Hugging Face's logo

willtensora
/
123e4567-e89b-12d3-a456-426614174000

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
willtensora commited on
Commit
ad0fd02
·
verified ·
1 Parent(s): d5c3da7

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 sha256:75f479de263b3e6fd6a9c914fe1b3de17f2b9d3e4a326af354db1de92a4e9e03
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4be31c2a19160dd5be5dd50e510f9f18d4bb6224246a2d5f255f8c36b5ef066b
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d4c4a47d9fd381c4373fdf8d4bde3e15bc85aa71527812b8071e2ff9f4ea41b
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f0a690086dca198709299fdcafa36a322704ffe3c26dabdab46013cbcbb063
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
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": 0.0016825574873808188,
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": 273.868,
45
  "eval_steps_per_second": 137.116,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 384024576.0,
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": 0.0033651149747616375,
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": 273.868,
45
  "eval_steps_per_second": 137.116,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.002243409983174425,
50
+ "grad_norm": 0.015588194131851196,
51
+ "learning_rate": 8e-05,
52
+ "loss": 11.9328,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0028042624789680315,
57
+ "grad_norm": 0.016935445368289948,
58
+ "learning_rate": 0.0001,
59
+ "loss": 11.9248,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0033651149747616375,
64
+ "grad_norm": 0.009075427427887917,
65
+ "learning_rate": 0.00012,
66
+ "loss": 11.926,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0033651149747616375,
71
+ "eval_loss": 11.93128776550293,
72
+ "eval_runtime": 2.8211,
73
+ "eval_samples_per_second": 266.211,
74
+ "eval_steps_per_second": 133.283,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 738508800.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null