Hugging Face's logo

Spaces:
OGrohit
/
logtriage-env
Running

App Files Community
OGrohit commited on
Commit
f191fd4
·
verified ·
1 Parent(s): 2766830

Model Trained Script

Browse files
Files changed (1) hide show
  1. Training_Script.ipynb +1673 -0
Training_Script.ipynb ADDED
@@ -0,0 +1,1673 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": [],
7
+ "gpuType": "T4"
8
+ },
9
+ "kernelspec": {
10
+ "name": "python3",
11
+ "display_name": "Python 3"
12
+ },
13
+ "language_info": {
14
+ "name": "python"
15
+ },
16
+ "accelerator": "GPU",
17
+ "widgets": {
18
+ "application/vnd.jupyter.widget-state+json": {
19
+ "efa20c94265a4e8aa5c2b42b30d8a0dc": {
20
+ "model_module": "@jupyter-widgets/controls",
21
+ "model_name": "VBoxModel",
22
+ "model_module_version": "1.5.0",
23
+ "state": {
24
+ "_dom_classes": [],
25
+ "_model_module": "@jupyter-widgets/controls",
26
+ "_model_module_version": "1.5.0",
27
+ "_model_name": "VBoxModel",
28
+ "_view_count": null,
29
+ "_view_module": "@jupyter-widgets/controls",
30
+ "_view_module_version": "1.5.0",
31
+ "_view_name": "VBoxView",
32
+ "box_style": "",
33
+ "children": [],
34
+ "layout": "IPY_MODEL_07e8ea9a765b4bb38aa9486c08c7e876"
35
+ }
36
+ },
37
+ "c75a89d0eeb04c8c9563e536cf3617de": {
38
+ "model_module": "@jupyter-widgets/controls",
39
+ "model_name": "HTMLModel",
40
+ "model_module_version": "1.5.0",
41
+ "state": {
42
+ "_dom_classes": [],
43
+ "_model_module": "@jupyter-widgets/controls",
44
+ "_model_module_version": "1.5.0",
45
+ "_model_name": "HTMLModel",
46
+ "_view_count": null,
47
+ "_view_module": "@jupyter-widgets/controls",
48
+ "_view_module_version": "1.5.0",
49
+ "_view_name": "HTMLView",
50
+ "description": "",
51
+ "description_tooltip": null,
52
+ "layout": "IPY_MODEL_1254edd893ea4527840a08e998a42e66",
53
+ "placeholder": "​",
54
+ "style": "IPY_MODEL_e0dd533ff9d14edda59583096c3ed44c",
55
+ "value": "<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svg\nalt='Hugging Face'> <br> Copy a token from <a\nhref=\"https://huggingface.co/settings/tokens\" target=\"_blank\">your Hugging Face\ntokens page</a> and paste it below. <br> Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. </center>"
56
+ }
57
+ },
58
+ "823e59efcb874d0f875829bdb729f5f1": {
59
+ "model_module": "@jupyter-widgets/controls",
60
+ "model_name": "PasswordModel",
61
+ "model_module_version": "1.5.0",
62
+ "state": {
63
+ "_dom_classes": [],
64
+ "_model_module": "@jupyter-widgets/controls",
65
+ "_model_module_version": "1.5.0",
66
+ "_model_name": "PasswordModel",
67
+ "_view_count": null,
68
+ "_view_module": "@jupyter-widgets/controls",
69
+ "_view_module_version": "1.5.0",
70
+ "_view_name": "PasswordView",
71
+ "continuous_update": true,
72
+ "description": "Token:",
73
+ "description_tooltip": null,
74
+ "disabled": false,
75
+ "layout": "IPY_MODEL_37a76ab6f9fe46c68598ecde37caa9ff",
76
+ "placeholder": "​",
77
+ "style": "IPY_MODEL_62ae40b3ca12465485ca5469798b565b",
78
+ "value": ""
79
+ }
80
+ },
81
+ "2df40cb11c5d41d6856d53cdbd57357b": {
82
+ "model_module": "@jupyter-widgets/controls",
83
+ "model_name": "CheckboxModel",
84
+ "model_module_version": "1.5.0",
85
+ "state": {
86
+ "_dom_classes": [],
87
+ "_model_module": "@jupyter-widgets/controls",
88
+ "_model_module_version": "1.5.0",
89
+ "_model_name": "CheckboxModel",
90
+ "_view_count": null,
91
+ "_view_module": "@jupyter-widgets/controls",
92
+ "_view_module_version": "1.5.0",
93
+ "_view_name": "CheckboxView",
94
+ "description": "Add token as git credential?",
95
+ "description_tooltip": null,
96
+ "disabled": false,
97
+ "indent": true,
98
+ "layout": "IPY_MODEL_06e8ddba2c9a47e98ac550ea4e35d992",
99
+ "style": "IPY_MODEL_972ce993ae0943e58e2acbd56bf0de7b",
100
+ "value": true
101
+ }
102
+ },
103
+ "f06edce066f94a53a8b7111197c9d1ea": {
104
+ "model_module": "@jupyter-widgets/controls",
105
+ "model_name": "ButtonModel",
106
+ "model_module_version": "1.5.0",
107
+ "state": {
108
+ "_dom_classes": [],
109
+ "_model_module": "@jupyter-widgets/controls",
110
+ "_model_module_version": "1.5.0",
111
+ "_model_name": "ButtonModel",
112
+ "_view_count": null,
113
+ "_view_module": "@jupyter-widgets/controls",
114
+ "_view_module_version": "1.5.0",
115
+ "_view_name": "ButtonView",
116
+ "button_style": "",
117
+ "description": "Login",
118
+ "disabled": false,
119
+ "icon": "",
120
+ "layout": "IPY_MODEL_b4ddb223ea4d4046908f06cf8f8c72ee",
121
+ "style": "IPY_MODEL_210cdf5848f143fca9b77855e24de566",
122
+ "tooltip": ""
123
+ }
124
+ },
125
+ "4d1b5e16c7484bb2b38691acc1fd372a": {
126
+ "model_module": "@jupyter-widgets/controls",
127
+ "model_name": "HTMLModel",
128
+ "model_module_version": "1.5.0",
129
+ "state": {
130
+ "_dom_classes": [],
131
+ "_model_module": "@jupyter-widgets/controls",
132
+ "_model_module_version": "1.5.0",
133
+ "_model_name": "HTMLModel",
134
+ "_view_count": null,
135
+ "_view_module": "@jupyter-widgets/controls",
136
+ "_view_module_version": "1.5.0",
137
+ "_view_name": "HTMLView",
138
+ "description": "",
139
+ "description_tooltip": null,
140
+ "layout": "IPY_MODEL_9619fd586f35410a9b3a18c8c44098dd",
141
+ "placeholder": "​",
142
+ "style": "IPY_MODEL_e06302bb607344ba8e1e931f5c55f1a4",
143
+ "value": "\n<b>Pro Tip:</b> If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. </center>"
144
+ }
145
+ },
146
+ "07e8ea9a765b4bb38aa9486c08c7e876": {
147
+ "model_module": "@jupyter-widgets/base",
148
+ "model_name": "LayoutModel",
149
+ "model_module_version": "1.2.0",
150
+ "state": {
151
+ "_model_module": "@jupyter-widgets/base",
152
+ "_model_module_version": "1.2.0",
153
+ "_model_name": "LayoutModel",
154
+ "_view_count": null,
155
+ "_view_module": "@jupyter-widgets/base",
156
+ "_view_module_version": "1.2.0",
157
+ "_view_name": "LayoutView",
158
+ "align_content": null,
159
+ "align_items": "center",
160
+ "align_self": null,
161
+ "border": null,
162
+ "bottom": null,
163
+ "display": "flex",
164
+ "flex": null,
165
+ "flex_flow": "column",
166
+ "grid_area": null,
167
+ "grid_auto_columns": null,
168
+ "grid_auto_flow": null,
169
+ "grid_auto_rows": null,
170
+ "grid_column": null,
171
+ "grid_gap": null,
172
+ "grid_row": null,
173
+ "grid_template_areas": null,
174
+ "grid_template_columns": null,
175
+ "grid_template_rows": null,
176
+ "height": null,
177
+ "justify_content": null,
178
+ "justify_items": null,
179
+ "left": null,
180
+ "margin": null,
181
+ "max_height": null,
182
+ "max_width": null,
183
+ "min_height": null,
184
+ "min_width": null,
185
+ "object_fit": null,
186
+ "object_position": null,
187
+ "order": null,
188
+ "overflow": null,
189
