Commit
•
9871d6b
1
Parent(s):
a7c4008
End of training
Browse files
runs/Feb28_15-32-18_7c779bfb7013/events.out.tfevents.1677598345.7c779bfb7013.343.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d12355210e12ed2c3f04dec18fc61a2154336b258c9dba8eaa122eba2f597542
|
| 3 |
+
size 6133
|
trainer_state.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 282,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 6.666666666666667e-05,
|
| 13 |
+
"loss": 3.4338,
|
| 14 |
+
"step": 94
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 2.4137182235717773,
|
| 19 |
+
"eval_runtime": 36.2713,
|
| 20 |
+
"eval_samples_per_second": 5.514,
|
| 21 |
+
"eval_steps_per_second": 0.689,
|
| 22 |
+
"step": 94
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 2.0,
|
| 26 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 27 |
+
"loss": 2.9565,
|
| 28 |
+
"step": 188
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_loss": 2.173758029937744,
|
| 33 |
+
"eval_runtime": 35.902,
|
| 34 |
+
"eval_samples_per_second": 5.571,
|
| 35 |
+
"eval_steps_per_second": 0.696,
|
| 36 |
+
"step": 188
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"learning_rate": 0.0,
|
| 41 |
+
"loss": 2.7101,
|
| 42 |
+
"step": 282
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_loss": 2.012174606323242,
|
| 47 |
+
"eval_runtime": 35.6264,
|
| 48 |
+
"eval_samples_per_second": 5.614,
|
| 49 |
+
"eval_steps_per_second": 0.702,
|
| 50 |
+
"step": 282
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.0,
|
| 54 |
+
"step": 282,
|
| 55 |
+
"total_flos": 1.07525797056e+18,
|
| 56 |
+
"train_loss": 3.0334743202155363,
|
| 57 |
+
"train_runtime": 718.9206,
|
| 58 |
+
"train_samples_per_second": 3.13,
|
| 59 |
+
"train_steps_per_second": 0.392
|
| 60 |
+
}
|
| 61 |
+
],
|
| 62 |
+
"max_steps": 282,
|
| 63 |
+
"num_train_epochs": 3,
|
| 64 |
+
"total_flos": 1.07525797056e+18,
|
| 65 |
+
"trial_name": null,
|
| 66 |
+
"trial_params": null
|
| 67 |
+
}
|