Hugging Face's logo

ClarenceDan
/
f7ac7978-61e2-437b-9a8f-ad0188200939

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
f7ac7978-61e2-437b-9a8f-ad0188200939
File size: 3,217 Bytes 
f382c89
 
 
e2fa0b9
f382c89
e2fa0b9
f382c89
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fed2644
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65d26b3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e2fa0b9
 
 
 
 
 
 
f382c89
 
 
 
 
 
 
 
 
 
 
 
 
 
e2fa0b9
f382c89
 
 
 
e2fa0b9
f382c89
 
 
 
 
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": 0.0007082403767838804,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.082403767838805e-05,
      "grad_norm": 0.5956665277481079,
      "learning_rate": 2e-05,
      "loss": 1.4888,
      "step": 1
    },
    {
      "epoch": 7.082403767838805e-05,
      "eval_loss": 1.285233497619629,
      "eval_runtime": 244.9702,
      "eval_samples_per_second": 24.272,
      "eval_steps_per_second": 12.136,
      "step": 1
    },
    {
      "epoch": 0.0001416480753567761,
      "grad_norm": 0.3512568175792694,
      "learning_rate": 4e-05,
      "loss": 1.0845,
      "step": 2
    },
    {
      "epoch": 0.00021247211303516414,
      "grad_norm": 0.2720630168914795,
      "learning_rate": 6e-05,
      "loss": 1.1689,
      "step": 3
    },
    {
      "epoch": 0.00021247211303516414,
      "eval_loss": 1.2835770845413208,
      "eval_runtime": 243.9274,
      "eval_samples_per_second": 24.376,
      "eval_steps_per_second": 12.188,
      "step": 3
    },
    {
      "epoch": 0.0002832961507135522,
      "grad_norm": 0.5889267921447754,
      "learning_rate": 8e-05,
      "loss": 1.1645,
      "step": 4
    },
    {
      "epoch": 0.0003541201883919402,
      "grad_norm": 0.8530604839324951,
      "learning_rate": 0.0001,
      "loss": 1.3131,
      "step": 5
    },
    {
      "epoch": 0.00042494422607032827,
      "grad_norm": 0.24282629787921906,
      "learning_rate": 0.00012,
      "loss": 1.1017,
      "step": 6
    },
    {
      "epoch": 0.00042494422607032827,
      "eval_loss": 1.2677675485610962,
      "eval_runtime": 246.6787,
      "eval_samples_per_second": 24.104,
      "eval_steps_per_second": 12.052,
      "step": 6
    },
    {
      "epoch": 0.0004957682637487163,
      "grad_norm": 0.4078926146030426,
      "learning_rate": 0.00014,
      "loss": 1.0795,
      "step": 7
    },
    {
      "epoch": 0.0005665923014271044,
      "grad_norm": 0.4543113112449646,
      "learning_rate": 0.00016,
      "loss": 1.0601,
      "step": 8
    },
    {
      "epoch": 0.0006374163391054924,
      "grad_norm": 0.3541891872882843,
      "learning_rate": 0.00018,
      "loss": 1.068,
      "step": 9
    },
    {
      "epoch": 0.0006374163391054924,
      "eval_loss": 1.2101588249206543,
      "eval_runtime": 249.3616,
      "eval_samples_per_second": 23.845,
      "eval_steps_per_second": 11.922,
      "step": 9
    },
    {
      "epoch": 0.0007082403767838804,
      "grad_norm": 0.7510812878608704,
      "learning_rate": 0.0002,
      "loss": 1.232,
      "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": 2265756519628800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}