End of training
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-224](https://huggingface.co/facebook/convnextv2-base-22k-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.9096045197740112
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-224](https://huggingface.co/facebook/convnextv2-base-22k-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.3801
|
| 36 |
+
- Accuracy: 0.9096
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.97,
|
| 3 |
+
"eval_accuracy": 0.9096045197740112,
|
| 4 |
+
"eval_loss": 0.3801310956478119,
|
| 5 |
+
"eval_runtime": 5.8514,
|
| 6 |
+
"eval_samples_per_second": 30.249,
|
| 7 |
+
"eval_steps_per_second": 7.69,
|
| 8 |
+
"train_loss": 0.23395052750905354,
|
| 9 |
+
"train_runtime": 1693.9771,
|
| 10 |
+
"train_samples_per_second": 9.357,
|
| 11 |
+
"train_steps_per_second": 0.584
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.97,
|
| 3 |
+
"eval_accuracy": 0.9096045197740112,
|
| 4 |
+
"eval_loss": 0.3801310956478119,
|
| 5 |
+
"eval_runtime": 5.8514,
|
| 6 |
+
"eval_samples_per_second": 30.249,
|
| 7 |
+
"eval_steps_per_second": 7.69
|
| 8 |
+
}
|
runs/Feb18_00-56-09_LPP00266034A.fsoft.fpt.vn/events.out.tfevents.1708219329.LPP00266034A.fsoft.fpt.vn.79790.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fb2c5fd4ca62bef256d39fbedd78271d52ad64036a4336929f8b99764d8de21
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.97,
|
| 3 |
+
"train_loss": 0.23395052750905354,
|
| 4 |
+
"train_runtime": 1693.9771,
|
| 5 |
+
"train_samples_per_second": 9.357,
|
| 6 |
+
"train_steps_per_second": 0.584
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,714 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9096045197740112,
|
| 3 |
+
"best_model_checkpoint": "convnextv2-base-22k-224-finetuned-eurosat-2/checkpoint-694",
|
| 4 |
+
"epoch": 9.974811083123425,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 990,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"learning_rate": 5.050505050505051e-06,
|
| 14 |
+
"loss": 1.2172,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.2,
|
| 19 |
+
"learning_rate": 1.0101010101010101e-05,
|
| 20 |
+
"loss": 1.0082,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.3,
|
| 25 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 26 |
+
"loss": 0.8736,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.4,
|
| 31 |
+
"learning_rate": 2.0202020202020203e-05,
|
| 32 |
+
"loss": 0.6853,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.5,
|
| 37 |
+
"learning_rate": 2.5252525252525256e-05,
|
| 38 |
+
"loss": 0.7756,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.6,
|
| 43 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 44 |
+
"loss": 0.71,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.71,
|
| 49 |
+
"learning_rate": 3.535353535353535e-05,
|
| 50 |
+
"loss": 0.5979,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.81,
|
| 55 |
+
"learning_rate": 4.0404040404040405e-05,
|
| 56 |
+
"loss": 0.6413,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.91,
|
| 61 |
+
"learning_rate": 4.545454545454546e-05,
|
| 62 |
+
"loss": 0.5227,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.0,
|
| 67 |
+
"eval_accuracy": 0.7796610169491526,
|
| 68 |
+
"eval_loss": 0.5333397388458252,
|
| 69 |
+
"eval_runtime": 5.7182,
|
| 70 |
+
"eval_samples_per_second": 30.954,
|
| 71 |
+
"eval_steps_per_second": 7.87,
|
| 72 |
+
"step": 99
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.01,
|
| 76 |
+
"learning_rate": 4.994388327721661e-05,
|
| 77 |
+
