeth",
|
| 64 |
+
"3": "can_opening",
|
| 65 |
+
"4": "car_horn",
|
| 66 |
+
"5": "cat",
|
| 67 |
+
"6": "chainsaw",
|
| 68 |
+
"7": "chirping_birds",
|
| 69 |
+
"8": "church_bells",
|
| 70 |
+
"9": "clapping",
|
| 71 |
+
"10": "clock_alarm",
|
| 72 |
+
"11": "clock_tick",
|
| 73 |
+
"12": "coughing",
|
| 74 |
+
"13": "cow",
|
| 75 |
+
"14": "crackling_fire",
|
| 76 |
+
"15": "crickets",
|
| 77 |
+
"16": "crow",
|
| 78 |
+
"17": "crying_baby",
|
| 79 |
+
"18": "dog",
|
| 80 |
+
"19": "door_wood_creaks",
|
| 81 |
+
"20": "door_wood_knock",
|
| 82 |
+
"21": "drinking_sipping",
|
| 83 |
+
"22": "engine",
|
| 84 |
+
"23": "fireworks",
|
| 85 |
+
"24": "footsteps",
|
| 86 |
+
"25": "frog",
|
| 87 |
+
"26": "glass_breaking",
|
| 88 |
+
"27": "hand_saw",
|
| 89 |
+
"28": "helicopter",
|
| 90 |
+
"29": "hen",
|
| 91 |
+
"30": "insects",
|
| 92 |
+
"31": "keyboard_typing",
|
| 93 |
+
"32": "laughing",
|
| 94 |
+
"33": "mouse_click",
|
| 95 |
+
"34": "pig",
|
| 96 |
+
"35": "pouring_water",
|
| 97 |
+
"36": "rain",
|
| 98 |
+
"37": "rooster",
|
| 99 |
+
"38": "sea_waves",
|
| 100 |
+
"39": "sheep",
|
| 101 |
+
"40": "siren",
|
| 102 |
+
"41": "sneezing",
|
| 103 |
+
"42": "snoring",
|
| 104 |
+
"43": "thunderstorm",
|
| 105 |
+
"44": "toilet_flush",
|
| 106 |
+
"45": "train",
|
| 107 |
+
"46": "vacuum_cleaner",
|
| 108 |
+
"47": "washing_machine",
|
| 109 |
+
"48": "water_drops",
|
| 110 |
+
"49": "wind"
|
| 111 |
+
},
|
| 112 |
+
"initializer_range": 0.02,
|
| 113 |
+
"intermediate_size": 3072,
|
| 114 |
+
"label2id": {
|
| 115 |
+
"airplane": 0,
|
| 116 |
+
"breathing": 1,
|
| 117 |
+
"brushing_teeth": 2,
|
| 118 |
+
"can_opening": 3,
|
| 119 |
+
"car_horn": 4,
|
| 120 |
+
"cat": 5,
|
| 121 |
+
"chainsaw": 6,
|
| 122 |
+
"chirping_birds": 7,
|
| 123 |
+
"church_bells": 8,
|
| 124 |
+
"clapping": 9,
|
| 125 |
+
"clock_alarm": 10,
|
| 126 |
+
"clock_tick": 11,
|
| 127 |
+
"coughing": 12,
|
| 128 |
+
"cow": 13,
|
| 129 |
+
"crackling_fire": 14,
|
| 130 |
+
"crickets": 15,
|
| 131 |
+
"crow": 16,
|
| 132 |
+
"crying_baby": 17,
|
| 133 |
+
"dog": 18,
|
| 134 |
+
"door_wood_creaks": 19,
|
| 135 |
+
"door_wood_knock": 20,
|
| 136 |
+
"drinking_sipping": 21,
|
| 137 |
+
"engine": 22,
|
| 138 |
+
"fireworks": 23,
|
| 139 |
+
"footsteps": 24,
|
| 140 |
+
"frog": 25,
|
| 141 |
+
"glass_breaking": 26,
|
| 142 |
+
"hand_saw": 27,
|
| 143 |
+
"helicopter": 28,
|
| 144 |
+
"hen": 29,
|
| 145 |
+
"insects": 30,
|
| 146 |
+
"keyboard_typing": 31,
|
| 147 |
+
"laughing": 32,
|
| 148 |
+
"mouse_click": 33,
|
| 149 |
+
"pig": 34,
|
| 150 |
+
"pouring_water": 35,
|
| 151 |
+
"rain": 36,
|
| 152 |
+
"rooster": 37,
|
| 153 |
+
"sea_waves": 38,
|
| 154 |
+
"sheep": 39,
|
| 155 |
+
"siren": 40,
|
| 156 |
+
"sneezing": 41,
|
| 157 |
+
"snoring": 42,
|
| 158 |
+
"thunderstorm": 43,
|
| 159 |
+
"toilet_flush": 44,
|
| 160 |
+
"train": 45,
|
| 161 |
+
"vacuum_cleaner": 46,
|
| 162 |
+
"washing_machine": 47,
|
| 163 |
+
"water_drops": 48,
|
| 164 |
+
"wind": 49
|
| 165 |
+
},
|
| 166 |
+
"layer_norm_eps": 1e-05,
|
| 167 |
+
"layerdrop": 0.0,
|
| 168 |
+
"mask_channel_length": 10,
|
| 169 |
+
"mask_channel_min_space": 1,
|
| 170 |
+
"mask_channel_other": 0.0,
|
| 171 |
+
"mask_channel_prob": 0.0,
|
| 172 |
+
"mask_channel_selection": "static",
|
| 173 |
+
"mask_feature_length": 10,
|
| 174 |
+
"mask_feature_min_masks": 0,
|
| 175 |
+
"mask_feature_prob": 0.0,
|
| 176 |
+
"mask_time_length": 10,
|
| 177 |
+
"mask_time_min_masks": 2,
|
| 178 |
+
"mask_time_min_space": 1,
|
| 179 |
+
"mask_time_other": 0.0,
|
| 180 |
+
"mask_time_prob": 0.05,
|
| 181 |
+
"mask_time_selection": "static",
|
| 182 |
+
"model_type": "wav2vec2",
|
| 183 |
+
"no_mask_channel_overlap": false,
|
| 184 |
+
"no_mask_time_overlap": false,
|
| 185 |
+
"num_adapter_layers": 3,
|
| 186 |
+
"num_attention_heads": 12,
|
| 187 |
+
"num_codevector_groups": 2,
|
| 188 |
+
"num_codevectors_per_group": 320,
|
| 189 |
+
"num_conv_pos_embedding_groups": 16,
|
| 190 |
+
"num_conv_pos_embeddings": 128,
|
| 191 |
+
"num_feat_extract_layers": 7,
|
| 192 |
+
"num_hidden_layers": 12,
|
| 193 |
+
"num_negatives": 100,
|
| 194 |
+
"output_hidden_size": 768,
|
| 195 |
+
"pad_token_id": 0,
|
