Paladiso commited on
Commit
21b2323
·
verified ·
1 Parent(s): 7c8a62d

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 sha256:3f1631967cb5fa724f809b213543871ffe6ef4240672a7e676f588677d53fbe0
3
  size 5327744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21516e85c787017964efa507150d36fffd6fbc3d1fa7092ffcce4c8f9fcdd60
3
  size 5327744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed1ae7941fc673b7ed5a7e6dd64366ee6913025c7a2054694a7ddd318d4a5380
3
  size 2857722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c6c931d744a37b9f1e205d12ec6dfc21532de6f7332192000ccb7f4518e41c6
3
  size 2857722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25323c61945258af26c4033ffa71ceceef1dba3efe40cb601f25c40a71d7fe52
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ac03ad177e9fb3a1f2746d63cacc7184139e141215c83c6db94bf6c42e2bbc
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": 0.0013231888852133643,
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,
@@ -94,6 +94,13 @@
94
  "eval_samples_per_second": 40.01,
95
  "eval_steps_per_second": 20.005,
96
  "step": 9
 
 
 
 
 
 
 
97
  }
98
  ],
99
  "logging_steps": 1,
@@ -108,12 +115,12 @@
108
  "should_evaluate": false,
109
  "should_log": false,
110
  "should_save": true,
111
- "should_training_stop": false
112
  },
113
  "attributes": {}
114
  }
115
  },
116
- "total_flos": 27598365130752.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0014702098724592935,
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,
 
94
  "eval_samples_per_second": 40.01,
95
  "eval_steps_per_second": 20.005,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0014702098724592935,
100
+ "grad_norm": 2.882256269454956,
101
+ "learning_rate": 0.0002,
102
+ "loss": 9.326,
103
+ "step": 10
104
  }
105
  ],
106
  "logging_steps": 1,
 
115
  "should_evaluate": false,
116
  "should_log": false,
117
  "should_save": true,
118
+ "should_training_stop": true
119
  },
120
  "attributes": {}
121
  }
122
  },
123
+ "total_flos": 31844267458560.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null