robertou2 commited on
Commit
a30c56f
·
verified ·
1 Parent(s): 9bccea2

Upload folder using huggingface_hub

Browse files
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4946127c9ef33fa8d1125f526fdd59066a4f0293be2ca321fff32b96e09f8cef
3
  size 632310976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06178b4401a026439007a37b305968baee62638cdd18cb014be501210ee2b7b4
3
  size 632310976
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:569c2d3526a8235bd638f7c39ea16306a28df2e6f2d5987e7cbd867c1df94722
3
  size 1264705163
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92115fa809f108574abf448a27866635d655f739e69aaf516ba549a5103cff5f
3
  size 1264705163
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:058db63148938dc5b8c14c050cfaafd3086e7d4bea156dc87c1a43b243b11df5
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8babedf40b9818db1d0e81e6ddf417455ce430cdb0d6b088d1b595b6fc2334
3
  size 14645
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf3e8864cf11c1e3212d4cb52536b4687c3caab65537f7014a32855cae5a3940
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c82be639ae806e65fe9f1f8dfaed7299a582bcae358d3b62377cec3c5160c12
3
  size 1465
trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 130,
3
- "best_metric": 0.5668935179710388,
4
- "best_model_checkpoint": "/content/drive/MyDrive/lora_model/outputs/task15_Qwen/Qwen2.5-3B-Instruct/checkpoint-130",
5
- "epoch": 6.842105263157895,
6
  "eval_steps": 10,
7
- "global_step": 130,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -173,36 +173,6 @@
173
  "eval_samples_per_second": 10.154,
174
  "eval_steps_per_second": 1.354,
175
  "step": 110
176
- },
177
- {
178
- "epoch": 6.315789473684211,
179
- "grad_norm": 1.649305820465088,
180
- "learning_rate": 0.0002948740897842223,
181
- "loss": 0.6742,
182
- "step": 120
183
- },
184
- {
185
- "epoch": 6.315789473684211,
186
- "eval_loss": 0.6724004149436951,
187
- "eval_runtime": 2.9459,
188
- "eval_samples_per_second": 10.184,
189
- "eval_steps_per_second": 1.358,
190
- "step": 120
191
- },
192
- {
193
- "epoch": 6.842105263157895,
194
- "grad_norm": 1.2425477504730225,
195
- "learning_rate": 0.00026169315177942135,
196
- "loss": 0.6651,
197
- "step": 130
198
- },
199
- {
200
- "epoch": 6.842105263157895,
201
- "eval_loss": 0.5668935179710388,
202
- "eval_runtime": 2.944,
203
- "eval_samples_per_second": 10.19,
204
- "eval_steps_per_second": 1.359,
205
- "step": 130
206
  }
207
  ],
208
  "logging_steps": 10,
@@ -222,7 +192,7 @@
222
  "attributes": {}
223
  }
224
  },
225
- "total_flos": 5647641905577984.0,
226
  "train_batch_size": 1,
227
  "trial_name": null,
228
  "trial_params": null
 
1
  {
2
+ "best_global_step": 110,
3
+ "best_metric": 0.7011998891830444,
4
+ "best_model_checkpoint": "/content/drive/MyDrive/lora_model/outputs/task15_Qwen/Qwen2.5-3B-Instruct/checkpoint-110",
5
+ "epoch": 5.7894736842105265,
6
  "eval_steps": 10,
7
+ "global_step": 110,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
173
  "eval_samples_per_second": 10.154,
174
  "eval_steps_per_second": 1.354,
175
  "step": 110
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
176
  }
177
  ],
178
  "logging_steps": 10,
 
192
  "attributes": {}
193
  }
194
  },
195
+ "total_flos": 4771148970172416.0,
196
  "train_batch_size": 1,
197
  "trial_name": null,
198
  "trial_params": null