Hugging Face's logo

adammandic87
/
84167ccb-8de7-4eb8-855c-ea1aaf8075fc

PEFT
Safetensors
olmo
axolotl
Generated from Trainer
Model card Files Community
84167ccb-8de7-4eb8-855c-ea1aaf8075fc
File size: 3,237 Bytes 
ae3a2d4
 
 
441e4ac
ae3a2d4
441e4ac
ae3a2d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99240b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ec5d5c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
441e4ac
 
 
 
 
 
 
ae3a2d4
 
 
 
 
 
 
 
 
 
 
 
 
 
441e4ac
ae3a2d4
 
 
 
441e4ac
ae3a2d4
 
 
 
 
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": 0.00035324767077317084,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.532476707731709e-05,
      "grad_norm": 0.2014792263507843,
      "learning_rate": 2e-05,
      "loss": 10.8416,
      "step": 1
    },
    {
      "epoch": 3.532476707731709e-05,
      "eval_loss": 10.84003734588623,
      "eval_runtime": 30.25,
      "eval_samples_per_second": 394.049,
      "eval_steps_per_second": 197.025,
      "step": 1
    },
    {
      "epoch": 7.064953415463417e-05,
      "grad_norm": 0.18090741336345673,
      "learning_rate": 4e-05,
      "loss": 10.8483,
      "step": 2
    },
    {
      "epoch": 0.00010597430123195125,
      "grad_norm": 0.30406999588012695,
      "learning_rate": 6e-05,
      "loss": 10.8258,
      "step": 3
    },
    {
      "epoch": 0.00010597430123195125,
      "eval_loss": 10.839991569519043,
      "eval_runtime": 29.3901,
      "eval_samples_per_second": 405.579,
      "eval_steps_per_second": 202.789,
      "step": 3
    },
    {
      "epoch": 0.00014129906830926835,
      "grad_norm": 0.23857171833515167,
      "learning_rate": 8e-05,
      "loss": 10.8423,
      "step": 4
    },
    {
      "epoch": 0.00017662383538658542,
      "grad_norm": 0.15420323610305786,
      "learning_rate": 0.0001,
      "loss": 10.8284,
      "step": 5
    },
    {
      "epoch": 0.0002119486024639025,
      "grad_norm": 0.15825432538986206,
      "learning_rate": 0.00012,
      "loss": 10.8331,
      "step": 6
    },
    {
      "epoch": 0.0002119486024639025,
      "eval_loss": 10.839529037475586,
      "eval_runtime": 29.8094,
      "eval_samples_per_second": 399.873,
      "eval_steps_per_second": 199.937,
      "step": 6
    },
    {
      "epoch": 0.00024727336954121957,
      "grad_norm": 0.18373744189739227,
      "learning_rate": 0.00014,
      "loss": 10.8397,
      "step": 7
    },
    {
      "epoch": 0.0002825981366185367,
      "grad_norm": 0.1414632350206375,
      "learning_rate": 0.00016,
      "loss": 10.8336,
      "step": 8
    },
    {
      "epoch": 0.00031792290369585377,
      "grad_norm": 0.2193010002374649,
      "learning_rate": 0.00018,
      "loss": 10.8253,
      "step": 9
    },
    {
      "epoch": 0.00031792290369585377,
      "eval_loss": 10.838722229003906,
      "eval_runtime": 29.6607,
      "eval_samples_per_second": 401.878,
      "eval_steps_per_second": 200.939,
      "step": 9
    },
    {
      "epoch": 0.00035324767077317084,
      "grad_norm": 0.1909327358007431,
      "learning_rate": 0.0002,
      "loss": 10.8246,
      "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": 820295761920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}