leixa commited on
Commit
ffca8b3
·
verified ·
1 Parent(s): 97d2f2c

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 sha256:575b73dab3eea82abe0d44eb0a886c772679eec9de8c955800f65f27b5f43086
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d7f90fe48923e9cbbf3cacfc483fb356692ecece4c03ddb69dc1cc7bbe321a
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d803d5b32045bc570550fa75819369589f89e6c0e278290c839f351837dd2614
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed93197da31bf52785071cebc30aa19deab7b442f5a873f2f68a8b176eff3ddb
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae23c720e43827fac7ec9738d78285292b2b49a0ea5579feabe2dcfc07f544e5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4e8be85bff89c7cc936ed5348f3f2f54c4d981583d63142a6ffcbd0200af65f
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": 0.007034822370735139,
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": 6.544,
134
  "eval_steps_per_second": 0.818,
135
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  }
137
  ],
138
  "logging_steps": 3,
@@ -152,7 +167,7 @@
152
  "attributes": {}
153
  }
154
  },
155
- "total_flos": 7.72814168653824e+16,
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": 0.008207292765857662,
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": 6.544,
134
  "eval_steps_per_second": 0.818,
135
  "step": 30
136
+ },
137
+ {
138
+ "epoch": 0.007738304607808653,
139
+ "grad_norm": 1.3703689575195312,
140
+ "learning_rate": 3.832773180720475e-05,
141
+ "loss": 1.875,
142
+ "step": 33
143
+ },
144
+ {
145
+ "epoch": 0.008207292765857662,
146
+ "eval_loss": 0.49850761890411377,
147
+ "eval_runtime": 1097.4891,
148
+ "eval_samples_per_second": 6.544,
149
+ "eval_steps_per_second": 0.818,
150
+ "step": 35
151
  }
152
  ],
153
  "logging_steps": 3,
 
167
  "attributes": {}
168
  }
169
  },
170
+ "total_flos": 9.01616530096128e+16,
171
  "train_batch_size": 8,
172
  "trial_name": null,
173
  "trial_params": null