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
6b985fc
·
verified ·
1 Parent(s): 24cf79d

Training in progress, step 26, 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 sha256:0840f8acf496333343a56b9f47564bd8197f6dd1a3aac978a1f5a3e5b3f3c3d7
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43828bc939a481227df8834c918c06386f8cee50a88151a5a0014aa9e818416e
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e4be29d9622bbe804825609e0df2de6e2d7f353392afe701d312628998d7319
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:542aaef498122810b67803ff5d2977ce3c2e6fcde4d1e637c00ec41dddb60938
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11ea774558660c983c4ebb1b877a56815c7461f80d4ca701f9cdca1dd0672420
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e74de10f5c0c2a9020bea32cb7fab60b0b58fcece1c0bb0df5e911041ee59517
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
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": 0.03978576893649579,
5
  "eval_steps": 13,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -30,6 +30,21 @@
30
  "eval_samples_per_second": 26.67,
31
  "eval_steps_per_second": 13.335,
32
  "step": 13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 10,
@@ -49,7 +64,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 3005541903237120.0,
53
  "train_batch_size": 2,
54
  "trial_name": null,
55
  "trial_params": null
 
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,
 
30
  "eval_samples_per_second": 26.67,
31
  "eval_steps_per_second": 13.335,
32
  "step": 13
33
+ },
34
+ {
35
+ "epoch": 0.061208875286916604,
36
+ "grad_norm": 0.6774999499320984,
37
+ "learning_rate": 8.535533905932738e-05,
38
+ "loss": 0.5548,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.07957153787299158,
43
+ "eval_loss": 0.45831599831581116,
44
+ "eval_runtime": 5.1833,
45
+ "eval_samples_per_second": 26.624,
46
+ "eval_steps_per_second": 13.312,
47
+ "step": 26
48
  }
49
  ],
50
  "logging_steps": 10,
 
64
  "attributes": {}
65
  }
66
  },
67
+ "total_flos": 6011083806474240.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null