dzanbek commited on
Commit
176fb08
·
verified ·
1 Parent(s): 8aa41f6

Training in progress, step 14, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01e2a98a8d0525983a11a0bcd675ddad5c73b092fbf60cc830ef478860793844
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66fa69c55f4cc539bfd7eeff21e2a8835faab284683500af2e49c58a7febcefc
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0f0b965c78fa719579b13f4a4df36b2ea0bc83dc71d5ea5be28ef1ab9b3c4fa
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc5474a7eb1ef6bcd05c2e54d7fb2b90bb75ef2c3ee218f2708da7c7a1b1a73
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89fec60704330078998cfd1b822f9cbac786033cfd4bb864071196460694e736
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b57ff65dae4d93bc6f3ce28e1c0ebd64b3f07e2650a62a688a062d79b9112b67
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e4cb1249623f16a121f1f7528c255e6aea1cd633fd38f639775465d7feebdcd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380805505206fcae9055c4a9e78aed7a5dda390c746cad96ecf2259c970f0ba0
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": 0.0017335403951027485,
5
  "eval_steps": 2,
6
- "global_step": 12,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -147,6 +147,28 @@
147
  "eval_samples_per_second": 7.067,
148
  "eval_steps_per_second": 3.535,
149
  "step": 12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
150
  }
151
  ],
152
  "logging_steps": 1,
@@ -166,7 +188,7 @@
166
  "attributes": {}
167
  }
168
  },
169
- "total_flos": 3920787866124288.0,
170
  "train_batch_size": 2,
171
  "trial_name": null,
172
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0020224637942865397,
5
  "eval_steps": 2,
6
+ "global_step": 14,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
147
  "eval_samples_per_second": 7.067,
148
  "eval_steps_per_second": 3.535,
149
  "step": 12
150
+ },
151
+ {
152
+ "epoch": 0.001878002094694644,
153
+ "grad_norm": 24.574901580810547,
154
+ "learning_rate": 7.938926261462366e-05,
155
+ "loss": 13.8176,
156
+ "step": 13
157
+ },
158
+ {
159
+ "epoch": 0.0020224637942865397,
160
+ "grad_norm": 49.8048210144043,
161
+ "learning_rate": 6.545084971874738e-05,
162
+ "loss": 16.2677,
163
+ "step": 14
164
+ },
165
+ {
166
+ "epoch": 0.0020224637942865397,
167
+ "eval_loss": 2.5962870121002197,
168
+ "eval_runtime": 412.0906,
169
+ "eval_samples_per_second": 7.074,
170
+ "eval_steps_per_second": 3.538,
171
+ "step": 14
172
  }
173
  ],
174
  "logging_steps": 1,
 
188
  "attributes": {}
189
  }
190
  },
191
+ "total_flos": 4574252510478336.0,
192
  "train_batch_size": 2,
193
  "trial_name": null,
194
  "trial_params": null