Training in progress, epoch 1
Browse files- all_results.json +8 -0
- confusion_matrix.jpg +0 -0
- model.safetensors +1 -1
- runs/Aug08_17-05-59_prod3/events.out.tfevents.1754644981.prod3.3071947.1 +3 -0
- runs/Aug10_19-30-42_prod3/events.out.tfevents.1754825450.prod3.154612.0 +3 -0
- test_results.json +8 -0
- trainer_state.json +786 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.090217391304348,
|
| 3 |
+
"eval_accuracy": 0.7714285714285715,
|
| 4 |
+
"eval_loss": 1.018705129623413,
|
| 5 |
+
"eval_runtime": 4.7483,
|
| 6 |
+
"eval_samples_per_second": 14.742,
|
| 7 |
+
"eval_steps_per_second": 3.791
|
| 8 |
+
}
|
confusion_matrix.jpg
CHANGED
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 344952716
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68dd4a675be43bd11f87d3757f6efd3f4b1c337853c735906fd7f198b4d4b221
|
| 3 |
size 344952716
|
runs/Aug08_17-05-59_prod3/events.out.tfevents.1754644981.prod3.3071947.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcc012db134b4b2a6a45163628dd9b9c76cff2fdfc69ce8f56ccd287141d21ed
|
| 3 |
+
size 411
|
runs/Aug10_19-30-42_prod3/events.out.tfevents.1754825450.prod3.154612.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f1f9c5ade32e3a52ae747bdeead543b23d5899307edcce49b84342def2df918
|
| 3 |
+
size 10884
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.090217391304348,
|
| 3 |
+
"eval_accuracy": 0.7714285714285715,
|
| 4 |
+
"eval_loss": 1.018705129623413,
|
| 5 |
+
"eval_runtime": 4.7483,
|
| 6 |
+
"eval_samples_per_second": 14.742,
|
| 7 |
+
"eval_steps_per_second": 3.791
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,786 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 558,
|
| 3 |
+
"best_metric": 0.7714285714285715,
|
| 4 |
+
"best_model_checkpoint": "./Models/Matcha_clips_224_fintuned_4/checkpoint-558",
|
| 5 |
+
"epoch": 9.090217391304348,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 920,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.010869565217391304,
|
| 14 |
+
"grad_norm": 5.376043796539307,
|
| 15 |
+
"learning_rate": 4.891304347826087e-06,
|
| 16 |
+
"loss": 1.9825,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.021739130434782608,
|
| 21 |
+
"grad_norm": 4.800479888916016,
|
| 22 |
+
"learning_rate": 1.032608695652174e-05,
|
| 23 |
+
"loss": 1.9728,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.03260869565217391,
|
| 28 |
+
"grad_norm": 4.874147891998291,
|
| 29 |
+
"learning_rate": 1.5760869565217393e-05,
|
| 30 |
+
"loss": 1.863,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.043478260869565216,
|
| 35 |
+
"grad_norm": 7.789337158203125,
|
| 36 |
+
"learning_rate": 2.1195652173913045e-05,
|
| 37 |
+
"loss": 1.7022,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05434782608695652,
|
| 42 |
+
"grad_norm": 12.864760398864746,
|
| 43 |
+
"learning_rate": 2.66304347826087e-05,
|
| 44 |
+
"loss": 1.7414,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06521739130434782,
|
| 49 |
+
"grad_norm": 8.978934288024902,
|
| 50 |
+
"learning_rate": 3.2065217391304345e-05,
|
| 51 |
+
"loss": 1.6658,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.07608695652173914,
|
| 56 |
+
"grad_norm": 7.047595977783203,
|
| 57 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 58 |
+
"loss": 1.6791,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.08695652173913043,
