Hugging Face's logo

cimol
/
e1cbbf9a-6ef4-4a89-8a71-d668dd19bc4f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
cimol commited on
Commit
66b3968
·
verified ·
1 Parent(s): de3fe1c

Training in progress, step 179, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +18 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:094fb811e1832432588e86348f3c555f60640cdf5ace236c71be3078339393a6
3
  size 69527352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc16c7c8736b6d6e1b66ace9bc87052a2e3c5b0375821913874cbd6f7b817b00
3
  size 69527352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6243f98f895e9a29af384b931ed7fa847c410b4851b891ed1c60334de7e8a26
3
  size 35778452
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e6c6d2c5b4cab5d2bfffb7b621c16d8c981821da7119a6a4a70f6b98840078a
3
  size 35778452
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87d9646918f4715734abcd2ba5e4223d3297698b0c91b7f1accbd3219cd06926
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a97165809320ae978d84aa4c51ad3ab619a25bb1aef0bf0694fa1f6d4e4bc929
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a006e6604711be41b0befe4ed017f7c2e1ee81935482ccd9e69573b7eb8f236
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0be4b23f1148022e22093640bf3d516e08bb9dd07f0614ecbb16cab8ef0c97
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.6525987386703491,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 2.510460251046025,
5
  "eval_steps": 50,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -144,6 +144,20 @@
144
  "eval_samples_per_second": 42.132,
145
  "eval_steps_per_second": 10.846,
146
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  ],
149
  "logging_steps": 10,
@@ -167,12 +181,12 @@
167
  "should_evaluate": false,
168
  "should_log": false,
169
  "should_save": true,
170
- "should_training_stop": false
171
  },
172
  "attributes": {}
173
  }
174
  },
175
- "total_flos": 1.471527419510784e+16,
176
  "train_batch_size": 8,
177
  "trial_name": null,
178
  "trial_params": null
 
1
  {
2
  "best_metric": 0.6525987386703491,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 2.99581589958159,
5
  "eval_steps": 50,
6
+ "global_step": 179,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
144
  "eval_samples_per_second": 42.132,
145
  "eval_steps_per_second": 10.846,
146
  "step": 150
147
+ },
148
+ {
149
+ "epoch": 2.6778242677824267,
150
+ "grad_norm": 0.1975071132183075,
151
+ "learning_rate": 6.1728263459614796e-06,
152
+ "loss": 0.6025,
153
+ "step": 160
154
+ },
155
+ {
156
+ "epoch": 2.8451882845188283,
157
+ "grad_norm": 0.15535539388656616,
158
+ "learning_rate": 1.396265834701982e-06,
159
+ "loss": 0.6434,
160
+ "step": 170
161
  }
162
  ],
163
  "logging_steps": 10,
 
181
  "should_evaluate": false,
182
  "should_log": false,
183
  "should_save": true,
184
+ "should_training_stop": true
185
  },
186
  "attributes": {}
187
  }
188
  },
189
+ "total_flos": 1.745679464398848e+16,
190
  "train_batch_size": 8,
191
  "trial_name": null,
192
  "trial_params": null