Hugging Face's logo

adammandic87
/
032cbbb5-bf71-40df-bff5-a79fb44167c5

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
adammandic87 commited on
Commit
caf6483
·
verified ·
1 Parent(s): 4f4dca5

Training in progress, step 39, 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 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43828bc939a481227df8834c918c06386f8cee50a88151a5a0014aa9e818416e
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b580750888ea7d8abce7a14d4f56dbd00f7db466644347e0d4b6e0599a474d
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:542aaef498122810b67803ff5d2977ce3c2e6fcde4d1e637c00ec41dddb60938
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a138952f84f9a99f08b97d104ff0a77c31e83057ec5e554c490cbc21ac96237
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:e74de10f5c0c2a9020bea32cb7fab60b0b58fcece1c0bb0df5e911041ee59517
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0472ce311e84cd5509f168867d58579c252d4413aee368c17e4cfad44ac2bb7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.07957153787299158,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 26.624,
46
  "eval_steps_per_second": 13.312,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 6011083806474240.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.11935730680948738,
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,
 
45
  "eval_samples_per_second": 26.624,
46
  "eval_steps_per_second": 13.312,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.09181331293037491,
51
+ "grad_norm": 0.5139346122741699,
52
+ "learning_rate": 5e-05,
53
+ "loss": 0.4389,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.11935730680948738,
58
+ "eval_loss": 0.43966734409332275,
59
+ "eval_runtime": 5.1801,
60
+ "eval_samples_per_second": 26.64,
61
+ "eval_steps_per_second": 13.32,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 8970386603507712.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null