Hugging Face's logo

shibajustfor
/
a690348b-9d15-46c5-92f0-37a6633c8cd5

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
custom_code
Model card Files
xet
 Community
shibajustfor commited on
Commit
00df1af
·
verified ·
1 Parent(s): 7df9bba

Training in progress, step 39, 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 +18 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd8611ed0c70e243248571db7b310515a93be64594b00c0b2776f29e41c3b1bd
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:599058326d1f80982a0cf2e8d7449b6bf4874b43030faee5b70e77fe63629f71
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2763b6396a016040e4679e2d6fe5c7a4d3eb1d3527651ef5da14448e346070a6
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993291be78324bbb38f7e73972c07b4f08ca634d335c400183e16a261d014bd5
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b67bd18c19d450b6e9540356d3dd1899dcc04f35f70c1cdcb528c1e2e8ee989
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa10da0a18ea67917350fb6e6f8db87ade3225f86b79930eb7ac553eb290db0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
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": 0.0035714285714285713,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 30.176,
46
  "eval_steps_per_second": 15.088,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 4556941443465216.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005357142857142857,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 30.176,
46
  "eval_steps_per_second": 15.088,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.004120879120879121,
51
+ "grad_norm": 15.32772445678711,
52
+ "learning_rate": 0.0002,
53
+ "loss": 1.6598,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.005357142857142857,
58
+ "eval_loss": 0.551670253276825,
59
+ "eval_runtime": 101.8402,
60
+ "eval_samples_per_second": 30.106,
61
+ "eval_steps_per_second": 15.053,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 6835412165197824.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null