Hugging Face's logo

kostiantynk-out
/
5fd639dd-05fc-4ec5-afc0-eb02c38708bb

PEFT
Safetensors
falcon
axolotl
Generated from Trainer
custom_code
Model card Files Community
5fd639dd-05fc-4ec5-afc0-eb02c38708bb
File size: 3,200 Bytes 
f07d90c
 
 
cee594f
f07d90c
cee594f
f07d90c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
227e4dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2da30c3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cee594f
 
 
 
 
 
 
f07d90c
 
 
 
 
 
 
 
 
 
 
 
 
 
cee594f
f07d90c
 
 
 
cee594f
f07d90c
 
 
 
 
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
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016256197675363732,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001625619767536373,
      "grad_norm": 2.0558841228485107,
      "learning_rate": 2e-05,
      "loss": 11.9422,
      "step": 1
    },
    {
      "epoch": 0.0001625619767536373,
      "eval_loss": 2.083211660385132,
      "eval_runtime": 70.5571,
      "eval_samples_per_second": 36.722,
      "eval_steps_per_second": 18.368,
      "step": 1
    },
    {
      "epoch": 0.0003251239535072746,
      "grad_norm": 0.6903805732727051,
      "learning_rate": 4e-05,
      "loss": 6.0204,
      "step": 2
    },
    {
      "epoch": 0.000487685930260912,
      "grad_norm": 0.8539021611213684,
      "learning_rate": 6e-05,
      "loss": 7.9875,
      "step": 3
    },
    {
      "epoch": 0.000487685930260912,
      "eval_loss": 2.0831315517425537,
      "eval_runtime": 69.1607,
      "eval_samples_per_second": 37.463,
      "eval_steps_per_second": 18.739,
      "step": 3
    },
    {
      "epoch": 0.0006502479070145493,
      "grad_norm": 1.5361990928649902,
      "learning_rate": 8e-05,
      "loss": 8.7738,
      "step": 4
    },
    {
      "epoch": 0.0008128098837681866,
      "grad_norm": 1.0650941133499146,
      "learning_rate": 0.0001,
      "loss": 7.3005,
      "step": 5
    },
    {
      "epoch": 0.000975371860521824,
      "grad_norm": 1.2282767295837402,
      "learning_rate": 0.00012,
      "loss": 7.6635,
      "step": 6
    },
    {
      "epoch": 0.000975371860521824,
      "eval_loss": 2.0658681392669678,
      "eval_runtime": 69.579,
      "eval_samples_per_second": 37.238,
      "eval_steps_per_second": 18.626,
      "step": 6
    },
    {
      "epoch": 0.0011379338372754612,
      "grad_norm": 2.628141164779663,
      "learning_rate": 0.00014,
      "loss": 8.1998,
      "step": 7
    },
    {
      "epoch": 0.0013004958140290985,
      "grad_norm": 2.1144790649414062,
      "learning_rate": 0.00016,
      "loss": 6.1864,
      "step": 8
    },
    {
      "epoch": 0.001463057790782736,
      "grad_norm": 2.139829635620117,
      "learning_rate": 0.00018,
      "loss": 6.9148,
      "step": 9
    },
    {
      "epoch": 0.001463057790782736,
      "eval_loss": 1.9335415363311768,
      "eval_runtime": 69.3155,
      "eval_samples_per_second": 37.38,
      "eval_steps_per_second": 18.697,
      "step": 9
    },
    {
      "epoch": 0.0016256197675363732,
      "grad_norm": 3.207768440246582,
      "learning_rate": 0.0002,
      "loss": 6.5363,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1632478030725120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}