Hugging Face's logo

JacksonBrune
/
c3f314de-00dc-4215-b8f2-f8d685d9723c

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
c3f314de-00dc-4215-b8f2-f8d685d9723c
File size: 2,125 Bytes 
7dc86aa
 
 
a374488
7dc86aa
a374488
7dc86aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f778d8e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a374488
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7dc86aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a374488
7dc86aa
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5182724252491694,
  "eval_steps": 13,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013289036544850499,
      "eval_loss": 2.4356181621551514,
      "eval_runtime": 0.8027,
      "eval_samples_per_second": 39.867,
      "eval_steps_per_second": 19.934,
      "step": 1
    },
    {
      "epoch": 0.132890365448505,
      "grad_norm": 3.1950788497924805,
      "learning_rate": 0.00019396926207859084,
      "loss": 1.7757,
      "step": 10
    },
    {
      "epoch": 0.17275747508305647,
      "eval_loss": 1.3727681636810303,
      "eval_runtime": 0.8042,
      "eval_samples_per_second": 39.79,
      "eval_steps_per_second": 19.895,
      "step": 13
    },
    {
      "epoch": 0.26578073089701,
      "grad_norm": 2.2735886573791504,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.263,
      "step": 20
    },
    {
      "epoch": 0.34551495016611294,
      "eval_loss": 1.2255778312683105,
      "eval_runtime": 0.8186,
      "eval_samples_per_second": 39.092,
      "eval_steps_per_second": 19.546,
      "step": 26
    },
    {
      "epoch": 0.39867109634551495,
      "grad_norm": 1.858064889907837,
      "learning_rate": 8.263518223330697e-05,
      "loss": 1.1259,
      "step": 30
    },
    {
      "epoch": 0.5182724252491694,
      "eval_loss": 1.2005141973495483,
      "eval_runtime": 0.8187,
      "eval_samples_per_second": 39.085,
      "eval_steps_per_second": 19.543,
      "step": 39
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1950379589763072.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}