adammandic87 commited on
Commit
1c1f96e
·
verified ·
1 Parent(s): 60cebd0

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 sha256:4569e3cac81108943796d359ff444e0b23a6a8f13623fe90cfffa02c6c7f9733
3
  size 81576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c45f71bec516b1f22964eb5db5a702c6ef1e194e7a597aad496df4b8c3c41e9
3
  size 81576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf5c86d0ce7df8ef22f5077c968adf202ead315512db43a8e6dca9cff7734af7
3
  size 173094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d86b06dd3e82d6aa960f65e0ff1739c61eaec469bcb35df9c3ec92347af1b41
3
  size 173094
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b6a6a011f28f85007de1213aaf2d9d99df9d84c0278f3612751bd8de1562285
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ece6b3cf12ab3425c1775b1dafa9dd975d0c94122e55acd5be3596d4a99c259
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": 0.023809523809523808,
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": 328.439,
103
  "eval_steps_per_second": 164.219,
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": 1168921460736.0,
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": 0.026455026455026454,
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": 328.439,
103
  "eval_steps_per_second": 164.219,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.026455026455026454,
108
+ "grad_norm": 0.27570220828056335,
109
+ "learning_rate": 0.0002,
110
+ "loss": 10.8264,
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": 1291965825024.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null