flytech commited on
Commit
3591e98
1 Parent(s): da0d1a0

Training in progress, step 2200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8459b9f832ef25a417640bf0233bf837cd58164df9c457efc3e290ab0e68c964
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3879db05063c5090ff0412004f6af70c6c85cc0ca75b514895ac158cf7402f3
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fb024f66bab43727577e41564d8e9829a6ce8f78c8ff35fab9e27a566b312a2
3
  size 126034975
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67271ad9d0d1fc2156dc075da167c0ed7deeda4c41573a8d093b70c4bb883372
3
  size 126034975
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b0a527772fa484fe0f5b977a5f9514063f30bbaa2addc71ee53b83bf0f23343
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17d896dbcbd4ca31eb08b7a70f5410cdc580dd613e857d91f68a6a2645d0af9f
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
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": 9.70873786407767,
5
  "eval_steps": 200,
6
- "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -137,13 +137,26 @@
137
  "eval_samples_per_second": 7.932,
138
  "eval_steps_per_second": 0.504,
139
  "step": 2000
 
 
 
 
 
 
 
 
 
 
 
 
 
140
  }
141
  ],
142
  "logging_steps": 200,
143
  "max_steps": 2472,
144
  "num_train_epochs": 12,
145
  "save_steps": 200,
146
- "total_flos": 6.439303461470208e+17,
147
  "trial_name": null,
148
  "trial_params": null
149
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 10.679611650485437,
5
  "eval_steps": 200,
6
+ "global_step": 2200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
137
  "eval_samples_per_second": 7.932,
138
  "eval_steps_per_second": 0.504,
139
  "step": 2000
140
+ },
141
+ {
142
+ "epoch": 10.68,
143
+ "learning_rate": 0.0002,
144
+ "loss": 0.0258,
145
+ "step": 2200
146
+ },
147
+ {
148
+ "epoch": 10.68,
149
+ "eval_runtime": 21.7533,
150
+ "eval_samples_per_second": 7.953,
151
+ "eval_steps_per_second": 0.506,
152
+ "step": 2200
153
  }
154
  ],
155
  "logging_steps": 200,
156
  "max_steps": 2472,
157
  "num_train_epochs": 12,
158
  "save_steps": 200,
159
+ "total_flos": 7.08301176963072e+17,
160
  "trial_name": null,
161
  "trial_params": null
162
  }