| 196 |
+
"proj_codevector_dim": 256,
|
| 197 |
+
"tdnn_dilation": [
|
| 198 |
+
1,
|
| 199 |
+
2,
|
| 200 |
+
3,
|
| 201 |
+
1,
|
| 202 |
+
1
|
| 203 |
+
],
|
| 204 |
+
"tdnn_dim": [
|
| 205 |
+
512,
|
| 206 |
+
512,
|
| 207 |
+
512,
|
| 208 |
+
512,
|
| 209 |
+
1500
|
| 210 |
+
],
|
| 211 |
+
"tdnn_kernel": [
|
| 212 |
+
5,
|
| 213 |
+
3,
|
| 214 |
+
3,
|
| 215 |
+
1,
|
| 216 |
+
1
|
| 217 |
+
],
|
| 218 |
+
"transformers_version": "4.56.1",
|
| 219 |
+
"use_weighted_layer_sum": false,
|
| 220 |
+
"vocab_size": 32,
|
| 221 |
+
"xvector_output_dim": 512
|
| 222 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.875,
|
| 4 |
+
"eval_f1_macro": 0.8751587301587301,
|
| 5 |
+
"eval_loss": 0.655569851398468,
|
| 6 |
+
"eval_runtime": 2.9004,
|
| 7 |
+
"eval_samples": 200,
|
| 8 |
+
"eval_samples_per_second": 68.957,
|
| 9 |
+
"eval_steps_per_second": 8.62
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45707f7e593430122518253e21adb4de88e579ce7e9cf4b9f263e5e8aa31cdc0
|
| 3 |
+
size 378351720
|
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 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 1.64162630016e+18,
|
| 4 |
+
"train_loss": 0.7825442723168267,
|
| 5 |
+
"train_runtime": 840.5538,
|
| 6 |
+
"train_samples": 1800,
|
| 7 |
+
"train_samples_per_second": 42.829,
|
| 8 |
+
"train_steps_per_second": 5.354
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,873 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 4275,
|
| 3 |
+
"best_metric": 0.8751587301587301,
|
| 4 |
+
"best_model_checkpoint": "./esc50-wav2vec2-attn/checkpoint-4275",
|
| 5 |
+
"epoch": 20.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.2222222222222222,
|
| 14 |
+
"grad_norm": 4.362800598144531,
|
| 15 |
+
"learning_rate": 3.2666666666666666e-06,
|
| 16 |
+
"loss": 3.9144,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.4444444444444444,
|
| 21 |
+
"grad_norm": Infinity,
|
| 22 |
+
"learning_rate": 6.6e-06,
|
| 23 |
+
"loss": 3.8743,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6666666666666666,
|
| 28 |
+
"grad_norm": 4.956060409545898,
|
| 29 |
+
"learning_rate": 9.933333333333334e-06,
|
| 30 |
+
"loss": 3.8406,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.8888888888888888,
|
| 35 |
+
"grad_norm": 9.889445304870605,
|
| 36 |
+
"learning_rate": 1.3266666666666668e-05,
|
| 37 |
+
"loss": 3.7226,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0,
|
| 42 |
+
"eval_accuracy": 0.205,
|
| 43 |
+
"eval_f1_macro": 0.14144966384623137,
|
| 44 |
+
"eval_loss": 3.6234569549560547,
|
| 45 |
+
"eval_runtime": 2.8782,
|
| 46 |
+
"eval_samples_per_second": 69.489,
|
| 47 |
+
"eval_steps_per_second": 8.686,
|
| 48 |
+
"step": 225
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.1111111111111112,
|
| 52 |
+
"grad_norm": 5.627626419067383,
|
| 53 |
+
"learning_rate": 1.66e-05,
|
| 54 |
+
"loss": 3.5617,
|
| 55 |
+
"step": 250
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.3333333333333333,
|
| 59 |
+
"grad_norm": 6.8414154052734375,
|
| 60 |
+
"learning_rate": 1.993333333333333e-05,
|
| 61 |
+
"loss": 3.4209,
|
| 62 |
+
"step": 300
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.5555555555555556,
|
| 66 |
+
"grad_norm": 7.82706356048584,
|
| 67 |
+
"learning_rate": 2.326666666666667e-05,
|
| 68 |
+
"loss": 3.2577,
|
| 69 |
+
"step": 350
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.7777777777777777,
|
| 73 |
+
"grad_norm": 8.264775276184082,
|
| 74 |
+
"learning_rate": 2.6600000000000003e-05,
|
| 75 |
+
"loss": 3.1186,
|
| 76 |
+
"step": 400
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.0,
|
| 80 |
+
"grad_norm": 8.502516746520996,
|
| 81 |
+
"learning_rate": 2.9933333333333334e-05,
|
| 82 |
+
"loss": 3.0002,
|
| 83 |
+
"step": 450
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.0,
|
| 87 |
+
"eval_accuracy": 0.435,
|
| 88 |
+
"eval_f1_macro": 0.3781537935748462,
|
| 89 |
+
"eval_loss": 2.8298535346984863,
|
| 90 |
+
"eval_runtime": 2.8565,
|
| 91 |
+
"eval_samples_per_second": 70.015,
|
| 92 |
+
"eval_steps_per_second": 8.752,
|
| 93 |
+
"step": 450
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.2222222222222223,
|
| 97 |
+
"grad_norm": 9.52200698852539,
