Hugging Face's logo

mamung
/
29b84e13-2f1c-406f-9e7e-fd35b6e5ff49

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
mamung commited on
Commit
3b94396
·
verified ·
1 Parent(s): 3450153

Training in progress, step 6, 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 sha256:4a79886202abcc0c1ffbb4ff6189af64ef92cab2c1d75ee0e50f3410c952e6f6
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ced54c5cf5a769f0a915e42b0b0af11d2b042c020ba4b09790c2db88d14acc4
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bd5a6dcc0aa59a0ef439514af5095e9b16d7c6c51e0898ec45ebdd681be2237
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0436dfba133e66b15d94ee68740359a7646eb0d0801a4b92f4233801f5077182
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:275777b5b59331eb7c9b21476fc6c694d689abc2e49b2c9c5c766965cbed556f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8780d7db06ab4ab1a3d9fe0bbb5d24157ffc53e0a958625307e31b1c79f0a6c9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.00018019370823635407,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 11.667,
45
  "eval_steps_per_second": 5.834,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 369021899243520.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00036038741647270814,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 11.667,
45
  "eval_steps_per_second": 5.834,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00024025827764847211,
50
+ "grad_norm": 0.19479113817214966,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.7555,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00030032284706059013,
57
+ "grad_norm": 0.136930450797081,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.5729,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00036038741647270814,
64
+ "grad_norm": 0.16922074556350708,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.5918,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00036038741647270814,
71
+ "eval_loss": 1.6521847248077393,
72
+ "eval_runtime": 600.6386,
73
+ "eval_samples_per_second": 11.673,
74
+ "eval_steps_per_second": 5.837,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 779046231736320.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null