Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- test_results.json +9 -0
- trainer_state.json +381 -0
- val_results.json +9 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
base_model: facebook/timesformer-base-finetuned-k400
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- f1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: videomae-surf-analytics-runpod
|
| 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 |
+
# videomae-surf-analytics-runpod
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4794
|
| 22 |
+
- Accuracy: 0.8340
|
| 23 |
+
- F1: 0.8347
|
| 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: 5e-05
|
| 43 |
+
- train_batch_size: 10
|
| 44 |
+
- eval_batch_size: 10
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- training_steps: 370
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
|
| 55 |
+
| 0.6213 | 0.2027 | 75 | 0.7774 | 0.6971 | 0.6902 |
|
| 56 |
+
| 0.3269 | 1.2027 | 150 | 0.6851 | 0.7593 | 0.7562 |
|
| 57 |
+
| 0.2339 | 2.2027 | 225 | 0.5252 | 0.8008 | 0.7993 |
|
| 58 |
+
| 0.1931 | 3.2027 | 300 | 0.4942 | 0.8340 | 0.8342 |
|
| 59 |
+
| 0.1037 | 4.1892 | 370 | 0.4794 | 0.8340 | 0.8347 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.41.2
|
| 65 |
+
- Pytorch 2.3.1+cu121
|
| 66 |
+
- Datasets 2.19.2
|
| 67 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.1891891891891895,
|
| 3 |
+
"eval_accuracy": 0.8340248962655602,
|
| 4 |
+
"eval_f1": 0.8346934110853106,
|
| 5 |
+
"eval_loss": 0.47942548990249634,
|
| 6 |
+
"eval_runtime": 73.4732,
|
| 7 |
+
"eval_samples_per_second": 3.28,
|
| 8 |
+
"eval_steps_per_second": 0.34
|
| 9 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.1891891891891895,
|
| 3 |
+
"eval_accuracy": 0.8067415730337079,
|
| 4 |
+
"eval_f1": 0.8059471321937128,
|
| 5 |
+
"eval_loss": 0.6186416745185852,
|
| 6 |
+
"eval_runtime": 137.3351,
|
| 7 |
+
"eval_samples_per_second": 3.24,
|
| 8 |
+
"eval_steps_per_second": 0.328
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,381 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8346934110853106,
|
| 3 |
+
"best_model_checkpoint": "videomae-surf-analytics-runpod/checkpoint-370",
|
| 4 |
+
"epoch": 4.1891891891891895,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 370,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02702702702702703,
|
| 13 |
+
"grad_norm": 17.739418029785156,
|
| 14 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 15 |
+
"loss": 1.4705,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05405405405405406,
|
| 20 |
+
"grad_norm": 6.248379707336426,
|
| 21 |
+
"learning_rate": 2.702702702702703e-05,
|
| 22 |
+
"loss": 1.1378,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08108108108108109,
|
| 27 |
+
"grad_norm": 6.359808444976807,
|
| 28 |
+
"learning_rate": 4.0540540540540545e-05,
|
| 29 |
+
"loss": 1.0852,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.10810810810810811,
|
| 34 |
+
"grad_norm": 7.196521282196045,
|
| 35 |
+
"learning_rate": 4.954954954954955e-05,
|
| 36 |
+
"loss": 0.7478,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.13513513513513514,
|
| 41 |
+
"grad_norm": 7.588693141937256,
|
| 42 |
+
"learning_rate": 4.804804804804805e-05,
|
| 43 |
+
"loss": 0.653,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.16216216216216217,
|
| 48 |
+
"grad_norm": 9.380898475646973,
|
| 49 |
+
"learning_rate": 4.654654654654655e-05,
|
| 50 |
+
"loss": 0.7808,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1891891891891892,
|
| 55 |
+
"grad_norm": 9.640559196472168,
|
| 56 |
+
"learning_rate": 4.5045045045045046e-05,
|
| 57 |
+
