Hugging Face's logo

tuanna08go
/
ff34825d-d226-4b29-80c4-e1fcab3fbe85

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
648abd7
·
verified ·
1 Parent(s): 6ec1001

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 sha256:06761bbefb9f722891eb71ee043f0127912f560554df5cd54fe9e1cbf007b870
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6052779b8880078b3c0fe7f616db9a15470c97272812210054c2a08fb42520fd
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b19556bd4ef72fabc73ef957396445cf4ee5bc09140c40207582dabecbf04d77
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9962544e2f207f444311eefd19a9a12d164ae9081f38b607255f02f2fd42d88a
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a6a0228e814f2ad5602f36a82ff891570a453da848b5ee571fc96543423ea4a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d44b3710080201a8770f78e80e52b1b298528f8ceebd24f76f2ea4d4cbf2a67
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": 0.28480146052031036,
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": 18.355,
61
  "eval_steps_per_second": 2.307,
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": 1.154128090843054e+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": 0.3651300775901415,
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": 18.355,
61
  "eval_steps_per_second": 2.307,
62
  "step": 30
63
+ },
64
+ {
65
+ "epoch": 0.2921040620721132,
66
+ "grad_norm": 0.124696284532547,
67
+ "learning_rate": 1.0332332985438248e-05,
68
+ "loss": 0.0014,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.2921040620721132,
73
+ "eval_loss": 0.0018709078431129456,
74
+ "eval_runtime": 50.3851,
75
+ "eval_samples_per_second": 18.319,
76
+ "eval_steps_per_second": 2.302,
77
+ "step": 40
78
+ },
79
+ {
80
+ "epoch": 0.3651300775901415,
81
+ "grad_norm": 0.03910544514656067,
82
+ "learning_rate": 0.0,
83
+ "loss": 0.0008,
84
+ "step": 50
85
+ },
86
+ {
87
+ "epoch": 0.3651300775901415,
88
+ "eval_loss": 0.0018442599102854729,
89
+ "eval_runtime": 50.1412,
90
+ "eval_samples_per_second": 18.408,
91
+ "eval_steps_per_second": 2.313,
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": 1.479651398516736e+17,
113
  "train_batch_size": 8,
114
  "trial_name": null,
115
  "trial_params": null