Hugging Face's logo

sn56m2
/
5d913ce8-d270-4ad6-8874-38456a847626

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
farmery commited on
Commit
dde04b9
•
1 Parent(s): bfd4770

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 sha256:5ea91f9e78f24095c3c255e8e13f2805cf5abd59fb8cd161123bd09b3a4c6a56
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93d5c1d6c1e0e553f40b6f4be09bf3db6bbc2490ec00759e4695fd4c24cbe050
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76d049c2a39c272f949f88dc498495bf0d305ee122db1a83b6febc86dbf1580c
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee60f9110557664eb652000c9f41db3076b9bcf175aacca0058c91cd55d8630
3
  size 81730196
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23b1cdc93839cf3d1839ae8fbc0a092fe54b0e38a1fa2ef42fb2cb7ea1f38aa8
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9cc97840e396f9967fd8f9e4ef92a2ce3e8dfe687ad4f22259913bb1a1605d5
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 sha256:1f9c8d472a9fcb528aad7900cb24b90313f284110ca432406a71ead59cbde1f3
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f74435840181ef5be67cebc46f6421ff7fb7533a96f7855fe36586ff3b95c263
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 sha256:8245d8d3d3816dd284f4381705afc1ac7d7e6002a14fe01153bec7adf5280188
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edfcdc8ec38ecceb363a6724b6b40828a842365deb928ebadcb5c58b2d9fa751
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:e01e0573ae2aa58b2e2ae712e76a15ee28e34fab0d7c2da6f89be4395d3de6b5
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62f93d329bdcf7d3756dec05f7e91ade831fa62b19bfbd47c2dc342f6c816929
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": 0.07758620689655173,
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": 20.426,
103
  "eval_steps_per_second": 2.619,
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": 4.704899053702349e+16,
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": 0.08620689655172414,
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": 20.426,
103
  "eval_steps_per_second": 2.619,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.08620689655172414,
108
+ "grad_norm": 0.9381762742996216,
109
+ "learning_rate": 0.0002,
110
+ "loss": 3.5532,
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": 5.227665615224832e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null