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 +640 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- imagefolder
|
|
@@ -23,7 +25,7 @@ model-index:
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
-
value: 0.
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -33,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
|
| 34 |
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 imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss: 0.
|
| 37 |
-
- Accuracy: 0.
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
| 6 |
+
- image-classification
|
| 7 |
+
- vision
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- imagefolder
|
|
|
|
| 25 |
metrics:
|
| 26 |
- name: Accuracy
|
| 27 |
type: accuracy
|
| 28 |
+
value: 0.9955156950672646
|
| 29 |
---
|
| 30 |
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 35 |
|
| 36 |
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 imagefolder dataset.
|
| 37 |
It achieves the following results on the evaluation set:
|
| 38 |
+
- Loss: 0.0411
|
| 39 |
+
- Accuracy: 0.9955
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9955156950672646,
|
| 4 |
+
"eval_loss": 0.0411064513027668,
|
| 5 |
+
"eval_runtime": 27.0318,
|
| 6 |
+
"eval_samples_per_second": 8.25,
|
| 7 |
+
"eval_steps_per_second": 1.036,
|
| 8 |
+
"total_flos": 4.893619144161485e+17,
|
| 9 |
+
"train_loss": 0.08755870511448836,
|
| 10 |
+
"train_runtime": 2689.1935,
|
| 11 |
+
"train_samples_per_second": 2.348,
|
| 12 |
+
"train_steps_per_second": 0.294
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9955156950672646,
|
| 4 |
+
"eval_loss": 0.0411064513027668,
|
| 5 |
+
"eval_runtime": 27.0318,
|
| 6 |
+
"eval_samples_per_second": 8.25,
|
| 7 |
+
"eval_steps_per_second": 1.036
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 4.893619144161485e+17,
|
| 4 |
+
"train_loss": 0.08755870511448836,
|
| 5 |
+
"train_runtime": 2689.1935,
|
| 6 |
+
"train_samples_per_second": 2.348,
|
| 7 |
+
"train_steps_per_second": 0.294
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,640 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0411064513027668,
|
| 3 |
+
"best_model_checkpoint": "./TransparentBagClassifier/checkpoint-316",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 790,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06329113924050633,
|
| 13 |
+
"grad_norm": 1.8177610635757446,
|
| 14 |
+
"learning_rate": 1.974683544303798e-05,
|
| 15 |
+
"loss": 0.6502,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.12658227848101267,
|
| 20 |
+
"grad_norm": 1.735235333442688,
|
| 21 |
+
"learning_rate": 1.949367088607595e-05,
|
| 22 |
+
"loss": 0.5886,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.189873417721519,
|
| 27 |
+
"grad_norm": 1.5866175889968872,
|
| 28 |
+
"learning_rate": 1.9240506329113926e-05,
|
| 29 |
+
"loss": 0.5145,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.25316455696202533,
|
| 34 |
+
"grad_norm": 2.1754307746887207,
|
| 35 |
+
"learning_rate": 1.89873417721519e-05,
|
| 36 |
+
"loss": 0.4214,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.31645569620253167,
|
| 41 |
+
"grad_norm": 1.926560401916504,
|
| 42 |
+
"learning_rate": 1.8734177215189874e-05,
|
| 43 |
+
"loss": 0.303,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.379746835443038,
|
| 48 |
+
"grad_norm": 1.284515619277954,
|
| 49 |
+
"learning_rate": 1.848101265822785e-05,
|
| 50 |
+
"loss": 0.2735,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4430379746835443,
|
| 55 |
+
"grad_norm": 1.0484488010406494,
|
| 56 |
+
