End of training
Browse files- README.md +15 -4
- all_results.json +6 -6
- model.safetensors +1 -1
- runs/Mar01_10-29-38_ca6729c6f81a/events.out.tfevents.1709288980.ca6729c6f81a.27.0 +3 -0
- train_results.json +6 -6
- trainer_state.json +268 -22
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -46,13 +46,24 @@ The following hyperparameters were used during training:
|
|
| 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 |
-
- num_epochs:
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
|
| 57 |
|
| 58 |
### Framework versions
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.4840
|
| 21 |
+
- Accuracy: 0.8648
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 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 |
+
- num_epochs: 12
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
+
| 1.3961 | 0.99 | 61 | 0.5629 | 0.7725 |
|
| 56 |
+
| 0.4982 | 2.0 | 123 | 0.3991 | 0.8435 |
|
| 57 |
+
| 0.3563 | 2.99 | 184 | 0.4330 | 0.8272 |
|
| 58 |
+
| 0.2314 | 4.0 | 246 | 0.3969 | 0.8554 |
|
| 59 |
+
| 0.1815 | 4.99 | 307 | 0.4492 | 0.8435 |
|
| 60 |
+
| 0.1332 | 6.0 | 369 | 0.4474 | 0.8580 |
|
| 61 |
+
| 0.0869 | 6.99 | 430 | 0.4520 | 0.8631 |
|
| 62 |
+
| 0.0844 | 8.0 | 492 | 0.4469 | 0.8640 |
|
| 63 |
+
| 0.0681 | 8.99 | 553 | 0.4533 | 0.8717 |
|
| 64 |
+
| 0.0574 | 10.0 | 615 | 0.4952 | 0.8597 |
|
| 65 |
+
| 0.0477 | 10.99 | 676 | 0.4772 | 0.8674 |
|
| 66 |
+
| 0.0454 | 11.9 | 732 | 0.4840 | 0.8648 |
|
| 67 |
|
| 68 |
|
| 69 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 11.9,
|
| 3 |
+
"total_flos": 7.238851133027512e+18,
|
| 4 |
+
"train_loss": 0.2366401759978852,
|
| 5 |
+
"train_runtime": 2240.6293,
|
| 6 |
+
"train_samples_per_second": 42.02,
|
| 7 |
+
"train_steps_per_second": 0.327
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343239356
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdb3ff87ca7808f0c4cf62a3446f5c26b1e35f88306fdf942ced906aa80be2a0
|
| 3 |
size 343239356
|
runs/Mar01_10-29-38_ca6729c6f81a/events.out.tfevents.1709288980.ca6729c6f81a.27.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47205af3a3d9a1e65bbce75aaa0bc3f746bb89ae057ad273eb57e6335958e7ea
|
| 3 |
+
size 13628
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 11.9,
|
| 3 |
+
"total_flos": 7.238851133027512e+18,
|
| 4 |
+
"train_loss": 0.2366401759978852,
|
| 5 |
+
"train_runtime": 2240.6293,
|
| 6 |
+
"train_samples_per_second": 42.02,
|
| 7 |
+
"train_steps_per_second": 0.327
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,45 +1,291 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "skincare-detection/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.52,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 32
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.99,
|
| 20 |
-
"eval_accuracy": 0.
|
| 21 |
-
"eval_loss": 0.
|
| 22 |
-
"eval_runtime": 12.
|
| 23 |
-
"eval_samples_per_second": 96.
|
| 24 |
-
"eval_steps_per_second": 3.
