Commit
•
46f5b3f
1
Parent(s):
6de6459
End of training
Browse files- README.md +5 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +727 -0
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: microsoft/beit-large-patch16-384
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -15,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# beit-large-patch16-384-limb-person-crop-8_1e-4_1e-3_0.05
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [microsoft/beit-large-patch16-384](https://huggingface.co/microsoft/beit-large-patch16-384) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: microsoft/beit-large-patch16-384
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 17 |
|
| 18 |
# beit-large-patch16-384-limb-person-crop-8_1e-4_1e-3_0.05
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [microsoft/beit-large-patch16-384](https://huggingface.co/microsoft/beit-large-patch16-384) on the c14kevincardenas/beta_caller_284_person_crop dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.7287
|
| 23 |
+
- Accuracy: 0.7662
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.7661691542288557,
|
| 4 |
+
"eval_loss": 0.7286587357521057,
|
| 5 |
+
"eval_runtime": 15.0764,
|
| 6 |
+
"eval_samples_per_second": 79.992,
|
| 7 |
+
"eval_steps_per_second": 2.52,
|
| 8 |
+
"total_flos": 5.510586115727032e+19,
|
| 9 |
+
"train_loss": 1.022248704411159,
|
| 10 |
+
"train_runtime": 1933.1394,
|
| 11 |
+
"train_samples_per_second": 35.331,
|
| 12 |
+
"train_steps_per_second": 1.107
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.7661691542288557,
|
| 4 |
+
"eval_loss": 0.7286587357521057,
|
| 5 |
+
"eval_runtime": 15.0764,
|
| 6 |
+
"eval_samples_per_second": 79.992,
|
| 7 |
+
"eval_steps_per_second": 2.52
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 5.510586115727032e+19,
|
| 4 |
+
"train_loss": 1.022248704411159,
|
| 5 |
+
"train_runtime": 1933.1394,
|
| 6 |
+
"train_samples_per_second": 35.331,
|
| 7 |
+
"train_steps_per_second": 1.107
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,727 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7286587357521057,
|
| 3 |
+
"best_model_checkpoint": "/media/mldrive/kcardenas/limb_classification_person_crop/beit-large-patch16-384/8_1e-4_1e-3_0.05/checkpoint-1712",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2140,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11682242990654206,
|
| 13 |
+
"grad_norm": 1276615.0,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 1.5814,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2336448598130841,
|
| 20 |
+
"grad_norm": 821654.8125,
|
| 21 |
+
"learning_rate": 1e-05,
|
| 22 |
+
"loss": 1.471,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.35046728971962615,
|
| 27 |
+
"grad_norm": 684046.3125,
|
| 28 |
+
"learning_rate": 1.5e-05,
|
| 29 |
+
"loss": 1.4122,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4672897196261682,
|
| 34 |
+
"grad_norm": 479149.25,
|
| 35 |
+
"learning_rate": 2e-05,
|
| 36 |
+
"loss": 1.4047,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5841121495327103,
|
| 41 |
+
"grad_norm": 486470.03125,
|
| 42 |
+
"learning_rate": 2.5e-05,
|
| 43 |
+
"loss": 1.3682,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.7009345794392523,
|
| 48 |
+
"grad_norm": 376188.6875,
|
| 49 |
+
"learning_rate": 3e-05,
|
| 50 |
+
"loss": 1.321,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.8177570093457944,
|
| 55 |
+
"grad_norm": 520384.96875,
|
| 56 |
+