|
| 63 |
+
"grad_norm": 9.732585906982422,
|
| 64 |
+
"learning_rate": 4.2934782608695655e-05,
|
| 65 |
+
"loss": 1.4575,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.09782608695652174,
|
| 70 |
+
"grad_norm": 14.573904037475586,
|
| 71 |
+
"learning_rate": 4.836956521739131e-05,
|
| 72 |
+
"loss": 1.5559,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.10108695652173913,
|
| 77 |
+
"eval_accuracy": 0.35714285714285715,
|
| 78 |
+
"eval_loss": 1.6018733978271484,
|
| 79 |
+
"eval_runtime": 5.1784,
|
| 80 |
+
"eval_samples_per_second": 13.518,
|
| 81 |
+
"eval_steps_per_second": 3.476,
|
| 82 |
+
"step": 93
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.007608695652174,
|
| 86 |
+
"grad_norm": 14.384367942810059,
|
| 87 |
+
"learning_rate": 4.957729468599034e-05,
|
| 88 |
+
"loss": 1.1631,
|
| 89 |
+
"step": 100
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.0184782608695653,
|
| 93 |
+
"grad_norm": 7.838768482208252,
|
| 94 |
+
"learning_rate": 4.897342995169083e-05,
|
| 95 |
+
"loss": 1.0314,
|
| 96 |
+
"step": 110
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.0293478260869566,
|
| 100 |
+
"grad_norm": 13.853711128234863,
|
| 101 |
+
"learning_rate": 4.836956521739131e-05,
|
| 102 |
+
"loss": 0.9719,
|
| 103 |
+
"step": 120
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.0402173913043478,
|
| 107 |
+
"grad_norm": 10.313530921936035,
|
| 108 |
+
"learning_rate": 4.776570048309179e-05,
|
| 109 |
+
"loss": 0.8127,
|
| 110 |
+
"step": 130
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.0510869565217391,
|
| 114 |
+
"grad_norm": 18.755401611328125,
|
| 115 |
+
"learning_rate": 4.716183574879227e-05,
|
| 116 |
+
"loss": 1.016,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.0619565217391305,
|
| 121 |
+
"grad_norm": 10.809492111206055,
|
| 122 |
+
"learning_rate": 4.655797101449276e-05,
|
| 123 |
+
"loss": 0.8474,
|
| 124 |
+
"step": 150
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.0728260869565218,
|
| 128 |
+
"grad_norm": 3.606818437576294,
|
| 129 |
+
"learning_rate": 4.595410628019324e-05,
|
| 130 |
+
"loss": 0.5612,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.083695652173913,
|
| 135 |
+
"grad_norm": 10.220298767089844,
|
| 136 |
+
"learning_rate": 4.5350241545893724e-05,
|
| 137 |
+
"loss": 0.962,
|
| 138 |
+
"step": 170
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.0945652173913043,
|
| 142 |
+
"grad_norm": 14.552356719970703,
|
| 143 |
+
"learning_rate": 4.4746376811594203e-05,
|
| 144 |
+
"loss": 0.9517,
|
| 145 |
+
"step": 180
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.1010869565217392,
|
| 149 |
+
"eval_accuracy": 0.7142857142857143,
|
| 150 |
+
"eval_loss": 0.9070804119110107,
|
| 151 |
+
"eval_runtime": 5.0526,
|
| 152 |
+
"eval_samples_per_second": 13.854,
|
| 153 |
+
"eval_steps_per_second": 3.563,
|
| 154 |
+
"step": 186
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.0043478260869567,
|
| 158 |
+
"grad_norm": 10.325079917907715,
|
| 159 |
+
"learning_rate": 4.414251207729469e-05,
|
| 160 |
+
"loss": 0.5439,
|
| 161 |
+
"step": 190
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.015217391304348,
|
| 165 |
+
"grad_norm": 2.7573156356811523,
|
| 166 |
+
"learning_rate": 4.353864734299517e-05,
|
| 167 |
+
"loss": 0.3143,
|
| 168 |
+
"step": 200