|
| 98 |
+
"learning_rate": 2.963703703703704e-05,
|
| 99 |
+
"loss": 2.6937,
|
| 100 |
+
"step": 500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.4444444444444446,
|
| 104 |
+
"grad_norm": 8.961172103881836,
|
| 105 |
+
"learning_rate": 2.9266666666666665e-05,
|
| 106 |
+
"loss": 2.4869,
|
| 107 |
+
"step": 550
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.6666666666666665,
|
| 111 |
+
"grad_norm": 12.154603004455566,
|
| 112 |
+
"learning_rate": 2.8896296296296298e-05,
|
| 113 |
+
"loss": 2.4099,
|
| 114 |
+
"step": 600
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.888888888888889,
|
| 118 |
+
"grad_norm": 10.498632431030273,
|
| 119 |
+
"learning_rate": 2.8525925925925924e-05,
|
| 120 |
+
"loss": 2.2889,
|
| 121 |
+
"step": 650
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 3.0,
|
| 125 |
+
"eval_accuracy": 0.585,
|
| 126 |
+
"eval_f1_macro": 0.533888888888889,
|
| 127 |
+
"eval_loss": 2.0598816871643066,
|
| 128 |
+
"eval_runtime": 2.8698,
|
| 129 |
+
"eval_samples_per_second": 69.691,
|
| 130 |
+
"eval_steps_per_second": 8.711,
|
| 131 |
+
"step": 675
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.111111111111111,
|
| 135 |
+
"grad_norm": 7.486043930053711,
|
| 136 |
+
"learning_rate": 2.8155555555555556e-05,
|
| 137 |
+
"loss": 2.055,
|
| 138 |
+
"step": 700
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.3333333333333335,
|
| 142 |
+
"grad_norm": 9.043672561645508,
|
| 143 |
+
"learning_rate": 2.7785185185185185e-05,
|
| 144 |
+
"loss": 1.8778,
|
| 145 |
+
"step": 750
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 3.5555555555555554,
|
| 149 |
+
"grad_norm": 12.435341835021973,
|
| 150 |
+
"learning_rate": 2.7414814814814815e-05,
|
| 151 |
+
"loss": 1.8209,
|
| 152 |
+
"step": 800
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.7777777777777777,
|
| 156 |
+
"grad_norm": 18.719287872314453,
|
| 157 |
+
"learning_rate": 2.7044444444444444e-05,
|
| 158 |
+
"loss": 1.5985,
|
| 159 |
+
"step": 850
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.0,
|
| 163 |
+
"grad_norm": 11.806514739990234,
|
| 164 |
+
"learning_rate": 2.6674074074074076e-05,
|
| 165 |
+
"loss": 1.6197,
|
| 166 |
+
"step": 900
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 4.0,
|
| 170 |
+
"eval_accuracy": 0.7,
|
| 171 |
+
"eval_f1_macro": 0.66,
|
| 172 |
+
"eval_loss": 1.5774518251419067,
|
| 173 |
+
"eval_runtime": 2.8913,
|
| 174 |
+
"eval_samples_per_second": 69.172,
|
| 175 |
+
"eval_steps_per_second": 8.647,
|
| 176 |
+
"step": 900
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.222222222222222,
|
| 180 |
+
"grad_norm": 11.915701866149902,
|
| 181 |
+
"learning_rate": 2.6303703703703702e-05,
|
| 182 |
+
"loss": 1.2872,
|
| 183 |
+
"step": 950
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.444444444444445,
|
| 187 |
+
"grad_norm": 26.78908920288086,
|
| 188 |
+
"learning_rate": 2.5933333333333335e-05,
|
| 189 |
+
"loss": 1.2329,
|
| 190 |
+
"step": 1000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 4.666666666666667,
|
| 194 |
+
"grad_norm": 9.02193546295166,
|
| 195 |
+
"learning_rate": 2.5562962962962964e-05,
|
| 196 |
+
"loss": 1.2363,
|
| 197 |
+
"step": 1050
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 4.888888888888889,
|
| 201 |
+
"grad_norm": 7.637599468231201,
|
| 202 |
+
"learning_rate": 2.5192592592592593e-05,
|
| 203 |
+
"loss": 1.1835,
|
| 204 |
+
"step": 1100
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 5.0,
|
| 208 |
+
"eval_accuracy": 0.72,
|
| 209 |
+
"eval_f1_macro": 0.7070447330447331,
|
| 210 |
+
"eval_loss": 1.303067684173584,
|
| 211 |
+
"eval_runtime": 2.8767,
|
| 212 |
+
"eval_samples_per_second": 69.525,
|
| 213 |
+
"eval_steps_per_second": 8.691,
|
| 214 |
+
"step": 1125
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 5.111111111111111,
|
| 218 |
+
"grad_norm": 31.952880859375,
|
| 219 |
+
"learning_rate": 2.4822222222222222e-05,
|
| 220 |
+
"loss": 1.0582,
|
| 221 |
+
"step": 1150
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 5.333333333333333,
|
| 225 |
+
"grad_norm": 11.701904296875,
|
| 226 |
+
"learning_rate": 2.4451851851851855e-05,
|
| 227 |
+
"loss": 0.8821,
|
| 228 |
+