"learning_rate": 3.5e-05,
|
| 57 |
+
"loss": 1.295,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.9345794392523364,
|
| 62 |
+
"grad_norm": 544985.25,
|
| 63 |
+
"learning_rate": 4e-05,
|
| 64 |
+
"loss": 1.2787,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.0,
|
| 69 |
+
"eval_accuracy": 0.37728026533996684,
|
| 70 |
+
"eval_loss": 1.425036907196045,
|
| 71 |
+
"eval_runtime": 14.9581,
|
| 72 |
+
"eval_samples_per_second": 80.625,
|
| 73 |
+
"eval_steps_per_second": 2.54,
|
| 74 |
+
"step": 214
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0514018691588785,
|
| 78 |
+
"grad_norm": 428270.46875,
|
| 79 |
+
"learning_rate": 4.5e-05,
|
| 80 |
+
"loss": 1.2546,
|
| 81 |
+
"step": 225
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.1682242990654206,
|
| 85 |
+
"grad_norm": 290375.71875,
|
| 86 |
+
"learning_rate": 5e-05,
|
| 87 |
+
"loss": 1.2541,
|
| 88 |
+
"step": 250
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.2850467289719627,
|
| 92 |
+
"grad_norm": 369930.53125,
|
| 93 |
+
"learning_rate": 5.500000000000001e-05,
|
| 94 |
+
"loss": 1.1907,
|
| 95 |
+
"step": 275
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.4018691588785046,
|
| 99 |
+
"grad_norm": 300592.46875,
|
| 100 |
+
"learning_rate": 6e-05,
|
| 101 |
+
"loss": 1.2422,
|
| 102 |
+
"step": 300
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.5186915887850467,
|
| 106 |
+
"grad_norm": 416197.59375,
|
| 107 |
+
"learning_rate": 6.500000000000001e-05,
|
| 108 |
+
"loss": 1.2124,
|
| 109 |
+
"step": 325
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.6355140186915889,
|
| 113 |
+
"grad_norm": 286849.03125,
|
| 114 |
+
"learning_rate": 7e-05,
|
| 115 |
+
"loss": 1.1897,
|
| 116 |
+
"step": 350
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.7523364485981308,
|
| 120 |
+
"grad_norm": 316147.9375,
|
| 121 |
+
"learning_rate": 7.500000000000001e-05,
|
| 122 |
+
"loss": 1.2249,
|
| 123 |
+
"step": 375
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.8691588785046729,
|
| 127 |
+
"grad_norm": 341742.9375,
|
| 128 |
+
"learning_rate": 8e-05,
|
| 129 |
+
"loss": 1.1379,
|
| 130 |
+
"step": 400
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.985981308411215,
|
| 134 |
+
"grad_norm": 350417.34375,
|
| 135 |
+
"learning_rate": 8.5e-05,
|
| 136 |
+
"loss": 1.181,
|
| 137 |
+
"step": 425
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 2.0,
|
| 141 |
+
"eval_accuracy": 0.572139303482587,
|
| 142 |
+
"eval_loss": 1.0375266075134277,
|
| 143 |
+
"eval_runtime": 15.2687,
|
| 144 |
+
"eval_samples_per_second": 78.985,
|
| 145 |
+
"eval_steps_per_second": 2.489,
|
| 146 |
+
"step": 428
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.102803738317757,
|
| 150 |
+
"grad_norm": 530801.1875,
|
| 151 |
+
"learning_rate": 9e-05,
|
| 152 |
+
"loss": 1.2035,
|
| 153 |
+
"step": 450
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.2196261682242993,
|
| 157 |
+
"grad_norm": 354914.9375,
|
| 158 |
+
"learning_rate": 9.5e-05,
|
| 159 |
+
"loss": 1.155,
|
| 160 |
+
"step": 475
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.336448598130841,
|
| 164 |
+
"grad_norm": 212917.859375,
|
| 165 |
+
"learning_rate": 0.0001,
|
| 166 |
+
"loss": 1.1589,
|
| 167 |
+
"step": 500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.453271028037383,
|
| 171 |
+
"grad_norm": 304632.125,
|
| 172 |
+
"learning_rate": 9.847560975609756e-05,
|
| 173 |
+
"loss": 1.1629,
|
| 174 |
+
"step": 525