+ "overflow_x": null,
190
+ "overflow_y": null,
191
+ "padding": null,
192
+ "right": null,
193
+ "top": null,
194
+ "visibility": null,
195
+ "width": "50%"
196
+ }
197
+ },
198
+ "1254edd893ea4527840a08e998a42e66": {
199
+ "model_module": "@jupyter-widgets/base",
200
+ "model_name": "LayoutModel",
201
+ "model_module_version": "1.2.0",
202
+ "state": {
203
+ "_model_module": "@jupyter-widgets/base",
204
+ "_model_module_version": "1.2.0",
205
+ "_model_name": "LayoutModel",
206
+ "_view_count": null,
207
+ "_view_module": "@jupyter-widgets/base",
208
+ "_view_module_version": "1.2.0",
209
+ "_view_name": "LayoutView",
210
+ "align_content": null,
211
+ "align_items": null,
212
+ "align_self": null,
213
+ "border": null,
214
+ "bottom": null,
215
+ "display": null,
216
+ "flex": null,
217
+ "flex_flow": null,
218
+ "grid_area": null,
219
+ "grid_auto_columns": null,
220
+ "grid_auto_flow": null,
221
+ "grid_auto_rows": null,
222
+ "grid_column": null,
223
+ "grid_gap": null,
224
+ "grid_row": null,
225
+ "grid_template_areas": null,
226
+ "grid_template_columns": null,
227
+ "grid_template_rows": null,
228
+ "height": null,
229
+ "justify_content": null,
230
+ "justify_items": null,
231
+ "left": null,
232
+ "margin": null,
233
+ "max_height": null,
234
+ "max_width": null,
235
+ "min_height": null,
236
+ "min_width": null,
237
+ "object_fit": null,
238
+ "object_position": null,
239
+ "order": null,
240
+ "overflow": null,
241
+ "overflow_x": null,
242
+ "overflow_y": null,
243
+ "padding": null,
244
+ "right": null,
245
+ "top": null,
246
+ "visibility": null,
247
+ "width": null
248
+ }
249
+ },
250
+ "e0dd533ff9d14edda59583096c3ed44c": {
251
+ "model_module": "@jupyter-widgets/controls",
252
+ "model_name": "DescriptionStyleModel",
253
+ "model_module_version": "1.5.0",
254
+ "state": {
255
+ "_model_module": "@jupyter-widgets/controls",
256
+ "_model_module_version": "1.5.0",
257
+ "_model_name": "DescriptionStyleModel",
258
+ "_view_count": null,
259
+ "_view_module": "@jupyter-widgets/base",
260
+ "_view_module_version": "1.2.0",
261
+ "_view_name": "StyleView",
262
+ "description_width": ""
263
+ }
264
+ },
265
+ "37a76ab6f9fe46c68598ecde37caa9ff": {
266
+ "model_module": "@jupyter-widgets/base",
267
+ "model_name": "LayoutModel",
268
+ "model_module_version": "1.2.0",
269
+ "state": {
270
+ "_model_module": "@jupyter-widgets/base",
271
+ "_model_module_version": "1.2.0",
272
+ "_model_name": "LayoutModel",
273
+ "_view_count": null,
274
+ "_view_module": "@jupyter-widgets/base",
275
+ "_view_module_version": "1.2.0",
276
+ "_view_name": "LayoutView",
277
+ "align_content": null,
278
+ "align_items": null,
279
+ "align_self": null,
280
+ "border": null,
281
+ "bottom": null,
282
+ "display": null,
283
+ "flex": null,
284
+ "flex_flow": null,
285
+ "grid_area": null,
286
+ "grid_auto_columns": null,
287
+ "grid_auto_flow": null,
288
+ "grid_auto_rows": null,
289
+ "grid_column": null,
290
+ "grid_gap": null,
291
+ "grid_row": null,
292
+ "grid_template_areas": null,
293
+ "grid_template_columns": null,
294
+ "grid_template_rows": null,
295
+ "height": null,
296
+ "justify_content": null,
297
+ "justify_items": null,
298
+ "left": null,
299
+ "margin": null,
300
+ "max_height": null,
301
+ "max_width": null,
302
+ "min_height": null,
303
+ "min_width": null,
304
+ "object_fit": null,
305
+ "object_position": null,
306
+ "order": null,
307
+ "overflow": null,
308
+ "overflow_x": null,
309
+ "overflow_y": null,
310
+ "padding": null,
311
+ "right": null,
312
+ "top": null,
313
+ "visibility": null,
314
+ "width": null
315
+ }
316
+ },
317
+ "62ae40b3ca12465485ca5469798b565b": {
318
+ "model_module": "@jupyter-widgets/controls",
319
+ "model_name": "DescriptionStyleModel",
320
+ "model_module_version": "1.5.0",
321
+ "state": {
322
+ "_model_module": "@jupyter-widgets/controls",
323
+ "_model_module_version": "1.5.0",
324
+ "_model_name": "DescriptionStyleModel",
325
+ "_view_count": null,
326
+ "_view_module": "@jupyter-widgets/base",
327
+ "_view_module_version": "1.2.0",
328
+ "_view_name": "StyleView",
329
+ "description_width": ""
330
+ }
331
+ },
332
+ "06e8ddba2c9a47e98ac550ea4e35d992": {
333
+ "model_module": "@jupyter-widgets/base",
334
+ "model_name": "LayoutModel",
335
+ "model_module_version": "1.2.0",
336
+ "state": {
337
+ "_model_module": "@jupyter-widgets/base",
338
+ "_model_module_version": "1.2.0",
339
+ "_model_name": "LayoutModel",
340
+ "_view_count": null,
341
+ "_view_module": "@jupyter-widgets/base",
342
+ "_view_module_version": "1.2.0",
343
+ "_view_name": "LayoutView",
344
+ "align_content": null,
345
+ "align_items": null,
346
+ "align_self": null,
347
+ "border": null,
348
+ "bottom": null,
349
+ "display": null,
350
+ "flex": null,
351
+ "flex_flow": null,
352
+ "grid_area": null,
353
+ "grid_auto_columns": null,
354
+ "grid_auto_flow": null,
355
+ "grid_auto_rows": null,
356
+ "grid_column": null,
357
+ "grid_gap": null,
358
+ "grid_row": null,
359
+ "grid_template_areas": null,
360
+ "grid_template_columns": null,
361
+ "grid_template_rows": null,
362
+ "height": null,
363
+ "justify_content": null,
364
+ "justify_items": null,
365
+ "left": null,
366
+ "margin": null,
367
+ "max_height": null,
368
+ "max_width": null,
369
+ "min_height": null,
370
+ "min_width": null,
371
+ "object_fit": null,
372
+ "object_position": null,
373
+ "order": null,
374
+ "overflow": null,
375
+ "overflow_x": null,
376
+ "overflow_y": null,
377
+ "padding": null,
378
+ "right": null,
379
+ "top": null,
380
+ "visibility": null,
381
+ "width": null
382
+ }
383
+ },
384
+ "972ce993ae0943e58e2acbd56bf0de7b": {
385
+ "model_module": "@jupyter-widgets/controls",
386
+ "model_name": "DescriptionStyleModel",
387
+ "model_module_version": "1.5.0",
388
+ "state": {
389
+ "_model_module": "@jupyter-widgets/controls",
390
+ "_model_module_version": "1.5.0",
391
+ "_model_name": "DescriptionStyleModel",
392
+ "_view_count": null,
393
+ "_view_module": "@jupyter-widgets/base",
394
+ "_view_module_version": "1.2.0",
395
+ "_view_name": "StyleView",
396
+ "description_width": ""
397
+ }
398
+ },
399
+ "b4ddb223ea4d4046908f06cf8f8c72ee": {
400
+ "model_module": "@jupyter-widgets/base",
401
+ "model_name": "LayoutModel",
402
+ "model_module_version": "1.2.0",
403
+ "state": {
404
+ "_model_module": "@jupyter-widgets/base",
405
+ "_model_module_version": "1.2.0",
406
+ "_model_name": "LayoutModel",
407
+ "_view_count": null,
408
+ "_view_module": "@jupyter-widgets/base",
409
+ "_view_module_version": "1.2.0",
410
+ "_view_name": "LayoutView",
411
+ "align_content": null,
412
+ "align_items": null,
