Hugging Face's logo

tuanna08go
/
e4b5996d-8b76-4d1d-beb8-ec81c40b9c44

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
98f4689
·
verified ·
1 Parent(s): c3adeef

Training in progress, step 39, 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 +25 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fb7d133465d83cddb4437c0ffcaa34bf1b6da182a8c0f8ef6dae45d7eae3c35
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:893ad4770f054a6527d693030631471ffabd03d205709be954f0bda34d15a798
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15a01693ae126effe02f939fae57900a802c3eebc5b7d49042dcfc7d660de768
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47494d1e4c59796b3455264b6a607a7d8191f94340298c2eea292c48c2ee5189
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:ed859eec0110661414346c20c7d973eb69b9f1a013e73669f8b55b9a902526cc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e587385a9b9f5d9fffdaa85e9d406e140d0cfe9a1c1f1dba8e30f1a4236e94a7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.2659846547314578,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 7.8041,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 7229895742586880.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3989769820971867,
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,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 7.8041,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.3069053708439898,
72
+ "grad_norm": 6.498897075653076,
73
+ "learning_rate": 5e-05,
74
+ "loss": 7.2391,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.3069053708439898,
79
+ "eval_loss": 1.9637117385864258,
80
+ "eval_runtime": 5.8807,
81
+ "eval_samples_per_second": 7.142,
82
+ "eval_steps_per_second": 3.571,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.35805626598465473,
87
+ "grad_norm": 16.6773681640625,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 8.4421,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.1042022588678144e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null