Upload folder using huggingface_hub
Browse files- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +6 -21
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 369133600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c5c16321fdb944c424aeed516f3a25c13b04d9de6a0e3444e26d465861f1a45
|
| 3 |
size 369133600
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 738413771
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5e668e079d9eb649e14cf1543fc2441115c7db52d4156b32cb23477cde111c2
|
| 3 |
size 738413771
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c09a2378c9b2760c4be147a5b754dcc709d51c34ad1657c58d394fdb1e62c9cd
|
| 3 |
size 14645
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:835ce587198e9409b36bcc44e52e098d4c0cea09e497c9b3cf477e54d1ab5d09
|
| 3 |
size 1465
|
trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "/content/drive/MyDrive/lora_model/outputs/task15_microsoft/Phi-4-mini-instruct/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 10,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -83,21 +83,6 @@
|
|
| 83 |
"eval_samples_per_second": 9.025,
|
| 84 |
"eval_steps_per_second": 1.203,
|
| 85 |
"step": 50
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"epoch": 4.0,
|
| 89 |
-
"grad_norm": 0.7584931254386902,
|
| 90 |
-
"learning_rate": 0.00023614713127100752,
|
| 91 |
-
"loss": 0.6581,
|
| 92 |
-
"step": 60
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 4.0,
|
| 96 |
-
"eval_loss": 0.5533124208450317,
|
| 97 |
-
"eval_runtime": 3.3307,
|
| 98 |
-
"eval_samples_per_second": 9.007,
|
| 99 |
-
"eval_steps_per_second": 1.201,
|
| 100 |
-
"step": 60
|
| 101 |
}
|
| 102 |
],
|
| 103 |
"logging_steps": 10,
|
|
@@ -117,7 +102,7 @@
|
|
| 117 |
"attributes": {}
|
| 118 |
}
|
| 119 |
},
|
| 120 |
-
"total_flos":
|
| 121 |
"train_batch_size": 1,
|
| 122 |
"trial_name": null,
|
| 123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 50,
|
| 3 |
+
"best_metric": 0.6476100087165833,
|
| 4 |
+
"best_model_checkpoint": "/content/drive/MyDrive/lora_model/outputs/task15_microsoft/Phi-4-mini-instruct/checkpoint-50",
|
| 5 |
+
"epoch": 3.3333333333333335,
|
| 6 |
"eval_steps": 10,
|
| 7 |
+
"global_step": 50,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 83 |
"eval_samples_per_second": 9.025,
|
| 84 |
"eval_steps_per_second": 1.203,
|
| 85 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
}
|
| 87 |
],
|
| 88 |
"logging_steps": 10,
|
|
|
|
| 102 |
"attributes": {}
|
| 103 |
}
|
| 104 |
},
|
| 105 |
+
"total_flos": 2058463713208320.0,
|
| 106 |
"train_batch_size": 1,
|
| 107 |
"trial_name": null,
|
| 108 |
"trial_params": null
|