dimasik2987 commited on
Commit
dd03192
·
verified ·
1 Parent(s): 369274d

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16b040c725068a69b0f89a6c0b6ee52b632d2b88bf7b1871f9fe4e6231c9460e
3
  size 684272496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3fa576ebbac5fc3b324cc9cbf99e0215c9ef9d32897a7e26935ce4bd1ebf3fd
3
  size 684272496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cee20f300468d8dcff07bb22344d5a3e1400c3527649bd3c7966ff68b438a19
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147adc4caac65cc9aa85f3e11bd9475eb6f9fac89d62bcdb54d162ce7a0acd09
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a040b3377ea29e2e573174f608927490657c8c978fdb95169126a63ddf2673b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81d341293548ca00e0e58d5d96dd5b9a987f30f65d8d779264a3bcee6bef50b4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bb840dbc65c27ef8840855786e35bfea033749e5d7571cf601f6645aa29cc1e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
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": 0.05917159763313609,
5
  "eval_steps": 3,
6
- "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -160,6 +160,49 @@
160
  "eval_samples_per_second": 9.621,
161
  "eval_steps_per_second": 4.81,
162
  "step": 15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 1,
@@ -179,7 +222,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 1.960375813668864e+16,
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": 0.07889546351084813,
5
  "eval_steps": 3,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
160
  "eval_samples_per_second": 9.621,
161
  "eval_steps_per_second": 4.81,
162
  "step": 15
163
+ },
164
+ {
165
+ "epoch": 0.0631163708086785,
166
+ "grad_norm": 1.6371982097625732,
167
+ "learning_rate": 0.00013090169943749476,
168
+ "loss": 0.336,
169
+ "step": 16
170
+ },
171
+ {
172
+ "epoch": 0.0670611439842209,
173
+ "grad_norm": 1.4365739822387695,
174
+ "learning_rate": 0.00011045284632676536,
175
+ "loss": 0.2788,
176
+ "step": 17
177
+ },
178
+ {
179
+ "epoch": 0.07100591715976332,
180
+ "grad_norm": 0.5848339796066284,
181
+ "learning_rate": 8.954715367323468e-05,
182
+ "loss": 0.0984,
183
+ "step": 18
184
+ },
185
+ {
186
+ "epoch": 0.07100591715976332,
187
+ "eval_loss": 0.21445059776306152,
188
+ "eval_runtime": 22.3011,
189
+ "eval_samples_per_second": 9.596,
190
+ "eval_steps_per_second": 4.798,
191
+ "step": 18
192
+ },
193
+ {
194
+ "epoch": 0.07495069033530571,
195
+ "grad_norm": 2.026401996612549,
196
+ "learning_rate": 6.909830056250527e-05,
197
+ "loss": 0.2734,
198
+ "step": 19
199
+ },
200
+ {
201
+ "epoch": 0.07889546351084813,
202
+ "grad_norm": 1.0910876989364624,
203
+ "learning_rate": 5.000000000000002e-05,
204
+ "loss": 0.215,
205
+ "step": 20
206
  }
207
  ],
208
  "logging_steps": 1,
 
222
  "attributes": {}
223
  }
224
  },
225
+ "total_flos": 2.613834418225152e+16,
226
  "train_batch_size": 2,
227
  "trial_name": null,
228
  "trial_params": null