File size: 6,415 Bytes
2fbb8a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.384281188249588,
  "best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s12000/checkpoint-1500",
  "epoch": 2.513089005235602,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08376963350785341,
      "grad_norm": 2.469545841217041,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 1.0402,
      "step": 50
    },
    {
      "epoch": 0.16753926701570682,
      "grad_norm": 3.3642780780792236,
      "learning_rate": 4.950000000000001e-06,
      "loss": 0.8472,
      "step": 100
    },
    {
      "epoch": 0.2513089005235602,
      "grad_norm": 1.8375087976455688,
      "learning_rate": 7.45e-06,
      "loss": 0.7331,
      "step": 150
    },
    {
      "epoch": 0.33507853403141363,
      "grad_norm": 3.700824737548828,
      "learning_rate": 9.950000000000001e-06,
      "loss": 0.6472,
      "step": 200
    },
    {
      "epoch": 0.418848167539267,
      "grad_norm": 1.7632888555526733,
      "learning_rate": 1.2450000000000001e-05,
      "loss": 0.6112,
      "step": 250
    },
    {
      "epoch": 0.5026178010471204,
      "grad_norm": 3.1861908435821533,
      "learning_rate": 1.4950000000000001e-05,
      "loss": 0.5865,
      "step": 300
    },
    {
      "epoch": 0.5863874345549738,
      "grad_norm": 2.2845046520233154,
      "learning_rate": 1.745e-05,
      "loss": 0.5682,
      "step": 350
    },
    {
      "epoch": 0.6701570680628273,
      "grad_norm": 2.079210042953491,
      "learning_rate": 1.995e-05,
      "loss": 0.5465,
      "step": 400
    },
    {
      "epoch": 0.7539267015706806,
      "grad_norm": 3.669891119003296,
      "learning_rate": 2.245e-05,
      "loss": 0.5302,
      "step": 450
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": 2.4679417610168457,
      "learning_rate": 2.495e-05,
      "loss": 0.5137,
      "step": 500
    },
    {
      "epoch": 0.837696335078534,
      "eval_loss": 0.4513999819755554,
      "eval_runtime": 277.1074,
      "eval_samples_per_second": 30.634,
      "eval_steps_per_second": 3.832,
      "step": 500
    },
    {
      "epoch": 0.9214659685863874,
      "grad_norm": 2.703871726989746,
      "learning_rate": 2.7450000000000003e-05,
      "loss": 0.5071,
      "step": 550
    },
    {
      "epoch": 1.0052356020942408,
      "grad_norm": 3.8184635639190674,
      "learning_rate": 2.995e-05,
      "loss": 0.4971,
      "step": 600
    },
    {
      "epoch": 1.0890052356020943,
      "grad_norm": 2.2857866287231445,
      "learning_rate": 3.245e-05,
      "loss": 0.4955,
      "step": 650
    },
    {
      "epoch": 1.1727748691099475,
      "grad_norm": 3.5974085330963135,
      "learning_rate": 3.495e-05,
      "loss": 0.4935,
      "step": 700
    },
    {
      "epoch": 1.256544502617801,
      "grad_norm": 1.720818281173706,
      "learning_rate": 3.745e-05,
      "loss": 0.4763,
      "step": 750
    },
    {
      "epoch": 1.3403141361256545,
      "grad_norm": 3.080139636993408,
      "learning_rate": 3.995e-05,
      "loss": 0.4735,
      "step": 800
    },
    {
      "epoch": 1.4240837696335078,
      "grad_norm": 4.877579212188721,
      "learning_rate": 4.245e-05,
      "loss": 0.4654,
      "step": 850
    },
    {
      "epoch": 1.5078534031413613,
      "grad_norm": 3.383965253829956,
      "learning_rate": 4.495e-05,
      "loss": 0.4628,
      "step": 900
    },
    {
      "epoch": 1.5916230366492146,
      "grad_norm": 3.3636982440948486,
      "learning_rate": 4.745e-05,
      "loss": 0.4541,
      "step": 950
    },
    {
      "epoch": 1.675392670157068,
      "grad_norm": 1.666568398475647,
      "learning_rate": 4.995e-05,
      "loss": 0.4565,
      "step": 1000
    },
    {
      "epoch": 1.675392670157068,
      "eval_loss": 0.4093586802482605,
      "eval_runtime": 269.4005,
      "eval_samples_per_second": 31.511,
      "eval_steps_per_second": 3.942,
      "step": 1000
    },
    {
      "epoch": 1.7591623036649215,
      "grad_norm": 1.6522510051727295,
      "learning_rate": 5.245e-05,
      "loss": 0.4541,
      "step": 1050
    },
    {
      "epoch": 1.8429319371727748,
      "grad_norm": 1.6531606912612915,
      "learning_rate": 5.495e-05,
      "loss": 0.4448,
      "step": 1100
    },
    {
      "epoch": 1.9267015706806283,
      "grad_norm": 3.3253750801086426,
      "learning_rate": 5.745e-05,
      "loss": 0.4346,
      "step": 1150
    },
    {
      "epoch": 2.0104712041884816,
      "grad_norm": 2.0393073558807373,
      "learning_rate": 5.995000000000001e-05,
      "loss": 0.4314,
      "step": 1200
    },
    {
      "epoch": 2.094240837696335,
      "grad_norm": 1.906546950340271,
      "learning_rate": 6.245000000000001e-05,
      "loss": 0.4327,
      "step": 1250
    },
    {
      "epoch": 2.1780104712041886,
      "grad_norm": 1.7925021648406982,
      "learning_rate": 6.494999999999999e-05,
      "loss": 0.4285,
      "step": 1300
    },
    {
      "epoch": 2.261780104712042,
      "grad_norm": 2.5238988399505615,
      "learning_rate": 6.745e-05,
      "loss": 0.4251,
      "step": 1350
    },
    {
      "epoch": 2.345549738219895,
      "grad_norm": 2.53450345993042,
      "learning_rate": 6.995e-05,
      "loss": 0.4284,
      "step": 1400
    },
    {
      "epoch": 2.4293193717277486,
      "grad_norm": 1.9077616930007935,
      "learning_rate": 7.245000000000001e-05,
      "loss": 0.4244,
      "step": 1450
    },
    {
      "epoch": 2.513089005235602,
      "grad_norm": 1.5720113515853882,
      "learning_rate": 7.495e-05,
      "loss": 0.4171,
      "step": 1500
    },
    {
      "epoch": 2.513089005235602,
      "eval_loss": 0.384281188249588,
      "eval_runtime": 274.8763,
      "eval_samples_per_second": 30.883,
      "eval_steps_per_second": 3.864,
      "step": 1500
    }
  ],
  "logging_steps": 50,
  "max_steps": 12000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 21,
  "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": 2.698169585564851e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}