"learning_rate": 1.8227848101265824e-05,
|
| 57 |
+
"loss": 0.2382,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.5063291139240507,
|
| 62 |
+
"grad_norm": 0.6332635879516602,
|
| 63 |
+
"learning_rate": 1.7974683544303798e-05,
|
| 64 |
+
"loss": 0.1651,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.569620253164557,
|
| 69 |
+
"grad_norm": 0.7192436456680298,
|
| 70 |
+
"learning_rate": 1.7721518987341772e-05,
|
| 71 |
+
"loss": 0.1691,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.6329113924050633,
|
| 76 |
+
"grad_norm": 0.5396292209625244,
|
| 77 |
+
"learning_rate": 1.746835443037975e-05,
|
| 78 |
+
"loss": 0.1371,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6962025316455697,
|
| 83 |
+
"grad_norm": 1.0010855197906494,
|
| 84 |
+
"learning_rate": 1.7215189873417723e-05,
|
| 85 |
+
"loss": 0.1054,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.759493670886076,
|
| 90 |
+
"grad_norm": 2.316347360610962,
|
| 91 |
+
"learning_rate": 1.6962025316455696e-05,
|
| 92 |
+
"loss": 0.1485,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.8227848101265823,
|
| 97 |
+
"grad_norm": 4.399435043334961,
|
| 98 |
+
"learning_rate": 1.6708860759493674e-05,
|
| 99 |
+
"loss": 0.0898,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.8860759493670886,
|
| 104 |
+
"grad_norm": 0.6504904627799988,
|
| 105 |
+
"learning_rate": 1.6455696202531647e-05,
|
| 106 |
+
"loss": 0.1151,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.9493670886075949,
|
| 111 |
+
"grad_norm": 0.26793766021728516,
|
| 112 |
+
"learning_rate": 1.620253164556962e-05,
|
| 113 |
+
"loss": 0.0694,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.0,
|
| 118 |
+
"eval_accuracy": 0.9820627802690582,
|
| 119 |
+
"eval_loss": 0.0719464123249054,
|
| 120 |
+
"eval_runtime": 29.347,
|
| 121 |
+
"eval_samples_per_second": 7.599,
|
| 122 |
+
"eval_steps_per_second": 0.954,
|
| 123 |
+
"step": 158
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0126582278481013,
|
| 127 |
+
"grad_norm": 0.31842896342277527,
|
| 128 |
+
"learning_rate": 1.5949367088607598e-05,
|
| 129 |
+
"loss": 0.0743,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.0759493670886076,
|
| 134 |
+
"grad_norm": 4.0135979652404785,
|
| 135 |
+
"learning_rate": 1.5696202531645572e-05,
|
| 136 |
+
"loss": 0.0614,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.139240506329114,
|
| 141 |
+
"grad_norm": 0.2785925567150116,
|
| 142 |
+
"learning_rate": 1.5443037974683546e-05,
|
| 143 |
+
"loss": 0.0635,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.2025316455696202,
|
| 148 |
+
"grad_norm": 0.21624621748924255,
|
| 149 |
+
"learning_rate": 1.5189873417721521e-05,
|
| 150 |
+
"loss": 0.0524,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.2658227848101267,
|
| 155 |
+
"grad_norm": 0.35363027453422546,
|
| 156 |
+
"learning_rate": 1.4936708860759495e-05,
|
| 157 |
+
"loss": 0.0342,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.3291139240506329,
|
| 162 |
+
"grad_norm": 1.0792415142059326,
|
| 163 |
+
"learning_rate": 1.468354430379747e-05,
|
| 164 |
+
"loss": 0.0497,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.3924050632911391,
|
| 169 |
+
"grad_norm": 0.19490359723567963,
|
| 170 |
+
"learning_rate": 1.4430379746835444e-05,
|
| 171 |
+
"loss": 0.0591,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.4556962025316456,
|
| 176 |
+
"grad_norm": 0.16427624225616455,
|
| 177 |
+
"learning_rate": 1.417721518987342e-05,
|
| 178 |
+
"loss": 0.037,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.518987341772152,
