Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +66 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 345,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.43,
|
| 13 |
+
"learning_rate": 1.710144927536232e-05,
|
| 14 |
+
"loss": 0.615,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.87,
|
| 19 |
+
"learning_rate": 1.420289855072464e-05,
|
| 20 |
+
"loss": 0.5381,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.3,
|
| 25 |
+
"learning_rate": 1.1304347826086957e-05,
|
| 26 |
+
"loss": 0.4313,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.74,
|
| 31 |
+
"learning_rate": 8.405797101449275e-06,
|
| 32 |
+
"loss": 0.4235,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.17,
|
| 37 |
+
"learning_rate": 5.507246376811595e-06,
|
| 38 |
+
"loss": 0.3594,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.61,
|
| 43 |
+
"learning_rate": 2.6086956521739132e-06,
|
| 44 |
+
"loss": 0.293,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.0,
|
| 49 |
+
"step": 345,
|
| 50 |
+
"total_flos": 611246037148560.0,
|
| 51 |
+
"train_loss": 0.42235686260720956,
|
| 52 |
+
"train_runtime": 52.7528,
|
| 53 |
+
"train_samples_per_second": 208.596,
|
| 54 |
+
"train_steps_per_second": 6.54
|
| 55 |
+
}
|
| 56 |
+
],
|
| 57 |
+
"logging_steps": 50,
|
| 58 |
+
"max_steps": 345,
|
| 59 |
+
"num_input_tokens_seen": 0,
|
| 60 |
+
"num_train_epochs": 3,
|
| 61 |
+
"save_steps": 500,
|
| 62 |
+
"total_flos": 611246037148560.0,
|
| 63 |
+
"train_batch_size": 32,
|
| 64 |
+
"trial_name": null,
|
| 65 |
+
"trial_params": null
|
| 66 |
+
}
|