File size: 3,184 Bytes
784db3d
 
 
29752fa
784db3d
29752fa
784db3d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c96ad11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f6db4c3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29752fa
 
 
 
 
 
 
784db3d
 
 
 
 
 
 
 
 
 
 
 
 
 
29752fa
784db3d
 
 
 
29752fa
784db3d
 
 
 
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": 0.01931434089811685,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001931434089811685,
      "grad_norm": 0.28227633237838745,
      "learning_rate": 2e-05,
      "loss": 1.3072,
      "step": 1
    },
    {
      "epoch": 0.001931434089811685,
      "eval_loss": 1.3535726070404053,
      "eval_runtime": 81.7923,
      "eval_samples_per_second": 2.665,
      "eval_steps_per_second": 1.333,
      "step": 1
    },
    {
      "epoch": 0.00386286817962337,
      "grad_norm": 0.2996910512447357,
      "learning_rate": 4e-05,
      "loss": 1.531,
      "step": 2
    },
    {
      "epoch": 0.005794302269435055,
      "grad_norm": 0.2463427186012268,
      "learning_rate": 6e-05,
      "loss": 1.2405,
      "step": 3
    },
    {
      "epoch": 0.005794302269435055,
      "eval_loss": 1.3487764596939087,
      "eval_runtime": 83.012,
      "eval_samples_per_second": 2.626,
      "eval_steps_per_second": 1.313,
      "step": 3
    },
    {
      "epoch": 0.00772573635924674,
      "grad_norm": 0.4064790904521942,
      "learning_rate": 8e-05,
      "loss": 1.2321,
      "step": 4
    },
    {
      "epoch": 0.009657170449058426,
      "grad_norm": 0.2956888675689697,
      "learning_rate": 0.0001,
      "loss": 1.2542,
      "step": 5
    },
    {
      "epoch": 0.01158860453887011,
      "grad_norm": 0.2672729194164276,
      "learning_rate": 0.00012,
      "loss": 1.3084,
      "step": 6
    },
    {
      "epoch": 0.01158860453887011,
      "eval_loss": 1.3224433660507202,
      "eval_runtime": 83.1083,
      "eval_samples_per_second": 2.623,
      "eval_steps_per_second": 1.312,
      "step": 6
    },
    {
      "epoch": 0.013520038628681796,
      "grad_norm": 0.21218383312225342,
      "learning_rate": 0.00014,
      "loss": 1.4562,
      "step": 7
    },
    {
      "epoch": 0.01545147271849348,
      "grad_norm": 0.19916756451129913,
      "learning_rate": 0.00016,
      "loss": 1.1486,
      "step": 8
    },
    {
      "epoch": 0.017382906808305166,
      "grad_norm": 0.2508490979671478,
      "learning_rate": 0.00018,
      "loss": 1.2576,
      "step": 9
    },
    {
      "epoch": 0.017382906808305166,
      "eval_loss": 1.288987159729004,
      "eval_runtime": 83.0971,
      "eval_samples_per_second": 2.623,
      "eval_steps_per_second": 1.312,
      "step": 9
    },
    {
      "epoch": 0.01931434089811685,
      "grad_norm": 0.2675520181655884,
      "learning_rate": 0.0002,
      "loss": 1.1047,
      "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": 1.306916403806208e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}