OscarXZQ/bbh-lora-tracking_shuffled_objects_five_objects
Browse files- all_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +13 -13
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 230340912537600.0,
|
| 4 |
+
"train_loss": 0.4312268676757812,
|
| 5 |
+
"train_runtime": 80.3257,
|
| 6 |
+
"train_samples_per_second": 3.112,
|
| 7 |
+
"train_steps_per_second": 3.112
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 230340912537600.0,
|
| 4 |
+
"train_loss": 0.4312268676757812,
|
| 5 |
+
"train_runtime": 80.3257,
|
| 6 |
+
"train_samples_per_second": 3.112,
|
| 7 |
+
"train_steps_per_second": 3.112
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,27 +1,27 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch":
|
| 13 |
-
"step":
|
| 14 |
-
"total_flos":
|
| 15 |
-
"train_loss": 0.
|
| 16 |
-
"train_runtime":
|
| 17 |
-
"train_samples_per_second":
|
| 18 |
-
"train_steps_per_second":
|
| 19 |
}
|
| 20 |
],
|
| 21 |
"logging_steps": 500,
|
| 22 |
-
"max_steps":
|
| 23 |
"num_input_tokens_seen": 0,
|
| 24 |
-
"num_train_epochs":
|
| 25 |
"save_steps": 500,
|
| 26 |
"stateful_callbacks": {
|
| 27 |
"TrainerControl": {
|
|
@@ -35,8 +35,8 @@
|
|
| 35 |
"attributes": {}
|
| 36 |
}
|
| 37 |
},
|
| 38 |
-
"total_flos":
|
| 39 |
-
"train_batch_size":
|
| 40 |
"trial_name": null,
|
| 41 |
"trial_params": null
|
| 42 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 250,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 10.0,
|
| 13 |
+
"step": 250,
|
| 14 |
+
"total_flos": 230340912537600.0,
|
| 15 |
+
"train_loss": 0.4312268676757812,
|
| 16 |
+
"train_runtime": 80.3257,
|
| 17 |
+
"train_samples_per_second": 3.112,
|
| 18 |
+
"train_steps_per_second": 3.112
|
| 19 |
}
|
| 20 |
],
|
| 21 |
"logging_steps": 500,
|
| 22 |
+
"max_steps": 250,
|
| 23 |
"num_input_tokens_seen": 0,
|
| 24 |
+
"num_train_epochs": 10,
|
| 25 |
"save_steps": 500,
|
| 26 |
"stateful_callbacks": {
|
| 27 |
"TrainerControl": {
|
|
|
|
| 35 |
"attributes": {}
|
| 36 |
}
|
| 37 |
},
|
| 38 |
+
"total_flos": 230340912537600.0,
|
| 39 |
+
"train_batch_size": 1,
|
| 40 |
"trial_name": null,
|
| 41 |
"trial_params": null
|
| 42 |
}
|