"loss": 0.6213,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.20270270270270271,
|
| 62 |
+
"eval_accuracy": 0.6970954356846473,
|
| 63 |
+
"eval_f1": 0.6901963848053563,
|
| 64 |
+
"eval_loss": 0.7773587703704834,
|
| 65 |
+
"eval_runtime": 77.0947,
|
| 66 |
+
"eval_samples_per_second": 3.126,
|
| 67 |
+
"eval_steps_per_second": 0.324,
|
| 68 |
+
"step": 75
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.0135135135135136,
|
| 72 |
+
"grad_norm": 4.199209690093994,
|
| 73 |
+
"learning_rate": 4.354354354354355e-05,
|
| 74 |
+
"loss": 0.4215,
|
| 75 |
+
"step": 80
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.0405405405405406,
|
| 79 |
+
"grad_norm": 3.8096096515655518,
|
| 80 |
+
"learning_rate": 4.204204204204204e-05,
|
| 81 |
+
"loss": 0.391,
|
| 82 |
+
"step": 90
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.0675675675675675,
|
| 86 |
+
"grad_norm": 13.743525505065918,
|
| 87 |
+
"learning_rate": 4.0540540540540545e-05,
|
| 88 |
+
"loss": 0.4713,
|
| 89 |
+
"step": 100
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.0945945945945945,
|
| 93 |
+
"grad_norm": 3.954926013946533,
|
| 94 |
+
"learning_rate": 3.903903903903904e-05,
|
| 95 |
+
"loss": 0.4197,
|
| 96 |
+
"step": 110
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.1216216216216217,
|
| 100 |
+
"grad_norm": 7.9359211921691895,
|
| 101 |
+
"learning_rate": 3.7537537537537536e-05,
|
| 102 |
+
"loss": 0.3719,
|
| 103 |
+
"step": 120
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.1486486486486487,
|
| 107 |
+
"grad_norm": 10.24318790435791,
|
| 108 |
+
"learning_rate": 3.603603603603604e-05,
|
| 109 |
+
"loss": 0.3922,
|
| 110 |
+
"step": 130
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.1756756756756757,
|
| 114 |
+
"grad_norm": 13.8519926071167,
|
| 115 |
+
"learning_rate": 3.453453453453453e-05,
|
| 116 |
+
"loss": 0.4027,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.2027027027027026,
|
| 121 |
+
"grad_norm": 1.3211474418640137,
|
| 122 |
+
"learning_rate": 3.3033033033033035e-05,
|
| 123 |
+
"loss": 0.3269,
|
| 124 |
+
"step": 150
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.2027027027027026,
|
| 128 |
+
"eval_accuracy": 0.7593360995850622,
|
| 129 |
+
"eval_f1": 0.7561505755143376,
|
| 130 |
+
"eval_loss": 0.6851304173469543,
|
| 131 |
+
"eval_runtime": 78.2702,
|
| 132 |
+
"eval_samples_per_second": 3.079,
|
| 133 |
+
"eval_steps_per_second": 0.319,
|
| 134 |
+
"step": 150
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.027027027027027,
|
| 138 |
+
"grad_norm": 6.484254360198975,
|
| 139 |
+
"learning_rate": 3.153153153153153e-05,
|
| 140 |
+
"loss": 0.1699,
|
| 141 |
+
"step": 160
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.054054054054054,
|
| 145 |
+
"grad_norm": 4.243548393249512,
|
| 146 |
+
"learning_rate": 3.0030030030030033e-05,
|
| 147 |
+
"loss": 0.1404,
|
| 148 |
+
"step": 170
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.081081081081081,
|
| 152 |
+
"grad_norm": 4.49724006652832,
|
| 153 |
+
"learning_rate": 2.852852852852853e-05,
|
| 154 |
+
"loss": 0.2383,
|
| 155 |
+
"step": 180
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.108108108108108,
|
| 159 |
+
"grad_norm": 5.5315632820129395,
|
| 160 |
+
"learning_rate": 2.702702702702703e-05,
|
| 161 |
+
"loss": 0.3597,
|
| 162 |
+
"step": 190
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.135135135135135,
|
| 166 |
+
"grad_norm": 7.347559452056885,
|
| 167 |
+
"learning_rate": 2.552552552552553e-05,
|
| 168 |
+
"loss": 0.1501,
|
| 169 |
+
"step": 200
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.1621621621621623,
|
| 173 |