"loss": 0.5778,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.11,
|
| 82 |
+
"learning_rate": 4.938271604938271e-05,
|
| 83 |
+
"loss": 0.5749,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.21,
|
| 88 |
+
"learning_rate": 4.882154882154882e-05,
|
| 89 |
+
"loss": 0.4366,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.31,
|
| 94 |
+
"learning_rate": 4.8260381593714935e-05,
|
| 95 |
+
"loss": 0.3629,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.41,
|
| 100 |
+
"learning_rate": 4.7699214365881036e-05,
|
| 101 |
+
"loss": 0.5,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.51,
|
| 106 |
+
"learning_rate": 4.713804713804714e-05,
|
| 107 |
+
"loss": 0.4734,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.61,
|
| 112 |
+
"learning_rate": 4.6576879910213244e-05,
|
| 113 |
+
"loss": 0.4109,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.71,
|
| 118 |
+
"learning_rate": 4.601571268237935e-05,
|
| 119 |
+
"loss": 0.5251,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.81,
|
| 124 |
+
"learning_rate": 4.545454545454546e-05,
|
| 125 |
+
"loss": 0.3881,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.91,
|
| 130 |
+
"learning_rate": 4.4893378226711566e-05,
|
| 131 |
+
"loss": 0.4248,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.99,
|
| 136 |
+
"eval_accuracy": 0.8531073446327684,
|
| 137 |
+
"eval_loss": 0.4144964814186096,
|
| 138 |
+
"eval_runtime": 5.6437,
|
| 139 |
+
"eval_samples_per_second": 31.363,
|
| 140 |
+
"eval_steps_per_second": 7.974,
|
| 141 |
+
"step": 198
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.02,
|
| 145 |
+
"learning_rate": 4.433221099887767e-05,
|
| 146 |
+
"loss": 0.3864,
|
| 147 |
+
"step": 200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.12,
|
| 151 |
+
"learning_rate": 4.3771043771043774e-05,
|
| 152 |
+
"loss": 0.2727,
|
| 153 |
+
"step": 210
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.22,
|
| 157 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 158 |
+
"loss": 0.3986,
|
| 159 |
+
"step": 220
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.32,
|
| 163 |
+
"learning_rate": 4.264870931537598e-05,
|
| 164 |
+
"loss": 0.2392,
|
| 165 |
+
"step": 230
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.42,
|
| 169 |
+
"learning_rate": 4.208754208754209e-05,
|
| 170 |
+
"loss": 0.357,
|
| 171 |
+
"step": 240
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.52,
|
| 175 |
+
"learning_rate": 4.15263748597082e-05,
|
| 176 |
+
"loss": 0.2285,
|
| 177 |
+
"step": 250
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.62,
|
| 181 |
+
"learning_rate": 4.0965207631874305e-05,
|
| 182 |
+
"loss": 0.3227,
|
| 183 |
+
"step": 260
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.72,
|
| 187 |
+
"learning_rate": 4.0404040404040405e-05,
|
| 188 |
+
"loss": 0.1759,
|
| 189 |
+
"step": 270
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.82,
|
| 193 |
+
"learning_rate": 3.984287317620651e-05,
|
| 194 |
+
"loss": 0.3358,
|
| 195 |
+
"step": 280
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.92,
|
| 199 |
+
"learning_rate": 3.9281705948372613e-05,
|
| 200 |
+
"loss": 0.2998,
|
| 201 |
+
"step": 290
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.99,
|
| 205 |
+
"eval_accuracy": 0.8757062146892656,
|
| 206 |
+
"eval_loss": 0.33070680499076843,
|
| 207 |
+
"eval_runtime": 5.6516,
|
| 208 |
+
"eval_samples_per_second": 31.318,
|
| 209 |
+
"eval_steps_per_second": 7.962,
|
| 210 |
+
"step": 297
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.02,
|
| 214 |
+
"learning_rate": 3.872053872053872e-05,