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.026086956521739,
|
| 172 |
+
"grad_norm": 2.0995430946350098,
|
| 173 |
+
"learning_rate": 4.2934782608695655e-05,
|
| 174 |
+
"loss": 0.2437,
|
| 175 |
+
"step": 210
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 2.0369565217391306,
|
| 179 |
+
"grad_norm": 3.4484243392944336,
|
| 180 |
+
"learning_rate": 4.2330917874396135e-05,
|
| 181 |
+
"loss": 0.2801,
|
| 182 |
+
"step": 220
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.0478260869565217,
|
| 186 |
+
"grad_norm": 8.872885704040527,
|
| 187 |
+
"learning_rate": 4.172705314009662e-05,
|
| 188 |
+
"loss": 0.1246,
|
| 189 |
+
"step": 230
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.0586956521739133,
|
| 193 |
+
"grad_norm": 12.566852569580078,
|
| 194 |
+
"learning_rate": 4.11231884057971e-05,
|
| 195 |
+
"loss": 0.1881,
|
| 196 |
+
"step": 240
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.0695652173913044,
|
| 200 |
+
"grad_norm": 6.908414840698242,
|
| 201 |
+
"learning_rate": 4.0519323671497586e-05,
|
| 202 |
+
"loss": 0.1273,
|
| 203 |
+
"step": 250
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.0804347826086955,
|
| 207 |
+
"grad_norm": 5.361249923706055,
|
| 208 |
+
"learning_rate": 3.991545893719807e-05,
|
| 209 |
+
"loss": 0.2715,
|
| 210 |
+
"step": 260
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.091304347826087,
|
| 214 |
+
"grad_norm": 23.682147979736328,
|
| 215 |
+
"learning_rate": 3.931159420289855e-05,
|
| 216 |
+
"loss": 0.2361,
|
| 217 |
+
"step": 270
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.101086956521739,
|
| 221 |
+
"eval_accuracy": 0.6857142857142857,
|
| 222 |
+
"eval_loss": 0.938868522644043,
|
| 223 |
+
"eval_runtime": 5.2093,
|
| 224 |
+
"eval_samples_per_second": 13.437,
|
| 225 |
+
"eval_steps_per_second": 3.455,
|
| 226 |
+
"step": 279
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.001086956521739,
|
| 230 |
+
"grad_norm": 2.6006569862365723,
|
| 231 |
+
"learning_rate": 3.870772946859904e-05,
|
| 232 |
+
"loss": 0.226,
|
| 233 |
+
"step": 280
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.0119565217391306,
|
| 237 |
+
"grad_norm": 1.2024024724960327,
|
| 238 |
+
"learning_rate": 3.8103864734299524e-05,
|
| 239 |
+
"loss": 0.0308,
|
| 240 |
+
"step": 290
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.0228260869565218,
|
| 244 |
+
"grad_norm": 1.2223767042160034,
|
| 245 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 246 |
+
"loss": 0.037,
|
| 247 |
+
"step": 300
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.033695652173913,
|
| 251 |
+
"grad_norm": 0.12124505639076233,
|
| 252 |
+
"learning_rate": 3.689613526570048e-05,
|
| 253 |
+
"loss": 0.0213,
|
| 254 |
+
"step": 310
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.0445652173913045,
|
| 258 |
+
"grad_norm": 0.24608278274536133,
|
| 259 |
+
"learning_rate": 3.629227053140097e-05,
|
| 260 |
+
"loss": 0.0428,
|
| 261 |
+
"step": 320
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.0554347826086956,
|
| 265 |
+
"grad_norm": 2.318938970565796,
|
| 266 |
+
"learning_rate": 3.568840579710145e-05,
|
| 267 |
+
"loss": 0.0189,
|
| 268 |
+
"step": 330
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.0663043478260867,
|
| 272 |
+
"grad_norm": 0.1917387992143631,
|
| 273 |
+
"learning_rate": 3.5084541062801935e-05,
|
