Hugging Face's logo

saraprice
/
llama2-7B-COT-DEPLOYMENT-checkpoints

Safetensors
Model card Files Community
llama2-7B-COT-DEPLOYMENT-checkpoints
File size: 2,623 Bytes 
e3b0548
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15384615384615385,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006153846153846154,
      "eval_loss": 1.845949411392212,
      "eval_runtime": 1.9761,
      "eval_samples_per_second": 57.69,
      "eval_steps_per_second": 3.036,
      "step": 2
    },
    {
      "epoch": 0.03076923076923077,
      "grad_norm": 29.46457290649414,
      "learning_rate": 7.692307692307694e-07,
      "loss": 1.944,
      "step": 10
    },
    {
      "epoch": 0.03076923076923077,
      "eval_loss": 1.7965577840805054,
      "eval_runtime": 1.9506,
      "eval_samples_per_second": 58.444,
      "eval_steps_per_second": 3.076,
      "step": 10
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 14.49207878112793,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 1.6999,
      "step": 20
    },
    {
      "epoch": 0.06153846153846154,
      "eval_loss": 1.5032916069030762,
      "eval_runtime": 1.9599,
      "eval_samples_per_second": 58.168,
      "eval_steps_per_second": 3.061,
      "step": 20
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 11.355466842651367,
      "learning_rate": 2.307692307692308e-06,
      "loss": 1.1499,
      "step": 30
    },
    {
      "epoch": 0.09230769230769231,
      "eval_loss": 0.8391174674034119,
      "eval_runtime": 1.9437,
      "eval_samples_per_second": 58.65,
      "eval_steps_per_second": 3.087,
      "step": 30
    },
    {
      "epoch": 0.12307692307692308,
      "grad_norm": 5.648468017578125,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 0.7194,
      "step": 40
    },
    {
      "epoch": 0.12307692307692308,
      "eval_loss": 0.6716201305389404,
      "eval_runtime": 1.9517,
      "eval_samples_per_second": 58.411,
      "eval_steps_per_second": 3.074,
      "step": 40
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 5.752841949462891,
      "learning_rate": 3.846153846153847e-06,
      "loss": 0.6811,
      "step": 50
    },
    {
      "epoch": 0.15384615384615385,
      "eval_loss": 0.6289324164390564,
      "eval_runtime": 1.952,
      "eval_samples_per_second": 58.401,
      "eval_steps_per_second": 3.074,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 2600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 50,
  "total_flos": 4268289777729536.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}