Superrrdamn commited on
Commit
904a1d7
·
verified ·
1 Parent(s): 3e9b755

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:b03e32b29f18f4aafe840e9e6ea064100f79519509ef7904a1bb6e9666cd1b71
3
  size 184584072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbe9be840c3e73d01b1f9b9d8bad30388f39399877a1a0baefcf3626870ef85
3
  size 184584072
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24d15a784e1cf2aa4f9eaff54f013792ce8d3b46a1a9a72d8b73e80a3d72effb
3
  size 94020308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f848ac8e584150ab43b1268aa56968de3223fa82881374212e2e73eeebbe84fb
3
  size 94020308
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e546f3d0cc030407310ddc97c51a1d129835cae0b7adbe07f853c4482364c3f8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f9c8466246784adca37141843ae311a771e871cf72714bcbcade1fbddb7478
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2bca8ddf05f322679d243aa2f45369d00c9c0525952759cece0ad0b30fcabbe
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d7c5182b2f032288a44ca4175101f97fe1e7458f1f586d7bf701dac390454d
3
  size 1064
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.6406570841889117,
5
  "eval_steps": 500,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -147,6 +147,20 @@
147
  "learning_rate": 8.225609429353187e-06,
148
  "loss": 2.026,
149
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
150
  }
151
  ],
152
  "logging_steps": 5,
@@ -166,7 +180,7 @@
166
  "attributes": {}
167
  }
168
  },
169
- "total_flos": 2.528754198916915e+16,
170
  "train_batch_size": 1,
171
  "trial_name": null,
172
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.8049281314168377,
5
  "eval_steps": 500,
6
+ "global_step": 110,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
147
  "learning_rate": 8.225609429353187e-06,
148
  "loss": 2.026,
149
  "step": 100
150
+ },
151
+ {
152
+ "epoch": 1.7227926078028748,
153
+ "grad_norm": 1.6016583442687988,
154
+ "learning_rate": 4.684610648167503e-06,
155
+ "loss": 2.0659,
156
+ "step": 105
157
+ },
158
+ {
159
+ "epoch": 1.8049281314168377,
160
+ "grad_norm": 1.5633082389831543,
161
+ "learning_rate": 2.100524384225555e-06,
162
+ "loss": 1.9925,
163
+ "step": 110
164
  }
165
  ],
166
  "logging_steps": 5,
 
180
  "attributes": {}
181
  }
182
  },
183
+ "total_flos": 2.785615979702477e+16,
184
  "train_batch_size": 1,
185
  "trial_name": null,
186
  "trial_params": null