| 274 |
+
"loss": 0.0675,
|
| 275 |
+
"step": 340
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.0771739130434783,
|
| 279 |
+
"grad_norm": 0.13483163714408875,
|
| 280 |
+
"learning_rate": 3.4480676328502414e-05,
|
| 281 |
+
"loss": 0.0921,
|
| 282 |
+
"step": 350
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.0880434782608694,
|
| 286 |
+
"grad_norm": 0.43146082758903503,
|
| 287 |
+
"learning_rate": 3.38768115942029e-05,
|
| 288 |
+
"loss": 0.0161,
|
| 289 |
+
"step": 360
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.098913043478261,
|
| 293 |
+
"grad_norm": 0.08563941717147827,
|
| 294 |
+
"learning_rate": 3.327294685990338e-05,
|
| 295 |
+
"loss": 0.0444,
|
| 296 |
+
"step": 370
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.101086956521739,
|
| 300 |
+
"eval_accuracy": 0.7571428571428571,
|
| 301 |
+
"eval_loss": 0.9734786748886108,
|
| 302 |
+
"eval_runtime": 5.2886,
|
| 303 |
+
"eval_samples_per_second": 13.236,
|
| 304 |
+
"eval_steps_per_second": 3.404,
|
| 305 |
+
"step": 372
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.008695652173913,
|
| 309 |
+
"grad_norm": 0.04769546538591385,
|
| 310 |
+
"learning_rate": 3.2669082125603866e-05,
|
| 311 |
+
"loss": 0.0041,
|
| 312 |
+
"step": 380
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 4.019565217391304,
|
| 316 |
+
"grad_norm": 0.07156966626644135,
|
| 317 |
+
"learning_rate": 3.2065217391304345e-05,
|
| 318 |
+
"loss": 0.0151,
|
| 319 |
+
"step": 390
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 4.030434782608696,
|
| 323 |
+
"grad_norm": 0.027476496994495392,
|
| 324 |
+
"learning_rate": 3.146135265700483e-05,
|
| 325 |
+
"loss": 0.0036,
|
| 326 |
+
"step": 400
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.041304347826087,
|
| 330 |
+
"grad_norm": 0.031293053179979324,
|
| 331 |
+
"learning_rate": 3.085748792270531e-05,
|
| 332 |
+
"loss": 0.0046,
|
| 333 |
+
"step": 410
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 4.052173913043478,
|
| 337 |
+
"grad_norm": 0.037460871040821075,
|
| 338 |
+
"learning_rate": 3.02536231884058e-05,
|
| 339 |
+
"loss": 0.005,
|
| 340 |
+
"step": 420
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 4.0630434782608695,
|
| 344 |
+
"grad_norm": 0.03713839128613472,
|
| 345 |
+
"learning_rate": 2.964975845410628e-05,
|
| 346 |
+
"loss": 0.0022,
|
| 347 |
+
"step": 430
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 4.073913043478261,
|
| 351 |
+
"grad_norm": 0.16258321702480316,
|
| 352 |
+
"learning_rate": 2.9045893719806766e-05,
|
| 353 |
+
"loss": 0.0311,
|
| 354 |
+
"step": 440
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 4.084782608695652,
|
| 358 |
+
"grad_norm": 0.05423327907919884,
|
| 359 |
+
"learning_rate": 2.8442028985507245e-05,
|
| 360 |
+
"loss": 0.0043,
|
| 361 |
+
"step": 450
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 4.095652173913043,
|
| 365 |
+
"grad_norm": 0.1273375302553177,
|
| 366 |
+
"learning_rate": 2.783816425120773e-05,
|
| 367 |
+
"loss": 0.0055,
|
| 368 |
+
"step": 460
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.101086956521739,
|
| 372 |
+
"eval_accuracy": 0.7428571428571429,
|
| 373 |
+
"eval_loss": 1.068024754524231,
|
| 374 |
+
"eval_runtime": 5.1661,
|
| 375 |
+
"eval_samples_per_second": 13.55,
|
| 376 |
+
"eval_steps_per_second": 3.484,
|
| 377 |