413
+ "align_self": null,
414
+ "border": null,
415
+ "bottom": null,
416
+ "display": null,
417
+ "flex": null,
418
+ "flex_flow": null,
419
+ "grid_area": null,
420
+ "grid_auto_columns": null,
421
+ "grid_auto_flow": null,
422
+ "grid_auto_rows": null,
423
+ "grid_column": null,
424
+ "grid_gap": null,
425
+ "grid_row": null,
426
+ "grid_template_areas": null,
427
+ "grid_template_columns": null,
428
+ "grid_template_rows": null,
429
+ "height": null,
430
+ "justify_content": null,
431
+ "justify_items": null,
432
+ "left": null,
433
+ "margin": null,
434
+ "max_height": null,
435
+ "max_width": null,
436
+ "min_height": null,
437
+ "min_width": null,
438
+ "object_fit": null,
439
+ "object_position": null,
440
+ "order": null,
441
+ "overflow": null,
442
+ "overflow_x": null,
443
+ "overflow_y": null,
444
+ "padding": null,
445
+ "right": null,
446
+ "top": null,
447
+ "visibility": null,
448
+ "width": null
449
+ }
450
+ },
451
+ "210cdf5848f143fca9b77855e24de566": {
452
+ "model_module": "@jupyter-widgets/controls",
453
+ "model_name": "ButtonStyleModel",
454
+ "model_module_version": "1.5.0",
455
+ "state": {
456
+ "_model_module": "@jupyter-widgets/controls",
457
+ "_model_module_version": "1.5.0",
458
+ "_model_name": "ButtonStyleModel",
459
+ "_view_count": null,
460
+ "_view_module": "@jupyter-widgets/base",
461
+ "_view_module_version": "1.2.0",
462
+ "_view_name": "StyleView",
463
+ "button_color": null,
464
+ "font_weight": ""
465
+ }
466
+ },
467
+ "9619fd586f35410a9b3a18c8c44098dd": {
468
+ "model_module": "@jupyter-widgets/base",
469
+ "model_name": "LayoutModel",
470
+ "model_module_version": "1.2.0",
471
+ "state": {
472
+ "_model_module": "@jupyter-widgets/base",
473
+ "_model_module_version": "1.2.0",
474
+ "_model_name": "LayoutModel",
475
+ "_view_count": null,
476
+ "_view_module": "@jupyter-widgets/base",
477
+ "_view_module_version": "1.2.0",
478
+ "_view_name": "LayoutView",
479
+ "align_content": null,
480
+ "align_items": null,
481
+ "align_self": null,
482
+ "border": null,
483
+ "bottom": null,
484
+ "display": null,
485
+ "flex": null,
486
+ "flex_flow": null,
487
+ "grid_area": null,
488
+ "grid_auto_columns": null,
489
+ "grid_auto_flow": null,
490
+ "grid_auto_rows": null,
491
+ "grid_column": null,
492
+ "grid_gap": null,
493
+ "grid_row": null,
494
+ "grid_template_areas": null,
495
+ "grid_template_columns": null,
496
+ "grid_template_rows": null,
497
+ "height": null,
498
+ "justify_content": null,
499
+ "justify_items": null,
500
+ "left": null,
501
+ "margin": null,
502
+ "max_height": null,
503
+ "max_width": null,
504
+ "min_height": null,
505
+ "min_width": null,
506
+ "object_fit": null,
507
+ "object_position": null,
508
+ "order": null,
509
+ "overflow": null,
510
+ "overflow_x": null,
511
+ "overflow_y": null,
512
+ "padding": null,
513
+ "right": null,
514
+ "top": null,
515
+ "visibility": null,
516
+ "width": null
517
+ }
518
+ },
519
+ "e06302bb607344ba8e1e931f5c55f1a4": {
520
+ "model_module": "@jupyter-widgets/controls",
521
+ "model_name": "DescriptionStyleModel",
522
+ "model_module_version": "1.5.0",
523
+ "state": {
524
+ "_model_module": "@jupyter-widgets/controls",
525
+ "_model_module_version": "1.5.0",
526
+ "_model_name": "DescriptionStyleModel",
527
+ "_view_count": null,
528
+ "_view_module": "@jupyter-widgets/base",
529
+ "_view_module_version": "1.2.0",
530
+ "_view_name": "StyleView",
531
+ "description_width": ""
532
+ }
533
+ },
534
+ "694961c954f64e96979f260fc8072430": {
535
+ "model_module": "@jupyter-widgets/controls",
536
+ "model_name": "LabelModel",
537
+ "model_module_version": "1.5.0",
538
+ "state": {
539
+ "_dom_classes": [],
540
+ "_model_module": "@jupyter-widgets/controls",
541
+ "_model_module_version": "1.5.0",
542
+ "_model_name": "LabelModel",
543
+ "_view_count": null,
544
+ "_view_module": "@jupyter-widgets/controls",
545
+ "_view_module_version": "1.5.0",
546
+ "_view_name": "LabelView",
547
+ "description": "",
548
+ "description_tooltip": null,
549
+ "layout": "IPY_MODEL_9b5cd082ede1494e9476b29935308eb2",
550
+ "placeholder": "​",
551
+ "style": "IPY_MODEL_14303e52186d40c38cb936202917dbec",
552
+ "value": "Connecting..."
553
+ }
554
+ },
555
+ "9b5cd082ede1494e9476b29935308eb2": {
556
+ "model_module": "@jupyter-widgets/base",
557
+ "model_name": "LayoutModel",
558
+ "model_module_version": "1.2.0",
559
+ "state": {
560
+ "_model_module": "@jupyter-widgets/base",
561
+ "_model_module_version": "1.2.0",
562
+ "_model_name": "LayoutModel",
563
+ "_view_count": null,
564
+ "_view_module": "@jupyter-widgets/base",
565
+ "_view_module_version": "1.2.0",
566
+ "_view_name": "LayoutView",
567
+ "align_content": null,
568
+ "align_items": null,
569
+ "align_self": null,
570
+ "border": null,
571
+ "bottom": null,
572
+ "display": null,
573
+ "flex": null,
574
+ "flex_flow": null,
575
+ "grid_area": null,
576
+ "grid_auto_columns": null,
577
+ "grid_auto_flow": null,
578
+ "grid_auto_rows": null,
579
+ "grid_column": null,
580
+ "grid_gap": null,
581
+ "grid_row": null,
582
+ "grid_template_areas": null,
583
+ "grid_template_columns": null,
584
+ "grid_template_rows": null,
585
+ "height": null,
586
+ "justify_content": null,
587
+ "justify_items": null,
588
+ "left": null,
589
+ "margin": null,
590
+ "max_height": null,
591
+ "max_width": null,
592
+ "min_height": null,
593
+ "min_width": null,
594
+ "object_fit": null,
595
+ "object_position": null,
596
+ "order": null,
597
+ "overflow": null,
598
+ "overflow_x": null,
599
+ "overflow_y": null,
600
+ "padding": null,
601
+ "right": null,
602
+ "top": null,
603
+ "visibility": null,
604
+ "width": null
605
+ }
606
+ },
607
+ "14303e52186d40c38cb936202917dbec": {
608
+ "model_module": "@jupyter-widgets/controls",
609
+ "model_name": "DescriptionStyleModel",
610
+ "model_module_version": "1.5.0",
611
+ "state": {
612
+ "_model_module": "@jupyter-widgets/controls",
613
+ "_model_module_version": "1.5.0",
614
+ "_model_name": "DescriptionStyleModel",
615
+ "_view_count": null,
616
+ "_view_module": "@jupyter-widgets/base",
617
+ "_view_module_version": "1.2.0",
618
+ "_view_name": "StyleView",
619
+ "description_width": ""
620
+ }
621
+ }
622
+ }
623
+ }
624
+ },
625
+ "cells": [
626
+ {
627
+ "cell_type": "code",
628
+ "execution_count": 1,
629
+ "metadata": {
630
+ "colab": {
631
+ "base_uri": "https://localhost:8080/"
632
+ },
633
+ "id": "PhHOWGEzx02F",
634
+ "outputId": "218d1fde-080b-455e-dc9a-3232320b6847"
635
+ },
636
+ "outputs": [
637
+ {
638
+ "output_type": "stream",
639
+ "name": "stdout",
640
+ "text": [
641
+ "Sun Apr 26 01:11:23 2026 \n",
642
