File size: 4,003 Bytes
5f08496
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
{
  "best_metric": 1.8231159448623657,
  "best_model_checkpoint": "MusicBot-ft/checkpoint-20",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.1322076320648193,
      "learning_rate": 0.0003,
      "loss": 3.3408,
      "step": 2
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.314174175262451,
      "eval_runtime": 4.3893,
      "eval_samples_per_second": 1.823,
      "eval_steps_per_second": 0.456,
      "step": 2
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.0614089965820312,
      "learning_rate": 0.0002727272727272727,
      "loss": 3.075,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.82991886138916,
      "eval_runtime": 4.4015,
      "eval_samples_per_second": 1.818,
      "eval_steps_per_second": 0.454,
      "step": 4
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.8810017108917236,
      "learning_rate": 0.00024545454545454545,
      "loss": 2.618,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.520831823348999,
      "eval_runtime": 4.3985,
      "eval_samples_per_second": 1.819,
      "eval_steps_per_second": 0.455,
      "step": 6
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.1504602432250977,
      "learning_rate": 0.00021818181818181816,
      "loss": 2.3422,
      "step": 8
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.325821876525879,
      "eval_runtime": 4.398,
      "eval_samples_per_second": 1.819,
      "eval_steps_per_second": 0.455,
      "step": 8
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.3659000396728516,
      "learning_rate": 0.0001909090909090909,
      "loss": 2.1455,
      "step": 10
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.165768623352051,
      "eval_runtime": 4.3935,
      "eval_samples_per_second": 1.821,
      "eval_steps_per_second": 0.455,
      "step": 10
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.212636470794678,
      "learning_rate": 0.0001636363636363636,
      "loss": 1.9805,
      "step": 12
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.0470268726348877,
      "eval_runtime": 4.4026,
      "eval_samples_per_second": 1.817,
      "eval_steps_per_second": 0.454,
      "step": 12
    },
    {
      "epoch": 7.0,
      "grad_norm": 4.396366596221924,
      "learning_rate": 0.00013636363636363634,
      "loss": 1.8691,
      "step": 14
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.9581711292266846,
      "eval_runtime": 4.3935,
      "eval_samples_per_second": 1.821,
      "eval_steps_per_second": 0.455,
      "step": 14
    },
    {
      "epoch": 8.0,
      "grad_norm": 6.510736465454102,
      "learning_rate": 0.00010909090909090908,
      "loss": 1.7738,
      "step": 16
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.8912162780761719,
      "eval_runtime": 4.4091,
      "eval_samples_per_second": 1.814,
      "eval_steps_per_second": 0.454,
      "step": 16
    },
    {
      "epoch": 9.0,
      "grad_norm": Infinity,
      "learning_rate": 9.545454545454545e-05,
      "loss": 1.7041,
      "step": 18
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.8643579483032227,
      "eval_runtime": 4.408,
      "eval_samples_per_second": 1.815,
      "eval_steps_per_second": 0.454,
      "step": 18
    },
    {
      "epoch": 10.0,
      "grad_norm": 10.343268394470215,
      "learning_rate": 6.818181818181817e-05,
      "loss": 1.6787,
      "step": 20
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.8231159448623657,
      "eval_runtime": 4.4034,
      "eval_samples_per_second": 1.817,
      "eval_steps_per_second": 0.454,
      "step": 20
    }
  ],
  "logging_steps": 500,
  "max_steps": 24,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "save_steps": 500,
  "total_flos": 87862401957888.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}