oldiday commited on
Commit
c61ecec
·
verified ·
1 Parent(s): 2911dc0

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 sha256:02dd83fe678360832db72d49ab942c66ffeba880f16a5eb53422a0e4d8c77c92
3
  size 15156512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ab4979862e36d468938de5fab39e1f7c8a10224f67a6b14007bc668198f96d3
3
  size 15156512
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53e1cfebd8ab909e2e0acaa183b57be6dafcd955f3690daf2028cc710981e39b
3
  size 7825914
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6dd32661eafed5c6fae57863a0695227376d89f96bafae7382689ed60f0aeb4
3
  size 7825914
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60011aba49a65dca3988560527defa4dc19d0ad21df74f6e66309136a9e5bda0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3fe446eed74741e0c70c343c7184f670a6d2092f91a6abc546d3c43eb77925
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": 0.04524886877828054,
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": 151.018,
161
  "eval_steps_per_second": 18.934,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 3857061657968640.0,
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": 0.05429864253393665,
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": 151.018,
161
  "eval_steps_per_second": 18.934,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.048265460030165915,
166
+ "grad_norm": 5.039991855621338,
167
+ "learning_rate": 3.104804738999169e-05,
168
+ "loss": 5.6358,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.05128205128205128,
173
+ "grad_norm": 4.412015438079834,
174
+ "learning_rate": 2.8479327524001636e-05,
175
+ "loss": 5.4325,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.05429864253393665,
180
+ "grad_norm": 4.06430721282959,
181
+ "learning_rate": 2.587248741756253e-05,
182
+ "loss": 5.3275,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.05429864253393665,
187
+ "eval_loss": 5.077151298522949,
188
+ "eval_runtime": 11.262,
189
+ "eval_samples_per_second": 148.731,
190
+ "eval_steps_per_second": 18.647,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 4628473989562368.0,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null