Hugging Face's logo

r1char9
/
Oblivion2.5-1.5B-Instruct-v1

PEFT
Safetensors
English
text-generation-inference
Model card Files
xet
Community
Oblivion2.5-1.5B-Instruct-v1
File size: 2,852 Bytes 
2c5ebe8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
 
{
  "best_global_step": 738,
  "best_metric": 0.1383887678384781,
  "best_model_checkpoint": "/mnt/tank/scratch/rgurtsiev/workflow/ai_models/Oblivion-Adapter-1.5B-v1-demo/checkpoint-738",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 738,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 2.056960105895996,
      "eval_runtime": 568.5606,
      "eval_samples_per_second": 3.424,
      "eval_steps_per_second": 0.072,
      "step": 82
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5458435416221619,
      "eval_runtime": 564.7929,
      "eval_samples_per_second": 3.447,
      "eval_steps_per_second": 0.073,
      "step": 164
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.18356487154960632,
      "eval_runtime": 561.3321,
      "eval_samples_per_second": 3.469,
      "eval_steps_per_second": 0.073,
      "step": 246
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.1636216789484024,
      "eval_runtime": 560.8768,
      "eval_samples_per_second": 3.471,
      "eval_steps_per_second": 0.073,
      "step": 328
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.14793169498443604,
      "eval_runtime": 562.082,
      "eval_samples_per_second": 3.464,
      "eval_steps_per_second": 0.073,
      "step": 410
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.14370538294315338,
      "eval_runtime": 559.2463,
      "eval_samples_per_second": 3.481,
      "eval_steps_per_second": 0.073,
      "step": 492
    },
    {
      "epoch": 6.098159509202454,
      "grad_norm": 1576.2506103515625,
      "learning_rate": 1.0970017636684305e-05,
      "loss": 0.1864,
      "step": 500
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.1408863216638565,
      "eval_runtime": 559.9693,
      "eval_samples_per_second": 3.477,
      "eval_steps_per_second": 0.073,
      "step": 574
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.13924846053123474,
      "eval_runtime": 562.5913,
      "eval_samples_per_second": 3.461,
      "eval_steps_per_second": 0.073,
      "step": 656
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.1383887678384781,
      "eval_runtime": 559.3973,
      "eval_samples_per_second": 3.481,
      "eval_steps_per_second": 0.073,
      "step": 738
    }
  ],
  "logging_steps": 500,
  "max_steps": 810,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.659506773537587e+17,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}