Upload 2 files
Browse files- train_results.json +8 -0
- trainer_state.json +65 -0
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.5972473204135895,
|
| 4 |
+
"train_runtime": 921.494,
|
| 5 |
+
"train_samples": 140,
|
| 6 |
+
"train_samples_per_second": 0.152,
|
| 7 |
+
"train_steps_per_second": 0.022
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 20,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.25,
|
| 13 |
+
"grad_norm": 26.25555680814376,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 1.483,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.25,
|
| 20 |
+
"grad_norm": 17.39430141746882,
|
| 21 |
+
"learning_rate": 9.330127018922195e-06,
|
| 22 |
+
"loss": 1.1048,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.5,
|
| 27 |
+
"grad_norm": 6.586149562982836,
|
| 28 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 29 |
+
"loss": 0.5822,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 3.75,
|
| 34 |
+
"grad_norm": 4.531727627541418,
|
| 35 |
+
"learning_rate": 1.7860619515673034e-06,
|
| 36 |
+
"loss": 0.3652,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 5.0,
|
| 41 |
+
"grad_norm": 3.7810551616818753,
|
| 42 |
+
"learning_rate": 0.0,
|
| 43 |
+
"loss": 0.2611,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.0,
|
| 48 |
+
"step": 20,
|
| 49 |
+
"total_flos": 523449139200.0,
|
| 50 |
+
"train_loss": 0.5972473204135895,
|
| 51 |
+
"train_runtime": 921.494,
|
| 52 |
+
"train_samples_per_second": 0.152,
|
| 53 |
+
"train_steps_per_second": 0.022
|
| 54 |
+
}
|
| 55 |
+
],
|
| 56 |
+
"logging_steps": 5,
|
| 57 |
+
"max_steps": 20,
|
| 58 |
+
"num_input_tokens_seen": 0,
|
| 59 |
+
"num_train_epochs": 5,
|
| 60 |
+
"save_steps": 500,
|
| 61 |
+
"total_flos": 523449139200.0,
|
| 62 |
+
"train_batch_size": 2,
|
| 63 |
+
"trial_name": null,
|
| 64 |
+
"trial_params": null
|
| 65 |
+
}
|