Hugging Face's logo

kooff11
/
65d9c680-cee4-4aed-81f6-b3492563fd49

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
kooff11 commited on
Commit
fcf5a96
•
1 Parent(s): 9107f98

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:f1a0640a688e8ecad6a1dc0f7dac5e04369e5866f8019d013056c2b49a1d92da
3
  size 78480072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa975466de44d48c2a4a3478f6a6f8d1c5aeb0a6daaed55a50c2fb74712588f
3
  size 78480072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a052c1554594789f6a27283a03b1edfc293303e67af51aa759549db71ec295b
3
  size 40131268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd787c6f805662bc481c8ddb8fa0560f2c402a6f3b59953aa7f44c1aec9af456
3
  size 40131268
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f5e5695fa7542edff8994f19e9aaae56bcda8213c0fe73a8aefebd39c185b1e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2dd46a4e54194d1ad37bd00a09e499856c7b341b087d0fab94647a2c927b5c2
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 sha256:6834c48e54755b6053cf2981d162510749689fe7667c5ba1b206bfb8c1e53278
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98fdc462c279888de818eb50aa126a537ac209141a25eed889c3c64604f6d1e0
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 sha256:4e79d34310f72a541db31128103499d25f09b09edbc24630786fd81613b4f18b
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8590dda5298fb4da8f7e4620457e014c2de7047b586fe98e97990180ac3f4fae
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:eb38218cb3dca9ff5224fe64700d834a6e097149d7060b864d3addda702df953
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41deacf26e0511f7846b10fc2d8251d62ba82fac0ce707ffc774c6f699da636c
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": 0.08294930875576037,
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": 38.098,
103
  "eval_steps_per_second": 4.788,
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": 1.4166364973432832e+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": 0.09216589861751152,
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": 38.098,
103
  "eval_steps_per_second": 4.788,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.09216589861751152,
108
+ "grad_norm": 7.361027717590332,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.2716,
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": 1.574040552603648e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null