|
| 183 |
+
"grad_norm": 7.667697429656982,
|
| 184 |
+
"learning_rate": 1.3924050632911395e-05,
|
| 185 |
+
"loss": 0.089,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.5822784810126582,
|
| 190 |
+
"grad_norm": 0.15142761170864105,
|
| 191 |
+
"learning_rate": 1.3670886075949368e-05,
|
| 192 |
+
"loss": 0.1013,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.6455696202531644,
|
| 197 |
+
"grad_norm": 3.7054553031921387,
|
| 198 |
+
"learning_rate": 1.3417721518987344e-05,
|
| 199 |
+
"loss": 0.077,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.7088607594936709,
|
| 204 |
+
"grad_norm": 0.13252966105937958,
|
| 205 |
+
"learning_rate": 1.3164556962025317e-05,
|
| 206 |
+
"loss": 0.0528,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.7721518987341773,
|
| 211 |
+
"grad_norm": 0.14607028663158417,
|
| 212 |
+
"learning_rate": 1.2911392405063293e-05,
|
| 213 |
+
"loss": 0.1078,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.8354430379746836,
|
| 218 |
+
"grad_norm": 0.17516593635082245,
|
| 219 |
+
"learning_rate": 1.2658227848101268e-05,
|
| 220 |
+
"loss": 0.0872,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.8987341772151898,
|
| 225 |
+
"grad_norm": 0.4909473955631256,
|
| 226 |
+
"learning_rate": 1.240506329113924e-05,
|
| 227 |
+
"loss": 0.1023,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.9620253164556962,
|
| 232 |
+
"grad_norm": 17.056110382080078,
|
| 233 |
+
"learning_rate": 1.2151898734177216e-05,
|
| 234 |
+
"loss": 0.0871,
|
| 235 |
+
"step": 310
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.0,
|
| 239 |
+
"eval_accuracy": 0.9955156950672646,
|
| 240 |
+
"eval_loss": 0.0411064513027668,
|
| 241 |
+
"eval_runtime": 30.7571,
|
| 242 |
+
"eval_samples_per_second": 7.25,
|
| 243 |
+
"eval_steps_per_second": 0.91,
|
| 244 |
+
"step": 316
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.0253164556962027,
|
| 248 |
+
"grad_norm": 0.14253969490528107,
|
| 249 |
+
"learning_rate": 1.189873417721519e-05,
|
| 250 |
+
"loss": 0.0258,
|
| 251 |
+
"step": 320
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.088607594936709,
|
| 255 |
+
"grad_norm": 0.1595589965581894,
|
| 256 |
+
"learning_rate": 1.1645569620253165e-05,
|
| 257 |
+
"loss": 0.0181,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.151898734177215,
|
| 262 |
+
"grad_norm": 0.11532098799943924,
|
| 263 |
+
"learning_rate": 1.139240506329114e-05,
|
| 264 |
+
"loss": 0.0369,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.2151898734177213,
|
| 269 |
+
"grad_norm": 0.10694638639688492,
|
| 270 |
+
"learning_rate": 1.1139240506329114e-05,
|
| 271 |
+
"loss": 0.055,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.278481012658228,
|
| 276 |
+
"grad_norm": 0.11190392822027206,
|
| 277 |
+
"learning_rate": 1.088607594936709e-05,
|
| 278 |
+
"loss": 0.0981,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.3417721518987342,
|
| 283 |
+
"grad_norm": 0.11986145377159119,
|
| 284 |
+
"learning_rate": 1.0632911392405063e-05,
|
| 285 |
+
"loss": 0.1199,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.4050632911392404,
|
| 290 |
+
"grad_norm": 0.8623329401016235,
|
| 291 |
+
"learning_rate": 1.0379746835443039e-05,
|
| 292 |
+
"loss": 0.076,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.4683544303797467,
|
| 297 |
+
"grad_norm": 0.34745362401008606,
|
| 298 |
+
"learning_rate": 1.0126582278481014e-05,
|
| 299 |
+
"loss": 0.0396,
|
| 300 |
+
"step": 390
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.5316455696202533,
|
| 304 |
+
"grad_norm": 2.8758838176727295,
