Hugging Face's logo

kokovova
/
001e3242-5b49-4f5c-adb9-5f7c985a648e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files
xet
 Community
kokovova commited on
Commit
002cbdb
·
verified ·
1 Parent(s): 33b33dc

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:ff35d08e687bac28b19a6527b0d12c6b4b5ddd751245461ca6183f1bbf586aae
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1472f22bf02b234b51a6cd54de9d8a94d6cf5cd5066a75a230b9d9b5312b741
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de3ba9ad462a64a922f1137e9698e8061bb8c2803b890a68c105c3be69dbfc4a
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9896e1cd299a06dbb30dd4dd686c7042c4344a8b4bbdcc002495f3944da5dc90
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:171c39a51d67c5fd26a97228c49c329b7ef38a53ea4a56f315f2a2274edd0e31
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b52214f9bd9fd90e146416d19db727ff822d3ff4dfe457467cf1dd46cfde3948
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": 0.00046185643192813515,
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": 10.7851,
46
  "step": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 3,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 6347829962342400.0,
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": 0.0009237128638562703,
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": 10.7851,
46
  "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.0005542277183137621,
50
+ "grad_norm": 1.7677651643753052,
51
+ "learning_rate": 0.00019510565162951537,
52
+ "loss": 9.961,
53
+ "step": 12
54
+ },
55
+ {
56
+ "epoch": 0.0006927846478922027,
57
+ "grad_norm": 1.8577923774719238,
58
+ "learning_rate": 0.00017071067811865476,
59
+ "loss": 9.6359,
60
+ "step": 15
61
+ },
62
+ {
63
+ "epoch": 0.0007389702910850163,
64
+ "eval_loss": 2.5026626586914062,
65
+ "eval_runtime": 824.3534,
66
+ "eval_samples_per_second": 11.06,
67
+ "eval_steps_per_second": 5.53,
68
+ "step": 16
69
+ },
70
+ {
71
+ "epoch": 0.0008313415774706432,
72
+ "grad_norm": 2.3252103328704834,
73
+ "learning_rate": 0.00013090169943749476,
74
+ "loss": 9.796,
75
+ "step": 18
76
  }
77
  ],
78
  "logging_steps": 3,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1.26956599246848e+16,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null