flytech commited on
Commit
4b1ae24
·
1 Parent(s): fec110c

Training in progress, step 1300, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41e44952fa1919bf97a546037011d88a01d4db9388c112f61e1cd2689bc67595
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53f4e472717da4cdcf12a2ce8b49aa25c416dc25186edacecbb543248642e07
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63497a648756d7ab8a007508b863d76c3ac8a71298b6b376198065403c52e6f3
3
  size 21689885
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36635a03c7da8c54a2d0a120b3f63bc6d68a40b56629bd15c929a510e42c864e
3
  size 21689885
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9eb395c53bc041eaa259bf1c70c07323ce9889492dd835455fff10243844c307
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc0133e70d610441e11bd205ddd072b548b4b3d57109a84bf771a0813f7ffaf
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:702bc2d32e44f82c118dea391eda1a1d9359f9a308190a0831931e01d2c2951f
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2870155ed085482229e6c054bc455ba54c71983ee464acfe9fca2a17664f6d3a
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.1342222222222222,
5
  "eval_steps": 100,
6
- "global_step": 1200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -163,13 +163,26 @@
163
  "eval_samples_per_second": 1.787,
164
  "eval_steps_per_second": 0.224,
165
  "step": 1200
 
 
 
 
 
 
 
 
 
 
 
 
 
166
  }
167
  ],
168
  "logging_steps": 100,
169
  "max_steps": 1686,
170
  "num_train_epochs": 3,
171
  "save_steps": 100,
172
- "total_flos": 4.505491854065664e+17,
173
  "trial_name": null,
174
  "trial_params": null
175
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.312,
5
  "eval_steps": 100,
6
+ "global_step": 1300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
163
  "eval_samples_per_second": 1.787,
164
  "eval_steps_per_second": 0.224,
165
  "step": 1200
166
+ },
167
+ {
168
+ "epoch": 2.31,
169
+ "learning_rate": 2.5576796308503624e-05,
170
+ "loss": 0.5479,
171
+ "step": 1300
172
+ },
173
+ {
174
+ "epoch": 2.31,
175
+ "eval_runtime": 1405.5826,
176
+ "eval_samples_per_second": 1.779,
177
+ "eval_steps_per_second": 0.223,
178
+ "step": 1300
179
  }
180
  ],
181
  "logging_steps": 100,
182
  "max_steps": 1686,
183
  "num_train_epochs": 3,
184
  "save_steps": 100,
185
+ "total_flos": 4.920744559509504e+17,
186
  "trial_name": null,
187
  "trial_params": null
188
  }