flytech commited on
Commit
6c407c8
·
1 Parent(s): dd6570a

Training in progress, step 800, 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:ff81bbdd5c04bd94b58979397ab8c51aad516e5145a8104ef0d6244d99f990d7
3
  size 67143296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:402576c87180344206acae5fcf619df208f359329377bdd0107171982e317c56
3
  size 67143296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59b57097aa711d4ecbd9e9e8a01e7eaeb6ca4e89b20154e9e6bdf9c501bdccf6
3
  size 33920095
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:026521f3d6159fef03020641ca43a68180d979cb9fa205e50135e79bf63e71d5
3
  size 33920095
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac6fcf6463e02f91a5308adfb13d94ab6f604b4647e4d2d65c653eae03b50e8b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e8faac1b72cc7bf9f026c349ca080abc19142b09be6f278cd43911aa1397ba
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2af986f5eea6511a2b711af95bc2ef2f105e2e10532eaa71f6daf1c546e03be
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f97bf5fc062ac3e4a876a0097c0718f2e93d4749d37498e737b83f15731a48
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": 4.2682926829268295,
5
  "eval_steps": 100,
6
- "global_step": 700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -98,13 +98,26 @@
98
  "eval_samples_per_second": 2.034,
99
  "eval_steps_per_second": 0.265,
100
  "step": 700
 
 
 
 
 
 
 
 
 
 
 
 
 
101
  }
102
  ],
103
  "logging_steps": 100,
104
  "max_steps": 1312,
105
  "num_train_epochs": 8,
106
  "save_steps": 100,
107
- "total_flos": 5.812724179560038e+16,
108
  "trial_name": null,
109
  "trial_params": null
110
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 4.878048780487805,
5
  "eval_steps": 100,
6
+ "global_step": 800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
98
  "eval_samples_per_second": 2.034,
99
  "eval_steps_per_second": 0.265,
100
  "step": 700
101
+ },
102
+ {
103
+ "epoch": 4.88,
104
+ "learning_rate": 0.0002,
105
+ "loss": 0.0431,
106
+ "step": 800
107
+ },
108
+ {
109
+ "epoch": 4.88,
110
+ "eval_runtime": 33.8539,
111
+ "eval_samples_per_second": 2.038,
112
+ "eval_steps_per_second": 0.266,
113
+ "step": 800
114
  }
115
  ],
116
  "logging_steps": 100,
117
  "max_steps": 1312,
118
  "num_train_epochs": 8,
119
  "save_steps": 100,
120
+ "total_flos": 6.644896574629478e+16,
121
  "trial_name": null,
122
  "trial_params": null
123
  }