"step": 1200
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 5.555555555555555,
|
| 232 |
+
"grad_norm": 13.303455352783203,
|
| 233 |
+
"learning_rate": 2.408148148148148e-05,
|
| 234 |
+
"loss": 0.9102,
|
| 235 |
+
"step": 1250
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 5.777777777777778,
|
| 239 |
+
"grad_norm": 12.172894477844238,
|
| 240 |
+
"learning_rate": 2.3711111111111113e-05,
|
| 241 |
+
"loss": 0.8899,
|
| 242 |
+
"step": 1300
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 6.0,
|
| 246 |
+
"grad_norm": 17.647672653198242,
|
| 247 |
+
"learning_rate": 2.334074074074074e-05,
|
| 248 |
+
"loss": 0.7858,
|
| 249 |
+
"step": 1350
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.0,
|
| 253 |
+
"eval_accuracy": 0.7,
|
| 254 |
+
"eval_f1_macro": 0.6953009213009212,
|
| 255 |
+
"eval_loss": 1.2473626136779785,
|
| 256 |
+
"eval_runtime": 2.9867,
|
| 257 |
+
"eval_samples_per_second": 66.963,
|
| 258 |
+
"eval_steps_per_second": 8.37,
|
| 259 |
+
"step": 1350
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 6.222222222222222,
|
| 263 |
+
"grad_norm": 3.5193300247192383,
|
| 264 |
+
"learning_rate": 2.297037037037037e-05,
|
| 265 |
+
"loss": 0.6652,
|
| 266 |
+
"step": 1400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.444444444444445,
|
| 270 |
+
"grad_norm": 5.703717231750488,
|
| 271 |
+
"learning_rate": 2.26e-05,
|
| 272 |
+
"loss": 0.6172,
|
| 273 |
+
"step": 1450
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 6.666666666666667,
|
| 277 |
+
"grad_norm": 5.758047103881836,
|
| 278 |
+
"learning_rate": 2.222962962962963e-05,
|
| 279 |
+
"loss": 0.67,
|
| 280 |
+
"step": 1500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 6.888888888888889,
|
| 284 |
+
"grad_norm": 33.762943267822266,
|
| 285 |
+
"learning_rate": 2.185925925925926e-05,
|
| 286 |
+
"loss": 0.5843,
|
| 287 |
+
"step": 1550
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 7.0,
|
| 291 |
+
"eval_accuracy": 0.76,
|
| 292 |
+
"eval_f1_macro": 0.7385472305472305,
|
| 293 |
+
"eval_loss": 0.9817761182785034,
|
| 294 |
+
"eval_runtime": 2.8876,
|
| 295 |
+
"eval_samples_per_second": 69.261,
|
| 296 |
+
"eval_steps_per_second": 8.658,
|
| 297 |
+
"step": 1575
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 7.111111111111111,
|
| 301 |
+
"grad_norm": 13.375953674316406,
|
| 302 |
+
"learning_rate": 2.148888888888889e-05,
|
| 303 |
+
"loss": 0.5566,
|
| 304 |
+
"step": 1600
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 7.333333333333333,
|
| 308 |
+
"grad_norm": 10.450238227844238,
|
| 309 |
+
"learning_rate": 2.1118518518518517e-05,
|
| 310 |
+
"loss": 0.4772,
|
| 311 |
+
"step": 1650
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 7.555555555555555,
|
| 315 |
+
"grad_norm": 9.287495613098145,
|
| 316 |
+
"learning_rate": 2.074814814814815e-05,
|
| 317 |
+
"loss": 0.4799,
|
| 318 |
+
"step": 1700
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 7.777777777777778,
|
| 322 |
+
"grad_norm": 8.345856666564941,
|
| 323 |
+
"learning_rate": 2.037777777777778e-05,
|
| 324 |
+
"loss": 0.467,
|
| 325 |
+
"step": 1750
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 8.0,
|
| 329 |
+
"grad_norm": 7.566125869750977,
|
| 330 |
+
"learning_rate": 2.0007407407407408e-05,
|
| 331 |
+
"loss": 0.4295,
|
| 332 |
+
"step": 1800
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 8.0,
|
| 336 |
+
"eval_accuracy": 0.8,
|
| 337 |
+
"eval_f1_macro": 0.7957647907647908,
|
| 338 |
+
"eval_loss": 0.8252587914466858,
|
| 339 |
+
"eval_runtime": 2.8766,
|
| 340 |
+
"eval_samples_per_second": 69.525,
|
| 341 |
+
"eval_steps_per_second": 8.691,
|
| 342 |
+
"step": 1800
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 8.222222222222221,
|
| 346 |
+
"grad_norm": 15.532505989074707,
|
| 347 |
+
"learning_rate": 1.9637037037037037e-05,
|
| 348 |
+
"loss": 0.3501,
|
| 349 |
+
"step": 1850
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 8.444444444444445,
|
| 353 |
+
"grad_norm": 6.413458824157715,
|
| 354 |
+
"learning_rate": 1.926666666666667e-05,
|
| 355 |
+
"loss": 0.3558,
|
| 356 |
+
"step": 1900
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 8.666666666666666,
|
| 360 |