+
"step": 465
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 5.005434782608695,
|
| 381 |
+
"grad_norm": 0.04361015558242798,
|
| 382 |
+
"learning_rate": 2.7234299516908214e-05,
|
| 383 |
+
"loss": 0.0042,
|
| 384 |
+
"step": 470
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 5.016304347826087,
|
| 388 |
+
"grad_norm": 0.018031172454357147,
|
| 389 |
+
"learning_rate": 2.66304347826087e-05,
|
| 390 |
+
"loss": 0.0019,
|
| 391 |
+
"step": 480
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 5.0271739130434785,
|
| 395 |
+
"grad_norm": 0.018111947923898697,
|
| 396 |
+
"learning_rate": 2.602657004830918e-05,
|
| 397 |
+
"loss": 0.0011,
|
| 398 |
+
"step": 490
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 5.038043478260869,
|
| 402 |
+
"grad_norm": 0.027051832526922226,
|
| 403 |
+
"learning_rate": 2.5422705314009666e-05,
|
| 404 |
+
"loss": 0.0015,
|
| 405 |
+
"step": 500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 5.048913043478261,
|
| 409 |
+
"grad_norm": 0.025533143430948257,
|
| 410 |
+
"learning_rate": 2.4818840579710145e-05,
|
| 411 |
+
"loss": 0.0526,
|
| 412 |
+
"step": 510
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 5.059782608695652,
|
| 416 |
+
"grad_norm": 0.03490010276436806,
|
| 417 |
+
"learning_rate": 2.4214975845410628e-05,
|
| 418 |
+
"loss": 0.0011,
|
| 419 |
+
"step": 520
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.070652173913044,
|
| 423 |
+
"grad_norm": 0.12445239722728729,
|
| 424 |
+
"learning_rate": 2.361111111111111e-05,
|
| 425 |
+
"loss": 0.0031,
|
| 426 |
+
"step": 530
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 5.081521739130435,
|
| 430 |
+
"grad_norm": 0.027472317218780518,
|
| 431 |
+
"learning_rate": 2.3007246376811593e-05,
|
| 432 |
+
"loss": 0.0013,
|
| 433 |
+
"step": 540
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5.092391304347826,
|
| 437 |
+
"grad_norm": 0.04045948013663292,
|
| 438 |
+
"learning_rate": 2.240338164251208e-05,
|
| 439 |
+
"loss": 0.0013,
|
| 440 |
+
"step": 550
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.101086956521739,
|
| 444 |
+
"eval_accuracy": 0.7714285714285715,
|
| 445 |
+
"eval_loss": 1.0187050104141235,
|
| 446 |
+
"eval_runtime": 5.1614,
|
| 447 |
+
"eval_samples_per_second": 13.562,
|
| 448 |
+
"eval_steps_per_second": 3.487,
|
| 449 |
+
"step": 558
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 6.002173913043478,
|
| 453 |
+
"grad_norm": 0.017682170495390892,
|
| 454 |
+
"learning_rate": 2.1799516908212562e-05,
|
| 455 |
+
"loss": 0.0078,
|
| 456 |
+
"step": 560
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 6.01304347826087,
|
| 460 |
+
"grad_norm": 0.025376908481121063,
|
| 461 |
+
"learning_rate": 2.1195652173913045e-05,
|
| 462 |
+
"loss": 0.0013,
|
| 463 |
+
"step": 570
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 6.023913043478261,
|
| 467 |
+
"grad_norm": 0.02693229354918003,
|
| 468 |
+
"learning_rate": 2.0591787439613528e-05,
|
| 469 |
+
"loss": 0.0011,
|
| 470 |
+
"step": 580
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 6.034782608695652,
|
| 474 |
+
"grad_norm": 0.02828039415180683,
|
| 475 |
+
"learning_rate": 1.998792270531401e-05,
|
| 476 |
+
"loss": 0.0009,
|
| 477 |
+
"step": 590
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 6.0456521739130435,
|
| 481 |
+
