Commit
•
03b3c85
1
Parent(s):
f9bbdcf
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Oct09_13-52-41_patrick-general-gpu/events.out.tfevents.1633787594.patrick-general-gpu.50676.0 +2 -2
- runs/Oct09_13-52-41_patrick-general-gpu/events.out.tfevents.1633788689.patrick-general-gpu.50676.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +70 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.6642599277978339,
|
| 4 |
+
"eval_loss": 1.5187355279922485,
|
| 5 |
+
"eval_runtime": 9.0184,
|
| 6 |
+
"eval_samples": 277,
|
| 7 |
+
"eval_samples_per_second": 30.715,
|
| 8 |
+
"eval_steps_per_second": 3.881,
|
| 9 |
+
"train_loss": 0.5809510844859801,
|
| 10 |
+
"train_runtime": 1072.8997,
|
| 11 |
+
"train_samples": 2490,
|
| 12 |
+
"train_samples_per_second": 6.962,
|
| 13 |
+
"train_steps_per_second": 1.742
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.6642599277978339,
|
| 4 |
+
"eval_loss": 1.5187355279922485,
|
| 5 |
+
"eval_runtime": 9.0184,
|
| 6 |
+
"eval_samples": 277,
|
| 7 |
+
"eval_samples_per_second": 30.715,
|
| 8 |
+
"eval_steps_per_second": 3.881
|
| 9 |
+
}
|
runs/Oct09_13-52-41_patrick-general-gpu/events.out.tfevents.1633787594.patrick-general-gpu.50676.0
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 sha256:9fb99abcabfb2dd00806ca2163ba64b181a3477626e22b2900e00158fba59300
|
| 3 |
+
size 5231
|
runs/Oct09_13-52-41_patrick-general-gpu/events.out.tfevents.1633788689.patrick-general-gpu.50676.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d7b45ecd6a4225d7da460c266be63c1ec04e2de618f739a1ef40d404217d31b
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.5809510844859801,
|
| 4 |
+
"train_runtime": 1072.8997,
|
| 5 |
+
"train_samples": 2490,
|
| 6 |
+
"train_samples_per_second": 6.962,
|
| 7 |
+
"train_steps_per_second": 1.742
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 1869,
|
| 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": 1.3333333333333333e-05,
|
| 13 |
+
"loss": 0.6969,
|
| 14 |
+
"step": 623
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.5342960288808665,
|
| 19 |
+
"eval_loss": 0.7039318680763245,
|
| 20 |
+
"eval_runtime": 9.0213,
|
| 21 |
+
"eval_samples_per_second": 30.705,
|
| 22 |
+
"eval_steps_per_second": 3.88,
|
| 23 |
+
"step": 623
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 6.666666666666667e-06,
|
| 28 |
+
"loss": 0.5903,
|
| 29 |
+
"step": 1246
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.7184115523465704,
|
| 34 |
+
"eval_loss": 0.6461479663848877,
|
| 35 |
+
"eval_runtime": 8.9942,
|
| 36 |
+
"eval_samples_per_second": 30.798,
|
| 37 |
+
"eval_steps_per_second": 3.891,
|
| 38 |
+
"step": 1246
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 0.0,
|
| 43 |
+
"loss": 0.4557,
|
| 44 |
+
"step": 1869
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_accuracy": 0.6642599277978339,
|
| 49 |
+
"eval_loss": 1.5187355279922485,
|
| 50 |
+
"eval_runtime": 9.0028,
|
| 51 |
+
"eval_samples_per_second": 30.768,
|
| 52 |
+
"eval_steps_per_second": 3.888,
|
| 53 |
+
"step": 1869
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.0,
|
| 57 |
+
"step": 1869,
|
| 58 |
+
"total_flos": 6961527284060160.0,
|
| 59 |
+
"train_loss": 0.5809510844859801,
|
| 60 |
+
"train_runtime": 1072.8997,
|
| 61 |
+
"train_samples_per_second": 6.962,
|
| 62 |
+
"train_steps_per_second": 1.742
|
| 63 |
+
}
|
| 64 |
+
],
|
| 65 |
+
"max_steps": 1869,
|
| 66 |
+
"num_train_epochs": 3,
|
| 67 |
+
"total_flos": 6961527284060160.0,
|
| 68 |
+
"trial_name": null,
|
| 69 |
+
"trial_params": null
|
| 70 |
+
}
|