+
"grad_norm": 4.636125564575195,
|
| 361 |
+
"learning_rate": 1.8896296296296295e-05,
|
| 362 |
+
"loss": 0.3139,
|
| 363 |
+
"step": 1950
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 8.88888888888889,
|
| 367 |
+
"grad_norm": 0.6558843851089478,
|
| 368 |
+
"learning_rate": 1.8525925925925928e-05,
|
| 369 |
+
"loss": 0.3041,
|
| 370 |
+
"step": 2000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 9.0,
|
| 374 |
+
"eval_accuracy": 0.8,
|
| 375 |
+
"eval_f1_macro": 0.7926046176046176,
|
| 376 |
+
"eval_loss": 0.8176364302635193,
|
| 377 |
+
"eval_runtime": 2.8845,
|
| 378 |
+
"eval_samples_per_second": 69.336,
|
| 379 |
+
"eval_steps_per_second": 8.667,
|
| 380 |
+
"step": 2025
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 9.11111111111111,
|
| 384 |
+
"grad_norm": 18.850481033325195,
|
| 385 |
+
"learning_rate": 1.8155555555555554e-05,
|
| 386 |
+
"loss": 0.3166,
|
| 387 |
+
"step": 2050
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 9.333333333333334,
|
| 391 |
+
"grad_norm": 22.011247634887695,
|
| 392 |
+
"learning_rate": 1.7785185185185186e-05,
|
| 393 |
+
"loss": 0.2472,
|
| 394 |
+
"step": 2100
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 9.555555555555555,
|
| 398 |
+
"grad_norm": 0.4794563353061676,
|
| 399 |
+
"learning_rate": 1.7414814814814815e-05,
|
| 400 |
+
"loss": 0.2419,
|
| 401 |
+
"step": 2150
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 9.777777777777779,
|
| 405 |
+
"grad_norm": 1.2854745388031006,
|
| 406 |
+
"learning_rate": 1.7044444444444445e-05,
|
| 407 |
+
"loss": 0.1906,
|
| 408 |
+
"step": 2200
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 10.0,
|
| 412 |
+
"grad_norm": 18.808258056640625,
|
| 413 |
+
"learning_rate": 1.6674074074074074e-05,
|
| 414 |
+
"loss": 0.2178,
|
| 415 |
+
"step": 2250
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 10.0,
|
| 419 |
+
"eval_accuracy": 0.795,
|
| 420 |
+
"eval_f1_macro": 0.7861341991341991,
|
| 421 |
+
"eval_loss": 0.845029890537262,
|
| 422 |
+
"eval_runtime": 2.8982,
|
| 423 |
+
"eval_samples_per_second": 69.008,
|
| 424 |
+
"eval_steps_per_second": 8.626,
|
| 425 |
+
"step": 2250
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 10.222222222222221,
|
| 429 |
+
"grad_norm": 0.6055029630661011,
|
| 430 |
+
"learning_rate": 1.6303703703703706e-05,
|
| 431 |
+
"loss": 0.2369,
|
| 432 |
+
"step": 2300
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 10.444444444444445,
|
| 436 |
+
"grad_norm": 0.2815465033054352,
|
| 437 |
+
"learning_rate": 1.5933333333333332e-05,
|
| 438 |
+
"loss": 0.1514,
|
| 439 |
+
"step": 2350
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 10.666666666666666,
|
| 443 |
+
"grad_norm": 0.5796032547950745,
|
| 444 |
+
"learning_rate": 1.5562962962962965e-05,
|
| 445 |
+
"loss": 0.1704,
|
| 446 |
+
"step": 2400
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 10.88888888888889,
|
| 450 |
+
"grad_norm": 15.787017822265625,
|
| 451 |
+
"learning_rate": 1.5192592592592592e-05,
|
| 452 |
+
"loss": 0.1874,
|
| 453 |
+
"step": 2450
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 11.0,
|
| 457 |
+
"eval_accuracy": 0.81,
|
| 458 |
+
"eval_f1_macro": 0.8044646464646463,
|
| 459 |
+
"eval_loss": 0.7450368404388428,
|
| 460 |
+
"eval_runtime": 2.8672,
|
| 461 |
+
"eval_samples_per_second": 69.755,
|
| 462 |
+
"eval_steps_per_second": 8.719,
|
| 463 |
+
"step": 2475
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 11.11111111111111,
|
| 467 |
+
"grad_norm": 5.2899017333984375,
|
| 468 |
+
"learning_rate": 1.4822222222222221e-05,
|
| 469 |
+
"loss": 0.1407,
|
| 470 |
+
"step": 2500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 11.333333333333334,
|
| 474 |
+
"grad_norm": 1.0392882823944092,
|
| 475 |
+
"learning_rate": 1.4451851851851852e-05,
|
| 476 |
+
"loss": 0.1423,
|
| 477 |
+
"step": 2550
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 11.555555555555555,
|
| 481 |
+
"grad_norm": 0.22039936482906342,
|
| 482 |
+
"learning_rate": 1.4081481481481481e-05,
|
| 483 |
+
"loss": 0.1214,
|
| 484 |
+
"step": 2600
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 11.777777777777779,
|
| 488 |
+
"grad_norm": 1.2269922494888306,