+
"grad_norm": 0.20061562955379486,
|
| 174 |
+
"learning_rate": 2.4024024024024024e-05,
|
| 175 |
+
"loss": 0.1769,
|
| 176 |
+
"step": 210
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.189189189189189,
|
| 180 |
+
"grad_norm": 0.2758616507053375,
|
| 181 |
+
"learning_rate": 2.2522522522522523e-05,
|
| 182 |
+
"loss": 0.2339,
|
| 183 |
+
"step": 220
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.2027027027027026,
|
| 187 |
+
"eval_accuracy": 0.8008298755186722,
|
| 188 |
+
"eval_f1": 0.7992975614249908,
|
| 189 |
+
"eval_loss": 0.5251602530479431,
|
| 190 |
+
"eval_runtime": 75.07,
|
| 191 |
+
"eval_samples_per_second": 3.21,
|
| 192 |
+
"eval_steps_per_second": 0.333,
|
| 193 |
+
"step": 225
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 3.0135135135135136,
|
| 197 |
+
"grad_norm": 8.580607414245605,
|
| 198 |
+
"learning_rate": 2.102102102102102e-05,
|
| 199 |
+
"loss": 0.8979,
|
| 200 |
+
"step": 230
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.0405405405405403,
|
| 204 |
+
"grad_norm": 0.5315948724746704,
|
| 205 |
+
"learning_rate": 1.951951951951952e-05,
|
| 206 |
+
"loss": 0.0559,
|
| 207 |
+
"step": 240
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 3.0675675675675675,
|
| 211 |
+
"grad_norm": 0.13150528073310852,
|
| 212 |
+
"learning_rate": 1.801801801801802e-05,
|
| 213 |
+
"loss": 0.1062,
|
| 214 |
+
"step": 250
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 3.0945945945945947,
|
| 218 |
+
"grad_norm": 19.857810974121094,
|
| 219 |
+
"learning_rate": 1.6516516516516518e-05,
|
| 220 |
+
"loss": 0.1066,
|
| 221 |
+
"step": 260
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 3.1216216216216215,
|
| 225 |
+
"grad_norm": 1.9958362579345703,
|
| 226 |
+
"learning_rate": 1.5015015015015016e-05,
|
| 227 |
+
"loss": 0.1944,
|
| 228 |
+
"step": 270
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 3.1486486486486487,
|
| 232 |
+
"grad_norm": 16.243772506713867,
|
| 233 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 234 |
+
"loss": 0.137,
|
| 235 |
+
"step": 280
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 3.175675675675676,
|
| 239 |
+
"grad_norm": 3.6971592903137207,
|
| 240 |
+
"learning_rate": 1.2012012012012012e-05,
|
| 241 |
+
"loss": 0.1812,
|
| 242 |
+
"step": 290
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.2027027027027026,
|
| 246 |
+
"grad_norm": 1.1694248914718628,
|
| 247 |
+
"learning_rate": 1.051051051051051e-05,
|
| 248 |
+
"loss": 0.1931,
|
| 249 |
+
"step": 300
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.2027027027027026,
|
| 253 |
+
"eval_accuracy": 0.8340248962655602,
|
| 254 |
+
"eval_f1": 0.8341831246711504,
|
| 255 |
+
"eval_loss": 0.4942285716533661,
|
| 256 |
+
"eval_runtime": 73.8969,
|
| 257 |
+
"eval_samples_per_second": 3.261,
|
| 258 |
+
"eval_steps_per_second": 0.338,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 4.027027027027027,
|
| 263 |
+
"grad_norm": 2.825990915298462,
|
| 264 |
+
"learning_rate": 9.00900900900901e-06,
|
| 265 |
+
"loss": 0.0731,
|
| 266 |
+
"step": 310
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.054054054054054,
|
| 270 |
+
"grad_norm": 0.2709617614746094,
|
| 271 |
+
"learning_rate": 7.507507507507508e-06,
|
| 272 |
+
"loss": 0.0751,
|
| 273 |
+
"step": 320
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 4.081081081081081,
|
| 277 |
+
"grad_norm": 0.10882856696844101,
|
| 278 |
+
"learning_rate": 6.006006006006006e-06,
|
| 279 |
+
"loss": 0.0774,
|
| 280 |
+
"step": 330
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 4.108108108108108,
|
| 284 |
+
"grad_norm": 0.09481658786535263,
