Hugging Face's logo

chauhoang
/
78162bad-ca18-b072-91a2-c6a11d0c1bf1

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
e837ccf
·
verified ·
1 Parent(s): 9df26e4

Training in progress, step 50, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +41 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8db441a0c0d21810ce6d0706918c9201f1982719953abef7eab948e367d5ed6
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11194d2411eb48b87832e79d8772a562981af13fb6bfd3313290c99c096109d7
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff0f28a80d5b1b8e808bdcbd449cf3cd4ae69d71afbfcebc141ae310dca05284
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb1711b4c5aeb1873af780db8e4f0f8b4ccb605b7ccba2589d5fd303c3c26d66
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0473a82658c627429c106558fb3bb262aa9211c031722dafa14ae2d5bab0f9e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc8b30dc45df2e7849e049e2f88f3af04b8eb2fec3f79a4131192a96147a0392
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.01295788686768004,
5
  "eval_steps": 10,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -88,6 +88,43 @@
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 0.7966,
90
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +139,12 @@
102
  "should_evaluate": false,
103
  "should_log": false,
104
  "should_save": true,
105
- "should_training_stop": false
106
  },
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 1950379589763072.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.016612675471384668,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 0.7966,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.013290140377107733,
94
+ "grad_norm": 0.9960245490074158,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.755,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.013290140377107733,
101
+ "eval_loss": 0.7165237665176392,
102
+ "eval_runtime": 70.0285,
103
+ "eval_samples_per_second": 18.107,
104
+ "eval_steps_per_second": 9.053,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.0149514079242462,
109
+ "grad_norm": 0.8190529942512512,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 0.7666,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.016612675471384668,
116
+ "grad_norm": 0.927686870098114,
117
+ "learning_rate": 0.0,
118
+ "loss": 0.7215,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.016612675471384668,
123
+ "eval_loss": 0.7126367688179016,
124
+ "eval_runtime": 69.167,
125
+ "eval_samples_per_second": 18.332,
126
+ "eval_steps_per_second": 9.166,
127
+ "step": 50
128
  }
129
  ],
130
  "logging_steps": 5,
 
139
  "should_evaluate": false,
140
  "should_log": false,
141
  "should_save": true,
142
+ "should_training_stop": true
143
  },
144
  "attributes": {}
145
  }
146
  },
147
+ "total_flos": 2500486653542400.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null