Commit
•
2e43239
1
Parent(s):
ffc4d52
End of training
Browse files- README.md +3 -3
- all_results.json +8 -0
- runs/May24_17-33-03_5970881f307e/events.out.tfevents.1716584963.5970881f307e.25.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +739 -0
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-tiny-22k-384](https://huggingface.co/facebook/convnextv2-tiny-22k-384) 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: 0.9375
|
| 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-tiny-22k-384](https://huggingface.co/facebook/convnextv2-tiny-22k-384) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.2767
|
| 36 |
+
- Accuracy: 0.9375
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 1.952142618502398e+19,
|
| 4 |
+
"train_loss": 0.23986065309697932,
|
| 5 |
+
"train_runtime": 12740.4964,
|
| 6 |
+
"train_samples_per_second": 20.699,
|
| 7 |
+
"train_steps_per_second": 0.648
|
| 8 |
+
}
|
runs/May24_17-33-03_5970881f307e/events.out.tfevents.1716584963.5970881f307e.25.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea95f2a1666982bf4d8e5bb0ce89590ad52c3dcc53126e53882d8fe7454a5c16
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 1.952142618502398e+19,
|
| 4 |
+
"train_loss": 0.23986065309697932,
|
| 5 |
+
"train_runtime": 12740.4964,
|
| 6 |
+
"train_samples_per_second": 20.699,
|
| 7 |
+
"train_steps_per_second": 0.648
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,739 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2901732623577118,
|
| 3 |
+
"best_model_checkpoint": "./cconvnext-tiny-15ep-1e-4/checkpoint-8250",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18,
|
| 13 |
+
"grad_norm": 17.5977840423584,
|
| 14 |
+
"learning_rate": 9.996375239002369e-05,
|
| 15 |
+
"loss": 1.9015,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.36,
|
| 20 |
+
"grad_norm": 19.579683303833008,
|
| 21 |
+
"learning_rate": 9.985506211566388e-05,
|
| 22 |
+
"loss": 0.9353,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.55,
|
| 27 |
+
"grad_norm": 14.599044799804688,
|
| 28 |
+
"learning_rate": 9.967408676742751e-05,
|
| 29 |
+
"loss": 0.7327,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.73,
|
| 34 |
+
"grad_norm": 13.404082298278809,
|
| 35 |
+
"learning_rate": 9.942108874226811e-05,
|
| 36 |
+
"loss": 0.6524,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.91,
|
| 41 |
+
"grad_norm": 15.84705924987793,
|
| 42 |
+
"learning_rate": 9.909643486313533e-05,
|
| 43 |
+
"loss": 0.5838,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_accuracy": 0.8811133200795228,
|
| 49 |
+
"eval_loss": 0.40972331166267395,
|
| 50 |
+
"eval_runtime": 70.3463,
|
| 51 |
+
"eval_samples_per_second": 35.752,
|
| 52 |
+
"eval_steps_per_second": 1.123,
|
| 53 |
+
"step": 550
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.09,
|
| 57 |
+
"grad_norm": 23.304401397705078,
|
| 58 |
+
"learning_rate": 9.870059584711668e-05,
|
| 59 |
+
"loss": 0.5633,
|
| 60 |
+
"step": 600
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.27,
|
| 64 |
+
"grad_norm": 8.285646438598633,
|
| 65 |
+
"learning_rate": 9.82341456229428e-05,
|
| 66 |
+
"loss": 0.4562,
|
| 67 |
+
"step": 700
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.45,
|
| 71 |
+
"grad_norm": 17.91335678100586,
|
| 72 |
+
"learning_rate": 9.769776049884563e-05,
|
| 73 |
+
"loss": 0.444,
|
| 74 |
+
"step": 800
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.64,