+ "+-----------------------------------------------------------------------------------------+\n",
643
+ "| NVIDIA-SMI 580.82.07 Driver Version: 580.82.07 CUDA Version: 13.0 |\n",
644
+ "+-----------------------------------------+------------------------+----------------------+\n",
645
+ "| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |\n",
646
+ "| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |\n",
647
+ "| | | MIG M. |\n",
648
+ "|=========================================+========================+======================|\n",
649
+ "| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |\n",
650
+ "| N/A 43C P8 9W / 70W | 0MiB / 15360MiB | 0% Default |\n",
651
+ "| | | N/A |\n",
652
+ "+-----------------------------------------+------------------------+----------------------+\n",
653
+ "\n",
654
+ "+-----------------------------------------------------------------------------------------+\n",
655
+ "| Processes: |\n",
656
+ "| GPU GI CI PID Type Process name GPU Memory |\n",
657
+ "| ID ID Usage |\n",
658
+ "|=========================================================================================|\n",
659
+ "| No running processes found |\n",
660
+ "+-----------------------------------------------------------------------------------------+\n"
661
+ ]
662
+ }
663
+ ],
664
+ "source": [
665
+ "!nvidia-smi"
666
+ ]
667
+ },
668
+ {
669
+ "cell_type": "code",
670
+ "source": [
671
+ " import torch\n",
672
+ " print(f\"CUDA available: {torch.cuda.is_available()}\")\n",
673
+ " if torch.cuda.is_available():\n",
674
+ " print(f\"GPU: {torch.cuda.get_device_name(0)}\")\n",
675
+ " props = torch.cuda.get_device_properties(0)\n",
676
+ " print(f\"VRAM: {props.total_memory / 1e9:.1f} GB\")"
677
+ ],
678
+ "metadata": {
679
+ "colab": {
680
+ "base_uri": "https://localhost:8080/"
681
+ },
682
+ "id": "fHa9jIEV1NhP",
683
+ "outputId": "b7c9160f-f2ac-431d-f64f-f451cd1153aa"
684
+ },
685
+ "execution_count": 2,
686
+ "outputs": [
687
+ {
688
+ "output_type": "stream",
689
+ "name": "stdout",
690
+ "text": [
691
+ "CUDA available: True\n",
692
+ "GPU: Tesla T4\n",
693
+ "VRAM: 15.6 GB\n"
694
+ ]
695
+ }
696
+ ]
697
+ },
698
+ {
699
+ "cell_type": "code",
700
+ "execution_count": 3,
701
+ "metadata": {
702
+ "id": "Gi8sLt91Y_PE",
703
+ "colab": {
704
+ "base_uri": "https://localhost:8080/"
705
+ },
706
+ "outputId": "2b1c9027-ee85-4dd7-892c-79afc490e5b5"
707
+ },
708
+ "outputs": [
709
+ {
710
+ "output_type": "stream",
711
+ "name": "stdout",
712
+ "text": [
713
+ "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/1.8 MB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m85.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
714
+ "\u001b[?25h"
715
+ ]
716
+ }
717
+ ],
718
+ "source": [
719
+ "!pip install -q -U pip\n",
720
+ "!pip install -q torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121\n",
721
+ "!pip install -q bitsandbytes peft trl transformers datasets accelerate matplotlib requests huggingface_hub unsloth"
722
+ ]
723
+ },
724
+ {
725
+ "cell_type": "code",
726
+ "source": [
727
+ "from huggingface_hub import login\n",
728
+ "login() # paste your HF token when prompted\n"
729
+ ],
730
+ "metadata": {
731
+ "id": "tL1kUtkE3aB1",
732
+ "colab": {
733
+ "base_uri": "https://localhost:8080/",
734
+ "height": 17,
735
+ "referenced_widgets": [
736
+ "efa20c94265a4e8aa5c2b42b30d8a0dc",
737
+ "c75a89d0eeb04c8c9563e536cf3617de",
738
+ "823e59efcb874d0f875829bdb729f5f1",
739
+ "2df40cb11c5d41d6856d53cdbd57357b",
740
+ "f06edce066f94a53a8b7111197c9d1ea",
741
+ "4d1b5e16c7484bb2b38691acc1fd372a",
742
+ "07e8ea9a765b4bb38aa9486c08c7e876",
743
+ "1254edd893ea4527840a08e998a42e66",
744
+ "e0dd533ff9d14edda59583096c3ed44c",
745
+ "37a76ab6f9fe46c68598ecde37caa9ff",
746
+ "62ae40b3ca12465485ca5469798b565b",
747
+ "06e8ddba2c9a47e98ac550ea4e35d992",
748
+ "972ce993ae0943e58e2acbd56bf0de7b",
749
+ "b4ddb223ea4d4046908f06cf8f8c72ee",
750
+ "210cdf5848f143fca9b77855e24de566",
751
+ "9619fd586f35410a9b3a18c8c44098dd",
752
+ "e06302bb607344ba8e1e931f5c55f1a4",
753
+ "694961c954f64e96979f260fc8072430",
754
+ "9b5cd082ede1494e9476b29935308eb2",
755
+ "14303e52186d40c38cb936202917dbec"
756
+ ]
757
+ },
758
+ "outputId": "f936cb56-604f-4013-8612-5d649afb97e2"
759
+ },
760
+ "execution_count": 4,
761
+ "outputs": [
762
+ {
763
+ "output_type": "display_data",
764
+ "data": {
765
+ "text/plain": [
766
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
767
+ ],
768
+ "application/vnd.jupyter.widget-view+json": {
769
+ "version_major": 2,
770
+ "version_minor": 0,
771
+ "model_id": "efa20c94265a4e8aa5c2b42b30d8a0dc"
772
+ }
773
+ },
774
+ "metadata": {}
775
+ }
776
+ ]
777
+ },
778
+ {
779
+ "cell_type": "code",
780
+ "source": [
781
+ "!python train.py \\\n",
782
+ " --model Qwen/Qwen2.5-3B-Instruct \\\n",
783
+ " --task all \\\n",
784
+ " --episodes 30 \\\n",
785
+ " --load_in_4bit \\\n",
786
+ " --grpo_max_steps 10 \\\n",
787
+ " --env_url https://ogrohit-logtriage-env.hf.space \\\n",
788
+ " --push_to_hub \\\n",
789
+ " --hub_model_id OGrohit/logtriage-sre-agent"
790
+ ],
791
+ "metadata": {
792
+ "colab": {
793
+ "base_uri": "https://localhost:8080/"
794
+ },
795
+ "id": "psC2BtB6HXFm",
796
+ "outputId": "85a43f8f-f0f3-470f-be0f-d050d94e3425"
797
+ },
798
+ "execution_count": 5,
799
+ "outputs": [
800
+ {
801
+ "output_type": "stream",
802
+ "name": "stdout",
803
+ "text": [
804
+ "2026-04-26 01:14:42.333349: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
805
+ "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
806
+ "E0000 00:00:1777166082.355494 10026 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
807
+ "E0000 00:00:1777166082.362449 10026 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
808
+ "W0000 00:00:1777166082.381114 10026 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
809
+ "W0000 00:00:1777166082.381164 10026 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
810
+ "W0000 00:00:1777166082.381169 10026 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
811
+ "W0000 00:00:1777166082.381173 10026 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
812
+ "2026-04-26 01:14:42.385910: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
813
+ "To enable the following instructions: AVX2 AVX512F FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
814
+ "Skipping import of cpp extensions due to incompatible torch version. Please upgrade to torch >= 2.11.0 (found 2.10.0+cu128).\n",
815
+ "/content/train.py:45: UserWarning: WARNING: Unsloth should be imported before trl, transformers, peft to ensure all optimizations are applied. Your code may run slower or encounter memory issues without these optimizations.\n",