|
| 489 |
+
"learning_rate": 1.371111111111111e-05,
|
| 490 |
+
"loss": 0.1706,
|
| 491 |
+
"step": 2650
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 12.0,
|
| 495 |
+
"grad_norm": 0.16958917677402496,
|
| 496 |
+
"learning_rate": 1.3340740740740741e-05,
|
| 497 |
+
"loss": 0.1225,
|
| 498 |
+
"step": 2700
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 12.0,
|
| 502 |
+
"eval_accuracy": 0.845,
|
| 503 |
+
"eval_f1_macro": 0.8408946608946608,
|
| 504 |
+
"eval_loss": 0.7663388848304749,
|
| 505 |
+
"eval_runtime": 2.8819,
|
| 506 |
+
"eval_samples_per_second": 69.398,
|
| 507 |
+
"eval_steps_per_second": 8.675,
|
| 508 |
+
"step": 2700
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 12.222222222222221,
|
| 512 |
+
"grad_norm": 16.176551818847656,
|
| 513 |
+
"learning_rate": 1.297037037037037e-05,
|
| 514 |
+
"loss": 0.1082,
|
| 515 |
+
"step": 2750
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 12.444444444444445,
|
| 519 |
+
"grad_norm": 0.7906608581542969,
|
| 520 |
+
"learning_rate": 1.26e-05,
|
| 521 |
+
"loss": 0.0837,
|
| 522 |
+
"step": 2800
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 12.666666666666666,
|
| 526 |
+
"grad_norm": 0.1822936087846756,
|
| 527 |
+
"learning_rate": 1.2229629629629629e-05,
|
| 528 |
+
"loss": 0.0779,
|
| 529 |
+
"step": 2850
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 12.88888888888889,
|
| 533 |
+
"grad_norm": 0.1906086951494217,
|
| 534 |
+
"learning_rate": 1.185925925925926e-05,
|
| 535 |
+
"loss": 0.0818,
|
| 536 |
+
"step": 2900
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 13.0,
|
| 540 |
+
"eval_accuracy": 0.855,
|
| 541 |
+
"eval_f1_macro": 0.8530952380952379,
|
| 542 |
+
"eval_loss": 0.7127139568328857,
|
| 543 |
+
"eval_runtime": 2.8693,
|
| 544 |
+
"eval_samples_per_second": 69.703,
|
| 545 |
+
"eval_steps_per_second": 8.713,
|
| 546 |
+
"step": 2925
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 13.11111111111111,
|
| 550 |
+
"grad_norm": 0.28385430574417114,
|
| 551 |
+
"learning_rate": 1.1488888888888889e-05,
|
| 552 |
+
"loss": 0.0873,
|
| 553 |
+
"step": 2950
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 13.333333333333334,
|
| 557 |
+
"grad_norm": 0.17537418007850647,
|
| 558 |
+
"learning_rate": 1.1118518518518518e-05,
|
| 559 |
+
"loss": 0.0536,
|
| 560 |
+
"step": 3000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 13.555555555555555,
|
| 564 |
+
"grad_norm": 0.2917730212211609,
|
| 565 |
+
"learning_rate": 1.0748148148148149e-05,
|
| 566 |
+
"loss": 0.0555,
|
| 567 |
+
"step": 3050
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 13.777777777777779,
|
| 571 |
+
"grad_norm": 0.14240045845508575,
|
| 572 |
+
"learning_rate": 1.0377777777777778e-05,
|
| 573 |
+
"loss": 0.0579,
|
| 574 |
+
"step": 3100
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 14.0,
|
| 578 |
+
"grad_norm": 0.5113584399223328,
|
| 579 |
+
"learning_rate": 1.0007407407407407e-05,
|
| 580 |
+
"loss": 0.0874,
|
| 581 |
+
"step": 3150
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 14.0,
|
| 585 |
+
"eval_accuracy": 0.84,
|
| 586 |
+
"eval_f1_macro": 0.8395616605616606,
|
| 587 |
+
"eval_loss": 0.7242352366447449,
|
| 588 |
+
"eval_runtime": 2.8999,
|
| 589 |
+
"eval_samples_per_second": 68.968,
|
| 590 |
+
"eval_steps_per_second": 8.621,
|
| 591 |
+
"step": 3150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 14.222222222222221,
|
| 595 |
+
"grad_norm": 0.14713504910469055,
|
| 596 |
+
"learning_rate": 9.637037037037036e-06,
|
| 597 |
+
"loss": 0.035,
|
| 598 |
+
"step": 3200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 14.444444444444445,
|
| 602 |
+
"grad_norm": 0.18145354092121124,
|
| 603 |
+
"learning_rate": 9.266666666666667e-06,
|
| 604 |
+
"loss": 0.0658,
|
| 605 |
+
"step": 3250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 14.666666666666666,
|
| 609 |
+
"grad_norm": 0.14780841767787933,
|
| 610 |
+
"learning_rate": 8.896296296296296e-06,
|
| 611 |
+
"loss": 0.0424,
|
| 612 |
+
"step": 3300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 14.88888888888889,
|
| 616 |
+
"grad_norm": 0.2982366383075714,
|
| 617 |
+
"learning_rate": 8.525925925925925e-06,
