oldiday commited on
Commit
3db48bc
·
verified ·
1 Parent(s): a0947a7

Training in progress, step 45, 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:c75a508a773a1d4e86d334f4e03b288a4f6651605d1de4301bf836cad01f699e
3
  size 228140600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad3f77c98714886c69253fe2209d0f49f76345b5aef67c428f6020120a97a56
3
  size 228140600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:412ef6561036d292aab1862fa3c68de8e6f1a521760db12f3098fea917f4d8e7
3
  size 116472340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7acfdc5af309f984f2d268620053f389b403a9d7e75fea9f769d8643369183db
3
  size 116472340
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28aa984a8995e23145e5379ede84981a1e489c4cf41652e1960df7f446e10019
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eabfcd1b25a9d15bb11d9c2889384891cc1a9db7b0c9fa8eb6b8ffe55907bbf9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
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": 0.12371134020618557,
5
  "eval_steps": 9,
6
- "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -131,6 +131,35 @@
131
  "eval_samples_per_second": 6.829,
132
  "eval_steps_per_second": 0.864,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 1.2808770639888384e+17,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.15463917525773196,
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,
 
131
  "eval_samples_per_second": 6.829,
132
  "eval_steps_per_second": 0.864,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.13402061855670103,
137
+ "grad_norm": 1.8717230558395386,
138
+ "learning_rate": 7.649596321166024e-05,
139
+ "loss": 2.7933,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.14432989690721648,
144
+ "grad_norm": 1.8673449754714966,
145
+ "learning_rate": 7.191855733945387e-05,
146
+ "loss": 2.7106,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.15463917525773196,
151
+ "grad_norm": 1.9052813053131104,
152
+ "learning_rate": 6.710100716628344e-05,
153
+ "loss": 2.8453,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.15463917525773196,
158
+ "eval_loss": 0.7204706072807312,
159
+ "eval_runtime": 71.6809,
160
+ "eval_samples_per_second": 6.836,
161
+ "eval_steps_per_second": 0.865,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 1.5782235252719616e+17,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null