Commit
•
4cd1747
1
Parent(s):
ad3fe6c
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_accuracy": 0.8395989974937343,
|
| 4 |
+
"eval_loss": 0.7026506066322327,
|
| 5 |
+
"eval_runtime": 0.3395,
|
| 6 |
+
"eval_samples": 6,
|
| 7 |
+
"eval_samples_per_second": 17.674,
|
| 8 |
+
"eval_steps_per_second": 2.946,
|
| 9 |
+
"perplexity": 2.0190974540336963,
|
| 10 |
+
"train_loss": 1.0904766319537984,
|
| 11 |
+
"train_runtime": 2826.0502,
|
| 12 |
+
"train_samples": 229,
|
| 13 |
+
"train_samples_per_second": 8.103,
|
| 14 |
+
"train_steps_per_second": 1.026
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_accuracy": 0.8395989974937343,
|
| 4 |
+
"eval_loss": 0.7026506066322327,
|
| 5 |
+
"eval_runtime": 0.3395,
|
| 6 |
+
"eval_samples": 6,
|
| 7 |
+
"eval_samples_per_second": 17.674,
|
| 8 |
+
"eval_steps_per_second": 2.946,
|
| 9 |
+
"perplexity": 2.0190974540336963
|
| 10 |
+
}
|
runs/Apr22_10-23-58_ea2e7ccc4c59/events.out.tfevents.1682161969.ea2e7ccc4c59.623.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c49db47b1c74fa3f591e2bc54b9c3530d4ff9e410b53d764b4c4eabda2e45b6f
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"train_loss": 1.0904766319537984,
|
| 4 |
+
"train_runtime": 2826.0502,
|
| 5 |
+
"train_samples": 229,
|
| 6 |
+
"train_samples_per_second": 8.103,
|
| 7 |
+
"train_steps_per_second": 1.026
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"global_step": 2900,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 17.24,
|
| 12 |
+
"learning_rate": 0.00041379310344827585,
|
| 13 |
+
"loss": 2.4,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 34.48,
|
| 18 |
+
"learning_rate": 0.0003275862068965517,
|
| 19 |
+
"loss": 1.5498,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 51.72,
|
| 24 |
+
"learning_rate": 0.0002413793103448276,
|
| 25 |
+
"loss": 1.0188,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 68.97,
|
| 30 |
+
"learning_rate": 0.00015517241379310346,
|
| 31 |
+
"loss": 0.6721,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 86.21,
|
| 36 |
+
"learning_rate": 6.896551724137931e-05,
|
| 37 |
+
"loss": 0.4353,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 100.0,
|
| 42 |
+
"step": 2900,
|
| 43 |
+
"total_flos": 6027390213120000.0,
|
| 44 |
+
"train_loss": 1.0904766319537984,
|
| 45 |
+
"train_runtime": 2826.0502,
|
| 46 |
+
"train_samples_per_second": 8.103,
|
| 47 |
+
"train_steps_per_second": 1.026
|
| 48 |
+
}
|
| 49 |
+
],
|
| 50 |
+
"max_steps": 2900,
|
| 51 |
+
"num_train_epochs": 100,
|
| 52 |
+
"total_flos": 6027390213120000.0,
|
| 53 |
+
"trial_name": null,
|
| 54 |
+
"trial_params": null
|
| 55 |
+
}
|