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.5700934579439254,
|
| 178 |
+
"grad_norm": 199257.875,
|
| 179 |
+
"learning_rate": 9.695121951219512e-05,
|
| 180 |
+
"loss": 1.1869,
|
| 181 |
+
"step": 550
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.6869158878504673,
|
| 185 |
+
"grad_norm": 333972.34375,
|
| 186 |
+
"learning_rate": 9.542682926829268e-05,
|
| 187 |
+
"loss": 1.1715,
|
| 188 |
+
"step": 575
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.803738317757009,
|
| 192 |
+
"grad_norm": 339221.59375,
|
| 193 |
+
"learning_rate": 9.390243902439024e-05,
|
| 194 |
+
"loss": 1.1284,
|
| 195 |
+
"step": 600
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.9205607476635516,
|
| 199 |
+
"grad_norm": 261420.609375,
|
| 200 |
+
"learning_rate": 9.237804878048782e-05,
|
| 201 |
+
"loss": 1.1663,
|
| 202 |
+
"step": 625
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 3.0,
|
| 206 |
+
"eval_accuracy": 0.6086235489220564,
|
| 207 |
+
"eval_loss": 1.0081062316894531,
|
| 208 |
+
"eval_runtime": 15.1144,
|
| 209 |
+
"eval_samples_per_second": 79.791,
|
| 210 |
+
"eval_steps_per_second": 2.514,
|
| 211 |
+
"step": 642
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.0373831775700935,
|
| 215 |
+
"grad_norm": 309623.21875,
|
| 216 |
+
"learning_rate": 9.085365853658538e-05,
|
| 217 |
+
"loss": 1.1429,
|
| 218 |
+
"step": 650
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.1542056074766354,
|
| 222 |
+
"grad_norm": 160663.140625,
|
| 223 |
+
"learning_rate": 8.932926829268294e-05,
|
| 224 |
+
"loss": 1.1022,
|
| 225 |
+
"step": 675
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.2710280373831777,
|
| 229 |
+
"grad_norm": 274984.09375,
|
| 230 |
+
"learning_rate": 8.78048780487805e-05,
|
| 231 |
+
"loss": 1.1147,
|
| 232 |
+
"step": 700
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.3878504672897196,
|
| 236 |
+
"grad_norm": 303066.5,
|
| 237 |
+
"learning_rate": 8.628048780487805e-05,
|
| 238 |
+
"loss": 1.1132,
|
| 239 |
+
"step": 725
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.5046728971962615,
|
| 243 |
+
"grad_norm": 289778.75,
|
| 244 |
+
"learning_rate": 8.475609756097561e-05,
|
| 245 |
+
"loss": 1.0983,
|
| 246 |
+
"step": 750
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.621495327102804,
|
| 250 |
+
"grad_norm": 235902.796875,
|
| 251 |
+
"learning_rate": 8.323170731707317e-05,
|
| 252 |
+
"loss": 1.0705,
|
| 253 |
+
"step": 775
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 3.7383177570093458,
|
| 257 |
+
"grad_norm": 285825.75,
|
| 258 |
+
"learning_rate": 8.170731707317073e-05,
|
| 259 |
+
"loss": 1.0712,
|
| 260 |
+
"step": 800
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.8551401869158877,
|
| 264 |
+
"grad_norm": 223396.53125,
|
| 265 |
+
"learning_rate": 8.018292682926831e-05,
|
| 266 |
+
"loss": 1.119,
|
| 267 |
+
"step": 825
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.97196261682243,
|
| 271 |
+
"grad_norm": 255677.21875,
|
| 272 |
+
"learning_rate": 7.865853658536587e-05,
|
| 273 |
+
"loss": 1.0721,
|
| 274 |
+
"step": 850
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 4.0,
|
| 278 |
+
"eval_accuracy": 0.6699834162520729,
|
| 279 |
+
"eval_loss": 0.8916388154029846,
|
| 280 |
+
"eval_runtime": 15.2761,
|
| 281 |
+
"eval_samples_per_second": 78.947,
|
| 282 |
+
"eval_steps_per_second": 2.488,
|
| 283 |
+
"step": 856
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 4.088785046728972,