|
| 25 |
"step": 61
|
| 26 |
},
|
| 27 |
{
|
| 28 |
-
"epoch":
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
|
| 34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
}
|
| 36 |
],
|
| 37 |
"logging_steps": 32,
|
| 38 |
-
"max_steps":
|
| 39 |
"num_input_tokens_seen": 0,
|
| 40 |
-
"num_train_epochs":
|
| 41 |
"save_steps": 500,
|
| 42 |
-
"total_flos":
|
| 43 |
"train_batch_size": 32,
|
| 44 |
"trial_name": null,
|
| 45 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8716852010265184,
|
| 3 |
+
"best_model_checkpoint": "skincare-detection/checkpoint-553",
|
| 4 |
+
"epoch": 11.902439024390244,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 732,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.52,
|
| 13 |
+
"grad_norm": 1.0143417119979858,
|
| 14 |
+
"learning_rate": 8.64864864864865e-05,
|
| 15 |
+
"loss": 1.3961,
|
| 16 |
"step": 32
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.99,
|
| 20 |
+
"eval_accuracy": 0.7724550898203593,
|
| 21 |
+
"eval_loss": 0.5629431009292603,
|
| 22 |
+
"eval_runtime": 12.1216,
|
| 23 |
+
"eval_samples_per_second": 96.439,
|
| 24 |
+
"eval_steps_per_second": 3.052,
|
| 25 |
"step": 61
|
| 26 |
},
|
| 27 |
{
|
| 28 |
+
"epoch": 1.04,
|
| 29 |
+
"grad_norm": 0.6657726764678955,
|
| 30 |
+
"learning_rate": 0.000172972972972973,
|
| 31 |
+
"loss": 0.6454,
|
| 32 |
+
"step": 64
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.56,
|
| 36 |
+
"grad_norm": 0.6649633049964905,
|
| 37 |
+
"learning_rate": 0.0001933130699088146,
|
| 38 |
+
"loss": 0.4982,
|
| 39 |
+
"step": 96
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.0,
|
| 43 |
+
"eval_accuracy": 0.8434559452523525,
|
| 44 |
+
"eval_loss": 0.3991105854511261,
|
| 45 |
+
"eval_runtime": 12.1709,
|
| 46 |
+
"eval_samples_per_second": 96.049,
|
| 47 |
+
"eval_steps_per_second": 3.04,
|
| 48 |
+
"step": 123
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.08,
|
| 52 |
+
"grad_norm": 0.7564620971679688,
|
| 53 |
+
"learning_rate": 0.00018358662613981763,
|
| 54 |
+
"loss": 0.4536,
|
| 55 |
+
"step": 128
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 2.6,
|
| 59 |
+
"grad_norm": 0.6977857351303101,
|
| 60 |
+
"learning_rate": 0.00017386018237082067,
|
| 61 |
+
"loss": 0.3563,
|
| 62 |
+
"step": 160
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.99,
|
| 66 |
+
"eval_accuracy": 0.8272027373823782,
|
| 67 |
+
"eval_loss": 0.43296942114830017,
|
| 68 |
+
"eval_runtime": 12.3181,
|
| 69 |
+
"eval_samples_per_second": 94.901,
|
| 70 |
+
"eval_steps_per_second": 3.004,
|
| 71 |
+
"step": 184
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.12,
|
| 75 |
+
"grad_norm": 0.7642468214035034,
|
| 76 |
+
"learning_rate": 0.0001641337386018237,
|
| 77 |
+
"loss": 0.3169,
|
| 78 |
+
"step": 192
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.64,
|
| 82 |
+
"grad_norm": 0.9004422426223755,
|
| 83 |
+
"learning_rate": 0.00015440729483282676,
|
| 84 |
+
"loss": 0.2314,
|
| 85 |
+
"step": 224
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 4.0,
|
| 89 |
+
"eval_accuracy": 0.8554319931565441,
|
| 90 |
+
"eval_loss": 0.39688870310783386,
|
| 91 |
+
"eval_runtime": 12.3055,
|
| 92 |
+
"eval_samples_per_second": 94.998,
