Hugging Face's logo

Paladiso
/
56e46106-55ee-42fc-b514-64b2448c7b69

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
1
Paladiso commited on
Commit
43e68a6
·
verified ·
1 Parent(s): f095402

Training in progress, step 9, 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 +32 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fa0ac5421769d5719178d5a3107fde5b044b10fb6c80c58eec6a9c6decd05f1
3
  size 59933632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:390a101b182cb73ae204abe265d9806d02b9d0906f549f8c86968eb3855f701b
3
  size 59933632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b645069f9a659914796b2d7b0efd0b6a4ddca4744902a0add688904ed228e27
3
  size 31822948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0a83f8b8eb6cee4dc763f570d495f60ec5f6e39a1b669870b84f047bc72b5cc
3
  size 31822948
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6872307f4470a047155c6b916b2c9040d688e2f96562192a9d5c5fb6108984b7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439abbe02fcba947df87386a52c344ddf41c37c93f11c43daac794f1cc139033
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.00018801999279256695,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 14.608,
66
  "eval_steps_per_second": 7.304,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 411363981656064.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0002820299891888504,
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,
 
65
  "eval_samples_per_second": 14.608,
66
  "eval_steps_per_second": 7.304,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00021935665825799478,
71
+ "grad_norm": 2.1884148120880127,
72
+ "learning_rate": 0.00014,
73
+ "loss": 1.9445,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.0002506933237234226,
78
+ "grad_norm": 1.762728214263916,
79
+ "learning_rate": 0.00016,
80
+ "loss": 1.6886,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.0002820299891888504,
85
+ "grad_norm": 2.1065804958343506,
86
+ "learning_rate": 0.00018,
87
+ "loss": 1.6875,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.0002820299891888504,
92
+ "eval_loss": 1.4193613529205322,
93
+ "eval_runtime": 920.8157,
94
+ "eval_samples_per_second": 14.592,
95
+ "eval_steps_per_second": 7.297,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 617045972484096.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null