Hugging Face's logo

nathanialhunt
/
d0d5477a-e58c-463b-b484-65dd21403b48

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
d0d5477a-e58c-463b-b484-65dd21403b48
File size: 3,056 Bytes 
0ce8ff0
 
 
3c8946e
0ce8ff0
3c8946e
0ce8ff0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e295458
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3c8946e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0ce8ff0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3c8946e
0ce8ff0
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00032841321680745865,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.649035742305096e-05,
      "grad_norm": 1.0238981246948242,
      "learning_rate": 2e-05,
      "loss": 1.7931,
      "step": 1
    },
    {
      "epoch": 3.649035742305096e-05,
      "eval_loss": 1.98862886428833,
      "eval_runtime": 701.2135,
      "eval_samples_per_second": 16.456,
      "eval_steps_per_second": 8.229,
      "step": 1
    },
    {
      "epoch": 7.298071484610192e-05,
      "grad_norm": 1.4650105237960815,
      "learning_rate": 4e-05,
      "loss": 2.2947,
      "step": 2
    },
    {
      "epoch": 0.00010947107226915287,
      "grad_norm": 1.2507858276367188,
      "learning_rate": 6e-05,
      "loss": 2.2756,
      "step": 3
    },
    {
      "epoch": 0.00010947107226915287,
      "eval_loss": 1.979144811630249,
      "eval_runtime": 483.2723,
      "eval_samples_per_second": 23.877,
      "eval_steps_per_second": 11.939,
      "step": 3
    },
    {
      "epoch": 0.00014596142969220384,
      "grad_norm": 0.9717092514038086,
      "learning_rate": 8e-05,
      "loss": 1.7241,
      "step": 4
    },
    {
      "epoch": 0.0001824517871152548,
      "grad_norm": 1.0161713361740112,
      "learning_rate": 0.0001,
      "loss": 1.7689,
      "step": 5
    },
    {
      "epoch": 0.00021894214453830574,
      "grad_norm": 0.9307000637054443,
      "learning_rate": 0.00012,
      "loss": 1.6985,
      "step": 6
    },
    {
      "epoch": 0.00021894214453830574,
      "eval_loss": 1.840909719467163,
      "eval_runtime": 757.7667,
      "eval_samples_per_second": 15.228,
      "eval_steps_per_second": 7.614,
      "step": 6
    },
    {
      "epoch": 0.0002554325019613567,
      "grad_norm": 1.9005385637283325,
      "learning_rate": 0.00014,
      "loss": 1.9594,
      "step": 7
    },
    {
      "epoch": 0.00029192285938440767,
      "grad_norm": 1.6968870162963867,
      "learning_rate": 0.00016,
      "loss": 1.7966,
      "step": 8
    },
    {
      "epoch": 0.00032841321680745865,
      "grad_norm": 0.9660829901695251,
      "learning_rate": 0.00018,
      "loss": 1.7219,
      "step": 9
    },
    {
      "epoch": 0.00032841321680745865,
      "eval_loss": 1.6114068031311035,
      "eval_runtime": 751.3421,
      "eval_samples_per_second": 15.358,
      "eval_steps_per_second": 7.68,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1953769004728320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}