flytech commited on
Commit
56df1f4
·
1 Parent(s): 94974d5

Training in progress, step 900, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:402576c87180344206acae5fcf619df208f359329377bdd0107171982e317c56
3
  size 67143296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:625c24ad2702a76c58af2535cf9c27d049e84fb7e01989449430541b3b0fbfce
3
  size 67143296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:026521f3d6159fef03020641ca43a68180d979cb9fa205e50135e79bf63e71d5
3
  size 33920095
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9478eb7b3f3027bb4070c6389e3eba25e44251abcc324317c1e9a1079f1fc04b
3
  size 33920095
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11e8faac1b72cc7bf9f026c349ca080abc19142b09be6f278cd43911aa1397ba
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518e379eb95b8761d691fa2f3663a7e6b2114c816fd3f33c63e566311da0ce7c
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68f97bf5fc062ac3e4a876a0097c0718f2e93d4749d37498e737b83f15731a48
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1c649bd14a49756b729525a4732fa77be1d6c78a716ad6162c210414e48318
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": 4.878048780487805,
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,
@@ -111,13 +111,26 @@
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
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 5.487804878048781,
5
  "eval_steps": 100,
6
+ "global_step": 900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
111
  "eval_samples_per_second": 2.038,
112
  "eval_steps_per_second": 0.266,
113
  "step": 800
114
+ },
115
+ {
116
+ "epoch": 5.49,
117
+ "learning_rate": 0.0002,
118
+ "loss": 0.0356,
119
+ "step": 900
120
+ },
121
+ {
122
+ "epoch": 5.49,
123
+ "eval_runtime": 33.8728,
124
+ "eval_samples_per_second": 2.037,
125
+ "eval_steps_per_second": 0.266,
126
+ "step": 900
127
  }
128
  ],
129
  "logging_steps": 100,
130
  "max_steps": 1312,
131
  "num_train_epochs": 8,
132
  "save_steps": 100,
133
+ "total_flos": 7.473948323217408e+16,
134
  "trial_name": null,
135
  "trial_params": null
136
  }