dixedus commited on
Commit
6b64b0d
·
verified ·
1 Parent(s): 807d6da

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 sha256:6db8dfabb41c6405940ccf6091fffc4349210783cfed0a6174e8c5d090b1e710
3
  size 692169624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1cef6a4469ab592303d3c5c94f8232948353946144a97be83c4278929a205e
3
  size 692169624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d581fec9637df16c26b6222a6cd1f19a468ce8a17858917dca2b63a2fe9e52e
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66724b2400235f8266143204a53eb0237fa7145d1b7a818ea11a628eb5ddde8f
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:300e898fa5a1070babf54be755e6755373a5c60ddc254902e3f1ebacda147586
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60379b7ec7fc50400ed25c0728f72548d8aacb996c92794cc4fa8f2026f83ce9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
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": 0.055248618784530384,
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": 6.692,
161
  "eval_steps_per_second": 0.839,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 1.2656352719536128e+17,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.06629834254143646,
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": 6.692,
161
  "eval_steps_per_second": 0.839,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.058931860036832415,
166
+ "grad_norm": 1.9434477090835571,
167
+ "learning_rate": 3.104804738999169e-05,
168
+ "loss": 2.4655,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.06261510128913444,
173
+ "grad_norm": 2.0563454627990723,
174
+ "learning_rate": 2.8479327524001636e-05,
175
+ "loss": 2.3624,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.06629834254143646,
180
+ "grad_norm": 2.1307311058044434,
181
+ "learning_rate": 2.587248741756253e-05,
182
+ "loss": 2.4587,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.06629834254143646,
187
+ "eval_loss": 0.5953105092048645,
188
+ "eval_runtime": 205.3342,
189
+ "eval_samples_per_second": 6.682,
190
+ "eval_steps_per_second": 0.838,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 1.5187623263443354e+17,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null