Hugging Face's logo

shibajustfor
/
712e19a3-bcea-41ce-b45a-f4ec75414de3

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
shibajustfor commited on
Commit
b78dac6
·
verified ·
1 Parent(s): 46a2430

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:d569eba82aad7ab394ea604b5166e6f3983f358f80a2b02058260372946ac756
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:869975cfa850246234f13319108be7a819dd23d30615f3648e216d38f405328c
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9664a5bfbf85baf03b08ba92ad6d7dc3f6f56770d92c6ec201abf7476b11ea5
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65be91c8e2e79b9cbe24ef0dd199d3b20b680763f2b7cf70e7a64ea9809beb89
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d2aff60beab76e3dff8714c95d134c8ceb54e51de38d33300f0b5926b304adf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4227482c26908ff5808884547f48594d890e98ec96dd41141791360e0b881095
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.005482725898850736,
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": 61.387,
61
  "eval_steps_per_second": 30.704,
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": 997588715175936.0,
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": 0.007029135767757354,
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": 61.387,
61
  "eval_steps_per_second": 30.704,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.005623308614205884,
66
+ "grad_norm": 0.9557920694351196,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.6672,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.007029135767757354,
73
+ "grad_norm": 1.0672272443771362,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.6929,
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": 1278959891251200.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null