|
| 93 |
+
"eval_steps_per_second": 3.007,
|
| 94 |
+
"step": 246
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.16,
|
| 98 |
+
"grad_norm": 0.9273125529289246,
|
| 99 |
+
"learning_rate": 0.0001446808510638298,
|
| 100 |
+
"loss": 0.2055,
|
| 101 |
+
"step": 256
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.68,
|
| 105 |
+
"grad_norm": 0.6541422009468079,
|
| 106 |
+
"learning_rate": 0.00013495440729483285,
|
| 107 |
+
"loss": 0.1815,
|
| 108 |
+
"step": 288
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.99,
|
| 112 |
+
"eval_accuracy": 0.8434559452523525,
|
| 113 |
+
"eval_loss": 0.44923701882362366,
|
| 114 |
+
"eval_runtime": 12.4125,
|
| 115 |
+
"eval_samples_per_second": 94.179,
|
| 116 |
+
"eval_steps_per_second": 2.981,
|
| 117 |
+
"step": 307
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 5.2,
|
| 121 |
+
"grad_norm": 1.0498323440551758,
|
| 122 |
+
"learning_rate": 0.00012522796352583589,
|
| 123 |
+
"loss": 0.1514,
|
| 124 |
+
"step": 320
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 5.72,
|
| 128 |
+
"grad_norm": 1.087367057800293,
|
| 129 |
+
"learning_rate": 0.00011550151975683892,
|
| 130 |
+
"loss": 0.1332,
|
| 131 |
+
"step": 352
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 6.0,
|
| 135 |
+
"eval_accuracy": 0.8579982891360137,
|
| 136 |
+
"eval_loss": 0.44741156697273254,
|
| 137 |
+
"eval_runtime": 12.1735,
|
| 138 |
+
"eval_samples_per_second": 96.029,
|
| 139 |
+
"eval_steps_per_second": 3.039,
|
| 140 |
+
"step": 369
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 6.24,
|
| 144 |
+
"grad_norm": 0.9595869183540344,
|
| 145 |
+
"learning_rate": 0.00010577507598784195,
|
| 146 |
+
"loss": 0.1201,
|
| 147 |
+
"step": 384
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.76,
|
| 151 |
+
"grad_norm": 0.39300984144210815,
|
| 152 |
+
"learning_rate": 9.6048632218845e-05,
|
| 153 |
+
"loss": 0.0869,
|
| 154 |
+
"step": 416
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 6.99,
|
| 158 |
+
"eval_accuracy": 0.863130881094953,
|
| 159 |
+
"eval_loss": 0.45202794671058655,
|
| 160 |
+
"eval_runtime": 12.4693,
|
| 161 |
+
"eval_samples_per_second": 93.75,
|
| 162 |
+
"eval_steps_per_second": 2.967,
|
| 163 |
+
"step": 430
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 7.28,
|
| 167 |
+
"grad_norm": 0.9669052362442017,
|
| 168 |
+
"learning_rate": 8.632218844984803e-05,
|
| 169 |
+
"loss": 0.0991,
|
| 170 |
+
"step": 448
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 7.8,
|
| 174 |
+
"grad_norm": 0.8003025650978088,
|
| 175 |
+
"learning_rate": 7.659574468085106e-05,
|
| 176 |
+
"loss": 0.0844,
|
| 177 |
+
"step": 480
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 8.0,
|
| 181 |
+
"eval_accuracy": 0.8639863130881095,
|
| 182 |
+
"eval_loss": 0.44686540961265564,
|
| 183 |
+
"eval_runtime": 12.1322,
|
| 184 |
+
"eval_samples_per_second": 96.355,
|
| 185 |
+
"eval_steps_per_second": 3.05,
|
| 186 |
+
"step": 492
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 8.33,
|
| 190 |
+
"grad_norm": 0.3683207333087921,
|
| 191 |
+
"learning_rate": 6.686930091185411e-05,
|
| 192 |
+
"loss": 0.0811,
|
| 193 |
+
"step": 512
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 8.85,
