Hugging Face's logo

phungkhaccuong
/
18d6d3aa-3fae-4913-8e78-59701e8aa297

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
phungkhaccuong commited on
Commit
518d471
·
verified ·
1 Parent(s): 027c438

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:a204212c2d65acbb00b0f37a852b9be66a976e7bcf076e6064105736916f18a8
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21b676609e98e932eca37c09ec8cc3ffe000935c3be8daeedd99ac2ecbaaa70b
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:810e486ceafb827ccf39fab6c7ac637aea7f21ec2e307ee069d2557ff585f219
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c3915aece43c2f9bb8dcd39aed9ca307e6be7952a60087b70290dd0476582d
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8584eb0606268fe40a7b607403caf1bbfdb0ed83707fc0a067fb7329a1dc8581
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a997aa8bfab00a35d7cfa486126e3d295d226a899068a295415cfc8e8058a7c
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": 0.036312849162011177,
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": 31.241,
38
  "eval_steps_per_second": 15.724,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 332529571725312.0,
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": 0.07262569832402235,
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": 31.241,
38
  "eval_steps_per_second": 15.724,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.04189944134078212,
43
+ "grad_norm": 4.385186672210693,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 5.0465,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.055865921787709494,
50
+ "grad_norm": 3.310457706451416,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 4.4644,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.055865921787709494,
57
+ "eval_loss": 4.217800617218018,
58
+ "eval_runtime": 4.9043,
59
+ "eval_samples_per_second": 30.789,
60
+ "eval_steps_per_second": 15.497,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.06983240223463687,
65
+ "grad_norm": 3.4962682723999023,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 4.1238,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 665059143450624.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null