|
| 618 |
+
"loss": 0.0469,
|
| 619 |
+
"step": 3350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 15.0,
|
| 623 |
+
"eval_accuracy": 0.855,
|
| 624 |
+
"eval_f1_macro": 0.8562178932178931,
|
| 625 |
+
"eval_loss": 0.6220372915267944,
|
| 626 |
+
"eval_runtime": 2.8763,
|
| 627 |
+
"eval_samples_per_second": 69.534,
|
| 628 |
+
"eval_steps_per_second": 8.692,
|
| 629 |
+
"step": 3375
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 15.11111111111111,
|
| 633 |
+
"grad_norm": 0.11205285787582397,
|
| 634 |
+
"learning_rate": 8.155555555555556e-06,
|
| 635 |
+
"loss": 0.0355,
|
| 636 |
+
"step": 3400
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 15.333333333333334,
|
| 640 |
+
"grad_norm": 0.11701209098100662,
|
| 641 |
+
"learning_rate": 7.785185185185185e-06,
|
| 642 |
+
"loss": 0.0311,
|
| 643 |
+
"step": 3450
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 15.555555555555555,
|
| 647 |
+
"grad_norm": 0.15519364178180695,
|
| 648 |
+
"learning_rate": 7.414814814814815e-06,
|
| 649 |
+
"loss": 0.0252,
|
| 650 |
+
"step": 3500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 15.777777777777779,
|
| 654 |
+
"grad_norm": 0.2080957293510437,
|
| 655 |
+
"learning_rate": 7.044444444444445e-06,
|
| 656 |
+
"loss": 0.0355,
|
| 657 |
+
"step": 3550
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 16.0,
|
| 661 |
+
"grad_norm": 0.16233320534229279,
|
| 662 |
+
"learning_rate": 6.674074074074074e-06,
|
| 663 |
+
"loss": 0.0531,
|
| 664 |
+
"step": 3600
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 16.0,
|
| 668 |
+
"eval_accuracy": 0.875,
|
| 669 |
+
"eval_f1_macro": 0.8743174603174602,
|
| 670 |
+
"eval_loss": 0.5916269421577454,
|
| 671 |
+
"eval_runtime": 2.9356,
|
| 672 |
+
"eval_samples_per_second": 68.13,
|
| 673 |
+
"eval_steps_per_second": 8.516,
|
| 674 |
+
"step": 3600
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 16.22222222222222,
|
| 678 |
+
"grad_norm": 0.15035021305084229,
|
| 679 |
+
"learning_rate": 6.303703703703704e-06,
|
| 680 |
+
"loss": 0.0239,
|
| 681 |
+
"step": 3650
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 16.444444444444443,
|
| 685 |
+
"grad_norm": 0.12058259546756744,
|
| 686 |
+
"learning_rate": 5.933333333333333e-06,
|
| 687 |
+
"loss": 0.0233,
|
| 688 |
+
"step": 3700
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 16.666666666666668,
|
| 692 |
+
"grad_norm": 0.11992493271827698,
|
| 693 |
+
"learning_rate": 5.562962962962963e-06,
|
| 694 |
+
"loss": 0.0254,
|
| 695 |
+
"step": 3750
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 16.88888888888889,
|
| 699 |
+
"grad_norm": 0.1040111556649208,
|
| 700 |
+
"learning_rate": 5.192592592592593e-06,
|
| 701 |
+
"loss": 0.0351,
|
| 702 |
+
"step": 3800
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 17.0,
|
| 706 |
+
"eval_accuracy": 0.85,
|
| 707 |
+
"eval_f1_macro": 0.8484761904761904,
|
| 708 |
+
"eval_loss": 0.673793613910675,
|
| 709 |
+
"eval_runtime": 2.9183,
|
| 710 |
+
"eval_samples_per_second": 68.534,
|
| 711 |
+
"eval_steps_per_second": 8.567,
|
| 712 |
+
"step": 3825
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 17.11111111111111,
|
| 716 |
+
"grad_norm": 0.14537616074085236,
|
| 717 |
+
"learning_rate": 4.822222222222222e-06,
|
| 718 |
+
"loss": 0.0222,
|
| 719 |
+
"step": 3850
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 17.333333333333332,
|
| 723 |
+
"grad_norm": 0.14161454141139984,
|
| 724 |
+
"learning_rate": 4.451851851851852e-06,
|
| 725 |
+
"loss": 0.0209,
|
| 726 |
+
"step": 3900
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 17.555555555555557,
|
| 730 |
+
"grad_norm": 0.0898861438035965,
|
| 731 |
+
"learning_rate": 4.081481481481481e-06,
|
| 732 |
+
"loss": 0.0206,
|
| 733 |
+
"step": 3950
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 17.77777777777778,
|
| 737 |
+
"grad_norm": 0.10038736462593079,
|
| 738 |
+
"learning_rate": 3.7111111111111113e-06,
|
| 739 |
+
"loss": 0.0319,
|
| 740 |
+
"step": 4000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 18.0,
|
| 744 |
+
"grad_norm": 0.1036420613527298,
|
| 745 |
+
"learning_rate": 3.340740740740741e-06,
|
| 746 |
+
"loss": 0.0205,
|
| 747 |
+