816
+ "\n",
817
+ "Please restructure your imports with 'import unsloth' at the top of your file.\n",
818
+ " from unsloth import FastLanguageModel\n",
819
+ "🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n",
820
+ "🦥 Unsloth Zoo will now patch everything to make training faster!\n",
821
+ "Unable to import `torchao` Tensor objects. This may affect loading checkpoints serialized with `torchao`\n",
822
+ "Flax classes are deprecated and will be removed in Diffusers v1.0.0. We recommend migrating to PyTorch classes or pinning your version of Diffusers.\n",
823
+ "Flax classes are deprecated and will be removed in Diffusers v1.0.0. We recommend migrating to PyTorch classes or pinning your version of Diffusers.\n",
824
+ "\n",
825
+ "[LOGGING] LogTriageEnv GRPO Training\n",
826
+ " Model: Qwen/Qwen2.5-3B-Instruct\n",
827
+ " Task: all\n",
828
+ " Episodes: 30\n",
829
+ " Device: cuda\n",
830
+ " Env URL: https://ogrohit-logtriage-env.hf.space\n",
831
+ "\n",
832
+ "[OK] Connected to LogTriageEnv at https://ogrohit-logtriage-env.hf.space\n",
833
+ "[MODEL] Loading model: Qwen/Qwen2.5-3B-Instruct\n",
834
+ "[QLoRA] Loading model with BitsAndBytes 4-bit...\n",
835
+ "tokenizer_config.json: 7.30kB [00:00, 4.55MB/s]\n",
836
+ "vocab.json: 2.78MB [00:00, 104MB/s]\n",
837
+ "merges.txt: 1.67MB [00:00, 111MB/s]\n",
838
+ "tokenizer.json: 7.03MB [00:00, 139MB/s]\n",
839
+ "[OK] 4-bit BitsAndBytesConfig applied\n",
840
+ "config.json: 100% 661/661 [00:00<00:00, 5.12MB/s]\n",
841
+ "model.safetensors.index.json: 35.6kB [00:00, 101MB/s]\n",
842
+ "Fetching 2 files: 0% 0/2 [00:00<?, ?it/s]\n",
843
+ "model-00001-of-00002.safetensors: 0% 0.00/3.97G [00:00<?, ?B/s]\u001b[A\n",
844
+ "\n",
845
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:00<?, ?B/s]\u001b[A\u001b[A\n",
846
+ "\n",
847
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:00<?, ?B/s]\u001b[A\u001b[A\n",
848
+ "model-00001-of-00002.safetensors: 0% 0.00/3.97G [00:00<?, ?B/s]\u001b[A\n",
849
+ "model-00001-of-00002.safetensors: 0% 0.00/3.97G [00:00<?, ?B/s]\u001b[A\n",
850
+ "\n",
851
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:00<?, ?B/s]\u001b[A\u001b[A\n",
852
+ "\n",
853
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:00<?, ?B/s]\u001b[A\u001b[A\n",
854
+ "model-00001-of-00002.safetensors: 0% 0.00/3.97G [00:00<?, ?B/s]\u001b[A\n",
855
+ "model-00001-of-00002.safetensors: 0% 0.00/3.97G [00:00<?, ?B/s]\u001b[A\n",
856
+ "\n",
857
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:00<?, ?B/s]\u001b[A\u001b[A\n",
858
+ "model-00001-of-00002.safetensors: 0% 0.00/3.97G [00:01<?, ?B/s]\u001b[A\n",
859
+ "\n",
860
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:01<?, ?B/s]\u001b[A\u001b[A\n",
861
+ "\n",
862
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:01<?, ?B/s]\u001b[A\u001b[A\n",
863
+ "model-00001-of-00002.safetensors: 0% 0.00/3.97G [00:01<?, ?B/s]\u001b[A\n",
864
+ "\n",
865
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:01<?, ?B/s]\u001b[A\u001b[A\n",
866
+ "model-00001-of-00002.safetensors: 0% 0.00/3.97G [00:01<?, ?B/s]\u001b[A\n",
867
+ "model-00001-of-00002.safetensors: 0% 20.3k/3.97G [00:01<10:54:45, 101kB/s]\u001b[A\n",
868
+ "\n",
869
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:01<?, ?B/s]\u001b[A\u001b[A\n",
870
+ "\n",
871
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:01<?, ?B/s]\u001b[A\u001b[A\n",
872
+ "\n",
873
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:02<?, ?B/s]\u001b[A\u001b[A\n",
874
+ "\n",
875
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:02<?, ?B/s]\u001b[A\u001b[A\n",
876
+ "\n",
877
+ "model-00002-of-00002.safetensors: 0% 0.00/2.20G [00:09<?, ?B/s]\u001b[A\u001b[A\n",
878
+ "\n",
879
+ "model-00002-of-00002.safetensors: 4% 90.8M/2.20G [00:15<02:10, 16.2MB/s]\u001b[A\u001b[A\n",
880
+ "\n",
881
+ "model-00002-of-00002.safetensors: 10% 225M/2.20G [00:15<00:40, 48.7MB/s] \u001b[A\u001b[A\n",
882
+ "model-00001-of-00002.safetensors: 0% 20.3k/3.97G [00:15<10:54:45, 101kB/s]\u001b[A\n",
883
+ "model-00001-of-00002.safetensors: 8% 335M/3.97G [00:21<03:33, 17.0MB/s] \u001b[A\n",
884
+ "\n",
885
+ "model-00002-of-00002.safetensors: 10% 225M/2.20G [00:25<00:40, 48.7MB/s]\u001b[A\u001b[A\n",
886
+ "\n",
887
+ "model-00002-of-00002.safetensors: 25% 560M/2.20G [00:30<01:02, 26.3MB/s]\u001b[A\u001b[A\n",
888
+ "model-00001-of-00002.safetensors: 8% 335M/3.97G [00:35<03:33, 17.0MB/s]\u001b[A\n",
889
+ "\n",
890
+ "model-00002-of-00002.safetensors: 25% 560M/2.20G [00:45<01:02, 26.3MB/s]\u001b[A\u001b[A\n",
891
+ "\n",
892
+ "model-00002-of-00002.safetensors: 44% 961M/2.20G [00:50<00:56, 22.2MB/s]\u001b[A\u001b[A\n",
893
+ "model-00001-of-00002.safetensors: 23% 921M/3.97G [00:50<02:41, 18.9MB/s]\u001b[A\n",
894
+ "\n",
895
+ "model-00002-of-00002.safetensors: 58% 1.28G/2.20G [01:02<00:38, 24.2MB/s]\u001b[A\u001b[A\n",
896
+ "model-00001-of-00002.safetensors: 31% 1.24G/3.97G [01:04<02:15, 20.1MB/s]\u001b[A\n",
897
+ "\n",
898
+ "model-00002-of-00002.safetensors: 72% 1.59G/2.20G [01:15<00:25, 23.8MB/s]\u001b[A\u001b[A\n",
899
+ "model-00001-of-00002.safetensors: 31% 1.24G/3.97G [01:15<02:15, 20.1MB/s]\u001b[A\n",
900
+ "model-00001-of-00002.safetensors: 41% 1.65G/3.97G [01:19<01:42, 22.6MB/s]\u001b[A\n",
901
+ "\n",
902
+ "model-00002-of-00002.safetensors: 72% 1.59G/2.20G [01:25<00:25, 23.8MB/s]\u001b[A\u001b[A\n",
903
+ "model-00001-of-00002.safetensors: 50% 2.00G/3.97G [01:26<01:11, 27.6MB/s]\u001b[A\n",
904
+ "\n",
905
+ "model-00002-of-00002.safetensors: 92% 2.03G/2.20G [01:26<00:06, 28.7MB/s]\u001b[A\u001b[A\n",
906
+ "\n",
907
+ "model-00002-of-00002.safetensors: 100% 2.20G/2.20G [01:37<00:00, 22.6MB/s]\n",
908
+ "\n",
909
+ "model-00001-of-00002.safetensors: 58% 2.32G/3.97G [01:38<01:00, 27.4MB/s]\u001b[A\n",
910
+ "model-00001-of-00002.safetensors: 68% 2.72G/3.97G [01:44<00:36, 34.7MB/s]\u001b[A\n",
911
+ "model-00001-of-00002.safetensors: 76% 3.03G/3.97G [01:48<00:23, 40.0MB/s]\u001b[A\n",
912
+ "model-00001-of-00002.safetensors: 84% 3.35G/3.97G [01:50<00:11, 52.9MB/s]\u001b[A\n",
913
+ "model-00001-of-00002.safetensors: 94% 3.72G/3.97G [01:55<00:04, 58.5MB/s]\u001b[A\n",
914
+ "model-00001-of-00002.safetensors: 100% 3.97G/3.97G [01:56<00:00, 34.2MB/s]\n",
915
+ "Fetching 2 files: 100% 2/2 [01:56<00:00, 58.32s/it] \n",
916
+ "Loading checkpoint shards: 100% 2/2 [00:26<00:00, 13.17s/it]\n",
917
+ "generation_config.json: 100% 242/242 [00:00<00:00, 1.63MB/s]\n",
918
+ "[OK] Model loaded in 4-bit quantized mode\n",
919
+ "[QLoRA] Applying LoRA adapter...\n",
920
