Commit
•
0d96170
1
Parent(s):
52a8d71
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.7884666754551509,
|
| 4 |
+
"eval_loss": 1.2736778259277344,
|
| 5 |
+
"eval_runtime": 49.3849,
|
| 6 |
+
"eval_samples": 2252,
|
| 7 |
+
"eval_samples_per_second": 45.601,
|
| 8 |
+
"eval_steps_per_second": 1.438,
|
| 9 |
+
"perplexity": 3.5739728705498077,
|
| 10 |
+
"train_loss": 1.5686970041758979,
|
| 11 |
+
"train_runtime": 1103.7707,
|
| 12 |
+
"train_samples": 42863,
|
| 13 |
+
"train_samples_per_second": 38.833,
|
| 14 |
+
"train_steps_per_second": 1.214
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.7884666754551509,
|
| 4 |
+
"eval_loss": 1.2736778259277344,
|
| 5 |
+
"eval_runtime": 49.3849,
|
| 6 |
+
"eval_samples": 2252,
|
| 7 |
+
"eval_samples_per_second": 45.601,
|
| 8 |
+
"eval_steps_per_second": 1.438,
|
| 9 |
+
"perplexity": 3.5739728705498077
|
| 10 |
+
}
|
runs/Nov06_18-31-38_hkmustamd-Super-Server/events.out.tfevents.1730890358.hkmustamd-Super-Server.3622900.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bf62781d9e635d53ea8896c385cfc17f39f9f3ec9cfd3bd537546915544da4f
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.5686970041758979,
|
| 4 |
+
"train_runtime": 1103.7707,
|
| 5 |
+
"train_samples": 42863,
|
| 6 |
+
"train_samples_per_second": 38.833,
|
| 7 |
+
"train_steps_per_second": 1.214
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 1340,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.37,
|
| 12 |
+
"learning_rate": 6.965174129353234e-07,
|
| 13 |
+
"loss": 1.8401,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.75,
|
| 18 |
+
"learning_rate": 2.8192371475953566e-07,
|
| 19 |
+
"loss": 1.4199,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.0,
|
| 24 |
+
"step": 1340,
|
| 25 |
+
"total_flos": 1.306756690477056e+16,
|
| 26 |
+
"train_loss": 1.5686970041758979,
|
| 27 |
+
"train_runtime": 1103.7707,
|
| 28 |
+
"train_samples_per_second": 38.833,
|
| 29 |
+
"train_steps_per_second": 1.214
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
+
"max_steps": 1340,
|
| 33 |
+
"num_train_epochs": 1,
|
| 34 |
+
"total_flos": 1.306756690477056e+16,
|
| 35 |
+
"trial_name": null,
|
| 36 |
+
"trial_params": null
|
| 37 |
+
}
|