|
| 305 |
+
"learning_rate": 9.87341772151899e-06,
|
| 306 |
+
"loss": 0.0168,
|
| 307 |
+
"step": 400
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.5949367088607596,
|
| 311 |
+
"grad_norm": 0.15997739136219025,
|
| 312 |
+
"learning_rate": 9.620253164556963e-06,
|
| 313 |
+
"loss": 0.0848,
|
| 314 |
+
"step": 410
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.6582278481012658,
|
| 318 |
+
"grad_norm": 0.1280534863471985,
|
| 319 |
+
"learning_rate": 9.367088607594937e-06,
|
| 320 |
+
"loss": 0.0895,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.721518987341772,
|
| 325 |
+
"grad_norm": 0.09299108386039734,
|
| 326 |
+
"learning_rate": 9.113924050632912e-06,
|
| 327 |
+
"loss": 0.0217,
|
| 328 |
+
"step": 430
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.7848101265822782,
|
| 332 |
+
"grad_norm": 0.09745831787586212,
|
| 333 |
+
"learning_rate": 8.860759493670886e-06,
|
| 334 |
+
"loss": 0.0136,
|
| 335 |
+
"step": 440
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.848101265822785,
|
| 339 |
+
"grad_norm": 0.3660314977169037,
|
| 340 |
+
"learning_rate": 8.607594936708861e-06,
|
| 341 |
+
"loss": 0.066,
|
| 342 |
+
"step": 450
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.911392405063291,
|
| 346 |
+
"grad_norm": 0.10188435018062592,
|
| 347 |
+
"learning_rate": 8.354430379746837e-06,
|
| 348 |
+
"loss": 0.0337,
|
| 349 |
+
"step": 460
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.9746835443037973,
|
| 353 |
+
"grad_norm": 0.08400288224220276,
|
| 354 |
+
"learning_rate": 8.10126582278481e-06,
|
| 355 |
+
"loss": 0.0561,
|
| 356 |
+
"step": 470
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.0,
|
| 360 |
+
"eval_accuracy": 0.9910313901345291,
|
| 361 |
+
"eval_loss": 0.041871435940265656,
|
| 362 |
+
"eval_runtime": 28.742,
|
| 363 |
+
"eval_samples_per_second": 7.759,
|
| 364 |
+
"eval_steps_per_second": 0.974,
|
| 365 |
+
"step": 474
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.037974683544304,
|
| 369 |
+
"grad_norm": 0.08712360262870789,
|
| 370 |
+
"learning_rate": 7.848101265822786e-06,
|
| 371 |
+
"loss": 0.0165,
|
| 372 |
+
"step": 480
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.1012658227848102,
|
| 376 |
+
"grad_norm": 0.08917823433876038,
|
| 377 |
+
"learning_rate": 7.5949367088607605e-06,
|
| 378 |
+
"loss": 0.0788,
|
| 379 |
+
"step": 490
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.1645569620253164,
|
| 383 |
+
"grad_norm": 12.753520965576172,
|
| 384 |
+
"learning_rate": 7.341772151898735e-06,
|
| 385 |
+
"loss": 0.0523,
|
| 386 |
+
"step": 500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.2278481012658227,
|
| 390 |
+
"grad_norm": 0.1649811565876007,
|
| 391 |
+
"learning_rate": 7.08860759493671e-06,
|
| 392 |
+
"loss": 0.0119,
|
| 393 |
+
"step": 510
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.291139240506329,
|
| 397 |
+
"grad_norm": 0.08447328209877014,
|
| 398 |
+
"learning_rate": 6.835443037974684e-06,
|
| 399 |
+
"loss": 0.0114,
|
| 400 |
+
"step": 520
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 3.3544303797468356,
|
| 404 |
+
"grad_norm": 0.48710471391677856,
|
| 405 |
+
"learning_rate": 6.582278481012659e-06,
|
| 406 |
+
"loss": 0.0506,
|
| 407 |
+
"step": 530
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.4177215189873418,
|
| 411 |
+
"grad_norm": 0.10614439100027084,
|
| 412 |
+
"learning_rate": 6.329113924050634e-06,
|
| 413 |
+
"loss": 0.0155,
|
| 414 |
+
"step": 540
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.481012658227848,
