nat-hunt commited on
Commit
2fa474b
·
verified ·
1 Parent(s): 2edb528

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:e056f7dd2c77c0151716a31e53acd300bee4e94886f70dd9208fb031749cd6f6
3
  size 5327744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee98deb96cddbb6bc298fed73a28a9e09e0b520096febeb745d1d169fe004599
3
  size 5327744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac0d1a2e96cc70f48ed65f89dfa42246a1311e146f5e84bdfcce7af295ab06d7
3
  size 2857722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbac8ea9de0b2fed306c75555b0ad35e1e343a8aa2c5b82266897864bbc56247
3
  size 2857722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85501daaab0c301949fa550583a1d6090576f079356806ca962c6e2db60935a0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4ea053e40e8daa5b30103f6f78239080e54d2c90cfefc2f0c019e098b03eca
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": 0.015894039735099338,
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": 153.992,
103
  "eval_steps_per_second": 77.318,
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": 22821725011968.0,
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": 0.017660044150110375,
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": 153.992,
103
  "eval_steps_per_second": 77.318,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.017660044150110375,
108
+ "grad_norm": 17.794754028320312,
109
+ "learning_rate": 0.0002,
110
+ "loss": 12.369,
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": 25475413966848.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null