Hugging Face's logo

tuanna08go
/
a45bc180-e906-4fa6-b3ca-f6bb98da93fb

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
e06b310
·
verified ·
1 Parent(s): e1ee5e8

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 sha256:19283cf2f5f8b60a4c09f96d8975b3ad32892d54420ed89028ee06da9debe909
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9029e48bf78ff152d1593eebe8d8f94eb5a7bbde967b71b0b8eb41b412c413d4
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07d81e57f8498eddd6e252b5780aa49c5d49057ea1fe6dd11ef55468c8a00dd8
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab67818960316cec17bf1bd117d3fbd82b06d169cb1a9f3e6deaa6cdc6bb1fc
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89be65360c462d9c4812bfee4e603b36894408ac274af51796d35fb242819f3e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21815cb6a56d83fd842ccbd218103284132df6f808c6bf2845a32a401544075d
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": 0.0018502265341461678,
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": 5.3622,
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": 7580436142227456.0,
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": 0.002372085300187395,
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": 5.3622,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.0018976682401499157,
94
+ "grad_norm": 7.63873815536499,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 5.4219,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.0018976682401499157,
101
+ "eval_loss": 1.3230457305908203,
102
+ "eval_runtime": 617.3808,
103
+ "eval_samples_per_second": 14.377,
104
+ "eval_steps_per_second": 7.188,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.0021348767701686554,
109
+ "grad_norm": 6.972021102905273,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 4.7516,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.002372085300187395,
116
+ "grad_norm": 8.430161476135254,
117
+ "learning_rate": 0.0,
118
+ "loss": 4.741,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.002372085300187395,
123
+ "eval_loss": 1.3194341659545898,
124
+ "eval_runtime": 616.3452,
125
+ "eval_samples_per_second": 14.401,
126
+ "eval_steps_per_second": 7.201,
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": 9771313639981056.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null