|
| 78 |
+
"grad_norm": 8.382722854614258,
|
| 79 |
+
"learning_rate": 9.709221818197624e-05,
|
| 80 |
+
"loss": 0.4898,
|
| 81 |
+
"step": 900
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.82,
|
| 85 |
+
"grad_norm": 10.226556777954102,
|
| 86 |
+
"learning_rate": 9.641839665080363e-05,
|
| 87 |
+
"loss": 0.4433,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.0,
|
| 92 |
+
"grad_norm": 19.516849517822266,
|
| 93 |
+
"learning_rate": 9.567727288213005e-05,
|
| 94 |
+
"loss": 0.4565,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.0,
|
| 99 |
+
"eval_accuracy": 0.8763419483101391,
|
| 100 |
+
"eval_loss": 0.42688119411468506,
|
| 101 |
+
"eval_runtime": 71.6777,
|
| 102 |
+
"eval_samples_per_second": 35.088,
|
| 103 |
+
"eval_steps_per_second": 1.102,
|
| 104 |
+
"step": 1100
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.18,
|
| 108 |
+
"grad_norm": 13.549880027770996,
|
| 109 |
+
"learning_rate": 9.486992143456792e-05,
|
| 110 |
+
"loss": 0.3639,
|
| 111 |
+
"step": 1200
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.36,
|
| 115 |
+
"grad_norm": 8.744523048400879,
|
| 116 |
+
"learning_rate": 9.399751289053267e-05,
|
| 117 |
+
"loss": 0.3795,
|
| 118 |
+
"step": 1300
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.55,
|
| 122 |
+
"grad_norm": 5.8690056800842285,
|
| 123 |
+
"learning_rate": 9.306131215901003e-05,
|
| 124 |
+
"loss": 0.3665,
|
| 125 |
+
"step": 1400
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.73,
|
| 129 |
+
"grad_norm": 8.52180290222168,
|
| 130 |
+
"learning_rate": 9.206267664155907e-05,
|
| 131 |
+
"loss": 0.3741,
|
| 132 |
+
"step": 1500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.91,
|
| 136 |
+
"grad_norm": 3.9724719524383545,
|
| 137 |
+
"learning_rate": 9.100305426420956e-05,
|
| 138 |
+
"loss": 0.3628,
|
| 139 |
+
"step": 1600
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 3.0,
|
| 143 |
+
"eval_accuracy": 0.9001988071570577,
|
| 144 |
+
"eval_loss": 0.3464488685131073,
|
| 145 |
+
"eval_runtime": 72.3767,
|
| 146 |
+
"eval_samples_per_second": 34.749,
|
| 147 |
+
"eval_steps_per_second": 1.092,
|
| 148 |
+
"step": 1650
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.09,
|
| 152 |
+
"grad_norm": 10.699442863464355,
|
| 153 |
+
"learning_rate": 8.988398137810777e-05,
|
| 154 |
+
"loss": 0.3206,
|
| 155 |
+
"step": 1700
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.27,
|
| 159 |
+
"grad_norm": 7.718528747558594,
|
| 160 |
+
"learning_rate": 8.870708053195413e-05,
|
| 161 |
+
"loss": 0.3157,
|
| 162 |
+
"step": 1800
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.45,
|
| 166 |
+
"grad_norm": 12.929231643676758,
|
| 167 |
+
"learning_rate": 8.74740581194627e-05,
|
| 168 |
+
"loss": 0.2883,
|
| 169 |
+
"step": 1900
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.64,
|
| 173 |
+
"grad_norm": 9.246111869812012,
|
| 174 |
+
"learning_rate": 8.618670190525352e-05,
|
| 175 |
+
"loss": 0.3361,
|
| 176 |
+
"step": 2000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.82,
|
| 180 |
+
"grad_norm": 8.94174861907959,
|
| 181 |
+
"learning_rate": 8.484687843276469e-05,
|
| 182 |
+
"loss": 0.3051,
|
| 183 |
+
"step": 2100
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.0,
|
| 187 |
+
"grad_norm": 13.777535438537598,
|
| 188 |
+
"learning_rate": 8.345653031794292e-05,
|
| 189 |
+
"loss": 0.2915,