"grad_norm": 0.012215801514685154,
|
| 482 |
+
"learning_rate": 1.9384057971014493e-05,
|
| 483 |
+
"loss": 0.0008,
|
| 484 |
+
"step": 600
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 6.056521739130435,
|
| 488 |
+
"grad_norm": 0.013270609080791473,
|
| 489 |
+
"learning_rate": 1.8780193236714976e-05,
|
| 490 |
+
"loss": 0.0027,
|
| 491 |
+
"step": 610
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 6.067391304347826,
|
| 495 |
+
"grad_norm": 0.00943638663738966,
|
| 496 |
+
"learning_rate": 1.817632850241546e-05,
|
| 497 |
+
"loss": 0.0009,
|
| 498 |
+
"step": 620
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 6.078260869565217,
|
| 502 |
+
"grad_norm": 0.020451508462429047,
|
| 503 |
+
"learning_rate": 1.757246376811594e-05,
|
| 504 |
+
"loss": 0.0027,
|
| 505 |
+
"step": 630
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 6.089130434782609,
|
| 509 |
+
"grad_norm": 0.010344174690544605,
|
| 510 |
+
"learning_rate": 1.6968599033816428e-05,
|
| 511 |
+
"loss": 0.001,
|
| 512 |
+
"step": 640
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 6.1,
|
| 516 |
+
"grad_norm": 0.020511051639914513,
|
| 517 |
+
"learning_rate": 1.636473429951691e-05,
|
| 518 |
+
"loss": 0.0009,
|
| 519 |
+
"step": 650
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 6.101086956521739,
|
| 523 |
+
"eval_accuracy": 0.7714285714285715,
|
| 524 |
+
"eval_loss": 1.0440902709960938,
|
| 525 |
+
"eval_runtime": 5.2143,
|
| 526 |
+
"eval_samples_per_second": 13.425,
|
| 527 |
+
"eval_steps_per_second": 3.452,
|
| 528 |
+
"step": 651
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 7.0097826086956525,
|
| 532 |
+
"grad_norm": 0.013392376713454723,
|
| 533 |
+
"learning_rate": 1.5760869565217393e-05,
|
| 534 |
+
"loss": 0.0009,
|
| 535 |
+
"step": 660
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 7.020652173913043,
|
| 539 |
+
"grad_norm": 0.017662443220615387,
|
| 540 |
+
"learning_rate": 1.5157004830917876e-05,
|
| 541 |
+
"loss": 0.0017,
|
| 542 |
+
"step": 670
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 7.031521739130435,
|
| 546 |
+
"grad_norm": 0.01805092766880989,
|
| 547 |
+
"learning_rate": 1.4553140096618359e-05,
|
| 548 |
+
"loss": 0.0007,
|
| 549 |
+
"step": 680
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 7.042391304347826,
|
| 553 |
+
"grad_norm": 0.025202885270118713,
|
| 554 |
+
"learning_rate": 1.3949275362318842e-05,
|
| 555 |
+
"loss": 0.0007,
|
| 556 |
+
"step": 690
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 7.053260869565217,
|
| 560 |
+
"grad_norm": 0.01182204857468605,
|
| 561 |
+
"learning_rate": 1.3345410628019326e-05,
|
| 562 |
+
"loss": 0.0008,
|
| 563 |
+
"step": 700
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 7.064130434782609,
|
| 567 |
+
"grad_norm": 0.00941186398267746,
|
| 568 |
+
"learning_rate": 1.2741545893719809e-05,
|
| 569 |
+
"loss": 0.0007,
|
| 570 |
+
"step": 710
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 7.075,
|
| 574 |
+
"grad_norm": 0.014904760755598545,
|
| 575 |
+
"learning_rate": 1.213768115942029e-05,
|
| 576 |
+
"loss": 0.0007,
|
| 577 |
+
"step": 720
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 7.085869565217392,
|
| 581 |
+
"grad_norm": 0.013263923116028309,
|
| 582 |
+
"learning_rate": 1.1533816425120773e-05,
|
| 583 |
+
"loss": 0.001,
|
| 584 |
+
"step": 730