+ "trainable params: 29,933,568 || all params: 3,115,872,256 || trainable%: 0.9607\n",
921
+ "[OK] LoRA adapter attached (r=16, alpha=32)\n",
922
+ "[OK] Model loaded\n",
923
+ "\n",
924
+ "\n",
925
+ "============================================================\n",
926
+ "[TRAIN] Training on task: single_crash\n",
927
+ "============================================================\n",
928
+ " Episode 1/30 | Reward: +0.350 | Steps: 8 | Rolling avg (10): 0.350\n",
929
+ " Episode 2/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.150\n",
930
+ " Episode 3/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.183\n",
931
+ " Episode 4/30 | Reward: +0.000 | Steps: 8 | Rolling avg (10): 0.137\n",
932
+ " Episode 5/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.100\n",
933
+ " Episode 6/30 | Reward: +0.350 | Steps: 3 | Rolling avg (10): 0.142\n",
934
+ " Episode 7/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.114\n",
935
+ " Episode 8/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.131\n",
936
+ " Episode 9/30 | Reward: +0.500 | Steps: 14 | Rolling avg (10): 0.172\n",
937
+ " Episode 10/30 | Reward: +0.250 | Steps: 3 | Rolling avg (10): 0.180\n",
938
+ " Episode 11/30 | Reward: +0.600 | Steps: 3 | Rolling avg (10): 0.205\n",
939
+ " Episode 12/30 | Reward: +0.400 | Steps: 7 | Rolling avg (10): 0.250\n",
940
+ " Episode 13/30 | Reward: +0.250 | Steps: 3 | Rolling avg (10): 0.250\n",
941
+ " Episode 14/30 | Reward: +0.150 | Steps: 4 | Rolling avg (10): 0.265\n",
942
+ " Episode 15/30 | Reward: +0.350 | Steps: 8 | Rolling avg (10): 0.305\n",
943
+ " Episode 16/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.265\n",
944
+ " Episode 17/30 | Reward: +0.650 | Steps: 5 | Rolling avg (10): 0.335\n",
945
+ " Episode 18/30 | Reward: +0.350 | Steps: 8 | Rolling avg (10): 0.345\n",
946
+ " Episode 19/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.290\n",
947
+ " Episode 20/30 | Reward: +0.150 | Steps: 4 | Rolling avg (10): 0.280\n",
948
+ " Episode 21/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.245\n",
949
+ " Episode 22/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.200\n",
950
+ " Episode 23/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.170\n",
951
+ " Episode 24/30 | Reward: +0.100 | Steps: 6 | Rolling avg (10): 0.165\n",
952
+ " [CHECKPOINT] Saved single_crash ep25 -> ./phase2_checkpoints/single_crash_ep25.json\n",
953
+ " Episode 25/30 | Reward: +0.150 | Steps: 4 | Rolling avg (10): 0.145\n",
954
+ " Episode 26/30 | Reward: +0.100 | Steps: 6 | Rolling avg (10): 0.160\n",
955
+ " Episode 27/30 | Reward: -0.050 | Steps: 6 | Rolling avg (10): 0.090\n",
956
+ " Episode 28/30 | Reward: +0.000 | Steps: 8 | Rolling avg (10): 0.055\n",
957
+ " Episode 29/30 | Reward: +0.100 | Steps: 6 | Rolling avg (10): 0.070\n",
958
+ " Episode 30/30 | Reward: +0.100 | Steps: 6 | Rolling avg (10): 0.065\n",
959
+ "\n",
960
+ "[STATS] single_crash Summary:\n",
961
+ " First 10 episodes avg: 0.180\n",
962
+ " Last 10 episodes avg: 0.065\n",
963
+ " Improvement: -0.115\n",
964
+ "\n",
965
+ "============================================================\n",
966
+ "[TRAIN] Training on task: cascading_failure\n",
967
+ "============================================================\n",
968
+ " Episode 1/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.250\n",
969
+ " Episode 2/30 | Reward: -0.200 | Steps: 8 | Rolling avg (10): 0.025\n",
970
+ " Episode 3/30 | Reward: +0.350 | Steps: 8 | Rolling avg (10): 0.133\n",
971
+ " Episode 4/30 | Reward: -0.200 | Steps: 8 | Rolling avg (10): 0.050\n",
972
+ " Episode 5/30 | Reward: +0.000 | Steps: 8 | Rolling avg (10): 0.040\n",
973
+ " Episode 6/30 | Reward: +0.000 | Steps: 8 | Rolling avg (10): 0.033\n",
974
+ " Episode 7/30 | Reward: +0.450 | Steps: 7 | Rolling avg (10): 0.093\n",
975
+ " Episode 8/30 | Reward: +0.300 | Steps: 4 | Rolling avg (10): 0.119\n",
976
+ " Episode 9/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.100\n",
977
+ " Episode 10/30 | Reward: +0.000 | Steps: 8 | Rolling avg (10): 0.090\n",
978
+ " Episode 11/30 | Reward: +0.500 | Steps: 6 | Rolling avg (10): 0.115\n",
979
+ " Episode 12/30 | Reward: +0.350 | Steps: 3 | Rolling avg (10): 0.170\n",
980
+ " Episode 13/30 | Reward: +0.300 | Steps: 4 | Rolling avg (10): 0.165\n",
981
+ " Episode 14/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.180\n",
982
+ " Episode 15/30 | Reward: +0.350 | Steps: 8 | Rolling avg (10): 0.215\n",
983
+ " Episode 16/30 | Reward: +0.350 | Steps: 8 | Rolling avg (10): 0.250\n",
984
+ " Episode 17/30 | Reward: +0.400 | Steps: 8 | Rolling avg (10): 0.245\n",
985
+ " Episode 18/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.210\n",
986
+ " Episode 19/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.210\n",
987
+ " Episode 20/30 | Reward: +0.650 | Steps: 5 | Rolling avg (10): 0.275\n",
988
+ " Episode 21/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.250\n",
989
+ " Episode 22/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.210\n",
990
+ " Episode 23/30 | Reward: +0.000 | Steps: 8 | Rolling avg (10): 0.180\n",
991
+ " Episode 24/30 | Reward: +0.100 | Steps: 6 | Rolling avg (10): 0.195\n",
992
+ " [CHECKPOINT] Saved cascading_failure ep25 -> ./phase2_checkpoints/cascading_failure_ep25.json\n",
993
+ " Episode 25/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.185\n",
994
+ " Episode 26/30 | Reward: +0.200 | Steps: 7 | Rolling avg (10): 0.170\n",
995
+ " Episode 27/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.125\n",
996
+ " Episode 28/30 | Reward: +0.300 | Steps: 4 | Rolling avg (10): 0.160\n",
997
+ " Episode 29/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.160\n",
998
+ " Episode 30/30 | Reward: +0.100 | Steps: 6 | Rolling avg (10): 0.105\n",
999
+ "\n",
1000
+ "[STATS] cascading_failure Summary:\n",
1001
+ " First 10 episodes avg: 0.090\n",
1002
+ " Last 10 episodes avg: 0.105\n",
1003
+ " Improvement: +0.015\n",
1004
+ "\n",
1005
+ "============================================================\n",
1006
+ "[TRAIN] Training on task: silent_degradation\n",
1007
+ "============================================================\n",
1008
+ " Episode 1/30 | Reward: +0.300 | Steps: 4 | Rolling avg (10): 0.300\n",
1009
+ " Episode 2/30 | Reward: +0.100 | Steps: 6 | Rolling avg (10): 0.200\n",
1010
+ " Episode 3/30 | Reward: -0.200 | Steps: 8 | Rolling avg (10): 0.067\n",
1011
+ " Episode 4/30 | Reward: +0.050 | Steps: 7 | Rolling avg (10): 0.063\n",
1012
+ " Episode 5/30 | Reward: +0.650 | Steps: 5 | Rolling avg (10): 0.180\n",
1013
+ " Episode 6/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.142\n",
