Hugging Face's logo

kooff11
/
04cd9d58-77d2-4065-abb8-8b161a76432d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
kooff11 commited on
Commit
ca4ffaa
•
1 Parent(s): 09c651d

Training in progress, step 10, checkpoint

Browse files
Files changed (8) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/scheduler.pt +1 -1
  8. last-checkpoint/trainer_state.json +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1faaaa163fd01d299452bd2a2fe7ce21bb10d0bac6a32edcfb730ae8f86f7c1a
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c688ae931b8cfced17fa5da88d35d60f9799d14dbf47948d32bfbbb1516c3d0a
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b10409e71e0c227efda781123e7664614b0a9bc17582c0c5baffdff6f7bc0f7e
3
  size 23159290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0726ebb7be1516a0d1b45dfb22ddaf39652f696dfdb1f88e56fb0bf08be2950
3
  size 23159290
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83755f92e0b31961d67d2da9e18664e012b9b3ac7214356235e7fb3f84d0056d
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9280de9461ecbf5174279ef363549529fd2c955e7822a9980dc1a4c75503e43b
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:967e9b98be3239b99d6529b39bee941ba668efc3fb745b113e6c7389b99b9e54
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9dbcaf8429e1882dffb20194ee9d723d569fb7b2c5b34dcc9e4dd7a80fe232f
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e55e3563b24e28435bf8bb5f384f100304d3875e2008ea67ac69f04eac510a1b
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb8b38f95667cbdce03e37031c372e0ae6f9049b540b5e30945430cdac6e89b
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:840ee3db5c8d91c883c04ec102f79f49dc3b48318a72c57161fc550c33698a64
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f28a01de8d8d6dbdc1b822c70ce4a573e43c23fc5eb4750f5d3a6fe57b47330
3
  size 15024
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": 0.002352479905900804,
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": 63.826,
103
  "eval_steps_per_second": 7.984,
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": 7015988662894592.0,
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": 0.0026138665621120044,
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": 63.826,
103
  "eval_steps_per_second": 7.984,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0026138665621120044,
108
+ "grad_norm": 0.6194673776626587,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.0491,
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": 7790166718545920.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null