|
| 190 |
+
"step": 2200
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 4.0,
|
| 194 |
+
"eval_accuracy": 0.9065606361829026,
|
| 195 |
+
"eval_loss": 0.33660224080085754,
|
| 196 |
+
"eval_runtime": 72.2343,
|
| 197 |
+
"eval_samples_per_second": 34.817,
|
| 198 |
+
"eval_steps_per_second": 1.094,
|
| 199 |
+
"step": 2200
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 4.18,
|
| 203 |
+
"grad_norm": 10.229923248291016,
|
| 204 |
+
"learning_rate": 8.201767343263612e-05,
|
| 205 |
+
"loss": 0.2636,
|
| 206 |
+
"step": 2300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.36,
|
| 210 |
+
"grad_norm": 6.8911027908325195,
|
| 211 |
+
"learning_rate": 8.053239398177191e-05,
|
| 212 |
+
"loss": 0.2446,
|
| 213 |
+
"step": 2400
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.55,
|
| 217 |
+
"grad_norm": 14.081520080566406,
|
| 218 |
+
"learning_rate": 7.900284547855991e-05,
|
| 219 |
+
"loss": 0.2407,
|
| 220 |
+
"step": 2500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.73,
|
| 224 |
+
"grad_norm": 15.959187507629395,
|
| 225 |
+
"learning_rate": 7.74312456221035e-05,
|
| 226 |
+
"loss": 0.2645,
|
| 227 |
+
"step": 2600
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 4.91,
|
| 231 |
+
"grad_norm": 8.710769653320312,
|
| 232 |
+
"learning_rate": 7.58198730819481e-05,
|
| 233 |
+
"loss": 0.2655,
|
| 234 |
+
"step": 2700
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.0,
|
| 238 |
+
"eval_accuracy": 0.9053677932405566,
|
| 239 |
+
"eval_loss": 0.3387199640274048,
|
| 240 |
+
"eval_runtime": 71.8817,
|
| 241 |
+
"eval_samples_per_second": 34.988,
|
| 242 |
+
"eval_steps_per_second": 1.099,
|
| 243 |
+
"step": 2750
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 5.09,
|
| 247 |
+
"grad_norm": 8.720322608947754,
|
| 248 |
+
"learning_rate": 7.417106419422819e-05,
|
| 249 |
+
"loss": 0.2436,
|
| 250 |
+
"step": 2800
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 5.27,
|
| 254 |
+
"grad_norm": 14.12549114227295,
|
| 255 |
+
"learning_rate": 7.24872095742033e-05,
|
| 256 |
+
"loss": 0.2238,
|
| 257 |
+
"step": 2900
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 5.45,
|
| 261 |
+
"grad_norm": 8.974920272827148,
|
| 262 |
+
"learning_rate": 7.077075065009433e-05,
|
| 263 |
+
"loss": 0.2007,
|
| 264 |
+
"step": 3000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.64,
|
| 268 |
+
"grad_norm": 3.3389041423797607,
|
| 269 |
+
"learning_rate": 6.902417612324615e-05,
|
| 270 |
+
"loss": 0.2043,
|
| 271 |
+
"step": 3100
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 5.82,
|
| 275 |
+
"grad_norm": 5.468075275421143,
|
| 276 |
+
"learning_rate": 6.725001835974853e-05,
|
| 277 |
+
"loss": 0.2399,
|
| 278 |
+
"step": 3200
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 6.0,
|
| 282 |
+
"grad_norm": 19.46337890625,
|
| 283 |
+
"learning_rate": 6.545084971874738e-05,
|
| 284 |
+
"loss": 0.2395,
|
| 285 |
+
"step": 3300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 6.0,
|
| 289 |
+
"eval_accuracy": 0.9125248508946322,
|
| 290 |
+
"eval_loss": 0.33130431175231934,
|
| 291 |
+
"eval_runtime": 70.0346,
|
| 292 |
+
"eval_samples_per_second": 35.911,
|
| 293 |
+
"eval_steps_per_second": 1.128,
|
| 294 |
+
"step": 3300
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.18,
|
| 298 |
+
"grad_norm": 5.854804039001465,
|
| 299 |
+
"learning_rate": 6.36292788227699e-05,
|