|
| 215 |
+
"loss": 0.4704,
|
| 216 |
+
"step": 300
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 3.12,
|
| 220 |
+
"learning_rate": 3.815937149270483e-05,
|
| 221 |
+
"loss": 0.1983,
|
| 222 |
+
"step": 310
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 3.22,
|
| 226 |
+
"learning_rate": 3.7598204264870936e-05,
|
| 227 |
+
"loss": 0.188,
|
| 228 |
+
"step": 320
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 3.32,
|
| 232 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 233 |
+
"loss": 0.2139,
|
| 234 |
+
"step": 330
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 3.43,
|
| 238 |
+
"learning_rate": 3.6475869809203144e-05,
|
| 239 |
+
"loss": 0.2216,
|
| 240 |
+
"step": 340
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.53,
|
| 244 |
+
"learning_rate": 3.5914702581369245e-05,
|
| 245 |
+
"loss": 0.2099,
|
| 246 |
+
"step": 350
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.63,
|
| 250 |
+
"learning_rate": 3.535353535353535e-05,
|
| 251 |
+
"loss": 0.278,
|
| 252 |
+
"step": 360
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.73,
|
| 256 |
+
"learning_rate": 3.4792368125701466e-05,
|
| 257 |
+
"loss": 0.226,
|
| 258 |
+
"step": 370
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 3.83,
|
| 262 |
+
"learning_rate": 3.423120089786757e-05,
|
| 263 |
+
"loss": 0.169,
|
| 264 |
+
"step": 380
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.93,
|
| 268 |
+
"learning_rate": 3.3670033670033675e-05,
|
| 269 |
+
"loss": 0.1704,
|
| 270 |
+
"step": 390
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 4.0,
|
| 274 |
+
"eval_accuracy": 0.8926553672316384,
|
| 275 |
+
"eval_loss": 0.26643165946006775,
|
| 276 |
+
"eval_runtime": 5.6592,
|
| 277 |
+
"eval_samples_per_second": 31.277,
|
| 278 |
+
"eval_steps_per_second": 7.952,
|
| 279 |
+
"step": 397
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 4.03,
|
| 283 |
+
"learning_rate": 3.3108866442199775e-05,
|
| 284 |
+
"loss": 0.1063,
|
| 285 |
+
"step": 400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 4.13,
|
| 289 |
+
"learning_rate": 3.254769921436588e-05,
|
| 290 |
+
"loss": 0.2143,
|
| 291 |
+
"step": 410
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 4.23,
|
| 295 |
+
"learning_rate": 3.198653198653199e-05,
|
| 296 |
+
"loss": 0.1802,
|
| 297 |
+
"step": 420
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.33,
|
| 301 |
+
"learning_rate": 3.14253647586981e-05,
|
| 302 |
+
"loss": 0.1159,
|
| 303 |
+
"step": 430
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.43,
|
| 307 |
+
"learning_rate": 3.08641975308642e-05,
|
| 308 |
+
"loss": 0.1606,
|
| 309 |
+
"step": 440
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 4.53,
|
| 313 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 314 |
+
"loss": 0.1828,
|
| 315 |
+
"step": 450
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 4.63,
|
| 319 |
+
"learning_rate": 2.9741863075196406e-05,
|
| 320 |
+
"loss": 0.1338,
|
| 321 |
+
"step": 460
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 4.74,
|
| 325 |
+
"learning_rate": 2.9180695847362517e-05,
|
| 326 |
+
"loss": 0.208,
|
| 327 |
+
"step": 470
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 4.84,
|
| 331 |
+
"learning_rate": 2.8619528619528618e-05,
|
| 332 |
+
"loss": 0.1392,
|
| 333 |
+
"step": 480
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 4.94,
|
| 337 |
+
"learning_rate": 2.8058361391694725e-05,
|
| 338 |
+
"loss": 0.0684,
|
| 339 |
+
"step": 490
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 5.0,
|
| 343 |
+