|
| 197 |
+
"grad_norm": 0.6750203371047974,
|
| 198 |
+
"learning_rate": 5.714285714285714e-05,
|
| 199 |
+
"loss": 0.0681,
|
| 200 |
+
"step": 544
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 8.99,
|
| 204 |
+
"eval_accuracy": 0.8716852010265184,
|
| 205 |
+
"eval_loss": 0.45333394408226013,
|
| 206 |
+
"eval_runtime": 12.2392,
|
| 207 |
+
"eval_samples_per_second": 95.513,
|
| 208 |
+
"eval_steps_per_second": 3.023,
|
| 209 |
+
"step": 553
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 9.37,
|
| 213 |
+
"grad_norm": 0.48275861144065857,
|
| 214 |
+
"learning_rate": 4.741641337386019e-05,
|
| 215 |
+
"loss": 0.0635,
|
| 216 |
+
"step": 576
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 9.89,
|
| 220 |
+
"grad_norm": 0.8461657762527466,
|
| 221 |
+
"learning_rate": 3.768996960486322e-05,
|
| 222 |
+
"loss": 0.0574,
|
| 223 |
+
"step": 608
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 10.0,
|
| 227 |
+
"eval_accuracy": 0.8597091531223268,
|
| 228 |
+
"eval_loss": 0.4952048361301422,
|
| 229 |
+
"eval_runtime": 12.278,
|
| 230 |
+
"eval_samples_per_second": 95.211,
|
| 231 |
+
"eval_steps_per_second": 3.014,
|
| 232 |
+
"step": 615
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 10.41,
|
| 236 |
+
"grad_norm": 0.2595687806606293,
|
| 237 |
+
"learning_rate": 2.796352583586626e-05,
|
| 238 |
+
"loss": 0.0518,
|
| 239 |
+
"step": 640
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 10.93,
|
| 243 |
+
"grad_norm": 0.39481160044670105,
|
| 244 |
+
"learning_rate": 1.82370820668693e-05,
|
| 245 |
+
"loss": 0.0477,
|
| 246 |
+
"step": 672
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 10.99,
|
| 250 |
+
"eval_accuracy": 0.8674080410607357,
|
| 251 |
+
"eval_loss": 0.4772116541862488,
|
| 252 |
+
"eval_runtime": 12.2102,
|
| 253 |
+
"eval_samples_per_second": 95.74,
|
| 254 |
+
"eval_steps_per_second": 3.03,
|
| 255 |
+
"step": 676
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 11.45,
|
| 259 |
+
"grad_norm": 0.43194687366485596,
|
| 260 |
+
"learning_rate": 8.510638297872341e-06,
|
| 261 |
+
"loss": 0.0454,
|
| 262 |
+
"step": 704
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 11.9,
|
| 266 |
+
"eval_accuracy": 0.864841745081266,
|
| 267 |
+
"eval_loss": 0.48397254943847656,
|
| 268 |
+
"eval_runtime": 12.6433,
|
| 269 |
+
"eval_samples_per_second": 92.46,
|
| 270 |
+
"eval_steps_per_second": 2.926,
|
| 271 |
+
"step": 732
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 11.9,
|
| 275 |
+
"step": 732,
|
| 276 |
+
"total_flos": 7.238851133027512e+18,
|
| 277 |
+
"train_loss": 0.2366401759978852,
|
| 278 |
+
"train_runtime": 2240.6293,
|
| 279 |
+
"train_samples_per_second": 42.02,
|
| 280 |
+
"train_steps_per_second": 0.327
|
| 281 |
}
|
| 282 |
],
|
| 283 |
"logging_steps": 32,
|
| 284 |
+
"max_steps": 732,
|
| 285 |
"num_input_tokens_seen": 0,
|
| 286 |
+
"num_train_epochs": 12,
|
| 287 |
"save_steps": 500,
|
| 288 |
+
"total_flos": 7.238851133027512e+18,
|
| 289 |
"train_batch_size": 32,
|
| 290 |
"trial_name": null,
|
| 291 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd196ff8c32cf67e6b93a873f443390233b9329421c2b02bd8fff51e4392f3e2
|
| 3 |
size 4920
|