|
| 287 |
+
"grad_norm": 242165.375,
|
| 288 |
+
"learning_rate": 7.713414634146343e-05,
|
| 289 |
+
"loss": 1.059,
|
| 290 |
+
"step": 875
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.205607476635514,
|
| 294 |
+
"grad_norm": 288031.0625,
|
| 295 |
+
"learning_rate": 7.560975609756099e-05,
|
| 296 |
+
"loss": 1.0495,
|
| 297 |
+
"step": 900
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.322429906542056,
|
| 301 |
+
"grad_norm": 333165.71875,
|
| 302 |
+
"learning_rate": 7.408536585365855e-05,
|
| 303 |
+
"loss": 1.0531,
|
| 304 |
+
"step": 925
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.4392523364485985,
|
| 308 |
+
"grad_norm": 282719.25,
|
| 309 |
+
"learning_rate": 7.25609756097561e-05,
|
| 310 |
+
"loss": 1.0041,
|
| 311 |
+
"step": 950
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 4.55607476635514,
|
| 315 |
+
"grad_norm": 319271.28125,
|
| 316 |
+
"learning_rate": 7.103658536585366e-05,
|
| 317 |
+
"loss": 1.0423,
|
| 318 |
+
"step": 975
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 4.672897196261682,
|
| 322 |
+
"grad_norm": 164577.203125,
|
| 323 |
+
"learning_rate": 6.951219512195122e-05,
|
| 324 |
+
"loss": 1.0098,
|
| 325 |
+
"step": 1000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 4.789719626168225,
|
| 329 |
+
"grad_norm": 250858.84375,
|
| 330 |
+
"learning_rate": 6.798780487804878e-05,
|
| 331 |
+
"loss": 1.0329,
|
| 332 |
+
"step": 1025
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.906542056074766,
|
| 336 |
+
"grad_norm": 242649.671875,
|
| 337 |
+
"learning_rate": 6.646341463414634e-05,
|
| 338 |
+
"loss": 1.0532,
|
| 339 |
+
"step": 1050
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 5.0,
|
| 343 |
+
"eval_accuracy": 0.7089552238805971,
|
| 344 |
+
"eval_loss": 0.8216565251350403,
|
| 345 |
+
"eval_runtime": 15.36,
|
| 346 |
+
"eval_samples_per_second": 78.516,
|
| 347 |
+
"eval_steps_per_second": 2.474,
|
| 348 |
+
"step": 1070
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 5.0233644859813085,
|
| 352 |
+
"grad_norm": 252819.21875,
|
| 353 |
+
"learning_rate": 6.49390243902439e-05,
|
| 354 |
+
"loss": 1.0531,
|
| 355 |
+
"step": 1075
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 5.140186915887851,
|
| 359 |
+
"grad_norm": 397919.9375,
|
| 360 |
+
"learning_rate": 6.341463414634146e-05,
|
| 361 |
+
"loss": 0.9858,
|
| 362 |
+
"step": 1100
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 5.257009345794392,
|
| 366 |
+
"grad_norm": 303093.3125,
|
| 367 |
+
"learning_rate": 6.189024390243902e-05,
|
| 368 |
+
"loss": 0.9712,
|
| 369 |
+
"step": 1125
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 5.373831775700935,
|
| 373 |
+
"grad_norm": 224522.3125,
|
| 374 |
+
"learning_rate": 6.036585365853659e-05,
|
| 375 |
+
"loss": 0.9886,
|
| 376 |
+
"step": 1150
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 5.490654205607477,
|
| 380 |
+
"grad_norm": 246638.484375,
|
| 381 |
+
"learning_rate": 5.884146341463415e-05,
|
| 382 |
+
"loss": 0.9614,
|
| 383 |
+
"step": 1175
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 5.607476635514018,
|
| 387 |
+
"grad_norm": 234227.765625,
|
| 388 |
+
"learning_rate": 5.731707317073171e-05,
|
| 389 |
+
"loss": 0.9942,
|
| 390 |
+
"step": 1200
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 5.724299065420561,
|
| 394 |
+
"grad_norm": 222045.953125,
|
| 395 |
+
"learning_rate": 5.5792682926829274e-05,
|
| 396 |
+
"loss": 1.0155,
|
| 397 |
