Commit
•
4fdd3ec
1
Parent(s):
7db2dfa
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- runs/Jun14_08-21-18_labgpu/events.out.tfevents.1655197283.labgpu.3997.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +85 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.6336674690246582,
|
| 4 |
+
"eval_matthews_correlation": 0.5277813760438573,
|
| 5 |
+
"eval_runtime": 7.0774,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 147.371,
|
| 8 |
+
"eval_steps_per_second": 18.51,
|
| 9 |
+
"train_loss": 29757.83613023134,
|
| 10 |
+
"train_runtime": 2069.8226,
|
| 11 |
+
"train_samples": 8551,
|
| 12 |
+
"train_samples_per_second": 41.313,
|
| 13 |
+
"train_steps_per_second": 2.585
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.6336674690246582,
|
| 4 |
+
"eval_matthews_correlation": 0.5277813760438573,
|
| 5 |
+
"eval_runtime": 7.0774,
|
| 6 |
+
"eval_samples": 1043,
|
| 7 |
+
"eval_samples_per_second": 147.371,
|
| 8 |
+
"eval_steps_per_second": 18.51
|
| 9 |
+
}
|
runs/Jun14_08-21-18_labgpu/events.out.tfevents.1655197283.labgpu.3997.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c0f33583fd8857bc11f373c62f4f3ba86210f552006eb6d638a7b9020281b51
|
| 3 |
+
size 375
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 29757.83613023134,
|
| 4 |
+
"train_runtime": 2069.8226,
|
| 5 |
+
"train_samples": 8551,
|
| 6 |
+
"train_samples_per_second": 41.313,
|
| 7 |
+
"train_steps_per_second": 2.585
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 5350,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.93,
|
| 12 |
+
"learning_rate": 9.065420560747664e-06,
|
| 13 |
+
"loss": 318405.12,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.87,
|
| 18 |
+
"learning_rate": 8.130841121495327e-06,
|
| 19 |
+
"loss": 0.5212,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.8,
|
| 24 |
+
"learning_rate": 7.196261682242991e-06,
|
| 25 |
+
"loss": 0.7034,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 3.74,
|
| 30 |
+
"learning_rate": 6.2616822429906544e-06,
|
| 31 |
+
"loss": 0.4659,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 4.67,
|
| 36 |
+
"learning_rate": 5.3271028037383174e-06,
|
| 37 |
+
"loss": 0.346,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 5.61,
|
| 42 |
+
"learning_rate": 4.392523364485981e-06,
|
| 43 |
+
"loss": 0.3146,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 6.54,
|
| 48 |
+
"learning_rate": 3.457943925233645e-06,
|
| 49 |
+
"loss": 0.2947,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 7.48,
|
| 54 |
+
"learning_rate": 2.5233644859813085e-06,
|
| 55 |
+
"loss": 0.343,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 8.41,
|
| 60 |
+
"learning_rate": 1.588785046728972e-06,
|
| 61 |
+
"loss": 0.3041,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 9.35,
|
| 66 |
+
"learning_rate": 6.542056074766355e-07,
|
| 67 |
+
"loss": 0.2609,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 10.0,
|
| 72 |
+
"step": 5350,
|
| 73 |
+
"total_flos": 1340551406822400.0,
|
| 74 |
+
"train_loss": 29757.83613023134,
|
| 75 |
+
"train_runtime": 2069.8226,
|
| 76 |
+
"train_samples_per_second": 41.313,
|
| 77 |
+
"train_steps_per_second": 2.585
|
| 78 |
+
}
|
| 79 |
+
],
|
| 80 |
+
"max_steps": 5350,
|
| 81 |
+
"num_train_epochs": 10,
|
| 82 |
+
"total_flos": 1340551406822400.0,
|
| 83 |
+
"trial_name": null,
|
| 84 |
+
"trial_params": null
|
| 85 |
+
}
|