Hugging Face's logo

marialvsantiago
/
053abcdf-3e57-498e-a841-b4fd75479bda

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files
xet
 Community
marialvsantiago commited on
Commit
42c095e
·
verified ·
1 Parent(s): 364bdd5

Training in progress, step 20, 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:a3b81731c72bbe50e8ce8c2bbdadfc3d120d289b775a68c533a53885ca745a91
3
  size 78480072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:482590ef591761e4a0ef4afb3771f26715ca88ccf468e2380cf57bfc3276708a
3
  size 78480072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66b66dde6ba9e3996e35847a77ee753b255fe6ee0cdc7ef558e2766be0c8642b
3
  size 157042234
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64c94b5d94febe024c4a9d3f0f0d42541380e15d2c8cab8ed054e2d3223a0d19
3
  size 157042234
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1873eb8829bf98214d73b583b7fbe40cc37709c10f01fd4f7f063d003c3b2ef8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8465a2e4614e1287f930b6a433b29ede97245ad18a14d916df3651304046346a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
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": 0.000412975696380268,
5
  "eval_steps": 8,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "learning_rate": 9e-05,
45
  "loss": 4.1173,
46
  "step": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 3,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1032964112646144.0,
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": 0.000825951392760536,
5
  "eval_steps": 8,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "learning_rate": 9e-05,
45
  "loss": 4.1173,
46
  "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.0004955708356563217,
50
+ "grad_norm": 2.6733851432800293,
51
+ "learning_rate": 9.755282581475769e-05,
52
+ "loss": 5.3002,
53
+ "step": 12
54
+ },
55
+ {
56
+ "epoch": 0.000619463544570402,
57
+ "grad_norm": 4.611398696899414,
58
+ "learning_rate": 8.535533905932738e-05,
59
+ "loss": 4.6689,
60
+ "step": 15
61
+ },
62
+ {
63
+ "epoch": 0.0006607611142084288,
64
+ "eval_loss": 4.535793304443359,
65
+ "eval_runtime": 622.9921,
66
+ "eval_samples_per_second": 16.366,
67
+ "eval_steps_per_second": 8.183,
68
+ "step": 16
69
+ },
70
+ {
71
+ "epoch": 0.0007433562534844825,
72
+ "grad_norm": 2.3664894104003906,
73
+ "learning_rate": 6.545084971874738e-05,
74
+ "loss": 4.1348,
75
+ "step": 18
76
  }
77
  ],
78
  "logging_steps": 3,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 2115116992561152.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null