Hugging Face's logo

lesso03
/
2a5e2651-d29b-45f8-a1a3-a1df604d2894

Safetensors
falcon_mamba
Model card Files Community
2a5e2651-d29b-45f8-a1a3-a1df604d2894
File size: 2,312 Bytes 
3a10b99
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.24415357410907745,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.008471704506946797,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016943409013893597,
      "eval_loss": 0.2542303204536438,
      "eval_runtime": 3002.3866,
      "eval_samples_per_second": 0.828,
      "eval_steps_per_second": 0.207,
      "step": 1
    },
    {
      "epoch": 0.0016943409013893595,
      "grad_norm": 0.17602235078811646,
      "learning_rate": 4.0600000000000004e-05,
      "loss": 0.4374,
      "step": 10
    },
    {
      "epoch": 0.003388681802778719,
      "grad_norm": 0.20099331438541412,
      "learning_rate": 8.120000000000001e-05,
      "loss": 0.4414,
      "step": 20
    },
    {
      "epoch": 0.005083022704168078,
      "grad_norm": 0.2623608410358429,
      "learning_rate": 0.00012179999999999999,
      "loss": 0.5019,
      "step": 30
    },
    {
      "epoch": 0.006777363605557438,
      "grad_norm": 0.401140421628952,
      "learning_rate": 0.00016240000000000002,
      "loss": 0.5029,
      "step": 40
    },
    {
      "epoch": 0.008471704506946797,
      "grad_norm": 1.6905375719070435,
      "learning_rate": 0.000203,
      "loss": 0.5199,
      "step": 50
    },
    {
      "epoch": 0.008471704506946797,
      "eval_loss": 0.24415357410907745,
      "eval_runtime": 2979.8855,
      "eval_samples_per_second": 0.834,
      "eval_steps_per_second": 0.209,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2747702395731968e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}