End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.5070321730630286,
|
| 4 |
+
"eval_loss": 2.3684260845184326,
|
| 5 |
+
"eval_runtime": 9.7402,
|
| 6 |
+
"eval_samples": 575,
|
| 7 |
+
"eval_samples_per_second": 59.034,
|
| 8 |
+
"eval_steps_per_second": 7.392,
|
| 9 |
+
"perplexity": 10.680568735677312,
|
| 10 |
+
"train_loss": 2.700293814781869,
|
| 11 |
+
"train_runtime": 444.9433,
|
| 12 |
+
"train_samples": 3259,
|
| 13 |
+
"train_samples_per_second": 21.974,
|
| 14 |
+
"train_steps_per_second": 0.681
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.5070321730630286,
|
| 4 |
+
"eval_loss": 2.3684260845184326,
|
| 5 |
+
"eval_runtime": 9.7402,
|
| 6 |
+
"eval_samples": 575,
|
| 7 |
+
"eval_samples_per_second": 59.034,
|
| 8 |
+
"eval_steps_per_second": 7.392,
|
| 9 |
+
"perplexity": 10.680568735677312
|
| 10 |
+
}
|
runs/Apr24_10-52-30_2c630289b464/events.out.tfevents.1650798120.2c630289b464.10677.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7d1da78ed1309f094faef366f13fbfe92f2ac41a41d892d6745d0e0a6ba18e2
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"train_loss": 2.700293814781869,
|
| 4 |
+
"train_runtime": 444.9433,
|
| 5 |
+
"train_samples": 3259,
|
| 6 |
+
"train_samples_per_second": 21.974,
|
| 7 |
+
"train_steps_per_second": 0.681
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.3684260845184326,
|
| 3 |
+
"best_model_checkpoint": "models/checkpoint-303",
|
| 4 |
+
"epoch": 2.9914110429447853,
|
| 5 |
+
"global_step": 303,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.99,
|
| 12 |
+
"eval_accuracy": 0.48085171490501083,
|
| 13 |
+
"eval_loss": 2.563568353652954,
|
| 14 |
+
"eval_runtime": 9.7149,
|
| 15 |
+
"eval_samples_per_second": 59.187,
|
| 16 |
+
"eval_steps_per_second": 7.411,
|
| 17 |
+
"step": 101
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.99,
|
| 21 |
+
"eval_accuracy": 0.501789281312423,
|
| 22 |
+
"eval_loss": 2.4074697494506836,
|
| 23 |
+
"eval_runtime": 9.6785,
|
| 24 |
+
"eval_samples_per_second": 59.41,
|
| 25 |
+
"eval_steps_per_second": 7.439,
|
| 26 |
+
"step": 202
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.99,
|
| 30 |
+
"eval_accuracy": 0.5070321730630286,
|
| 31 |
+
"eval_loss": 2.3684260845184326,
|
| 32 |
+
"eval_runtime": 9.6634,
|
| 33 |
+
"eval_samples_per_second": 59.503,
|
| 34 |
+
"eval_steps_per_second": 7.451,
|
| 35 |
+
"step": 303
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.99,
|
| 39 |
+
"step": 303,
|
| 40 |
+
"total_flos": 5095194624000000.0,
|
| 41 |
+
"train_loss": 2.700293814781869,
|
| 42 |
+
"train_runtime": 444.9433,
|
| 43 |
+
"train_samples_per_second": 21.974,
|
| 44 |
+
"train_steps_per_second": 0.681
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"max_steps": 303,
|
| 48 |
+
"num_train_epochs": 3,
|
| 49 |
+
"total_flos": 5095194624000000.0,
|
| 50 |
+
"trial_name": null,
|
| 51 |
+
"trial_params": null
|
| 52 |
+
}
|