DesDea1 commited on
Commit
9218822
·
verified ·
1 Parent(s): 57a7ede

Training in progress, step 10, 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:a9caa8aad73a9fab00ceef17acba24aad73730ff8f050123448b4176c1829802
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d43640e8ec74faa570a1cc2b38e3ad963075b9591215d29a8dbdbdb48ece327
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc6c833d7c4fbccce451889d5c92a79582558810d40aad84c8eeb0d0ca7681ba
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e7c63209a7aaab325efcd7ec3d35989c8664ca427bb2fa7d7ac78293be3301
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d43ab25a0e82acb814d1ea8e6e3081e15589e0ffbcf9e9292c2a91fda2e5dfa4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:515434d98fe67129d3ffce3593c3a9bf82763540181ebe61a9db9cd9167023b3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.011128284389489953,
5
  "eval_steps": 3,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 2.32,
103
  "eval_steps_per_second": 2.32,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 6676985552044032.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.012364760432766615,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 2.32,
103
  "eval_steps_per_second": 2.32,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.012364760432766615,
108
+ "grad_norm": 15.392157554626465,
109
+ "learning_rate": 0.0002,
110
+ "loss": 3.2731,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 7418872835604480.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null