mamung commited on
Commit
2ed5f9a
·
verified ·
1 Parent(s): 4b870e9

Training in progress, step 54, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fe65eb23721f7220a89c33aa8147d2305f1f2c11469d788b4ee14d373df4d3b
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe6d4f42001a866807fabf39f7009f5ed64636eca8752ecce8831a62c918e49d
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1468f00d1b00dedafbb3a3f0d6aa7b53ec1c5f4cf90c80df61d973d4dfe2b89
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03669da72977c22ca754bf8ea8c9fbd85fd8b749e54c7aded5c5fa7231419406
3
  size 671466706
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0498481dc13586eb056bf15062506f1ff8e314200eb2c09558f026d1062ec3a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c9b98a522023efb72d5ea76453db813b341022ab0b021338e401600719c6645
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.8602150537634409,
5
  "eval_steps": 9,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -160,6 +160,35 @@
160
  "eval_samples_per_second": 8.963,
161
  "eval_steps_per_second": 4.507,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 2.6856376277925888e+17,
183
  "train_batch_size": 2,
184
  "trial_name": null,
185
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.032258064516129,
5
  "eval_steps": 9,
6
+ "global_step": 54,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
160
  "eval_samples_per_second": 8.963,
161
  "eval_steps_per_second": 4.507,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.9175627240143369,
166
+ "grad_norm": 1.2157355546951294,
167
+ "learning_rate": 0.00014539904997395468,
168
+ "loss": 1.7012,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.974910394265233,
173
+ "grad_norm": 1.4276927709579468,
174
+ "learning_rate": 0.0001346117057077493,
175
+ "loss": 1.8858,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 1.032258064516129,
180
+ "grad_norm": 1.1759012937545776,
181
+ "learning_rate": 0.00012334453638559057,
182
+ "loss": 2.0545,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 1.032258064516129,
187
+ "eval_loss": 1.7873010635375977,
188
+ "eval_runtime": 19.7531,
189
+ "eval_samples_per_second": 8.961,
190
+ "eval_steps_per_second": 4.506,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 3.2227651533511066e+17,
212
  "train_batch_size": 2,
213
  "trial_name": null,
214
  "trial_params": null