Hugging Face's logo

shibajustfor
/
a690348b-9d15-46c5-92f0-37a6633c8cd5

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
custom_code
Model card Files
xet
 Community
shibajustfor commited on
Commit
61fe217
·
verified ·
1 Parent(s): 70e0bda

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 +18 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:599058326d1f80982a0cf2e8d7449b6bf4874b43030faee5b70e77fe63629f71
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1727f853b9e8ba255d5ea9317762f4e1793033bcde59d2bb760e22ffdc7f57
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:993291be78324bbb38f7e73972c07b4f08ca634d335c400183e16a261d014bd5
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:658e2d96e9fecced259e32c1033db384057a326dd60b7ccc12f0c34b9eddffef
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aa10da0a18ea67917350fb6e6f8db87ade3225f86b79930eb7ac553eb290db0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278d4a00e1718b7c6f8c526b67f8fe3ce060285ec159b66817ed10e7568e0f9f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
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": 0.005357142857142857,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 30.106,
61
  "eval_steps_per_second": 15.053,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 6835412165197824.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006868131868131868,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 30.106,
61
  "eval_steps_per_second": 15.053,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.005494505494505495,
66
+ "grad_norm": 18.163021087646484,
67
+ "learning_rate": 0.0002,
68
+ "loss": 2.1522,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.006868131868131868,
73
+ "grad_norm": 14.604914665222168,
74
+ "learning_rate": 0.0002,
75
+ "loss": 1.9446,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 8763348929740800.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null