| 300 |
+
"loss": 0.1906,
|
| 301 |
+
"step": 3400
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 6.36,
|
| 305 |
+
"grad_norm": 11.46949577331543,
|
| 306 |
+
"learning_rate": 6.178794677547137e-05,
|
| 307 |
+
"loss": 0.1857,
|
| 308 |
+
"step": 3500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.55,
|
| 312 |
+
"grad_norm": 7.80468225479126,
|
| 313 |
+
"learning_rate": 5.992952333228728e-05,
|
| 314 |
+
"loss": 0.1863,
|
| 315 |
+
"step": 3600
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.73,
|
| 319 |
+
"grad_norm": 6.652174472808838,
|
| 320 |
+
"learning_rate": 5.805670302954321e-05,
|
| 321 |
+
"loss": 0.1743,
|
| 322 |
+
"step": 3700
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 6.91,
|
| 326 |
+
"grad_norm": 9.390819549560547,
|
| 327 |
+
"learning_rate": 5.617220127763474e-05,
|
| 328 |
+
"loss": 0.2065,
|
| 329 |
+
"step": 3800
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 7.0,
|
| 333 |
+
"eval_accuracy": 0.9180914512922466,
|
| 334 |
+
"eval_loss": 0.3119599223136902,
|
| 335 |
+
"eval_runtime": 74.2948,
|
| 336 |
+
"eval_samples_per_second": 33.852,
|
| 337 |
+
"eval_steps_per_second": 1.063,
|
| 338 |
+
"step": 3850
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.09,
|
| 342 |
+
"grad_norm": 7.0801544189453125,
|
| 343 |
+
"learning_rate": 5.427875042394199e-05,
|
| 344 |
+
"loss": 0.1487,
|
| 345 |
+
"step": 3900
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.27,
|
| 349 |
+
"grad_norm": 6.336465358734131,
|
| 350 |
+
"learning_rate": 5.2379095791187124e-05,
|
| 351 |
+
"loss": 0.1712,
|
| 352 |
+
"step": 4000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.45,
|
| 356 |
+
"grad_norm": 6.033371448516846,
|
| 357 |
+
"learning_rate": 5.047599169697884e-05,
|
| 358 |
+
"loss": 0.1643,
|
| 359 |
+
"step": 4100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.64,
|
| 363 |
+
"grad_norm": 13.526623725891113,
|
| 364 |
+
"learning_rate": 4.85721974603152e-05,
|
| 365 |
+
"loss": 0.1716,
|
| 366 |
+
"step": 4200
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 7.82,
|
| 370 |
+
"grad_norm": 13.018455505371094,
|
| 371 |
+
"learning_rate": 4.667047340083481e-05,
|
| 372 |
+
"loss": 0.159,
|
| 373 |
+
"step": 4300
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 8.0,
|
| 377 |
+
"grad_norm": 19.489803314208984,
|
| 378 |
+
"learning_rate": 4.477357683661734e-05,
|
| 379 |
+
"loss": 0.1503,
|
| 380 |
+
"step": 4400
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.0,
|
| 384 |
+
"eval_accuracy": 0.9220675944333996,
|
| 385 |
+
"eval_loss": 0.30650895833969116,
|
| 386 |
+
"eval_runtime": 70.0541,
|
| 387 |
+
"eval_samples_per_second": 35.901,
|
| 388 |
+
"eval_steps_per_second": 1.128,
|
| 389 |
+
"step": 4400
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 8.18,
|
| 393 |
+
"grad_norm": 12.573568344116211,
|
| 394 |
+
"learning_rate": 4.288425808633575e-05,
|
| 395 |
+
"loss": 0.1518,
|
| 396 |
+
"step": 4500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 8.36,
|
| 400 |
+
"grad_norm": 13.930220603942871,
|
| 401 |
+
"learning_rate": 4.100525648155731e-05,
|
| 402 |
+
"loss": 0.1289,
|
| 403 |
+
"step": 4600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 8.55,
|
| 407 |
+
"grad_norm": 5.025359153747559,
|
| 408 |
+
"learning_rate": 3.913929639497462e-05,
|
| 409 |
+
"loss": 0.1243,
|
| 410 |
+
"step": 4700