1014
+ " Episode 7/30 | Reward: +0.650 | Steps: 5 | Rolling avg (10): 0.214\n",
1015
+ " Episode 8/30 | Reward: +0.050 | Steps: 7 | Rolling avg (10): 0.194\n",
1016
+ " Episode 9/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.200\n",
1017
+ " Episode 10/30 | Reward: +0.000 | Steps: 8 | Rolling avg (10): 0.180\n",
1018
+ " Episode 11/30 | Reward: +0.350 | Steps: 8 | Rolling avg (10): 0.185\n",
1019
+ " Episode 12/30 | Reward: +0.000 | Steps: 8 | Rolling avg (10): 0.175\n",
1020
+ " Episode 13/30 | Reward: +0.350 | Steps: 8 | Rolling avg (10): 0.230\n",
1021
+ " Episode 14/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.220\n",
1022
+ " Episode 15/30 | Reward: +0.050 | Steps: 7 | Rolling avg (10): 0.160\n",
1023
+ " Episode 16/30 | Reward: +0.350 | Steps: 3 | Rolling avg (10): 0.200\n",
1024
+ " Episode 17/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.130\n",
1025
+ " Episode 18/30 | Reward: +0.350 | Steps: 6 | Rolling avg (10): 0.160\n",
1026
+ " Episode 19/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.160\n",
1027
+ " Episode 20/30 | Reward: +0.350 | Steps: 8 | Rolling avg (10): 0.195\n",
1028
+ " Episode 21/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.185\n",
1029
+ " Episode 22/30 | Reward: +0.300 | Steps: 4 | Rolling avg (10): 0.215\n",
1030
+ " Episode 23/30 | Reward: -0.200 | Steps: 8 | Rolling avg (10): 0.160\n",
1031
+ " Episode 24/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.190\n",
1032
+ " [CHECKPOINT] Saved silent_degradation ep25 -> ./phase2_checkpoints/silent_degradation_ep25.json\n",
1033
+ " Episode 25/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.210\n",
1034
+ " Episode 26/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.170\n",
1035
+ " Episode 27/30 | Reward: +0.250 | Steps: 5 | Rolling avg (10): 0.200\n",
1036
+ " Episode 28/30 | Reward: +0.000 | Steps: 8 | Rolling avg (10): 0.165\n",
1037
+ " Episode 29/30 | Reward: -0.050 | Steps: 8 | Rolling avg (10): 0.135\n",
1038
+ " Episode 30/30 | Reward: +0.100 | Steps: 7 | Rolling avg (10): 0.110\n",
1039
+ "\n",
1040
+ "[STATS] silent_degradation Summary:\n",
1041
+ " First 10 episodes avg: 0.180\n",
1042
+ " Last 10 episodes avg: 0.110\n",
1043
+ " Improvement: -0.070\n",
1044
+ "[PLOT] Reward curve saved -> reward_curve.png\n",
1045
+ "\n",
1046
+ "[GRPO] Collected 589 trajectory steps from rollout.\n",
1047
+ "[GRPO] Running GRPO fine-tuning on 589 trajectory steps...\n",
1048
+ "[GRPO] Precision: fp16 (bf16 unsupported on this GPU)\n",
1049
+ " 0% 0/10 [00:00<?, ?it/s][WARN] GRPO trainer error: No inf checks were recorded prior to update.\n",
1050
+ "[WARN] Continuing with rollout-only results.\n",
1051
+ "[SAVE] Merging LoRA adapter into base weights...\n",
1052
+ "/usr/local/lib/python3.12/dist-packages/peft/tuners/lora/bnb.py:397: UserWarning: Merge lora module to 4-bit linear may get different generations due to rounding errors.\n",
1053
+ " warnings.warn(\n",
1054
+ "[OK] LoRA merged — saving full model\n",
1055
+ "\n",
1056
+ "[SAVE] Model saved -> ./logtriage-trained\n",
1057
+ "\n",
1058
+ "[PUSH] Pushing to HuggingFace Hub: OGrohit/logtriage-sre-agent\n",
1059
+ "\n",
1060
+ "README.md: 100% 684/684 [00:00<00:00, 4.60MB/s]\n",
1061
+ "Processing Files (0 / 0) : | | 0.00B / 0.00B \n",
1062
+ "New Data Upload : | | 0.00B / 0.00B \u001b[A\n",
1063
+ "\n",
1064
+ " ...4fmqprp/model.safetensors: 1% 30.8M/2.68G [00:00<?, ?B/s]\u001b[A\u001b[A\n",
1065
+ "\n",
1066
+ "Processing Files (0 / 1) : 1% 30.8M/2.68G [00:02<04:13, 10.4MB/s, 11.8MB/s ]\n",
1067
+ "\n",
1068
+ "Processing Files (0 / 1) : 2% 53.5M/2.68G [00:03<02:14, 19.5MB/s, 19.1MB/s ]\n",
1069
+ "\n",
1070
+ "Processing Files (0 / 1) : 3% 84.5M/2.68G [00:03<01:14, 34.7MB/s, 28.2MB/s ]\n",
1071
+ "\n",
1072
+ "Processing Files (0 / 1) : 4% 115M/2.68G [00:03<00:50, 51.2MB/s, 36.1MB/s ] \n",
1073
+ "\n",
1074
+ "Processing Files (0 / 1) : 5% 146M/2.68G [00:03<00:37, 68.1MB/s, 43.0MB/s ]\n",
1075
+ "\n",
1076
+ "Processing Files (0 / 1) : 7% 178M/2.68G [00:03<00:29, 85.2MB/s, 49.4MB/s ]\n",
1077
+ "\n",
1078
+ "Processing Files (0 / 1) : 8% 209M/2.68G [00:04<00:24, 99.8MB/s, 54.9MB/s ]\n",
1079
+ "\n",
1080
+ "Processing Files (0 / 1) : 9% 240M/2.68G [00:04<00:21, 113MB/s, 59.9MB/s ] \n",
1081
+ "\n",
1082
+ "Processing Files (0 / 1) : 10% 271M/2.68G [00:04<00:19, 123MB/s, 64.4MB/s ]\n",
1083
+ "\n",
1084
+ "Processing Files (0 / 1) : 11% 294M/2.68G [00:04<00:19, 121MB/s, 66.7MB/s ]\n",
1085
+ "\n",
1086
+ "Processing Files (0 / 1) : 12% 333M/2.68G [00:04<00:16, 141MB/s, 72.3MB/s ]\n",
1087
+ "\n",
1088
+ "Processing Files (0 / 1) : 13% 356M/2.68G [00:05<00:17, 135MB/s, 74.2MB/s ]\n",
1089
+ "\n",
1090
+ "Processing Files (0 / 1) : 14% 387M/2.68G [00:05<00:16, 141MB/s, 77.5MB/s ]\n",
1091
+ "\n",
1092
+ "Processing Files (0 / 1) : 16% 419M/2.68G [00:05<00:15, 145MB/s, 80.5MB/s ]\n",
1093
+ "\n",
1094
+ "Processing Files (0 / 1) : 17% 449M/2.68G [00:05<00:15, 148MB/s, 83.2MB/s ]\n",
1095
+ "\n",
1096
+ "Processing Files (0 / 1) : 18% 481M/2.68G [00:05<00:14, 150MB/s, 85.8MB/s ]\n",
1097
+ "\n",
1098
+ "Processing Files (0 / 1) : 19% 512M/2.68G [00:06<00:14, 152MB/s, 88.2MB/s ]\n",
1099
+ "\n",
1100
+ "Processing Files (0 / 1) : 20% 543M/2.68G [00:06<00:13, 153MB/s, 90.4MB/s ]\n",
1101
+ "\n",
1102
+ "Processing Files (0 / 1) : 21% 574M/2.68G [00:06<00:13, 154MB/s, 92.5MB/s ]\n",
1103
+ "\n",
1104
+ "Processing Files (0 / 1) : 23% 605M/2.68G [00:06<00:13, 154MB/s, 94.5MB/s ]\n",
1105
+ "\n",
1106
+ "Processing Files (0 / 1) : 24% 636M/2.68G [00:06<00:13, 155MB/s, 96.4MB/s ]\n",
1107
+ "\n",
1108
+ "Processing Files (0 / 1) : 25% 668M/2.68G [00:07<00:12, 156MB/s, 98.2MB/s ]\n",
1109
+ "\n",
1110
+ "Processing Files (0 / 1) : 26% 699M/2.68G [00:07<00:12, 156MB/s, 99.9MB/s ]\n",
1111
+ "\n",
1112
+ "Processing Files (0 / 1) : 27% 730M/2.68G [00:07<00:12, 155MB/s, 101MB/s ]\n",
1113
+ "\n",
1114
+ "Processing Files (0 / 1) : 28% 761M/2.68G [00:07<00:12, 155MB/s, 103MB/s ]\n",
1115
+ "\n",
1116
+ "Processing Files (0 / 1) : 30% 791M/2.68G [00:07<00:12, 154MB/s, 104MB/s ]\n",
1117
+ "\n",
1118
+ "Processing Files (0 / 1) : 31% 822M/2.68G [00:08<00:12, 154MB/s, 105MB/s ]\n",
1119
+ "\n",
1120
+ "Processing Files (0 / 1) : 32% 846M/2.68G [00:08<00:12, 143MB/s, 106MB/s ]\n",
1121
+ "\n",
1122
+ "Processing Files (0 / 1) : 32% 869M/2.68G [00:08<00:13, 134MB/s, 106MB/s ]\n",
1123
+ "\n",
1124
+ "Processing Files (0 / 1) : 33% 884M/2.68G [00:08<00:15, 118MB/s, 105MB/s ]\n",
1125
+ "\n",
1126
+ "Processing Files (0 / 1) : 34% 907M/2.68G [00:08<00:15, 117MB/s, 105MB/s ]\n",
1127
+ "\n",
1128
