Commit
•
8648d54
1
Parent(s):
55d5419
End of training
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Sep19_13-18-31_patrick-general-gpu/events.out.tfevents.1632057532.patrick-general-gpu.502385.0 +2 -2
- runs/Sep19_13-18-31_patrick-general-gpu/events.out.tfevents.1632058180.patrick-general-gpu.502385.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +76 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_combined_score": 0.8911934607933856,
|
| 4 |
+
"eval_loss": 0.48608845472335815,
|
| 5 |
+
"eval_pearson": 0.8925961944446151,
|
| 6 |
+
"eval_runtime": 15.3906,
|
| 7 |
+
"eval_samples": 1500,
|
| 8 |
+
"eval_samples_per_second": 97.462,
|
| 9 |
+
"eval_spearmanr": 0.8897907271421561,
|
| 10 |
+
"eval_steps_per_second": 12.215,
|
| 11 |
+
"train_loss": 0.5799058207759151,
|
| 12 |
+
"train_runtime": 624.1289,
|
| 13 |
+
"train_samples": 5749,
|
| 14 |
+
"train_samples_per_second": 27.634,
|
| 15 |
+
"train_steps_per_second": 1.73
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_combined_score": 0.8911934607933856,
|
| 4 |
+
"eval_loss": 0.48608845472335815,
|
| 5 |
+
"eval_pearson": 0.8925961944446151,
|
| 6 |
+
"eval_runtime": 15.3906,
|
| 7 |
+
"eval_samples": 1500,
|
| 8 |
+
"eval_samples_per_second": 97.462,
|
| 9 |
+
"eval_spearmanr": 0.8897907271421561,
|
| 10 |
+
"eval_steps_per_second": 12.215
|
| 11 |
+
}
|
runs/Sep19_13-18-31_patrick-general-gpu/events.out.tfevents.1632057532.patrick-general-gpu.502385.0
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:c2aad9b117f2b5848ee75cd7edb5a2e76259f704bd52c837b78b9392b4d0d0ce
|
| 3 |
+
size 5312
|
runs/Sep19_13-18-31_patrick-general-gpu/events.out.tfevents.1632058180.patrick-general-gpu.502385.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29b0e18d7a46bf1019237cc31b3372617bffdea4fe949b8819aa8f73ebc32ea1
|
| 3 |
+
size 473
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.5799058207759151,
|
| 4 |
+
"train_runtime": 624.1289,
|
| 5 |
+
"train_samples": 5749,
|
| 6 |
+
"train_samples_per_second": 27.634,
|
| 7 |
+
"train_steps_per_second": 1.73
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 1080,
|
| 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": 1.1174,
|
| 14 |
+
"step": 360
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_combined_score": 0.8815940360468737,
|
| 19 |
+
"eval_loss": 0.5000496506690979,
|
| 20 |
+
"eval_pearson": 0.8832304460348288,
|
| 21 |
+
"eval_runtime": 15.5329,
|
| 22 |
+
"eval_samples_per_second": 96.569,
|
| 23 |
+
"eval_spearmanr": 0.8799576260589187,
|
| 24 |
+
"eval_steps_per_second": 12.103,
|
| 25 |
+
"step": 360
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"learning_rate": 6.666666666666667e-06,
|
| 30 |
+
"loss": 0.3835,
|
| 31 |
+
"step": 720
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.0,
|
| 35 |
+
"eval_combined_score": 0.8901405153644659,
|
| 36 |
+
"eval_loss": 0.4672209620475769,
|
| 37 |
+
"eval_pearson": 0.8914800693934992,
|
| 38 |
+
"eval_runtime": 15.3324,
|
| 39 |
+
"eval_samples_per_second": 97.832,
|
| 40 |
+
"eval_spearmanr": 0.8888009613354327,
|
| 41 |
+
"eval_steps_per_second": 12.262,
|
| 42 |
+
"step": 720
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"learning_rate": 0.0,
|
| 47 |
+
"loss": 0.2388,
|
| 48 |
+
"step": 1080
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_combined_score": 0.8911934607933856,
|
| 53 |
+
"eval_loss": 0.48608845472335815,
|
| 54 |
+
"eval_pearson": 0.8925961944446151,
|
| 55 |
+
"eval_runtime": 15.3291,
|
| 56 |
+
"eval_samples_per_second": 97.853,
|
| 57 |
+
"eval_spearmanr": 0.8897907271421561,
|
| 58 |
+
"eval_steps_per_second": 12.264,
|
| 59 |
+
"step": 1080
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.0,
|
| 63 |
+
"step": 1080,
|
| 64 |
+
"total_flos": 4537835628033024.0,
|
| 65 |
+
"train_loss": 0.5799058207759151,
|
| 66 |
+
"train_runtime": 624.1289,
|
| 67 |
+
"train_samples_per_second": 27.634,
|
| 68 |
+
"train_steps_per_second": 1.73
|
| 69 |
+
}
|
| 70 |
+
],
|
| 71 |
+
"max_steps": 1080,
|
| 72 |
+
"num_train_epochs": 3,
|
| 73 |
+
"total_flos": 4537835628033024.0,
|
| 74 |
+
"trial_name": null,
|
| 75 |
+
"trial_params": null
|
| 76 |
+
}
|