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 8.73,
|
| 414 |
+
"grad_norm": 10.068098068237305,
|
| 415 |
+
"learning_rate": 3.728908329032567e-05,
|
| 416 |
+
"loss": 0.1484,
|
| 417 |
+
"step": 4800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 8.91,
|
| 421 |
+
"grad_norm": 7.712088584899902,
|
| 422 |
+
"learning_rate": 3.545729979973005e-05,
|
| 423 |
+
"loss": 0.1503,
|
| 424 |
+
"step": 4900
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 9.0,
|
| 428 |
+
"eval_accuracy": 0.927634194831014,
|
| 429 |
+
"eval_loss": 0.29477769136428833,
|
| 430 |
+
"eval_runtime": 72.6614,
|
| 431 |
+
"eval_samples_per_second": 34.613,
|
| 432 |
+
"eval_steps_per_second": 1.087,
|
| 433 |
+
"step": 4950
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 9.09,
|
| 437 |
+
"grad_norm": 9.499425888061523,
|
| 438 |
+
"learning_rate": 3.364660183412892e-05,
|
| 439 |
+
"loss": 0.117,
|
| 440 |
+
"step": 5000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 9.27,
|
| 444 |
+
"grad_norm": 3.1358752250671387,
|
| 445 |
+
"learning_rate": 3.1859614732467954e-05,
|
| 446 |
+
"loss": 0.118,
|
| 447 |
+
"step": 5100
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 9.45,
|
| 451 |
+
"grad_norm": 8.783591270446777,
|
| 452 |
+
"learning_rate": 3.0098929455206904e-05,
|
| 453 |
+
"loss": 0.1064,
|
| 454 |
+
"step": 5200
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 9.64,
|
| 458 |
+
"grad_norm": 4.272777557373047,
|
| 459 |
+
"learning_rate": 2.8367098827674578e-05,
|
| 460 |
+
"loss": 0.1294,
|
| 461 |
+
"step": 5300
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 9.82,
|
| 465 |
+
"grad_norm": 5.206827163696289,
|
| 466 |
+
"learning_rate": 2.6666633838716314e-05,
|
| 467 |
+
"loss": 0.1452,
|
| 468 |
+
"step": 5400
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 10.0,
|
| 472 |
+
"grad_norm": 27.840124130249023,
|
| 473 |
+
"learning_rate": 2.500000000000001e-05,
|
| 474 |
+
"loss": 0.1125,
|
| 475 |
+
"step": 5500
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 10.0,
|
| 479 |
+
"eval_accuracy": 0.9304174950298211,
|
| 480 |
+
"eval_loss": 0.2917528450489044,
|
| 481 |
+
"eval_runtime": 71.1465,
|
| 482 |
+
"eval_samples_per_second": 35.35,
|
| 483 |
+
"eval_steps_per_second": 1.11,
|
| 484 |
+
"step": 5500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 10.18,
|
| 488 |
+
"grad_norm": 10.059708595275879,
|
| 489 |
+
"learning_rate": 2.336961377126001e-05,
|
| 490 |
+
"loss": 0.1115,
|
| 491 |
+
"step": 5600
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 10.36,
|
| 495 |
+
"grad_norm": 3.956040143966675,
|
| 496 |
+
"learning_rate": 2.1777839056661554e-05,
|
| 497 |
+
"loss": 0.099,
|
| 498 |
+
"step": 5700
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 10.55,
|
| 502 |
+
"grad_norm": 4.310999870300293,
|
| 503 |
+
"learning_rate": 2.0226983777365604e-05,
|
| 504 |
+
"loss": 0.1056,
|
| 505 |
+
"step": 5800
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 10.73,
|
| 509 |
+
"grad_norm": 10.636781692504883,
|
| 510 |
+
"learning_rate": 1.8719296525263922e-05,
|
| 511 |
+
"loss": 0.0998,
|
| 512 |
+
"step": 5900
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 10.91,
|
| 516 |
+
"grad_norm": 8.48064136505127,
|
| 517 |
+
"learning_rate": 1.725696330273575e-05,
|
| 518 |
+
"loss": 0.1057,
|
| 519 |
+
"step": 6000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 11.0,
|
| 523 |
+
