Hugging Face's logo

Paladiso
/
0c6c9df4-71bb-4138-9f19-cb71e610e37a

PEFT
Safetensors
olmo
axolotl
Generated from Trainer
Model card Files
xet
 Community
Paladiso commited on
Commit
a48de41
·
verified ·
1 Parent(s): 87b7339

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 sha256:4ac28c63b161856975fce35f0d77331a70a1e2c8ea0ecd1fcab3a585c9da31f1
3
  size 81576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb375bff6222943faeb64bcf5cd2a7bbf83342511b1875324307a326320ee5a8
3
  size 81576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:984d42bd82dcaca63271e4183d329def28aaa892b68fb96b741d40ac552733da
3
  size 173094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd37241d023d6c4863375ca16152e19f2934d94d7d66a485240415b28e80ad8
3
  size 173094
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": 0.0009695402763189787,
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": 356.312,
45
  "eval_steps_per_second": 178.293,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 328118304768.0,
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": 0.0019390805526379575,
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": 356.312,
45
  "eval_steps_per_second": 178.293,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.001292720368425305,
50
+ "grad_norm": 0.18902043998241425,
51
+ "learning_rate": 8e-05,
52
+ "loss": 10.8192,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0016159004605316313,
57
+ "grad_norm": 0.20040695369243622,
58
+ "learning_rate": 0.0001,
59
+ "loss": 10.8182,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0019390805526379575,
64
+ "grad_norm": 0.1375870704650879,
65
+ "learning_rate": 0.00012,
66
+ "loss": 10.8247,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0019390805526379575,
71
+ "eval_loss": 10.822270393371582,
72
+ "eval_runtime": 3.7611,
73
+ "eval_samples_per_second": 346.438,
74
+ "eval_steps_per_second": 173.352,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 615221821440.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null