willtensora commited on
Commit
4a350d8
·
verified ·
1 Parent(s): 6c537ae

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 sha256:02e249ebbe91bd59a6f77b9bbaa151b92e8ad5496ddb65ebacfde5acd51abf1b
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e6fad84c3fde16ca164f1fea552cfe5cea32c310350bc6bbf6ebf2e4c4d3d65
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e21f5f0b913222d8595b40e04f94461abf5386506b5b3e8f5ebe92315ea5319
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde0052ec52aab79b03456867ae0cdb164a073e242a121e575ba8f9cfb5fd12f
3
  size 64219860
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5aaf83edafe3f0458acd0973d335c9b1ecd6f6be907432ff7a65f6a14de7b43c
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e318cbc915779aee4828ee1c8268023da721e9e15d45f3436786ef9984fec05
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2df423cf962a73ab18fe19e5e03773d88340393d7f5d6aa4acae670cc123b2b9
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb573e2a2379f038e31f7d0bbf6296f5b7e673dfe76f867ec3febc397374e944
3
  size 14512
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": 0.030328559393428812,
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": 36.683,
103
  "eval_steps_per_second": 9.244,
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": 5699203900637184.0,
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": 0.03369839932603201,
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": 36.683,
103
  "eval_steps_per_second": 9.244,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.03369839932603201,
108
+ "grad_norm": 20.928890228271484,
109
+ "learning_rate": 0.0002,
110
+ "loss": 6.8495,
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": 6332448778485760.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null