"eval_accuracy": 0.932803180914513,
|
| 524 |
+
"eval_loss": 0.2953931987285614,
|
| 525 |
+
"eval_runtime": 71.8417,
|
| 526 |
+
"eval_samples_per_second": 35.008,
|
| 527 |
+
"eval_steps_per_second": 1.1,
|
| 528 |
+
"step": 6050
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 11.09,
|
| 532 |
+
"grad_norm": 1.377661943435669,
|
| 533 |
+
"learning_rate": 1.5842104353153287e-05,
|
| 534 |
+
"loss": 0.0873,
|
| 535 |
+
"step": 6100
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 11.27,
|
| 539 |
+
"grad_norm": 2.6207616329193115,
|
| 540 |
+
"learning_rate": 1.4476771086731567e-05,
|
| 541 |
+
"loss": 0.0913,
|
| 542 |
+
"step": 6200
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 11.45,
|
| 546 |
+
"grad_norm": 8.88305950164795,
|
| 547 |
+
"learning_rate": 1.3162943106179749e-05,
|
| 548 |
+
"loss": 0.0874,
|
| 549 |
+
"step": 6300
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 11.64,
|
| 553 |
+
"grad_norm": 7.829620361328125,
|
| 554 |
+
"learning_rate": 1.1902525336466464e-05,
|
| 555 |
+
"loss": 0.0901,
|
| 556 |
+
"step": 6400
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 11.82,
|
| 560 |
+
"grad_norm": 1.778537392616272,
|
| 561 |
+
"learning_rate": 1.0697345262860636e-05,
|
| 562 |
+
"loss": 0.0922,
|
| 563 |
+
"step": 6500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 12.0,
|
| 567 |
+
"grad_norm": 3.688204526901245,
|
| 568 |
+
"learning_rate": 9.549150281252633e-06,
|
| 569 |
+
"loss": 0.0937,
|
| 570 |
+
"step": 6600
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 12.0,
|
| 574 |
+
"eval_accuracy": 0.9335984095427435,
|
| 575 |
+
"eval_loss": 0.2958705723285675,
|
| 576 |
+
"eval_runtime": 71.9587,
|
| 577 |
+
"eval_samples_per_second": 34.951,
|
| 578 |
+
"eval_steps_per_second": 1.098,
|
| 579 |
+
"step": 6600
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 12.18,
|
| 583 |
+
"grad_norm": 5.87827730178833,
|
| 584 |
+
"learning_rate": 8.459605164597267e-06,
|
| 585 |
+
"loss": 0.0973,
|
| 586 |
+
"step": 6700
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 12.36,
|
| 590 |
+
"grad_norm": 2.3431482315063477,
|
| 591 |
+
"learning_rate": 7.430289649152156e-06,
|
| 592 |
+
"loss": 0.0857,
|
| 593 |
+
"step": 6800
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 12.55,
|
| 597 |
+
"grad_norm": 1.375058650970459,
|
| 598 |
+
"learning_rate": 6.462696144011149e-06,
|
| 599 |
+
"loss": 0.0912,
|
| 600 |
+
"step": 6900
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 12.73,
|
| 604 |
+
"grad_norm": 5.9749979972839355,
|
| 605 |
+
"learning_rate": 5.558227567253832e-06,
|
| 606 |
+
"loss": 0.073,
|
| 607 |
+
"step": 7000
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 12.91,
|
| 611 |
+
"grad_norm": 8.656426429748535,
|
| 612 |
+
"learning_rate": 4.7181953118484556e-06,
|
| 613 |
+
"loss": 0.0966,
|
| 614 |
+
"step": 7100
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 13.0,
|
| 618 |
+
"eval_accuracy": 0.9351888667992048,
|
| 619 |
+
"eval_loss": 0.29395705461502075,
|
| 620 |
+
"eval_runtime": 71.5553,
|
| 621 |
+
"eval_samples_per_second": 35.148,
|
| 622 |
+
"eval_steps_per_second": 1.104,
|
| 623 |
+
"step": 7150
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 13.09,
|
| 627 |
+
"grad_norm": 6.880538463592529,
|
| 628 |
+
"learning_rate": 3.9438173442575e-06,
|
| 629 |
+
"loss": 0.0836,
|
| 630 |
+
"step": 7200
