QuickRead/fine-tune-Pegasus
Browse files- all_results.json +18 -0
- eval_results.json +13 -0
- train_results.json +8 -0
- trainer_state.json +31 -0
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_gen_len": 67.0552,
|
| 4 |
+
"eval_loss": 2.324213981628418,
|
| 5 |
+
"eval_rouge1": 17.993,
|
| 6 |
+
"eval_rouge2": 2.9392,
|
| 7 |
+
"eval_rougeL": 12.313,
|
| 8 |
+
"eval_rougeLsum": 13.3091,
|
| 9 |
+
"eval_runtime": 7752.5256,
|
| 10 |
+
"eval_samples": 11332,
|
| 11 |
+
"eval_samples_per_second": 1.462,
|
| 12 |
+
"eval_steps_per_second": 0.183,
|
| 13 |
+
"train_loss": 2.7845563131665427,
|
| 14 |
+
"train_runtime": 39.3075,
|
| 15 |
+
"train_samples": 500,
|
| 16 |
+
"train_samples_per_second": 12.72,
|
| 17 |
+
"train_steps_per_second": 1.603
|
| 18 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_gen_len": 67.0552,
|
| 4 |
+
"eval_loss": 2.324213981628418,
|
| 5 |
+
"eval_rouge1": 17.993,
|
| 6 |
+
"eval_rouge2": 2.9392,
|
| 7 |
+
"eval_rougeL": 12.313,
|
| 8 |
+
"eval_rougeLsum": 13.3091,
|
| 9 |
+
"eval_runtime": 7752.5256,
|
| 10 |
+
"eval_samples": 11332,
|
| 11 |
+
"eval_samples_per_second": 1.462,
|
| 12 |
+
"eval_steps_per_second": 0.183
|
| 13 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 2.7845563131665427,
|
| 4 |
+
"train_runtime": 39.3075,
|
| 5 |
+
"train_samples": 500,
|
| 6 |
+
"train_samples_per_second": 12.72,
|
| 7 |
+
"train_steps_per_second": 1.603
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 63,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.79,
|
| 12 |
+
"learning_rate": 5.7149999999999995e-06,
|
| 13 |
+
"loss": 2.8257,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"step": 63,
|
| 19 |
+
"total_flos": 1193890577645568.0,
|
| 20 |
+
"train_loss": 2.7845563131665427,
|
| 21 |
+
"train_runtime": 39.3075,
|
| 22 |
+
"train_samples_per_second": 12.72,
|
| 23 |
+
"train_steps_per_second": 1.603
|
| 24 |
+
}
|
| 25 |
+
],
|
| 26 |
+
"max_steps": 63,
|
| 27 |
+
"num_train_epochs": 1,
|
| 28 |
+
"total_flos": 1193890577645568.0,
|
| 29 |
+
"trial_name": null,
|
| 30 |
+
"trial_params": null
|
| 31 |
+
}
|