Hugging Face's logo

kk-aivio
/
4f83fc75-c47b-4ffc-9c5d-992d2de52d08

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files
xet
 Community
kk-aivio commited on
Commit
afdf379
·
verified ·
1 Parent(s): 36bf393

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 sha256:9955909659988d13e6be8d56470ce222f172e301aa21f7128ce7137ddb5aba8a
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ac270f640fd4c8eb1f2f1bf4e57a01924e05135594eaae31d6bcc155b07706
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2ba688477d6d52727ef9f78672e0ca52dfceee1469f1413eb4696bb5bcd7687
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43fc4e41e79be51e0190860e395b73a443e68870cdb882f8e17d171deecfda7a
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d5081b267af95cf9f6203c3aaa67179c8d8bf336dbaefda7c27713282c1dbdc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:290db72453c0549da48ac2c903de9d8ef739ca7e660c6a1235dab2d77509f626
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": 0.00099676052828308,
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": 34.069,
45
  "eval_steps_per_second": 17.035,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 150029199212544.0,
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": 0.00199352105656616,
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": 34.069,
45
  "eval_steps_per_second": 17.035,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0013290140377107734,
50
+ "grad_norm": 0.9208881258964539,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.1699,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0016612675471384666,
57
+ "grad_norm": 1.0633083581924438,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.2754,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00199352105656616,
64
+ "grad_norm": 1.0281527042388916,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.2609,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00199352105656616,
71
+ "eval_loss": 1.1824383735656738,
72
+ "eval_runtime": 37.281,
73
+ "eval_samples_per_second": 34.012,
74
+ "eval_steps_per_second": 17.006,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 300058398425088.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null