Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- trainer_state.json +39 -6
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 988097824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1080eca2e2b2303df23691e909bc44bf473c367036322fbcadfdec34865aa63
|
| 3 |
size 988097824
|
trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "check-point-qwen2.5-bags/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 2000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -19,6 +19,39 @@
|
|
| 19 |
"eval_samples_per_second": 86.784,
|
| 20 |
"eval_steps_per_second": 21.696,
|
| 21 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
}
|
| 23 |
],
|
| 24 |
"logging_steps": 8344,
|
|
@@ -38,7 +71,7 @@
|
|
| 38 |
"attributes": {}
|
| 39 |
}
|
| 40 |
},
|
| 41 |
-
"total_flos":
|
| 42 |
"train_batch_size": 4,
|
| 43 |
"trial_name": null,
|
| 44 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 8000,
|
| 3 |
+
"best_metric": 0.13777850568294525,
|
| 4 |
+
"best_model_checkpoint": "check-point-qwen2.5-bags/checkpoint-8000",
|
| 5 |
+
"epoch": 1.9176005273566248,
|
| 6 |
"eval_steps": 2000,
|
| 7 |
+
"global_step": 8000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 19 |
"eval_samples_per_second": 86.784,
|
| 20 |
"eval_steps_per_second": 21.696,
|
| 21 |
"step": 2000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.95883022712291,
|
| 25 |
+
"eval_entropy": 0.1454699612403101,
|
| 26 |
+
"eval_loss": 0.14876286685466766,
|
| 27 |
+
"eval_mean_token_accuracy": 0.954681836819464,
|
| 28 |
+
"eval_num_tokens": 65536000.0,
|
| 29 |
+
"eval_runtime": 11.8969,
|
| 30 |
+
"eval_samples_per_second": 86.745,
|
| 31 |
+
"eval_steps_per_second": 21.686,
|
| 32 |
+
"step": 4000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.43818541379517,
|
| 36 |
+
"eval_entropy": 0.1354526253633721,
|
| 37 |
+
"eval_loss": 0.14411340653896332,
|
| 38 |
+
"eval_mean_token_accuracy": 0.9560297101505043,
|
| 39 |
+
"eval_num_tokens": 98297856.0,
|
| 40 |
+
"eval_runtime": 11.9057,
|
| 41 |
+
"eval_samples_per_second": 86.682,
|
| 42 |
+
"eval_steps_per_second": 21.67,
|
| 43 |
+
"step": 6000
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 1.9176005273566248,
|
| 47 |
+
"eval_entropy": 0.13540720385174418,
|
| 48 |
+
"eval_loss": 0.13777850568294525,
|
| 49 |
+
"eval_mean_token_accuracy": 0.9574325225611989,
|
| 50 |
+
"eval_num_tokens": 131065856.0,
|
| 51 |
+
"eval_runtime": 11.8969,
|
| 52 |
+
"eval_samples_per_second": 86.745,
|
| 53 |
+
"eval_steps_per_second": 21.686,
|
| 54 |
+
"step": 8000
|
| 55 |
}
|
| 56 |
],
|
| 57 |
"logging_steps": 8344,
|
|
|
|
| 71 |
"attributes": {}
|
| 72 |
}
|
| 73 |
},
|
| 74 |
+
"total_flos": 2.8144933446038323e+17,
|
| 75 |
"train_batch_size": 4,
|
| 76 |
"trial_name": null,
|
| 77 |
"trial_params": null
|