+
"step": 1225
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 5.841121495327103,
|
| 401 |
+
"grad_norm": 195089.328125,
|
| 402 |
+
"learning_rate": 5.4268292682926834e-05,
|
| 403 |
+
"loss": 0.9541,
|
| 404 |
+
"step": 1250
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 5.957943925233645,
|
| 408 |
+
"grad_norm": 187357.359375,
|
| 409 |
+
"learning_rate": 5.2743902439024394e-05,
|
| 410 |
+
"loss": 0.9923,
|
| 411 |
+
"step": 1275
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 6.0,
|
| 415 |
+
"eval_accuracy": 0.7139303482587065,
|
| 416 |
+
"eval_loss": 0.814013659954071,
|
| 417 |
+
"eval_runtime": 15.2349,
|
| 418 |
+
"eval_samples_per_second": 79.161,
|
| 419 |
+
"eval_steps_per_second": 2.494,
|
| 420 |
+
"step": 1284
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 6.074766355140187,
|
| 424 |
+
"grad_norm": 250117.3125,
|
| 425 |
+
"learning_rate": 5.121951219512195e-05,
|
| 426 |
+
"loss": 0.968,
|
| 427 |
+
"step": 1300
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 6.191588785046729,
|
| 431 |
+
"grad_norm": 299302.9375,
|
| 432 |
+
"learning_rate": 4.969512195121951e-05,
|
| 433 |
+
"loss": 0.9159,
|
| 434 |
+
"step": 1325
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 6.308411214953271,
|
| 438 |
+
"grad_norm": 247804.5625,
|
| 439 |
+
"learning_rate": 4.817073170731707e-05,
|
| 440 |
+
"loss": 0.9384,
|
| 441 |
+
"step": 1350
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 6.425233644859813,
|
| 445 |
+
"grad_norm": 356666.28125,
|
| 446 |
+
"learning_rate": 4.664634146341464e-05,
|
| 447 |
+
"loss": 0.9005,
|
| 448 |
+
"step": 1375
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 6.542056074766355,
|
| 452 |
+
"grad_norm": 230017.3125,
|
| 453 |
+
"learning_rate": 4.51219512195122e-05,
|
| 454 |
+
"loss": 0.9046,
|
| 455 |
+
"step": 1400
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 6.658878504672897,
|
| 459 |
+
"grad_norm": 234827.875,
|
| 460 |
+
"learning_rate": 4.359756097560976e-05,
|
| 461 |
+
"loss": 0.9122,
|
| 462 |
+
"step": 1425
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 6.775700934579439,
|
| 466 |
+
"grad_norm": 224243.6875,
|
| 467 |
+
"learning_rate": 4.207317073170732e-05,
|
| 468 |
+
"loss": 0.922,
|
| 469 |
+
"step": 1450
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 6.892523364485982,
|
| 473 |
+
"grad_norm": 248143.25,
|
| 474 |
+
"learning_rate": 4.0548780487804884e-05,
|
| 475 |
+
"loss": 0.9099,
|
| 476 |
+
"step": 1475
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 7.0,
|
| 480 |
+
"eval_accuracy": 0.7379767827529021,
|
| 481 |
+
"eval_loss": 0.7681299448013306,
|
| 482 |
+
"eval_runtime": 15.2011,
|
| 483 |
+
"eval_samples_per_second": 79.336,
|
| 484 |
+
"eval_steps_per_second": 2.5,
|
| 485 |
+
"step": 1498
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 7.009345794392523,
|
| 489 |
+
"grad_norm": 207523.8125,
|
| 490 |
+
"learning_rate": 3.9024390243902444e-05,
|
| 491 |
+
"loss": 0.9062,
|
| 492 |
+
"step": 1500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 7.126168224299065,
|
| 496 |
+
"grad_norm": 252034.734375,
|
| 497 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 498 |
+
"loss": 0.8461,
|
| 499 |
+
"step": 1525
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 7.242990654205608,
|
| 503 |
+
"grad_norm": 197750.71875,
|
| 504 |
+
"learning_rate": 3.597560975609756e-05,
|
| 505 |
+
"loss": 0.9418,
|
| 506 |
+
"step": 1550
