trenden commited on
Commit
10f9dc9
·
verified ·
1 Parent(s): 40d073b

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:de3f58613850e396c5bc4a23efd35dd500e3d5776a021d53e48d6693315d4375
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8dbb0fee4f3ca16b4df63234c2f69f5a87e83febf613dfdab7f97f07c78f467
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f595aa1ea4b69ce7d43aea697cbdb42c1367324112c31e637eb8b5660365dda
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b8988d3f0bb014415608adba8dcd6d3a8301ff03f319a2881a256d302a6f359
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe213872b5386d78d524fc96c00179d5ecbf1809134c6bcd38d68d75f189b8db
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d9508d4c56a4e802598d2cc23494b85de097ae6233975dde5d44259b24162ec
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": 0.00015867488837662365,
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": 11.409,
103
  "eval_steps_per_second": 5.704,
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": 3642998670753792.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00017630543152958184,
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": 11.409,
103
  "eval_steps_per_second": 5.704,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.00017630543152958184,
108
+ "grad_norm": 4.7204108238220215,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.0242,
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": 4053477394219008.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null