Hugging Face's logo

dzanbek
/
5bad54b6-e7b2-43d8-bb2e-cbc5d064f10c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
dzanbek commited on
Commit
d61a00e
·
verified ·
1 Parent(s): 8e6c2fa

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:ca7f6ccbc7512d895a76e468aa7586ac4af80ee280bde28627e274ae2e441e62
3
  size 101752088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dfd47fd10f934bbb25bbc624bd03cc0ce2b5e303805a9fd9cd29096a74e313f
3
  size 101752088
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1c359ab1b8fdaea4e0f6dcad1441c95fb6dac1b11876ea09acbca844b267f34
3
  size 203713238
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645063ee227c11d8fb6cbad7dc35adcb03bae1ba9f3bbae0edffca8181a96c8c
3
  size 203713238
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a23da42bf25c27763c225d43c01a1c1eeacc08d995b08155eedd57ebfabed4ae
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9b3cb071fb5edf463f62e94083e2a383e07000b99a11f181c47793324f9ea9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
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": 0.003719546215361726,
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": 0.00018,
45
  "loss": 2.537,
46
  "step": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 3,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1646346004070400.0,
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": 0.007439092430723452,
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": 0.00018,
45
  "loss": 2.537,
46
  "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.004463455458434071,
50
+ "grad_norm": 3.136127233505249,
51
+ "learning_rate": 0.00019510565162951537,
52
+ "loss": 2.3122,
53
+ "step": 12
54
+ },
55
+ {
56
+ "epoch": 0.0055793193230425885,
57
+ "grad_norm": 1.3226345777511597,
58
+ "learning_rate": 0.00017071067811865476,
59
+ "loss": 2.1302,
60
+ "step": 15
61
+ },
62
+ {
63
+ "epoch": 0.0059512739445787615,
64
+ "eval_loss": 2.030067205429077,
65
+ "eval_runtime": 134.0048,
66
+ "eval_samples_per_second": 8.447,
67
+ "eval_steps_per_second": 4.224,
68
+ "step": 16
69
+ },
70
+ {
71
+ "epoch": 0.006695183187651107,
72
+ "grad_norm": 1.5775707960128784,
73
+ "learning_rate": 0.00013090169943749476,
74
+ "loss": 2.0017,
75
+ "step": 18
76
  }
77
  ],
78
  "logging_steps": 3,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 3292692008140800.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null