|
| 418 |
+
"grad_norm": 0.08778823167085648,
|
| 419 |
+
"learning_rate": 6.075949367088608e-06,
|
| 420 |
+
"loss": 0.0118,
|
| 421 |
+
"step": 550
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.5443037974683547,
|
| 425 |
+
"grad_norm": 0.08901780843734741,
|
| 426 |
+
"learning_rate": 5.8227848101265824e-06,
|
| 427 |
+
"loss": 0.0144,
|
| 428 |
+
"step": 560
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.607594936708861,
|
| 432 |
+
"grad_norm": 3.638420581817627,
|
| 433 |
+
"learning_rate": 5.569620253164557e-06,
|
| 434 |
+
"loss": 0.0123,
|
| 435 |
+
"step": 570
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.670886075949367,
|
| 439 |
+
"grad_norm": 0.07501719892024994,
|
| 440 |
+
"learning_rate": 5.3164556962025316e-06,
|
| 441 |
+
"loss": 0.0112,
|
| 442 |
+
"step": 580
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 3.7341772151898733,
|
| 446 |
+
"grad_norm": 0.07867681980133057,
|
| 447 |
+
"learning_rate": 5.063291139240507e-06,
|
| 448 |
+
"loss": 0.0175,
|
| 449 |
+
"step": 590
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.7974683544303796,
|
| 453 |
+
"grad_norm": 1.1297374963760376,
|
| 454 |
+
"learning_rate": 4.8101265822784815e-06,
|
| 455 |
+
"loss": 0.0109,
|
| 456 |
+
"step": 600
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.8607594936708862,
|
| 460 |
+
"grad_norm": 0.27534130215644836,
|
| 461 |
+
"learning_rate": 4.556962025316456e-06,
|
| 462 |
+
"loss": 0.0386,
|
| 463 |
+
"step": 610
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 3.9240506329113924,
|
| 467 |
+
"grad_norm": 0.07276225835084915,
|
| 468 |
+
"learning_rate": 4.303797468354431e-06,
|
| 469 |
+
"loss": 0.0186,
|
| 470 |
+
"step": 620
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.9873417721518987,
|
| 474 |
+
"grad_norm": 0.07785341143608093,
|
| 475 |
+
"learning_rate": 4.050632911392405e-06,
|
| 476 |
+
"loss": 0.0673,
|
| 477 |
+
"step": 630
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 4.0,
|
| 481 |
+
"eval_accuracy": 0.9865470852017937,
|
| 482 |
+
"eval_loss": 0.04242047667503357,
|
| 483 |
+
"eval_runtime": 41.253,
|
| 484 |
+
"eval_samples_per_second": 5.406,
|
| 485 |
+
"eval_steps_per_second": 0.679,
|
| 486 |
+
"step": 632
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 4.050632911392405,
|
| 490 |
+
"grad_norm": 0.07723096013069153,
|
| 491 |
+
"learning_rate": 3.7974683544303802e-06,
|
| 492 |
+
"loss": 0.0101,
|
| 493 |
+
"step": 640
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 4.113924050632911,
|
| 497 |
+
"grad_norm": 0.07696326822042465,
|
| 498 |
+
"learning_rate": 3.544303797468355e-06,
|
| 499 |
+
"loss": 0.0289,
|
| 500 |
+
"step": 650
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.177215189873418,
|
| 504 |
+
"grad_norm": 0.07799258828163147,
|
| 505 |
+
"learning_rate": 3.2911392405063294e-06,
|
| 506 |
+
"loss": 0.0604,
|
| 507 |
+
"step": 660
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 4.2405063291139244,
|
| 511 |
+
"grad_norm": 0.08302771300077438,
|
| 512 |
+
"learning_rate": 3.037974683544304e-06,
|
| 513 |
+
"loss": 0.0096,
|
| 514 |
+
"step": 670
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 4.30379746835443,
|
| 518 |
+
"grad_norm": 0.0777091532945633,
|
| 519 |
+
"learning_rate": 2.7848101265822785e-06,
|
| 520 |
+
"loss": 0.0096,
|
| 521 |
+
"step": 680
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 4.367088607594937,
|
| 525 |
+
"grad_norm": 0.1073741614818573,
|
| 526 |
+
"learning_rate": 2.5316455696202535e-06,
|
| 527 |
+
"loss": 0.0128,