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 7.359813084112149,
|
| 510 |
+
"grad_norm": 310201.53125,
|
| 511 |
+
"learning_rate": 3.445121951219512e-05,
|
| 512 |
+
"loss": 0.8688,
|
| 513 |
+
"step": 1575
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.4766355140186915,
|
| 517 |
+
"grad_norm": 422490.28125,
|
| 518 |
+
"learning_rate": 3.292682926829269e-05,
|
| 519 |
+
"loss": 0.8598,
|
| 520 |
+
"step": 1600
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.593457943925234,
|
| 524 |
+
"grad_norm": 254273.59375,
|
| 525 |
+
"learning_rate": 3.140243902439025e-05,
|
| 526 |
+
"loss": 0.9292,
|
| 527 |
+
"step": 1625
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.710280373831775,
|
| 531 |
+
"grad_norm": 234645.15625,
|
| 532 |
+
"learning_rate": 2.9878048780487805e-05,
|
| 533 |
+
"loss": 0.8837,
|
| 534 |
+
"step": 1650
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.827102803738318,
|
| 538 |
+
"grad_norm": 307339.125,
|
| 539 |
+
"learning_rate": 2.8353658536585365e-05,
|
| 540 |
+
"loss": 0.853,
|
| 541 |
+
"step": 1675
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 7.94392523364486,
|
| 545 |
+
"grad_norm": 290561.53125,
|
| 546 |
+
"learning_rate": 2.682926829268293e-05,
|
| 547 |
+
"loss": 0.8518,
|
| 548 |
+
"step": 1700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 8.0,
|
| 552 |
+
"eval_accuracy": 0.7661691542288557,
|
| 553 |
+
"eval_loss": 0.7286587357521057,
|
| 554 |
+
"eval_runtime": 14.8767,
|
| 555 |
+
"eval_samples_per_second": 81.067,
|
| 556 |
+
"eval_steps_per_second": 2.554,
|
| 557 |
+
"step": 1712
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 8.060747663551401,
|
| 561 |
+
"grad_norm": 348833.1875,
|
| 562 |
+
"learning_rate": 2.530487804878049e-05,
|
| 563 |
+
"loss": 0.8419,
|
| 564 |
+
"step": 1725
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 8.177570093457945,
|
| 568 |
+
"grad_norm": 291791.3125,
|
| 569 |
+
"learning_rate": 2.378048780487805e-05,
|
| 570 |
+
"loss": 0.7757,
|
| 571 |
+
"step": 1750
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 8.294392523364486,
|
| 575 |
+
"grad_norm": 267995.8125,
|
| 576 |
+
"learning_rate": 2.225609756097561e-05,
|
| 577 |
+
"loss": 0.8469,
|
| 578 |
+
"step": 1775
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 8.411214953271028,
|
| 582 |
+
"grad_norm": 319772.28125,
|
| 583 |
+
"learning_rate": 2.073170731707317e-05,
|
| 584 |
+
"loss": 0.7999,
|
| 585 |
+
"step": 1800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 8.52803738317757,
|
| 589 |
+
"grad_norm": 231708.9375,
|
| 590 |
+
"learning_rate": 1.9207317073170733e-05,
|
| 591 |
+
"loss": 0.8224,
|
| 592 |
+
"step": 1825
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 8.644859813084112,
|
| 596 |
+
"grad_norm": 236476.03125,
|
| 597 |
+
"learning_rate": 1.7682926829268292e-05,
|
| 598 |
+
"loss": 0.8285,
|
| 599 |
+
"step": 1850
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 8.761682242990654,
|
| 603 |
+
"grad_norm": 223335.609375,
|
| 604 |
+
"learning_rate": 1.6158536585365855e-05,
|
| 605 |
+
"loss": 0.7811,
|
| 606 |
+
"step": 1875
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 8.878504672897197,
|
| 610 |
+
"grad_norm": 218836.765625,
|
| 611 |
+
"learning_rate": 1.4634146341463415e-05,
|
| 612 |
+
"loss": 0.7736,
|
| 613 |
+
"step": 1900
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 8.995327102803738,
|
| 617 |
+
"grad_norm": 190812.828125,
|
| 618 |
+
