Hugging Face's logo

ivangrapher
/
f067d804-cf60-45c6-8409-593a1c2e69c0

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
ivangrapher commited on
Commit
33fc104
·
verified ·
1 Parent(s): 9aeceef

Training in progress, step 30, checkpoint

Browse files
Files changed (4) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/rng_state.pth +1 -1
  3. last-checkpoint/scheduler.pt +1 -1
  4. last-checkpoint/trainer_state.json +40 -4
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f765b9632202c0efb7a5d3cedf9a340b9d6f815a1474dfc1563bea017423a632
3
  size 70667778
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81bed8336bc20b533adb47e471d0f5fd076f3d16bcc7557120e9fb5c886b2755
3
  size 70667778
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13b3b2d51edb91b19514e00464be84376ddc6cde97f307e24325d1f9c173ff54
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b3f133924a5a7000ba418177e484222c050fae9c6f8411732bb5412e99cbb96
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
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": 0.015088645794039984,
5
  "eval_steps": 8,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,42 @@
73
  "learning_rate": 0.00013090169943749476,
74
  "loss": 0.0,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -87,12 +123,12 @@
87
  "should_evaluate": false,
88
  "should_log": false,
89
  "should_save": true,
90
- "should_training_stop": false
91
  },
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1459932459171840.0,
96
  "train_batch_size": 4,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.022632968691059976,
5
  "eval_steps": 8,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "learning_rate": 0.00013090169943749476,
74
  "loss": 0.0,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.015843078083741986,
79
+ "grad_norm": NaN,
80
+ "learning_rate": 8.435655349597689e-05,
81
+ "loss": 0.0,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.018106374952847983,
86
+ "grad_norm": NaN,
87
+ "learning_rate": 4.12214747707527e-05,
88
+ "loss": 0.0,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.018106374952847983,
93
+ "eval_loss": NaN,
94
+ "eval_runtime": 36.7863,
95
+ "eval_samples_per_second": 60.702,
96
+ "eval_steps_per_second": 15.196,
97
+ "step": 24
98
+ },
99
+ {
100
+ "epoch": 0.02036967182195398,
101
+ "grad_norm": NaN,
102
+ "learning_rate": 1.0899347581163221e-05,
103
+ "loss": 0.0,
104
+ "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.022632968691059976,
108
+ "grad_norm": NaN,
109
+ "learning_rate": 0.0,
110
+ "loss": 0.0,
111
+ "step": 30
112
  }
113
  ],
114
  "logging_steps": 3,
 
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": 2189898688757760.0,
132
  "train_batch_size": 4,
133
  "trial_name": null,
134
  "trial_params": null