Hugging Face's logo

duyphu
/
dd99cfae-4152-4304-b09a-31a00951788f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
duyphu commited on
Commit
5a617ec
·
verified ·
1 Parent(s): eeb5870

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 +32 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b317a4ed15ab8a58797a5e0e6de3a33d7a0482c55d796cc768bd74896c1abb01
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e742afbd1847ef2698fe226fa44c77468e3c89a6490297b211df3c28e7daf9
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7afee6da0e5ac98b83474d2a2ae9258a58f891a405483d9baf3fe6afef2c3a50
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87f113bc9955e4fcb5f82a15aa35cef6bb0d57b913f241cea33c7bcb4ab1319
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:baecc8988a2f594185c875288190c60274795754df975adfaa0c8b19740a1a71
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eba564523b8e7170117124c450887f82a78e23aad68f44ac77face0466e16e2
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": 0.01864467551093582,
5
  "eval_steps": 10,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,35 @@
37
  "eval_samples_per_second": 7.736,
38
  "eval_steps_per_second": 3.868,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 4762627938975744.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03728935102187164,
5
  "eval_steps": 10,
6
+ "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 7.736,
38
  "eval_steps_per_second": 3.868,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.02151308712800287,
43
+ "grad_norm": 1.9536420106887817,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 2.2906,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.02868411617067049,
50
+ "grad_norm": 5.312585830688477,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 1.2111,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.02868411617067049,
57
+ "eval_loss": 1.4129958152770996,
58
+ "eval_runtime": 38.111,
59
+ "eval_samples_per_second": 7.714,
60
+ "eval_steps_per_second": 3.857,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.035855145213338116,
65
+ "grad_norm": 1.6094022989273071,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 1.2905,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 9571494984155136.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null