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 13.27,
|
| 634 |
+
"grad_norm": 3.5548784732818604,
|
| 635 |
+
"learning_rate": 3.2362164385026706e-06,
|
| 636 |
+
"loss": 0.1008,
|
| 637 |
+
"step": 7300
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 13.45,
|
| 641 |
+
"grad_norm": 6.498635292053223,
|
| 642 |
+
"learning_rate": 2.596418548250029e-06,
|
| 643 |
+
"loss": 0.0736,
|
| 644 |
+
"step": 7400
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 13.64,
|
| 648 |
+
"grad_norm": 2.343573808670044,
|
| 649 |
+
"learning_rate": 2.0253513192751373e-06,
|
| 650 |
+
"loss": 0.0719,
|
| 651 |
+
"step": 7500
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 13.82,
|
| 655 |
+
"grad_norm": 8.872209548950195,
|
| 656 |
+
"learning_rate": 1.523842744465437e-06,
|
| 657 |
+
"loss": 0.0879,
|
| 658 |
+
"step": 7600
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 14.0,
|
| 662 |
+
"grad_norm": 3.882363796234131,
|
| 663 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 664 |
+
"loss": 0.0735,
|
| 665 |
+
"step": 7700
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 14.0,
|
| 669 |
+
"eval_accuracy": 0.9339960238568589,
|
| 670 |
+
"eval_loss": 0.2915794849395752,
|
| 671 |
+
"eval_runtime": 69.9779,
|
| 672 |
+
"eval_samples_per_second": 35.94,
|
| 673 |
+
"eval_steps_per_second": 1.129,
|
| 674 |
+
"step": 7700
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 14.18,
|
| 678 |
+
"grad_norm": 1.7305363416671753,
|
| 679 |
+
"learning_rate": 7.323082076153509e-07,
|
| 680 |
+
"loss": 0.0824,
|
| 681 |
+
"step": 7800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 14.36,
|
| 685 |
+
"grad_norm": 10.12863826751709,
|
| 686 |
+
"learning_rate": 4.434298949819449e-07,
|
| 687 |
+
"loss": 0.0825,
|
| 688 |
+
"step": 7900
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 14.55,
|
| 692 |
+
"grad_norm": 0.9927307367324829,
|
| 693 |
+
"learning_rate": 2.2640387134577058e-07,
|
| 694 |
+
"loss": 0.0861,
|
| 695 |
+
"step": 8000
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 14.73,
|
| 699 |
+
"grad_norm": 7.997195720672607,
|
| 700 |
+
"learning_rate": 8.15448036932176e-08,
|
| 701 |
+
"loss": 0.0824,
|
| 702 |
+
"step": 8100
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 14.91,
|
| 706 |
+
"grad_norm": 7.195863246917725,
|
| 707 |
+
"learning_rate": 9.06272382371065e-09,
|
| 708 |
+
"loss": 0.0881,
|
| 709 |
+
"step": 8200
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 15.0,
|
| 713 |
+
"eval_accuracy": 0.9355864811133201,
|
| 714 |
+
"eval_loss": 0.2901732623577118,
|
| 715 |
+
"eval_runtime": 71.1315,
|
| 716 |
+
"eval_samples_per_second": 35.357,
|
| 717 |
+
"eval_steps_per_second": 1.111,
|
| 718 |
+
"step": 8250
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 15.0,
|
| 722 |
+
"step": 8250,
|
| 723 |
+
"total_flos": 1.952142618502398e+19,
|
| 724 |
+
"train_loss": 0.23986065309697932,
|
| 725 |
+
"train_runtime": 12740.4964,
|
| 726 |
+
"train_samples_per_second": 20.699,
|
| 727 |
+
"train_steps_per_second": 0.648
|
| 728 |
+
}
|
| 729 |
+
],
|
| 730 |
+
"logging_steps": 100,
|
| 731 |
+
"max_steps": 8250,
|
| 732 |
+
"num_input_tokens_seen": 0,
|
| 733 |
+
"num_train_epochs": 15,
|
| 734 |
+
"save_steps": 500,
|
| 735 |
+
"total_flos": 1.952142618502398e+19,
|
| 736 |
+
"train_batch_size": 32,
|
| 737 |
+
"trial_name": null,
|
| 738 |
+
"trial_params": null
|
| 739 |
+
}
|