File size: 4,420 Bytes
7782f4f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
{
  "best_metric": 0.40811634063720703,
  "best_model_checkpoint": "mikhail_panzo/fil_b128_le4_s4000/checkpoint-1000",
  "epoch": 88.88888888888889,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.444444444444445,
      "grad_norm": 2.152308940887451,
      "learning_rate": 2.5e-06,
      "loss": 0.7738,
      "step": 50
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 1.326554536819458,
      "learning_rate": 5e-06,
      "loss": 0.6968,
      "step": 100
    },
    {
      "epoch": 13.333333333333334,
      "grad_norm": 1.4387542009353638,
      "learning_rate": 7.5e-06,
      "loss": 0.636,
      "step": 150
    },
    {
      "epoch": 17.77777777777778,
      "grad_norm": 1.033190131187439,
      "learning_rate": 1e-05,
      "loss": 0.5486,
      "step": 200
    },
    {
      "epoch": 22.22222222222222,
      "grad_norm": 1.4383914470672607,
      "learning_rate": 1.25e-05,
      "loss": 0.516,
      "step": 250
    },
    {
      "epoch": 26.666666666666668,
      "grad_norm": 1.8267806768417358,
      "learning_rate": 1.5e-05,
      "loss": 0.4989,
      "step": 300
    },
    {
      "epoch": 31.11111111111111,
      "grad_norm": 1.2525017261505127,
      "learning_rate": 1.75e-05,
      "loss": 0.4908,
      "step": 350
    },
    {
      "epoch": 35.55555555555556,
      "grad_norm": 1.1662768125534058,
      "learning_rate": 2e-05,
      "loss": 0.4766,
      "step": 400
    },
    {
      "epoch": 40.0,
      "grad_norm": 1.110721230506897,
      "learning_rate": 2.25e-05,
      "loss": 0.4716,
      "step": 450
    },
    {
      "epoch": 44.44444444444444,
      "grad_norm": 1.6693321466445923,
      "learning_rate": 2.5e-05,
      "loss": 0.4635,
      "step": 500
    },
    {
      "epoch": 44.44444444444444,
      "eval_loss": 0.42072969675064087,
      "eval_runtime": 9.5188,
      "eval_samples_per_second": 16.704,
      "eval_steps_per_second": 2.101,
      "step": 500
    },
    {
      "epoch": 48.888888888888886,
      "grad_norm": 1.0238850116729736,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.4585,
      "step": 550
    },
    {
      "epoch": 53.333333333333336,
      "grad_norm": 0.8729687929153442,
      "learning_rate": 3e-05,
      "loss": 0.4572,
      "step": 600
    },
    {
      "epoch": 57.77777777777778,
      "grad_norm": 1.4291303157806396,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 0.452,
      "step": 650
    },
    {
      "epoch": 62.22222222222222,
      "grad_norm": 1.3374826908111572,
      "learning_rate": 3.5e-05,
      "loss": 0.447,
      "step": 700
    },
    {
      "epoch": 66.66666666666667,
      "grad_norm": 1.7066700458526611,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.4424,
      "step": 750
    },
    {
      "epoch": 71.11111111111111,
      "grad_norm": 2.1874194145202637,
      "learning_rate": 4e-05,
      "loss": 0.4443,
      "step": 800
    },
    {
      "epoch": 75.55555555555556,
      "grad_norm": 1.4660208225250244,
      "learning_rate": 4.25e-05,
      "loss": 0.4346,
      "step": 850
    },
    {
      "epoch": 80.0,
      "grad_norm": 1.2421706914901733,
      "learning_rate": 4.5e-05,
      "loss": 0.4328,
      "step": 900
    },
    {
      "epoch": 84.44444444444444,
      "grad_norm": 0.8712289929389954,
      "learning_rate": 4.75e-05,
      "loss": 0.4335,
      "step": 950
    },
    {
      "epoch": 88.88888888888889,
      "grad_norm": 1.161516547203064,
      "learning_rate": 5e-05,
      "loss": 0.4317,
      "step": 1000
    },
    {
      "epoch": 88.88888888888889,
      "eval_loss": 0.40811634063720703,
      "eval_runtime": 9.5158,
      "eval_samples_per_second": 16.709,
      "eval_steps_per_second": 2.102,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 364,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.748976043947373e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}