Nexspear commited on
Commit
63904c6
·
verified ·
1 Parent(s): 236c900

Training in progress, step 35, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94cb0414b1c9b2a60887b5b43f58e8185969e299164c315cac6220389eb98e7f
3
  size 191968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:473cc1b7c18be2967d46f87ef1c27dd2455038c0dbbd14e00e3ea51f96a5b490
3
  size 191968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c535d24c8f78df51f3b609038c504bd274057ac2942269306dbf56fbad98dac9
3
  size 253144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd220ddd424e463fcdc9d22a69889fc47893f491dcec5f0285a4e718ba580980
3
  size 253144
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6f8d91445b23c7a2b71c10f72fc68a8d50c4ad52ee6befbb53c1732cd7664d4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1483fe5ee1de3351fec80a493a35970862157e2df5a1f01c39c538d167a91ab7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
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": 0.02105632567117038,
5
  "eval_steps": 5,
6
- "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -133,6 +133,21 @@
133
  "eval_samples_per_second": 452.766,
134
  "eval_steps_per_second": 56.596,
135
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  }
137
  ],
138
  "logging_steps": 3,
@@ -152,7 +167,7 @@
152
  "attributes": {}
153
  }
154
  },
155
- "total_flos": 3430182813696.0,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02456571328303211,
5
  "eval_steps": 5,
6
+ "global_step": 35,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
133
  "eval_samples_per_second": 452.766,
134
  "eval_steps_per_second": 56.596,
135
  "step": 30
136
+ },
137
+ {
138
+ "epoch": 0.023161958238287417,
139
+ "grad_norm": 0.12643229961395264,
140
+ "learning_rate": 3.832773180720475e-05,
141
+ "loss": 10.3652,
142
+ "step": 33
143
+ },
144
+ {
145
+ "epoch": 0.02456571328303211,
146
+ "eval_loss": 10.363306999206543,
147
+ "eval_runtime": 5.2135,
148
+ "eval_samples_per_second": 460.341,
149
+ "eval_steps_per_second": 57.543,
150
+ "step": 35
151
  }
152
  ],
153
  "logging_steps": 3,
 
167
  "attributes": {}
168
  }
169
  },
170
+ "total_flos": 3987936116736.0,
171
  "train_batch_size": 8,
172
  "trial_name": null,
173
  "trial_params": null