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 7.096739130434782,
|
| 588 |
+
"grad_norm": 0.01642896980047226,
|
| 589 |
+
"learning_rate": 1.0929951690821257e-05,
|
| 590 |
+
"loss": 0.0014,
|
| 591 |
+
"step": 740
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 7.101086956521739,
|
| 595 |
+
"eval_accuracy": 0.7714285714285715,
|
| 596 |
+
"eval_loss": 1.056229591369629,
|
| 597 |
+
"eval_runtime": 5.1211,
|
| 598 |
+
"eval_samples_per_second": 13.669,
|
| 599 |
+
"eval_steps_per_second": 3.515,
|
| 600 |
+
"step": 744
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 8.006521739130434,
|
| 604 |
+
"grad_norm": 0.016901936382055283,
|
| 605 |
+
"learning_rate": 1.032608695652174e-05,
|
| 606 |
+
"loss": 0.0008,
|
| 607 |
+
"step": 750
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 8.017391304347827,
|
| 611 |
+
"grad_norm": 0.014034947380423546,
|
| 612 |
+
"learning_rate": 9.722222222222223e-06,
|
| 613 |
+
"loss": 0.0007,
|
| 614 |
+
"step": 760
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 8.028260869565218,
|
| 618 |
+
"grad_norm": 0.01714772917330265,
|
| 619 |
+
"learning_rate": 9.118357487922705e-06,
|
| 620 |
+
"loss": 0.0009,
|
| 621 |
+
"step": 770
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 8.039130434782608,
|
| 625 |
+
"grad_norm": 0.009475274942815304,
|
| 626 |
+
"learning_rate": 8.51449275362319e-06,
|
| 627 |
+
"loss": 0.0006,
|
| 628 |
+
"step": 780
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 8.05,
|
| 632 |
+
"grad_norm": 0.018608668819069862,
|
| 633 |
+
"learning_rate": 7.910628019323673e-06,
|
| 634 |
+
"loss": 0.0008,
|
| 635 |
+
"step": 790
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 8.060869565217391,
|
| 639 |
+
"grad_norm": 0.018759367987513542,
|
| 640 |
+
"learning_rate": 7.3067632850241555e-06,
|
| 641 |
+
"loss": 0.0007,
|
| 642 |
+
"step": 800
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 8.071739130434782,
|
| 646 |
+
"grad_norm": 0.01856890134513378,
|
| 647 |
+
"learning_rate": 6.702898550724638e-06,
|
| 648 |
+
"loss": 0.0007,
|
| 649 |
+
"step": 810
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 8.082608695652175,
|
| 653 |
+
"grad_norm": 0.022196952253580093,
|
| 654 |
+
"learning_rate": 6.099033816425121e-06,
|
| 655 |
+
"loss": 0.0009,
|
| 656 |
+
"step": 820
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 8.093478260869565,
|
| 660 |
+
"grad_norm": 0.024934960529208183,
|
| 661 |
+
"learning_rate": 5.495169082125605e-06,
|
| 662 |
+
"loss": 0.0009,
|
| 663 |
+
"step": 830
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 8.101086956521739,
|
| 667 |
+
"eval_accuracy": 0.7714285714285715,
|
| 668 |
+
"eval_loss": 1.0678843259811401,
|
| 669 |
+
"eval_runtime": 5.1663,
|
| 670 |
+
"eval_samples_per_second": 13.549,
|
| 671 |
+
"eval_steps_per_second": 3.484,
|
| 672 |
+
"step": 837
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 9.003260869565217,
|
| 676 |
+
"grad_norm": 0.009687897749245167,
|
| 677 |
+
"learning_rate": 4.891304347826087e-06,
|
| 678 |
+
"loss": 0.0006,
|
| 679 |
+
"step": 840
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 9.014130434782608,
|
| 683 |
+
"grad_norm": 0.009451821446418762,
|
| 684 |
+
"learning_rate": 4.28743961352657e-06,
|
| 685 |
+
"loss": 0.0008,
|
| 686 |
+
"step": 850
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 9.025,