"eval_accuracy": 0.8700564971751412,
|
| 344 |
+
"eval_loss": 0.4352767765522003,
|
| 345 |
+
"eval_runtime": 5.6244,
|
| 346 |
+
"eval_samples_per_second": 31.47,
|
| 347 |
+
"eval_steps_per_second": 8.001,
|
| 348 |
+
"step": 496
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 5.04,
|
| 352 |
+
"learning_rate": 2.7497194163860833e-05,
|
| 353 |
+
"loss": 0.1994,
|
| 354 |
+
"step": 500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 5.14,
|
| 358 |
+
"learning_rate": 2.6936026936026937e-05,
|
| 359 |
+
"loss": 0.1901,
|
| 360 |
+
"step": 510
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 5.24,
|
| 364 |
+
"learning_rate": 2.6374859708193044e-05,
|
| 365 |
+
"loss": 0.1812,
|
| 366 |
+
"step": 520
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 5.34,
|
| 370 |
+
"learning_rate": 2.581369248035915e-05,
|
| 371 |
+
"loss": 0.1002,
|
| 372 |
+
"step": 530
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 5.44,
|
| 376 |
+
"learning_rate": 2.5252525252525256e-05,
|
| 377 |
+
"loss": 0.0685,
|
| 378 |
+
"step": 540
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 5.54,
|
| 382 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 383 |
+
"loss": 0.1548,
|
| 384 |
+
"step": 550
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 5.64,
|
| 388 |
+
"learning_rate": 2.4130190796857467e-05,
|
| 389 |
+
"loss": 0.1409,
|
| 390 |
+
"step": 560
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 5.74,
|
| 394 |
+
"learning_rate": 2.356902356902357e-05,
|
| 395 |
+
"loss": 0.1636,
|
| 396 |
+
"step": 570
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 5.84,
|
| 400 |
+
"learning_rate": 2.3007856341189676e-05,
|
| 401 |
+
"loss": 0.1475,
|
| 402 |
+
"step": 580
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 5.94,
|
| 406 |
+
"learning_rate": 2.2446689113355783e-05,
|
| 407 |
+
"loss": 0.1546,
|
| 408 |
+
"step": 590
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.99,
|
| 412 |
+
"eval_accuracy": 0.8870056497175142,
|
| 413 |
+
"eval_loss": 0.39201802015304565,
|
| 414 |
+
"eval_runtime": 5.5831,
|
| 415 |
+
"eval_samples_per_second": 31.703,
|
| 416 |
+
"eval_steps_per_second": 8.06,
|
| 417 |
+
"step": 595
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 6.05,
|
| 421 |
+
"learning_rate": 2.1885521885521887e-05,
|
| 422 |
+
"loss": 0.1232,
|
| 423 |
+
"step": 600
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 6.15,
|
| 427 |
+
"learning_rate": 2.132435465768799e-05,
|
| 428 |
+
"loss": 0.0651,
|
| 429 |
+
"step": 610
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 6.25,
|
| 433 |
+
"learning_rate": 2.07631874298541e-05,
|
| 434 |
+
"loss": 0.0332,
|
| 435 |
+
"step": 620
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 6.35,
|
| 439 |
+
"learning_rate": 2.0202020202020203e-05,
|
| 440 |
+
"loss": 0.0536,
|
| 441 |
+
"step": 630
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 6.45,
|
| 445 |
+
"learning_rate": 1.9640852974186307e-05,
|
| 446 |
+
"loss": 0.2526,
|
| 447 |
+
"step": 640
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 6.55,
|
| 451 |
+
"learning_rate": 1.9079685746352414e-05,
|
| 452 |
+
"loss": 0.218,
|
| 453 |
+
"step": 650
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 6.65,
|
| 457 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 458 |
+
"loss": 0.0199,
|
| 459 |
+
"step": 660
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 6.75,
|
| 463 |
+
"learning_rate": 1.7957351290684622e-05,
|
| 464 |
+
"loss": 0.0679,
|
| 465 |
+
"step": 670
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 6.85,
