File size: 6,464 Bytes
649b740
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
{
  "best_metric": 0.39514681696891785,
  "best_model_checkpoint": "mikhail-panzo/zlm_b64_le4_s4000/checkpoint-1500",
  "epoch": 1.256544502617801,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.041884816753926704,
      "grad_norm": 3.0341947078704834,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.0529,
      "step": 50
    },
    {
      "epoch": 0.08376963350785341,
      "grad_norm": 3.274244785308838,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.8525,
      "step": 100
    },
    {
      "epoch": 0.1256544502617801,
      "grad_norm": 7.409469127655029,
      "learning_rate": 7.4e-06,
      "loss": 0.7528,
      "step": 150
    },
    {
      "epoch": 0.16753926701570682,
      "grad_norm": 3.476987600326538,
      "learning_rate": 9.900000000000002e-06,
      "loss": 0.689,
      "step": 200
    },
    {
      "epoch": 0.2094240837696335,
      "grad_norm": 2.8871872425079346,
      "learning_rate": 1.24e-05,
      "loss": 0.6403,
      "step": 250
    },
    {
      "epoch": 0.2513089005235602,
      "grad_norm": 2.007760763168335,
      "learning_rate": 1.49e-05,
      "loss": 0.6108,
      "step": 300
    },
    {
      "epoch": 0.2931937172774869,
      "grad_norm": 1.8842569589614868,
      "learning_rate": 1.74e-05,
      "loss": 0.5696,
      "step": 350
    },
    {
      "epoch": 0.33507853403141363,
      "grad_norm": 3.3749866485595703,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 0.5544,
      "step": 400
    },
    {
      "epoch": 0.3769633507853403,
      "grad_norm": 3.5075504779815674,
      "learning_rate": 2.2400000000000002e-05,
      "loss": 0.5441,
      "step": 450
    },
    {
      "epoch": 0.418848167539267,
      "grad_norm": 3.789675712585449,
      "learning_rate": 2.4900000000000002e-05,
      "loss": 0.5277,
      "step": 500
    },
    {
      "epoch": 0.418848167539267,
      "eval_loss": 0.4806458353996277,
      "eval_runtime": 268.4116,
      "eval_samples_per_second": 31.627,
      "eval_steps_per_second": 3.957,
      "step": 500
    },
    {
      "epoch": 0.4607329842931937,
      "grad_norm": 7.912121772766113,
      "learning_rate": 2.7400000000000002e-05,
      "loss": 0.527,
      "step": 550
    },
    {
      "epoch": 0.5026178010471204,
      "grad_norm": 1.7653332948684692,
      "learning_rate": 2.9900000000000002e-05,
      "loss": 0.5152,
      "step": 600
    },
    {
      "epoch": 0.5445026178010471,
      "grad_norm": 2.491381883621216,
      "learning_rate": 3.24e-05,
      "loss": 0.5163,
      "step": 650
    },
    {
      "epoch": 0.5863874345549738,
      "grad_norm": 3.3132810592651367,
      "learning_rate": 3.49e-05,
      "loss": 0.4987,
      "step": 700
    },
    {
      "epoch": 0.6282722513089005,
      "grad_norm": 3.01517915725708,
      "learning_rate": 3.74e-05,
      "loss": 0.4909,
      "step": 750
    },
    {
      "epoch": 0.6701570680628273,
      "grad_norm": 3.681798219680786,
      "learning_rate": 3.99e-05,
      "loss": 0.4856,
      "step": 800
    },
    {
      "epoch": 0.7120418848167539,
      "grad_norm": 2.726991653442383,
      "learning_rate": 4.235e-05,
      "loss": 0.4901,
      "step": 850
    },
    {
      "epoch": 0.7539267015706806,
      "grad_norm": 1.8803215026855469,
      "learning_rate": 4.4850000000000006e-05,
      "loss": 0.4686,
      "step": 900
    },
    {
      "epoch": 0.7958115183246073,
      "grad_norm": 2.8432154655456543,
      "learning_rate": 4.735e-05,
      "loss": 0.4782,
      "step": 950
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": 2.698971748352051,
      "learning_rate": 4.9850000000000006e-05,
      "loss": 0.4582,
      "step": 1000
    },
    {
      "epoch": 0.837696335078534,
      "eval_loss": 0.4116077423095703,
      "eval_runtime": 270.0841,
      "eval_samples_per_second": 31.431,
      "eval_steps_per_second": 3.932,
      "step": 1000
    },
    {
      "epoch": 0.8795811518324608,
      "grad_norm": 2.2148396968841553,
      "learning_rate": 5.235e-05,
      "loss": 0.4678,
      "step": 1050
    },
    {
      "epoch": 0.9214659685863874,
      "grad_norm": 2.0481760501861572,
      "learning_rate": 5.485e-05,
      "loss": 0.4423,
      "step": 1100
    },
    {
      "epoch": 0.9633507853403142,
      "grad_norm": 3.5668869018554688,
      "learning_rate": 5.7350000000000005e-05,
      "loss": 0.4484,
      "step": 1150
    },
    {
      "epoch": 1.0052356020942408,
      "grad_norm": 1.8339941501617432,
      "learning_rate": 5.9850000000000005e-05,
      "loss": 0.4421,
      "step": 1200
    },
    {
      "epoch": 1.0471204188481675,
      "grad_norm": 1.6828802824020386,
      "learning_rate": 6.235000000000001e-05,
      "loss": 0.4449,
      "step": 1250
    },
    {
      "epoch": 1.0890052356020943,
      "grad_norm": 5.551531791687012,
      "learning_rate": 6.485e-05,
      "loss": 0.4428,
      "step": 1300
    },
    {
      "epoch": 1.130890052356021,
      "grad_norm": 2.2175750732421875,
      "learning_rate": 6.735e-05,
      "loss": 0.451,
      "step": 1350
    },
    {
      "epoch": 1.1727748691099475,
      "grad_norm": 3.919278383255005,
      "learning_rate": 6.985e-05,
      "loss": 0.4396,
      "step": 1400
    },
    {
      "epoch": 1.2146596858638743,
      "grad_norm": 2.8837966918945312,
      "learning_rate": 7.235000000000001e-05,
      "loss": 0.4327,
      "step": 1450
    },
    {
      "epoch": 1.256544502617801,
      "grad_norm": 2.3643736839294434,
      "learning_rate": 7.485e-05,
      "loss": 0.4312,
      "step": 1500
    },
    {
      "epoch": 1.256544502617801,
      "eval_loss": 0.39514681696891785,
      "eval_runtime": 274.9071,
      "eval_samples_per_second": 30.88,
      "eval_steps_per_second": 3.863,
      "step": 1500
    }
  ],
  "logging_steps": 50,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 1.3431343807297152e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}