|
| 528 |
+
"step": 690
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 4.430379746835443,
|
| 532 |
+
"grad_norm": 0.06873705983161926,
|
| 533 |
+
"learning_rate": 2.278481012658228e-06,
|
| 534 |
+
"loss": 0.1127,
|
| 535 |
+
"step": 700
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 4.493670886075949,
|
| 539 |
+
"grad_norm": 0.10447876155376434,
|
| 540 |
+
"learning_rate": 2.0253164556962026e-06,
|
| 541 |
+
"loss": 0.0099,
|
| 542 |
+
"step": 710
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 4.556962025316456,
|
| 546 |
+
"grad_norm": 0.07418622821569443,
|
| 547 |
+
"learning_rate": 1.7721518987341774e-06,
|
| 548 |
+
"loss": 0.0138,
|
| 549 |
+
"step": 720
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 4.620253164556962,
|
| 553 |
+
"grad_norm": 0.07888732105493546,
|
| 554 |
+
"learning_rate": 1.518987341772152e-06,
|
| 555 |
+
"loss": 0.0539,
|
| 556 |
+
"step": 730
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 4.6835443037974684,
|
| 560 |
+
"grad_norm": 0.07641228288412094,
|
| 561 |
+
"learning_rate": 1.2658227848101267e-06,
|
| 562 |
+
"loss": 0.0095,
|
| 563 |
+
"step": 740
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 4.746835443037975,
|
| 567 |
+
"grad_norm": 0.07773224264383316,
|
| 568 |
+
"learning_rate": 1.0126582278481013e-06,
|
| 569 |
+
"loss": 0.0501,
|
| 570 |
+
"step": 750
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 4.810126582278481,
|
| 574 |
+
"grad_norm": 0.08096041530370712,
|
| 575 |
+
"learning_rate": 7.59493670886076e-07,
|
| 576 |
+
"loss": 0.0093,
|
| 577 |
+
"step": 760
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 4.8734177215189876,
|
| 581 |
+
"grad_norm": 0.0873405709862709,
|
| 582 |
+
"learning_rate": 5.063291139240507e-07,
|
| 583 |
+
"loss": 0.0842,
|
| 584 |
+
"step": 770
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 4.936708860759493,
|
| 588 |
+
"grad_norm": 0.788959264755249,
|
| 589 |
+
"learning_rate": 2.5316455696202533e-07,
|
| 590 |
+
"loss": 0.0162,
|
| 591 |
+
"step": 780
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 5.0,
|
| 595 |
+
"grad_norm": 0.11727602779865265,
|
| 596 |
+
"learning_rate": 0.0,
|
| 597 |
+
"loss": 0.0099,
|
| 598 |
+
"step": 790
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 5.0,
|
| 602 |
+
"eval_accuracy": 0.9820627802690582,
|
| 603 |
+
"eval_loss": 0.05168794468045235,
|
| 604 |
+
"eval_runtime": 29.684,
|
| 605 |
+
"eval_samples_per_second": 7.512,
|
| 606 |
+
"eval_steps_per_second": 0.943,
|
| 607 |
+
"step": 790
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 5.0,
|
| 611 |
+
"step": 790,
|
| 612 |
+
"total_flos": 4.893619144161485e+17,
|
| 613 |
+
"train_loss": 0.08755870511448836,
|
| 614 |
+
"train_runtime": 2689.1935,
|
| 615 |
+
"train_samples_per_second": 2.348,
|
| 616 |
+
"train_steps_per_second": 0.294
|
| 617 |
+
}
|
| 618 |
+
],
|
| 619 |
+
"logging_steps": 10,
|
| 620 |
+
"max_steps": 790,
|
| 621 |
+
"num_input_tokens_seen": 0,
|
| 622 |
+
"num_train_epochs": 5,
|
| 623 |
+
"save_steps": 500,
|
| 624 |
+
"stateful_callbacks": {
|
| 625 |
+
"TrainerControl": {
|
| 626 |
+
"args": {
|
| 627 |
+
"should_epoch_stop": false,
|
| 628 |
+
"should_evaluate": false,
|
| 629 |
+
"should_log": false,
|
| 630 |
+
"should_save": true,
|
| 631 |
+
"should_training_stop": true
|
| 632 |
+
},
|
| 633 |
+
"attributes": {}
|
| 634 |
+
}
|
| 635 |
+
},
|
| 636 |
+
"total_flos": 4.893619144161485e+17,
|
| 637 |
+
"train_batch_size": 8,
|
| 638 |
+
"trial_name": null,
|
| 639 |
+
"trial_params": null
|
| 640 |
+
}
|