Hugging Face's logo

tuanna08go
/
16c5210f-4d0c-41b2-ac55-4e66607816eb

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
721be7b
·
verified ·
1 Parent(s): f21edd5

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 +34 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5b8f89925836d46192ff7267aab72d42a1e27443eaf2d3d7a63a6e2ca40c9f9
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:140ad575cb118b491f8706fbd258f238940bd6d1a153dd6f11f6299f72e8e4d4
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cc447ac2eaae739c1a618f000b967e0de06f8a2b28cdd5f8112cb2b7497b104
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5111833aa3a52e3c6e681407ac34263841bb96cc3983f2e8f7c5ff3377b4a5c1
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:a7b2d8fb6a6bd6620c662b499e75e2ca739075a3c24768431fdce3d1c7733c66
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc4f9f2e7d478b8afe53bc762d2235f30ebd0e274425a6b48feec6fae1b619f7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
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": 0.6172106824925816,
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,
@@ -60,6 +60,36 @@
60
  "eval_samples_per_second": 19.146,
61
  "eval_steps_per_second": 2.427,
62
  "step": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +104,12 @@
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": 1.093667202709586e+17,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.7912957467853611,
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,
 
60
  "eval_samples_per_second": 19.146,
61
  "eval_steps_per_second": 2.427,
62
  "step": 30
63
+ },
64
+ {
65
+ "epoch": 0.6330365974282888,
66
+ "grad_norm": 5.748447418212891,
67
+ "learning_rate": 1.0332332985438248e-05,
68
+ "loss": 8.4035,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.6330365974282888,
73
+ "eval_loss": 0.5215941071510315,
74
+ "eval_runtime": 22.3805,
75
+ "eval_samples_per_second": 19.034,
76
+ "eval_steps_per_second": 2.413,
77
+ "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.7912957467853611,
81
+ "grad_norm": 6.016201972961426,
82
+ "learning_rate": 0.0,
83
+ "loss": 8.3438,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.7912957467853611,
88
+ "eval_loss": 0.5206525325775146,
89
+ "eval_runtime": 22.3482,
90
+ "eval_samples_per_second": 19.062,
91
+ "eval_steps_per_second": 2.416,
92
+ "step": 50
93
  }
94
  ],
95
  "logging_steps": 10,
 
104
  "should_evaluate": false,
105
  "should_log": false,
106
  "should_save": true,
107
+ "should_training_stop": true
108
  },
109
  "attributes": {}
110
  }
111
  },
112
+ "total_flos": 1.402137439371264e+17,
113
  "train_batch_size": 8,
114
  "trial_name": null,
115
  "trial_params": null