|
| 285 |
+
"learning_rate": 4.504504504504505e-06,
|
| 286 |
+
"loss": 0.0567,
|
| 287 |
+
"step": 340
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 4.135135135135135,
|
| 291 |
+
"grad_norm": 0.3658810257911682,
|
| 292 |
+
"learning_rate": 3.003003003003003e-06,
|
| 293 |
+
"loss": 0.0438,
|
| 294 |
+
"step": 350
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 4.162162162162162,
|
| 298 |
+
"grad_norm": 0.9697806239128113,
|
| 299 |
+
"learning_rate": 1.5015015015015015e-06,
|
| 300 |
+
"loss": 0.098,
|
| 301 |
+
"step": 360
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 4.1891891891891895,
|
| 305 |
+
"grad_norm": 0.357666552066803,
|
| 306 |
+
"learning_rate": 0.0,
|
| 307 |
+
"loss": 0.1037,
|
| 308 |
+
"step": 370
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.1891891891891895,
|
| 312 |
+
"eval_accuracy": 0.8340248962655602,
|
| 313 |
+
"eval_f1": 0.8346934110853106,
|
| 314 |
+
"eval_loss": 0.47942548990249634,
|
| 315 |
+
"eval_runtime": 73.9617,
|
| 316 |
+
"eval_samples_per_second": 3.258,
|
| 317 |
+
"eval_steps_per_second": 0.338,
|
| 318 |
+
"step": 370
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 4.1891891891891895,
|
| 322 |
+
"step": 370,
|
| 323 |
+
"total_flos": 3.2102444558954004e+18,
|
| 324 |
+
"train_loss": 0.36656422937238536,
|
| 325 |
+
"train_runtime": 1888.2958,
|
| 326 |
+
"train_samples_per_second": 1.959,
|
| 327 |
+
"train_steps_per_second": 0.196
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 4.1891891891891895,
|
| 331 |
+
"eval_accuracy": 0.9784075573549258,
|
| 332 |
+
"eval_f1": 0.9783996585344938,
|
| 333 |
+
"eval_loss": 0.06370694935321808,
|
| 334 |
+
"eval_runtime": 252.958,
|
| 335 |
+
"eval_samples_per_second": 2.929,
|
| 336 |
+
"eval_steps_per_second": 0.296,
|
| 337 |
+
"step": 370
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 4.1891891891891895,
|
| 341 |
+
"eval_accuracy": 0.8067415730337079,
|
| 342 |
+
"eval_f1": 0.8059471321937128,
|
| 343 |
+
"eval_loss": 0.6186416745185852,
|
| 344 |
+
"eval_runtime": 137.3351,
|
| 345 |
+
"eval_samples_per_second": 3.24,
|
| 346 |
+
"eval_steps_per_second": 0.328,
|
| 347 |
+
"step": 370
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 4.1891891891891895,
|
| 351 |
+
"eval_accuracy": 0.8340248962655602,
|
| 352 |
+
"eval_f1": 0.8346934110853106,
|
| 353 |
+
"eval_loss": 0.47942548990249634,
|
| 354 |
+
"eval_runtime": 73.4732,
|
| 355 |
+
"eval_samples_per_second": 3.28,
|
| 356 |
+
"eval_steps_per_second": 0.34,
|
| 357 |
+
"step": 370
|
| 358 |
+
}
|
| 359 |
+
],
|
| 360 |
+
"logging_steps": 10,
|
| 361 |
+
"max_steps": 370,
|
| 362 |
+
"num_input_tokens_seen": 0,
|
| 363 |
+
"num_train_epochs": 9223372036854775807,
|
| 364 |
+
"save_steps": 500,
|
| 365 |
+
"stateful_callbacks": {
|
| 366 |
+
"TrainerControl": {
|
| 367 |
+
"args": {
|
| 368 |
+
"should_epoch_stop": false,
|
| 369 |
+
"should_evaluate": false,
|
| 370 |
+
"should_log": false,
|
| 371 |
+
"should_save": true,
|
| 372 |
+
"should_training_stop": true
|
| 373 |
+
},
|
| 374 |
+
"attributes": {}
|
| 375 |
+
}
|
| 376 |
+
},
|
| 377 |
+
"total_flos": 3.2102444558954004e+18,
|
| 378 |
+
"train_batch_size": 10,
|
| 379 |
+
"trial_name": null,
|
| 380 |
+
"trial_params": null
|
| 381 |
+
}
|
val_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.1891891891891895,
|
| 3 |
+
"eval_accuracy": 0.8340248962655602,
|
| 4 |
+
"eval_f1": 0.8346934110853106,
|
| 5 |
+
"eval_loss": 0.47942548990249634,
|
| 6 |
+
"eval_runtime": 73.4732,
|
| 7 |
+
"eval_samples_per_second": 3.28,
|
| 8 |
+
"eval_steps_per_second": 0.34
|
| 9 |
+
}
|