Hugging Face's logo

Guilherme34
/
Samantha-multimodal-v2

PEFT
Safetensors
Model card Files Community
Samantha-multimodal-v2
File size: 2,287 Bytes 
3b76797
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6535947712418301,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16339869281045752,
      "grad_norm": 2.9138197898864746,
      "learning_rate": 1.893939393939394e-05,
      "loss": 1.3885,
      "step": 25
    },
    {
      "epoch": 0.16339869281045752,
      "eval_loss": 0.6594953536987305,
      "eval_runtime": 633.7486,
      "eval_samples_per_second": 0.483,
      "eval_steps_per_second": 0.062,
      "step": 25
    },
    {
      "epoch": 0.32679738562091504,
      "grad_norm": 2.861112117767334,
      "learning_rate": 1.2626262626262628e-05,
      "loss": 0.6223,
      "step": 50
    },
    {
      "epoch": 0.32679738562091504,
      "eval_loss": 0.6024950742721558,
      "eval_runtime": 634.1943,
      "eval_samples_per_second": 0.483,
      "eval_steps_per_second": 0.061,
      "step": 50
    },
    {
      "epoch": 0.49019607843137253,
      "grad_norm": 4.142775058746338,
      "learning_rate": 6.313131313131314e-06,
      "loss": 0.6025,
      "step": 75
    },
    {
      "epoch": 0.49019607843137253,
      "eval_loss": 0.5404363870620728,
      "eval_runtime": 634.4774,
      "eval_samples_per_second": 0.482,
      "eval_steps_per_second": 0.061,
      "step": 75
    },
    {
      "epoch": 0.6535947712418301,
      "grad_norm": 14.336810111999512,
      "learning_rate": 0.0,
      "loss": 0.5024,
      "step": 100
    },
    {
      "epoch": 0.6535947712418301,
      "eval_loss": 0.5124824643135071,
      "eval_runtime": 635.0592,
      "eval_samples_per_second": 0.482,
      "eval_steps_per_second": 0.061,
      "step": 100
    }
  ],
  "logging_steps": 25,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5140361035776000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}