Hugging Face's logo

gavrilstep
/
af7002b2-741b-4563-b1bc-174f11e1aae9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
af7002b2-741b-4563-b1bc-174f11e1aae9
File size: 3,323 Bytes 
a66f24d
 
 
7c6f2fe
a66f24d
7c6f2fe
a66f24d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
00b30d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7c6f2fe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a66f24d
 
 
 
 
 
 
 
 
 
 
 
 
 
7c6f2fe
a66f24d
 
 
 
7c6f2fe
a66f24d
 
 
 
 
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": 0.009012617664730624,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003004205888243541,
      "eval_loss": 2.7872743606567383,
      "eval_runtime": 88.3464,
      "eval_samples_per_second": 11.908,
      "eval_steps_per_second": 5.954,
      "step": 1
    },
    {
      "epoch": 0.0009012617664730623,
      "grad_norm": 1.1402565240859985,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.7378,
      "step": 3
    },
    {
      "epoch": 0.0018025235329461246,
      "grad_norm": 2.1231765747070312,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.939,
      "step": 6
    },
    {
      "epoch": 0.002403364710594833,
      "eval_loss": 2.432232618331909,
      "eval_runtime": 88.9769,
      "eval_samples_per_second": 11.823,
      "eval_steps_per_second": 5.912,
      "step": 8
    },
    {
      "epoch": 0.0027037852994191867,
      "grad_norm": 1.5503355264663696,
      "learning_rate": 0.00027,
      "loss": 2.5135,
      "step": 9
    },
    {
      "epoch": 0.0036050470658922492,
      "grad_norm": 1.399559736251831,
      "learning_rate": 0.00029265847744427303,
      "loss": 2.3922,
      "step": 12
    },
    {
      "epoch": 0.004506308832365312,
      "grad_norm": 1.0500314235687256,
      "learning_rate": 0.00025606601717798207,
      "loss": 2.0311,
      "step": 15
    },
    {
      "epoch": 0.004806729421189666,
      "eval_loss": 2.156785011291504,
      "eval_runtime": 89.5225,
      "eval_samples_per_second": 11.751,
      "eval_steps_per_second": 5.876,
      "step": 16
    },
    {
      "epoch": 0.005407570598838373,
      "grad_norm": 1.1485878229141235,
      "learning_rate": 0.0001963525491562421,
      "loss": 2.1654,
      "step": 18
    },
    {
      "epoch": 0.006308832365311436,
      "grad_norm": 1.0800117254257202,
      "learning_rate": 0.00012653483024396533,
      "loss": 2.0277,
      "step": 21
    },
    {
      "epoch": 0.0072100941317844985,
      "grad_norm": 1.12771475315094,
      "learning_rate": 6.183221215612904e-05,
      "loss": 2.1248,
      "step": 24
    },
    {
      "epoch": 0.0072100941317844985,
      "eval_loss": 2.105942487716675,
      "eval_runtime": 89.1213,
      "eval_samples_per_second": 11.804,
      "eval_steps_per_second": 5.902,
      "step": 24
    },
    {
      "epoch": 0.008111355898257561,
      "grad_norm": 1.0826979875564575,
      "learning_rate": 1.634902137174483e-05,
      "loss": 2.0851,
      "step": 27
    },
    {
      "epoch": 0.009012617664730624,
      "grad_norm": 0.8876891136169434,
      "learning_rate": 0.0,
      "loss": 2.0737,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8346231940055040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}