|
| 690 |
+
"grad_norm": 0.010965824127197266,
|
| 691 |
+
"learning_rate": 3.683574879227053e-06,
|
| 692 |
+
"loss": 0.0008,
|
| 693 |
+
"step": 860
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 9.035869565217391,
|
| 697 |
+
"grad_norm": 0.029875043779611588,
|
| 698 |
+
"learning_rate": 3.0797101449275365e-06,
|
| 699 |
+
"loss": 0.0009,
|
| 700 |
+
"step": 870
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 9.046739130434782,
|
| 704 |
+
"grad_norm": 0.013975279405713081,
|
| 705 |
+
"learning_rate": 2.4758454106280193e-06,
|
| 706 |
+
"loss": 0.0007,
|
| 707 |
+
"step": 880
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 9.057608695652174,
|
| 711 |
+
"grad_norm": 0.012320472858846188,
|
| 712 |
+
"learning_rate": 1.8719806763285025e-06,
|
| 713 |
+
"loss": 0.0007,
|
| 714 |
+
"step": 890
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 9.068478260869565,
|
| 718 |
+
"grad_norm": 0.00791542325168848,
|
| 719 |
+
"learning_rate": 1.2681159420289857e-06,
|
| 720 |
+
"loss": 0.0006,
|
| 721 |
+
"step": 900
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 9.079347826086957,
|
| 725 |
+
"grad_norm": 0.014570249244570732,
|
| 726 |
+
"learning_rate": 6.642512077294687e-07,
|
| 727 |
+
"loss": 0.0007,
|
| 728 |
+
"step": 910
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 9.090217391304348,
|
| 732 |
+
"grad_norm": 0.012345642782747746,
|
| 733 |
+
"learning_rate": 6.038647342995169e-08,
|
| 734 |
+
"loss": 0.0008,
|
| 735 |
+
"step": 920
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 9.090217391304348,
|
| 739 |
+
"eval_accuracy": 0.7714285714285715,
|
| 740 |
+
"eval_loss": 1.0686471462249756,
|
| 741 |
+
"eval_runtime": 5.2106,
|
| 742 |
+
"eval_samples_per_second": 13.434,
|
| 743 |
+
"eval_steps_per_second": 3.454,
|
| 744 |
+
"step": 920
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 9.090217391304348,
|
| 748 |
+
"step": 920,
|
| 749 |
+
"total_flos": 4.574507079339639e+18,
|
| 750 |
+
"train_loss": 0.29402525549167363,
|
| 751 |
+
"train_runtime": 968.7389,
|
| 752 |
+
"train_samples_per_second": 3.799,
|
| 753 |
+
"train_steps_per_second": 0.95
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 9.090217391304348,
|
| 757 |
+
"eval_accuracy": 0.7714285714285715,
|
| 758 |
+
"eval_loss": 1.018705129623413,
|
| 759 |
+
"eval_runtime": 4.7483,
|
| 760 |
+
"eval_samples_per_second": 14.742,
|
| 761 |
+
"eval_steps_per_second": 3.791,
|
| 762 |
+
"step": 920
|
| 763 |
+
}
|
| 764 |
+
],
|
| 765 |
+
"logging_steps": 10,
|
| 766 |
+
"max_steps": 920,
|
| 767 |
+
"num_input_tokens_seen": 0,
|
| 768 |
+
"num_train_epochs": 9223372036854775807,
|
| 769 |
+
"save_steps": 500,
|
| 770 |
+
"stateful_callbacks": {
|
| 771 |
+
"TrainerControl": {
|
| 772 |
+
"args": {
|
| 773 |
+
"should_epoch_stop": false,
|
| 774 |
+
"should_evaluate": false,
|
| 775 |
+
"should_log": false,
|
| 776 |
+
"should_save": true,
|
| 777 |
+
"should_training_stop": true
|
| 778 |
+
},
|
| 779 |
+
"attributes": {}
|
| 780 |
+
}
|
| 781 |
+
},
|
| 782 |
+
"total_flos": 4.574507079339639e+18,
|
| 783 |
+
"train_batch_size": 4,
|
| 784 |
+
"trial_name": null,
|
| 785 |
+
"trial_params": null
|
| 786 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaa568e7b011d0b9f130aeb3d7026b19146123d5db02987304373b307ee56b8a
|
| 3 |
size 5368
|