|
| 469 |
+
"learning_rate": 1.7396184062850733e-05,
|
| 470 |
+
"loss": 0.1341,
|
| 471 |
+
"step": 680
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 6.95,
|
| 475 |
+
"learning_rate": 1.6835016835016837e-05,
|
| 476 |
+
"loss": 0.0593,
|
| 477 |
+
"step": 690
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 6.99,
|
| 481 |
+
"eval_accuracy": 0.9096045197740112,
|
| 482 |
+
"eval_loss": 0.3801310956478119,
|
| 483 |
+
"eval_runtime": 5.6406,
|
| 484 |
+
"eval_samples_per_second": 31.379,
|
| 485 |
+
"eval_steps_per_second": 7.978,
|
| 486 |
+
"step": 694
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 7.05,
|
| 490 |
+
"learning_rate": 1.627384960718294e-05,
|
| 491 |
+
"loss": 0.0364,
|
| 492 |
+
"step": 700
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 7.15,
|
| 496 |
+
"learning_rate": 1.571268237934905e-05,
|
| 497 |
+
"loss": 0.0853,
|
| 498 |
+
"step": 710
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 7.25,
|
| 502 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 503 |
+
"loss": 0.1463,
|
| 504 |
+
"step": 720
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 7.36,
|
| 508 |
+
"learning_rate": 1.4590347923681259e-05,
|
| 509 |
+
"loss": 0.0741,
|
| 510 |
+
"step": 730
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 7.46,
|
| 514 |
+
"learning_rate": 1.4029180695847363e-05,
|
| 515 |
+
"loss": 0.0982,
|
| 516 |
+
"step": 740
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 7.56,
|
| 520 |
+
"learning_rate": 1.3468013468013468e-05,
|
| 521 |
+
"loss": 0.0335,
|
| 522 |
+
"step": 750
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 7.66,
|
| 526 |
+
"learning_rate": 1.2906846240179574e-05,
|
| 527 |
+
"loss": 0.0494,
|
| 528 |
+
"step": 760
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 7.76,
|
| 532 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 533 |
+
"loss": 0.0645,
|
| 534 |
+
"step": 770
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.86,
|
| 538 |
+
"learning_rate": 1.1784511784511786e-05,
|
| 539 |
+
"loss": 0.0971,
|
| 540 |
+
"step": 780
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 7.96,
|
| 544 |
+
"learning_rate": 1.1223344556677892e-05,
|
| 545 |
+
"loss": 0.0745,
|
| 546 |
+
"step": 790
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 8.0,
|
| 550 |
+
"eval_accuracy": 0.8983050847457628,
|
| 551 |
+
"eval_loss": 0.40303125977516174,
|
| 552 |
+
"eval_runtime": 5.6355,
|
| 553 |
+
"eval_samples_per_second": 31.408,
|
| 554 |
+
"eval_steps_per_second": 7.985,
|
| 555 |
+
"step": 794
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 8.06,
|
| 559 |
+
"learning_rate": 1.0662177328843996e-05,
|
| 560 |
+
"loss": 0.095,
|
| 561 |
+
"step": 800
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 8.16,
|
| 565 |
+
"learning_rate": 1.0101010101010101e-05,
|
| 566 |
+
"loss": 0.0438,
|
| 567 |
+
"step": 810
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 8.26,
|
| 571 |
+
"learning_rate": 9.539842873176207e-06,
|
| 572 |
+
"loss": 0.0136,
|
| 573 |
+
"step": 820
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 8.36,
|
| 577 |
+
"learning_rate": 8.978675645342311e-06,
|
| 578 |
+
"loss": 0.0702,
|
| 579 |
+
"step": 830
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 8.46,
|
| 583 |
+
"learning_rate": 8.417508417508419e-06,
|
| 584 |
+
"loss": 0.0943,
|
| 585 |
+
"step": 840
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 8.56,
|
| 589 |
+
"learning_rate": 7.856341189674524e-06,
|
| 590 |
+
"loss": 0.0746,
|
| 591 |
+
"step": 850
