Commit
•
1a6f07d
1
Parent(s):
34c7cb3
End of training
Browse files- all_results.json +10 -0
- eval_results.json +6 -0
- pytorch_model.bin +1 -1
- train_results.json +7 -0
- trainer_state.json +61 -0
all_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_runtime": 92.5118,
|
| 4 |
+
"eval_samples_per_second": 270.387,
|
| 5 |
+
"eval_steps_per_second": 0.53,
|
| 6 |
+
"train_loss": 0.8221148734484917,
|
| 7 |
+
"train_runtime": 8159.3229,
|
| 8 |
+
"train_samples_per_second": 217.574,
|
| 9 |
+
"train_steps_per_second": 0.425
|
| 10 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_runtime": 92.5118,
|
| 4 |
+
"eval_samples_per_second": 270.387,
|
| 5 |
+
"eval_steps_per_second": 0.53
|
| 6 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 851631805
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d915df1413e4642dcc7fc6b43a468d821f7e20ee0b4ded8d51522488d574ac1
|
| 3 |
size 851631805
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.8221148734484917,
|
| 4 |
+
"train_runtime": 8159.3229,
|
| 5 |
+
"train_samples_per_second": 217.574,
|
| 6 |
+
"train_steps_per_second": 0.425
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 3465,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.43,
|
| 12 |
+
"learning_rate": 4.278499278499279e-05,
|
| 13 |
+
"loss": 3.3442,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.87,
|
| 18 |
+
"learning_rate": 3.556998556998557e-05,
|
| 19 |
+
"loss": 0.7984,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.3,
|
| 24 |
+
"learning_rate": 2.8354978354978357e-05,
|
| 25 |
+
"loss": 0.4652,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.73,
|
| 30 |
+
"learning_rate": 2.113997113997114e-05,
|
| 31 |
+
"loss": 0.3644,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.16,
|
| 36 |
+
"learning_rate": 1.3924963924963927e-05,
|
| 37 |
+
"loss": 0.2928,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.6,
|
| 42 |
+
"learning_rate": 6.709956709956711e-06,
|
| 43 |
+
"loss": 0.2326,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"step": 3465,
|
| 49 |
+
"total_flos": 2.3687033473990656e+17,
|
| 50 |
+
"train_loss": 0.8221148734484917,
|
| 51 |
+
"train_runtime": 8159.3229,
|
| 52 |
+
"train_samples_per_second": 217.574,
|
| 53 |
+
"train_steps_per_second": 0.425
|
| 54 |
+
}
|
| 55 |
+
],
|
| 56 |
+
"max_steps": 3465,
|
| 57 |
+
"num_train_epochs": 3,
|
| 58 |
+
"total_flos": 2.3687033473990656e+17,
|
| 59 |
+
"trial_name": null,
|
| 60 |
+
"trial_params": null
|
| 61 |
+
}
|