Hugging Face's logo

quannh197
/
f5fb298c-df1a-4966-9c77-a5b493faeff6

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
quannh197 commited on
Commit
cf5528f
·
verified ·
1 Parent(s): 4303c3a

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 sha256:395735a6e96c5aeafdafa05b480dec5ba6765a1f6cfa5ae5ddec9166e67489d4
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3afc7018e29c21d30dec35657ae34358d0fb0f9abb809f70cd7e6ccbec83bdfb
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b41bb5e5634784fde2e81050cc44ce835821208b457099074d4d3efec1c2f75f
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f89c1bb53ccdc38897acac4e2172a0d936cde38f6e445661d7b718e3fd6156
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e1d42fa3a43f0b49fecc1fb9869481eef60e0607192a6ff7e39173952f7302
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": 0.056074766355140186,
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": 30.947,
45
  "eval_steps_per_second": 16.146,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 554869274443776.0,
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": 0.11214953271028037,
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": 30.947,
45
  "eval_steps_per_second": 16.146,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.07476635514018691,
50
+ "grad_norm": 1.0428029298782349,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.0578,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.09345794392523364,
57
+ "grad_norm": 1.082016944885254,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.9756,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.11214953271028037,
64
+ "grad_norm": 1.079058289527893,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.1077,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.11214953271028037,
71
+ "eval_loss": 2.4028377532958984,
72
+ "eval_runtime": 0.7562,
73
+ "eval_samples_per_second": 30.415,
74
+ "eval_steps_per_second": 15.868,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1155977655091200.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null