End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7679501651406831,
|
| 4 |
+
"eval_loss": 0.7943122386932373,
|
| 5 |
+
"eval_runtime": 7.2439,
|
| 6 |
+
"eval_samples": 469,
|
| 7 |
+
"eval_samples_per_second": 64.744,
|
| 8 |
+
"eval_steps_per_second": 16.29,
|
| 9 |
+
"perplexity": 2.2129185135829017,
|
| 10 |
+
"train_loss": 0.8620750466894024,
|
| 11 |
+
"train_runtime": 287.9872,
|
| 12 |
+
"train_samples": 1794,
|
| 13 |
+
"train_samples_per_second": 18.688,
|
| 14 |
+
"train_steps_per_second": 4.677
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7679501651406831,
|
| 4 |
+
"eval_loss": 0.7943122386932373,
|
| 5 |
+
"eval_runtime": 7.2439,
|
| 6 |
+
"eval_samples": 469,
|
| 7 |
+
"eval_samples_per_second": 64.744,
|
| 8 |
+
"eval_steps_per_second": 16.29,
|
| 9 |
+
"perplexity": 2.2129185135829017
|
| 10 |
+
}
|
runs/Aug13_19-07-26_a8028052eb97/events.out.tfevents.1660418473.a8028052eb97.269.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aaff0d792046b6984e76b243f09db2f01fac20fda394fe38563ad3c4acb1ec2
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.8620750466894024,
|
| 4 |
+
"train_runtime": 287.9872,
|
| 5 |
+
"train_samples": 1794,
|
| 6 |
+
"train_samples_per_second": 18.688,
|
| 7 |
+
"train_steps_per_second": 4.677
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 1347,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.11,
|
| 12 |
+
"learning_rate": 3.144023756495917e-05,
|
| 13 |
+
"loss": 0.988,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.23,
|
| 18 |
+
"learning_rate": 1.2880475129918337e-05,
|
| 19 |
+
"loss": 0.7995,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 3.0,
|
| 24 |
+
"step": 1347,
|
| 25 |
+
"total_flos": 351574777921536.0,
|
| 26 |
+
"train_loss": 0.8620750466894024,
|
| 27 |
+
"train_runtime": 287.9872,
|
| 28 |
+
"train_samples_per_second": 18.688,
|
| 29 |
+
"train_steps_per_second": 4.677
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
+
"max_steps": 1347,
|
| 33 |
+
"num_train_epochs": 3,
|
| 34 |
+
"total_flos": 351574777921536.0,
|
| 35 |
+
"trial_name": null,
|
| 36 |
+
"trial_params": null
|
| 37 |
+
}
|