Hugging Face's logo

tuanna08go
/
dbf1257f-984b-4518-b654-372d08f639ed

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
5f4337b
·
verified ·
1 Parent(s): 146b892

Training in progress, step 18, 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 +12 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b952d6cc0511866e49137368f8f072b6a1fb046daf0537703088de3d307068bf
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a1f8bf0e30a9d4c35c1ccc688b51ccbd0705ae5f833b37f5048a4160188352
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd451a7a0ebe9a067b682597d1c3e7c75fbfc4289383fd15d0e2357bdde90c63
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51b48c22476b3777cb9c9d7f49b7d30853d5deb6268fd45056933a7792bd9542
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f2e6817d1e235e63095d76c2980b842f02011f3faae798fc417ba16878ce11a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d035f156a334de56644238dc3b829f2f622267306f72062de6ced0f7c88439
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e555b1173ceea1f11ca45539c0fe5856e7571df97c436cc742ba6deb19b07e97
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd82e2c4dd46a0c4163e78a1bb05a9e321fb40a1c884136f2f4f92fe2449cbde
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": 0.8333333333333334,
5
  "eval_steps": 4,
6
- "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -46,6 +46,14 @@
46
  "eval_samples_per_second": 37.967,
47
  "eval_steps_per_second": 4.979,
48
  "step": 12
 
 
 
 
 
 
 
 
49
  }
50
  ],
51
  "logging_steps": 10,
@@ -60,12 +68,12 @@
60
  "should_evaluate": false,
61
  "should_log": false,
62
  "should_save": true,
63
- "should_training_stop": false
64
  },
65
  "attributes": {}
66
  }
67
  },
68
- "total_flos": 1.227801495601152e+16,
69
  "train_batch_size": 8,
70
  "trial_name": null,
71
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
  "eval_steps": 4,
6
+ "global_step": 18,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
46
  "eval_samples_per_second": 37.967,
47
  "eval_steps_per_second": 4.979,
48
  "step": 12
49
+ },
50
+ {
51
+ "epoch": 0.8888888888888888,
52
+ "eval_loss": 0.49720510840415955,
53
+ "eval_runtime": 3.2217,
54
+ "eval_samples_per_second": 37.868,
55
+ "eval_steps_per_second": 4.966,
56
+ "step": 16
57
  }
58
  ],
59
  "logging_steps": 10,
 
68
  "should_evaluate": false,
69
  "should_log": false,
70
  "should_save": true,
71
+ "should_training_stop": true
72
  },
73
  "attributes": {}
74
  }
75
  },
76
+ "total_flos": 1.4720828348301312e+16,
77
  "train_batch_size": 8,
78
  "trial_name": null,
79
  "trial_params": null