Commit
•
2f01377
1
Parent(s):
d4db72e
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +58 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.95,
|
| 3 |
+
"train_loss": 0.9649612274169922,
|
| 4 |
+
"train_runtime": 2280.9027,
|
| 5 |
+
"train_samples": 4213,
|
| 6 |
+
"train_samples_per_second": 1.754,
|
| 7 |
+
"train_steps_per_second": 0.877
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.95,
|
| 3 |
+
"train_loss": 0.9649612274169922,
|
| 4 |
+
"train_runtime": 2280.9027,
|
| 5 |
+
"train_samples": 4213,
|
| 6 |
+
"train_samples_per_second": 1.754,
|
| 7 |
+
"train_steps_per_second": 0.877
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9492168960607499,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.24,
|
| 13 |
+
"grad_norm": 2.33807110786438,
|
| 14 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 15 |
+
"loss": 1.1754,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.47,
|
| 20 |
+
"grad_norm": 1.748302698135376,
|
| 21 |
+
"learning_rate": 2.5e-05,
|
| 22 |
+
"loss": 0.9536,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.71,
|
| 27 |
+
"grad_norm": 1.8499162197113037,
|
| 28 |
+
"learning_rate": 1.25e-05,
|
| 29 |
+
"loss": 0.877,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.95,
|
| 34 |
+
"grad_norm": 1.7708240747451782,
|
| 35 |
+
"learning_rate": 0.0,
|
| 36 |
+
"loss": 0.8539,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.95,
|
| 41 |
+
"step": 2000,
|
| 42 |
+
"total_flos": 7429605690441728.0,
|
| 43 |
+
"train_loss": 0.9649612274169922,
|
| 44 |
+
"train_runtime": 2280.9027,
|
| 45 |
+
"train_samples_per_second": 1.754,
|
| 46 |
+
"train_steps_per_second": 0.877
|
| 47 |
+
}
|
| 48 |
+
],
|
| 49 |
+
"logging_steps": 500,
|
| 50 |
+
"max_steps": 2000,
|
| 51 |
+
"num_input_tokens_seen": 0,
|
| 52 |
+
"num_train_epochs": 1,
|
| 53 |
+
"save_steps": 1000,
|
| 54 |
+
"total_flos": 7429605690441728.0,
|
| 55 |
+
"train_batch_size": 1,
|
| 56 |
+
"trial_name": null,
|
| 57 |
+
"trial_params": null
|
| 58 |
+
}
|