Commit
•
a9b2473
1
Parent(s):
f42909f
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Sep16_18-42-03_patrick-general-gpu/events.out.tfevents.1631817737.patrick-general-gpu.194163.0 +2 -2
- runs/Sep16_18-42-03_patrick-general-gpu/events.out.tfevents.1631817898.patrick-general-gpu.194163.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +100 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.5492957746478874,
|
| 4 |
+
"eval_loss": 0.6887156963348389,
|
| 5 |
+
"eval_runtime": 0.5251,
|
| 6 |
+
"eval_samples": 71,
|
| 7 |
+
"eval_samples_per_second": 135.222,
|
| 8 |
+
"eval_steps_per_second": 17.141,
|
| 9 |
+
"train_loss": 0.6969355392456055,
|
| 10 |
+
"train_runtime": 156.8951,
|
| 11 |
+
"train_samples": 635,
|
| 12 |
+
"train_samples_per_second": 20.236,
|
| 13 |
+
"train_steps_per_second": 1.275
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.5492957746478874,
|
| 4 |
+
"eval_loss": 0.6887156963348389,
|
| 5 |
+
"eval_runtime": 0.5251,
|
| 6 |
+
"eval_samples": 71,
|
| 7 |
+
"eval_samples_per_second": 135.222,
|
| 8 |
+
"eval_steps_per_second": 17.141
|
| 9 |
+
}
|
runs/Sep16_18-42-03_patrick-general-gpu/events.out.tfevents.1631817737.patrick-general-gpu.194163.0
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:f8e60de9ce500a503ca0836e772695339000b5059c2ef3343e5f48627f392a31
|
| 3 |
+
size 5911
|
runs/Sep16_18-42-03_patrick-general-gpu/events.out.tfevents.1631817898.patrick-general-gpu.194163.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30b1840d6586c069fa74709ed71932ca8450da60381796351e4654c26d31b0ed
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.6969355392456055,
|
| 4 |
+
"train_runtime": 156.8951,
|
| 5 |
+
"train_samples": 635,
|
| 6 |
+
"train_samples_per_second": 20.236,
|
| 7 |
+
"train_steps_per_second": 1.275
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 200,
|
| 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": 1.6000000000000003e-05,
|
| 13 |
+
"loss": 0.7052,
|
| 14 |
+
"step": 40
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.5633802816901409,
|
| 19 |
+
"eval_loss": 0.6902039051055908,
|
| 20 |
+
"eval_runtime": 0.5271,
|
| 21 |
+
"eval_samples_per_second": 134.707,
|
| 22 |
+
"eval_steps_per_second": 17.076,
|
| 23 |
+
"step": 40
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 1.2e-05,
|
| 28 |
+
"loss": 0.6957,
|
| 29 |
+
"step": 80
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.43661971830985913,
|
| 34 |
+
"eval_loss": 0.7012577056884766,
|
| 35 |
+
"eval_runtime": 0.5221,
|
| 36 |
+
"eval_samples_per_second": 135.995,
|
| 37 |
+
"eval_steps_per_second": 17.239,
|
| 38 |
+
"step": 80
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"learning_rate": 8.000000000000001e-06,
|
| 43 |
+
"loss": 0.6898,
|
| 44 |
+
"step": 120
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_accuracy": 0.5352112676056338,
|
| 49 |
+
"eval_loss": 0.6898324489593506,
|
| 50 |
+
"eval_runtime": 0.5232,
|
| 51 |
+
"eval_samples_per_second": 135.691,
|
| 52 |
+
"eval_steps_per_second": 17.2,
|
| 53 |
+
"step": 120
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"learning_rate": 4.000000000000001e-06,
|
| 58 |
+
"loss": 0.6958,
|
| 59 |
+
"step": 160
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.0,
|
| 63 |
+
"eval_accuracy": 0.5633802816901409,
|
| 64 |
+
"eval_loss": 0.6874184608459473,
|
| 65 |
+
"eval_runtime": 0.5224,
|
| 66 |
+
"eval_samples_per_second": 135.906,
|
| 67 |
+
"eval_steps_per_second": 17.228,
|
| 68 |
+
"step": 160
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.0,
|
| 72 |
+
"learning_rate": 0.0,
|
| 73 |
+
"loss": 0.6982,
|
| 74 |
+
"step": 200
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 5.0,
|
| 78 |
+
"eval_accuracy": 0.5492957746478874,
|
| 79 |
+
"eval_loss": 0.6887156963348389,
|
| 80 |
+
"eval_runtime": 0.523,
|
| 81 |
+
"eval_samples_per_second": 135.751,
|
| 82 |
+
"eval_steps_per_second": 17.208,
|
| 83 |
+
"step": 200
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 5.0,
|
| 87 |
+
"step": 200,
|
| 88 |
+
"total_flos": 564638888601600.0,
|
| 89 |
+
"train_loss": 0.6969355392456055,
|
| 90 |
+
"train_runtime": 156.8951,
|
| 91 |
+
"train_samples_per_second": 20.236,
|
| 92 |
+
"train_steps_per_second": 1.275
|
| 93 |
+
}
|
| 94 |
+
],
|
| 95 |
+
"max_steps": 200,
|
| 96 |
+
"num_train_epochs": 5,
|
| 97 |
+
"total_flos": 564638888601600.0,
|
| 98 |
+
"trial_name": null,
|
| 99 |
+
"trial_params": null
|
| 100 |
+
}
|