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 8.66,
|
| 595 |
+
"learning_rate": 7.295173961840629e-06,
|
| 596 |
+
"loss": 0.0562,
|
| 597 |
+
"step": 860
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 8.77,
|
| 601 |
+
"learning_rate": 6.734006734006734e-06,
|
| 602 |
+
"loss": 0.0372,
|
| 603 |
+
"step": 870
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 8.87,
|
| 607 |
+
"learning_rate": 6.172839506172839e-06,
|
| 608 |
+
"loss": 0.0282,
|
| 609 |
+
"step": 880
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 8.97,
|
| 613 |
+
"learning_rate": 5.611672278338946e-06,
|
| 614 |
+
"loss": 0.0877,
|
| 615 |
+
"step": 890
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 9.0,
|
| 619 |
+
"eval_accuracy": 0.903954802259887,
|
| 620 |
+
"eval_loss": 0.38457363843917847,
|
| 621 |
+
"eval_runtime": 5.5773,
|
| 622 |
+
"eval_samples_per_second": 31.736,
|
| 623 |
+
"eval_steps_per_second": 8.068,
|
| 624 |
+
"step": 893
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 9.07,
|
| 628 |
+
"learning_rate": 5.050505050505051e-06,
|
| 629 |
+
"loss": 0.0087,
|
| 630 |
+
"step": 900
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 9.17,
|
| 634 |
+
"learning_rate": 4.489337822671156e-06,
|
| 635 |
+
"loss": 0.1049,
|
| 636 |
+
"step": 910
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 9.27,
|
| 640 |
+
"learning_rate": 3.928170594837262e-06,
|
| 641 |
+
"loss": 0.0294,
|
| 642 |
+
"step": 920
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 9.37,
|
| 646 |
+
"learning_rate": 3.367003367003367e-06,
|
| 647 |
+
"loss": 0.0892,
|
| 648 |
+
"step": 930
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 9.47,
|
| 652 |
+
"learning_rate": 2.805836139169473e-06,
|
| 653 |
+
"loss": 0.1025,
|
| 654 |
+
"step": 940
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 9.57,
|
| 658 |
+
"learning_rate": 2.244668911335578e-06,
|
| 659 |
+
"loss": 0.1009,
|
| 660 |
+
"step": 950
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 9.67,
|
| 664 |
+
"learning_rate": 1.6835016835016836e-06,
|
| 665 |
+
"loss": 0.0784,
|
| 666 |
+
"step": 960
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 9.77,
|
| 670 |
+
"learning_rate": 1.122334455667789e-06,
|
| 671 |
+
"loss": 0.0662,
|
| 672 |
+
"step": 970
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 9.87,
|
| 676 |
+
"learning_rate": 5.611672278338944e-07,
|
| 677 |
+
"loss": 0.0257,
|
| 678 |
+
"step": 980
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 9.97,
|
| 682 |
+
"learning_rate": 0.0,
|
| 683 |
+
"loss": 0.09,
|
| 684 |
+
"step": 990
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 9.97,
|
| 688 |
+
"eval_accuracy": 0.903954802259887,
|
| 689 |
+
"eval_loss": 0.3815687894821167,
|
| 690 |
+
"eval_runtime": 5.5808,
|
| 691 |
+
"eval_samples_per_second": 31.716,
|
| 692 |
+
"eval_steps_per_second": 8.063,
|
| 693 |
+
"step": 990
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 9.97,
|
| 697 |
+
"step": 990,
|
| 698 |
+
"total_flos": 1.252454560310016e+18,
|
| 699 |
+
"train_loss": 0.23395052750905354,
|
| 700 |
+
"train_runtime": 1693.9771,
|
| 701 |
+
"train_samples_per_second": 9.357,
|
| 702 |
+
"train_steps_per_second": 0.584
|
| 703 |
+
}
|
| 704 |
+
],
|
| 705 |
+
"logging_steps": 10,
|
| 706 |
+
"max_steps": 990,
|
| 707 |
+
"num_input_tokens_seen": 0,
|
| 708 |
+
"num_train_epochs": 10,
|
| 709 |
+
"save_steps": 500,
|
| 710 |
+
"total_flos": 1.252454560310016e+18,
|
| 711 |
+
"train_batch_size": 4,
|
| 712 |
+
"trial_name": null,
|
| 713 |
+
"trial_params": null
|
| 714 |
+
}
|