Hugging Face's logo

ClarenceDan
/
d683603e-40b4-405f-9385-888fba3e3fca

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
d683603e-40b4-405f-9385-888fba3e3fca
File size: 2,355 Bytes 
76d34ee
 
 
17ff77a
76d34ee
17ff77a
76d34ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17ff77a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76d34ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17ff77a
76d34ee
 
 
 
 
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
88
89
90
91
92
93
94
95
96
97
98
99
100
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006232633027761186,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010387721712935311,
      "grad_norm": 1.5019885301589966,
      "learning_rate": 2e-05,
      "loss": 1.939,
      "step": 1
    },
    {
      "epoch": 0.00010387721712935311,
      "eval_loss": 1.901095986366272,
      "eval_runtime": 112.8269,
      "eval_samples_per_second": 35.931,
      "eval_steps_per_second": 17.966,
      "step": 1
    },
    {
      "epoch": 0.00020775443425870621,
      "grad_norm": 1.2988160848617554,
      "learning_rate": 4e-05,
      "loss": 1.6544,
      "step": 2
    },
    {
      "epoch": 0.0003116316513880593,
      "grad_norm": 1.1926392316818237,
      "learning_rate": 6e-05,
      "loss": 1.779,
      "step": 3
    },
    {
      "epoch": 0.0003116316513880593,
      "eval_loss": 1.8887230157852173,
      "eval_runtime": 113.1435,
      "eval_samples_per_second": 35.831,
      "eval_steps_per_second": 17.915,
      "step": 3
    },
    {
      "epoch": 0.00041550886851741243,
      "grad_norm": 1.465193510055542,
      "learning_rate": 8e-05,
      "loss": 1.8448,
      "step": 4
    },
    {
      "epoch": 0.0005193860856467655,
      "grad_norm": 1.385634422302246,
      "learning_rate": 0.0001,
      "loss": 1.8131,
      "step": 5
    },
    {
      "epoch": 0.0006232633027761186,
      "grad_norm": 1.5537233352661133,
      "learning_rate": 0.00012,
      "loss": 1.8471,
      "step": 6
    },
    {
      "epoch": 0.0006232633027761186,
      "eval_loss": 1.7395198345184326,
      "eval_runtime": 112.8668,
      "eval_samples_per_second": 35.918,
      "eval_steps_per_second": 17.959,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 312560831692800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}