"learning_rate": 1.3109756097560976e-05,
|
| 619 |
+
"loss": 0.7881,
|
| 620 |
+
"step": 1925
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 9.0,
|
| 624 |
+
"eval_accuracy": 0.7703150912106136,
|
| 625 |
+
"eval_loss": 0.7457289695739746,
|
| 626 |
+
"eval_runtime": 15.1329,
|
| 627 |
+
"eval_samples_per_second": 79.694,
|
| 628 |
+
"eval_steps_per_second": 2.511,
|
| 629 |
+
"step": 1926
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 9.11214953271028,
|
| 633 |
+
"grad_norm": 238006.359375,
|
| 634 |
+
"learning_rate": 1.1585365853658537e-05,
|
| 635 |
+
"loss": 0.7099,
|
| 636 |
+
"step": 1950
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 9.228971962616823,
|
| 640 |
+
"grad_norm": 247640.84375,
|
| 641 |
+
"learning_rate": 1.0060975609756099e-05,
|
| 642 |
+
"loss": 0.7774,
|
| 643 |
+
"step": 1975
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 9.345794392523365,
|
| 647 |
+
"grad_norm": 202345.875,
|
| 648 |
+
"learning_rate": 8.53658536585366e-06,
|
| 649 |
+
"loss": 0.7442,
|
| 650 |
+
"step": 2000
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 9.462616822429906,
|
| 654 |
+
"grad_norm": 258587.703125,
|
| 655 |
+
"learning_rate": 7.0121951219512205e-06,
|
| 656 |
+
"loss": 0.6954,
|
| 657 |
+
"step": 2025
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 9.57943925233645,
|
| 661 |
+
"grad_norm": 284795.5625,
|
| 662 |
+
"learning_rate": 5.487804878048781e-06,
|
| 663 |
+
"loss": 0.8041,
|
| 664 |
+
"step": 2050
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 9.69626168224299,
|
| 668 |
+
"grad_norm": 366724.0625,
|
| 669 |
+
"learning_rate": 3.9634146341463414e-06,
|
| 670 |
+
"loss": 0.7696,
|
| 671 |
+
"step": 2075
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 9.813084112149532,
|
| 675 |
+
"grad_norm": 374679.125,
|
| 676 |
+
"learning_rate": 2.4390243902439027e-06,
|
| 677 |
+
"loss": 0.7717,
|
| 678 |
+
"step": 2100
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 9.929906542056075,
|
| 682 |
+
"grad_norm": 311900.8125,
|
| 683 |
+
"learning_rate": 9.146341463414634e-07,
|
| 684 |
+
"loss": 0.7472,
|
| 685 |
+
"step": 2125
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 10.0,
|
| 689 |
+
"eval_accuracy": 0.7669983416252073,
|
| 690 |
+
"eval_loss": 0.7452892065048218,
|
| 691 |
+
"eval_runtime": 15.4387,
|
| 692 |
+
"eval_samples_per_second": 78.115,
|
| 693 |
+
"eval_steps_per_second": 2.461,
|
| 694 |
+
"step": 2140
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 10.0,
|
| 698 |
+
"step": 2140,
|
| 699 |
+
"total_flos": 5.510586115727032e+19,
|
| 700 |
+
"train_loss": 1.022248704411159,
|
| 701 |
+
"train_runtime": 1933.1394,
|
| 702 |
+
"train_samples_per_second": 35.331,
|
| 703 |
+
"train_steps_per_second": 1.107
|
| 704 |
+
}
|
| 705 |
+
],
|
| 706 |
+
"logging_steps": 25,
|
| 707 |
+
"max_steps": 2140,
|
| 708 |
+
"num_input_tokens_seen": 0,
|
| 709 |
+
"num_train_epochs": 10,
|
| 710 |
+
"save_steps": 500,
|
| 711 |
+
"stateful_callbacks": {
|
| 712 |
+
"TrainerControl": {
|
| 713 |
+
"args": {
|
| 714 |
+
"should_epoch_stop": false,
|
| 715 |
+
"should_evaluate": false,
|
| 716 |
+
"should_log": false,
|
| 717 |
+
"should_save": true,
|
| 718 |
+
"should_training_stop": true
|
| 719 |
+
},
|
| 720 |
+
"attributes": {}
|
| 721 |
+
}
|
| 722 |
+
},
|
| 723 |
+
"total_flos": 5.510586115727032e+19,
|
| 724 |
+
"train_batch_size": 32,
|
| 725 |
+
"trial_name": null,
|
| 726 |
+
"trial_params": null
|
| 727 |
+
}
|