"step": 4050
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 18.0,
|
| 751 |
+
"eval_accuracy": 0.865,
|
| 752 |
+
"eval_f1_macro": 0.8666349206349205,
|
| 753 |
+
"eval_loss": 0.665629506111145,
|
| 754 |
+
"eval_runtime": 2.8759,
|
| 755 |
+
"eval_samples_per_second": 69.544,
|
| 756 |
+
"eval_steps_per_second": 8.693,
|
| 757 |
+
"step": 4050
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 18.22222222222222,
|
| 761 |
+
"grad_norm": 0.11664649099111557,
|
| 762 |
+
"learning_rate": 2.9703703703703705e-06,
|
| 763 |
+
"loss": 0.0202,
|
| 764 |
+
"step": 4100
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 18.444444444444443,
|
| 768 |
+
"grad_norm": 0.10043739527463913,
|
| 769 |
+
"learning_rate": 2.6e-06,
|
| 770 |
+
"loss": 0.0198,
|
| 771 |
+
"step": 4150
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 18.666666666666668,
|
| 775 |
+
"grad_norm": 0.07799684256315231,
|
| 776 |
+
"learning_rate": 2.2296296296296297e-06,
|
| 777 |
+
"loss": 0.0195,
|
| 778 |
+
"step": 4200
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 18.88888888888889,
|
| 782 |
+
"grad_norm": 0.08117303997278214,
|
| 783 |
+
"learning_rate": 1.8592592592592593e-06,
|
| 784 |
+
"loss": 0.0207,
|
| 785 |
+
"step": 4250
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 19.0,
|
| 789 |
+
"eval_accuracy": 0.875,
|
| 790 |
+
"eval_f1_macro": 0.8751587301587301,
|
| 791 |
+
"eval_loss": 0.655569851398468,
|
| 792 |
+
"eval_runtime": 2.9199,
|
| 793 |
+
"eval_samples_per_second": 68.496,
|
| 794 |
+
"eval_steps_per_second": 8.562,
|
| 795 |
+
"step": 4275
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 19.11111111111111,
|
| 799 |
+
"grad_norm": 0.09353518486022949,
|
| 800 |
+
"learning_rate": 1.4888888888888888e-06,
|
| 801 |
+
"loss": 0.0243,
|
| 802 |
+
"step": 4300
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 19.333333333333332,
|
| 806 |
+
"grad_norm": 0.12512549757957458,
|
| 807 |
+
"learning_rate": 1.1185185185185184e-06,
|
| 808 |
+
"loss": 0.019,
|
| 809 |
+
"step": 4350
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 19.555555555555557,
|
| 813 |
+
"grad_norm": 0.09048581123352051,
|
| 814 |
+
"learning_rate": 7.481481481481481e-07,
|
| 815 |
+
"loss": 0.0219,
|
| 816 |
+
"step": 4400
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 19.77777777777778,
|
| 820 |
+
"grad_norm": 0.10329825431108475,
|
| 821 |
+
"learning_rate": 3.777777777777778e-07,
|
| 822 |
+
"loss": 0.0194,
|
| 823 |
+
"step": 4450
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 20.0,
|
| 827 |
+
"grad_norm": 0.09893308579921722,
|
| 828 |
+
"learning_rate": 7.407407407407408e-09,
|
| 829 |
+
"loss": 0.0194,
|
| 830 |
+
"step": 4500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 20.0,
|
| 834 |
+
"eval_accuracy": 0.875,
|
| 835 |
+
"eval_f1_macro": 0.8751587301587301,
|
| 836 |
+
"eval_loss": 0.6624078154563904,
|
| 837 |
+
"eval_runtime": 2.9156,
|
| 838 |
+
"eval_samples_per_second": 68.595,
|
| 839 |
+
"eval_steps_per_second": 8.574,
|
| 840 |
+
"step": 4500
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 20.0,
|
| 844 |
+
"step": 4500,
|
| 845 |
+
"total_flos": 1.64162630016e+18,
|
| 846 |
+
"train_loss": 0.7825442723168267,
|
| 847 |
+
"train_runtime": 840.5538,
|
| 848 |
+
"train_samples_per_second": 42.829,
|
| 849 |
+
"train_steps_per_second": 5.354
|
| 850 |
+
}
|
| 851 |
+
],
|
| 852 |
+
"logging_steps": 50,
|
| 853 |
+
"max_steps": 4500,
|
| 854 |
+
"num_input_tokens_seen": 0,
|
| 855 |
+
"num_train_epochs": 20,
|
| 856 |
+
"save_steps": 500,
|
| 857 |
+
"stateful_callbacks": {
|
| 858 |
+
"TrainerControl": {
|
| 859 |
+
"args": {
|
| 860 |
+
"should_epoch_stop": false,
|
| 861 |
+
"should_evaluate": false,
|
| 862 |
+
"should_log": false,
|
| 863 |
+
"should_save": true,
|
| 864 |
+
"should_training_stop": true
|
| 865 |
+
},
|
| 866 |
+
"attributes": {}
|
| 867 |
+
}
|
| 868 |
+
},
|
| 869 |
+
"total_flos": 1.64162630016e+18,
|
| 870 |
+
"train_batch_size": 8,
|
| 871 |
+
"trial_name": null,
|
| 872 |
+
"trial_params": null
|
| 873 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5351cc4a35022a422ddf1e4dfcb892c5e29a158211003340e7ab9c65d55c2c4
|
| 3 |
+
size 5841
|