+ "Processing Files (0 / 1) : 34% 923M/2.68G [00:09<00:16, 105MB/s, 105MB/s ]\n",
1129
+ "\n",
1130
+ "Processing Files (0 / 1) : 35% 946M/2.68G [00:09<00:15, 109MB/s, 105MB/s ]\n",
1131
+ "\n",
1132
+ "Processing Files (0 / 1) : 36% 962M/2.68G [00:09<00:17, 99.0MB/s, 105MB/s ]\n",
1133
+ "\n",
1134
+ "Processing Files (0 / 1) : 37% 985M/2.68G [00:09<00:16, 104MB/s, 105MB/s ] \n",
1135
+ "\n",
1136
+ "Processing Files (0 / 1) : 37% 1.00G/2.68G [00:09<00:17, 96.5MB/s, 104MB/s ]\n",
1137
+ "\n",
1138
+ "Processing Files (0 / 1) : 38% 1.02G/2.68G [00:10<00:18, 91.1MB/s, 104MB/s ]\n",
1139
+ "\n",
1140
+ "Processing Files (0 / 1) : 39% 1.03G/2.68G [00:10<00:19, 86.5MB/s, 103MB/s ]\n",
1141
+ "\n",
1142
+ "Processing Files (0 / 1) : 39% 1.06G/2.68G [00:10<00:16, 96.6MB/s, 103MB/s ]\n",
1143
+ "\n",
1144
+ "Processing Files (0 / 1) : 40% 1.07G/2.68G [00:10<00:17, 90.3MB/s, 105MB/s ]\n",
1145
+ "\n",
1146
+ "Processing Files (0 / 1) : 41% 1.09G/2.68G [00:10<00:15, 99.4MB/s, 107MB/s ]\n",
1147
+ "\n",
1148
+ "Processing Files (0 / 1) : 41% 1.11G/2.68G [00:11<00:16, 92.7MB/s, 109MB/s ]\n",
1149
+ "\n",
1150
+ "Processing Files (0 / 1) : 42% 1.13G/2.68G [00:11<00:15, 100MB/s, 111MB/s ] \n",
1151
+ "\n",
1152
+ "Processing Files (0 / 1) : 43% 1.16G/2.68G [00:11<00:14, 105MB/s, 113MB/s ]\n",
1153
+ "\n",
1154
+ "Processing Files (0 / 1) : 44% 1.17G/2.68G [00:11<00:15, 97.6MB/s, 115MB/s ]\n",
1155
+ "\n",
1156
+ "Processing Files (0 / 1) : 45% 1.20G/2.68G [00:11<00:12, 114MB/s, 118MB/s ] \n",
1157
+ "\n",
1158
+ "Processing Files (0 / 1) : 46% 1.23G/2.68G [00:12<00:12, 119MB/s, 121MB/s ]\n",
1159
+ "\n",
1160
+ "Processing Files (0 / 1) : 47% 1.25G/2.68G [00:12<00:11, 119MB/s, 123MB/s ]\n",
1161
+ "\n",
1162
+ " ...4fmqprp/model.safetensors: 47% 1.25G/2.68G [00:09<00:11, 127MB/s]\u001b[A\u001b[A\n",
1163
+ "\n",
1164
+ "Processing Files (0 / 1) : 47% 1.27G/2.68G [00:12<00:18, 77.4MB/s, 124MB/s ]\n",
1165
+ "\n",
1166
+ "Processing Files (0 / 1) : 48% 1.29G/2.68G [00:12<00:14, 92.7MB/s, 127MB/s ]\n",
1167
+ "\n",
1168
+ "Processing Files (0 / 1) : 49% 1.31G/2.68G [00:13<00:15, 88.3MB/s, 125MB/s ]\n",
1169
+ "New Data Upload : 1% 793k/67.0M [00:13<18:19, 60.3kB/s, 77.7kB/s ]\u001b[A\n",
1170
+ "\n",
1171
+ " ...4fmqprp/model.safetensors: 49% 1.31G/2.68G [00:10<00:11, 123MB/s]\u001b[A\u001b[A\n",
1172
+ "\n",
1173
+ " ...4fmqprp/model.safetensors: 49% 1.31G/2.68G [00:10<00:11, 120MB/s]\u001b[A\u001b[A\n",
1174
+ "\n",
1175
+ "Processing Files (0 / 1) : 49% 1.31G/2.68G [00:13<00:32, 42.2MB/s, 117MB/s ]\n",
1176
+ "New Data Upload : 2% 1.59M/67.0M [00:13<07:56, 137kB/s, 155kB/s ]\u001b[A\n",
1177
+ "\n",
1178
+ "Processing Files (0 / 1) : 49% 1.31G/2.68G [00:13<00:39, 34.6MB/s, 114MB/s ]\n",
1179
+ "New Data Upload : 4% 2.38M/67.0M [00:13<04:23, 246kB/s, 233kB/s ]\u001b[A\n",
1180
+ "\n",
1181
+ "Processing Files (0 / 1) : 49% 1.31G/2.68G [00:14<00:43, 31.3MB/s, 111MB/s ]\n",
1182
+ "New Data Upload : 9% 6.34M/67.0M [00:14<01:00, 1.01MB/s, 622kB/s ]\u001b[A\n",
1183
+ "\n",
1184
+ " ...4fmqprp/model.safetensors: 49% 1.31G/2.68G [00:11<00:12, 113MB/s]\u001b[A\u001b[A\n",
1185
+ "\n",
1186
+ "Processing Files (0 / 1) : 49% 1.31G/2.68G [00:14<01:08, 19.9MB/s, 105MB/s ]\n",
1187
+ "New Data Upload : 11% 7.13M/67.0M [00:14<00:54, 1.10MB/s, 700kB/s ]\u001b[A\n",
1188
+ "\n",
1189
+ "Processing Files (0 / 1) : 49% 1.32G/2.68G [00:14<01:18, 17.3MB/s, 102MB/s ]\n",
1190
+ "New Data Upload : 13% 8.72M/67.0M [00:14<00:37, 1.56MB/s, 855kB/s ]\u001b[A\n",
1191
+ "\n",
1192
+ "Processing Files (0 / 1) : 49% 1.32G/2.68G [00:14<01:12, 18.8MB/s, 101MB/s ]\n",
1193
+ "New Data Upload : 20% 13.5M/67.0M [00:14<00:15, 3.49MB/s, 1.32MB/s ]\u001b[A\n",
1194
+ "\n",
1195
+ "Processing Files (0 / 1) : 50% 1.35G/2.68G [00:15<00:27, 48.6MB/s, 99.5MB/s ]\n",
1196
+ "New Data Upload : 27% 18.2M/67.0M [00:15<00:08, 5.73MB/s, 1.79MB/s ]\u001b[A\n",
1197
+ "\n",
1198
+ "Processing Files (0 / 1) : 51% 1.35G/2.68G [00:15<00:31, 42.0MB/s, 97.7MB/s ]\n",
1199
+ "New Data Upload : 34% 23.0M/67.0M [00:15<00:05, 8.19MB/s, 2.25MB/s ]\u001b[A\n",
1200
+ "\n",
1201
+ "Processing Files (0 / 1) : 51% 1.36G/2.68G [00:15<00:35, 37.0MB/s, 95.1MB/s ]\n",
1202
+ "New Data Upload : 41% 27.7M/67.0M [00:15<00:03, 10.7MB/s, 2.72MB/s ]\u001b[A\n",
1203
+ "\n",
1204
+ "Processing Files (0 / 1) : 51% 1.38G/2.68G [00:15<00:24, 53.9MB/s, 93.9MB/s ]\n",
1205
+ "New Data Upload : 48% 32.5M/67.0M [00:15<00:02, 13.2MB/s, 3.19MB/s ]\u001b[A\n",
1206
+ "\n",
1207
+ "Processing Files (0 / 1) : 53% 1.41G/2.68G [00:15<00:14, 85.0MB/s, 94.1MB/s ]\n",
1208
+ "New Data Upload : 58% 38.8M/67.0M [00:15<00:01, 17.1MB/s, 3.81MB/s ]\u001b[A\n",
1209
+ "\n",
1210
+ "Processing Files (0 / 1) : 54% 1.44G/2.68G [00:16<00:12, 98.3MB/s, 93.6MB/s ]\n",
1211
+ "\n",
1212
+ "Processing Files (0 / 1) : 55% 1.46G/2.68G [00:16<00:11, 108MB/s, 93.1MB/s ] \n",
1213
+ "New Data Upload : 65% 43.6M/67.0M [00:16<00:01, 15.1MB/s, 4.27MB/s ]\u001b[A\n",
1214
+ "\n",
1215
+ "Processing Files (0 / 1) : 56% 1.50G/2.68G [00:16<00:08, 133MB/s, 93.8MB/s ]\n",
1216
+ "New Data Upload : 73% 49.1M/67.0M [00:16<00:01, 17.8MB/s, 4.82MB/s ]\u001b[A\n",
1217
+ "\n",
1218
+ "Processing Files (0 / 1) : 57% 1.53G/2.68G [00:16<00:08, 132MB/s, 93.3MB/s ]\n",
1219
+ "New Data Upload : 82% 54.7M/67.0M [00:16<00:00, 20.2MB/s, 5.36MB/s ]\u001b[A\n",
1220
+ "\n",
1221
+ "Processing Files (0 / 1) : 58% 1.56G/2.68G [00:16<00:07, 142MB/s, 93.5MB/s ]\n",
1222
+ "New Data Upload : 91% 61.0M/67.0M [00:16<00:00, 23.1MB/s, 5.98MB/s ]\u001b[A\n",
1223
+ "\n",
1224
+ "Processing Files (0 / 1) : 59% 1.59G/2.68G [00:17<00:07, 149MB/s, 93.7MB/s ]\n",
1225
+ "New Data Upload : 98% 65.8M/67.0M [00:17<00:00, 23.2MB/s, 6.45MB/s ]\u001b[A\n",
1226
+ "\n",
1227
+ "Processing Files (0 / 1) : 60% 1.62G/2.68G [00:17<00:07, 145MB/s, 93.3MB/s ]\n",
1228
+ "New Data Upload : 99% 66.6M/67.0M [00:17<00:00, 18.0MB/s, 6.53MB/s ]\u001b[A\n",
1229
+ "\n",
1230
+ "Processing Files (0 / 1) : 62% 1.65G/2.68G [00:17<00:07, 144MB/s, 92.9MB/s ]\n",
1231
+ "\n",
1232
+ "Processing Files (0 / 1) : 63% 1.67G/2.68G [00:17<00:07, 141MB/s, 92.6MB/s ]\n",
1233
+ "\n",
1234
+ " ...4fmqprp/model.safetensors: 63% 1.67G/2.68G [00:15<00:09, 109MB/s]\u001b[A\u001b[A\n",
1235
+ "\n",
1236
+ "Processing Files (0 / 1) : 63% 1.70G/2.68G [00:18<00:09, 102MB/s, 88.8MB/s ]\n",
1237
+ "New Data Upload : 50% 67.0M/134M [00:18<00:09, 7.37MB/s, 6.57MB/s ] \u001b[A\n",
1238
+ "\n",
1239
+ "Processing Files (0 / 1) : 64% 1.72G/2.68G [00:18<00:09, 102MB/s, 87.7MB/s ]\n",
1240
+ "New Data Upload : 50% 67.6M/134M [00:18<00:10, 6.52MB/s, 6.63MB/s ]\u001b[A\n",
1241
+ "\n",
1242
+ "Processing Files (0 / 1) : 65% 1.74G/2.68G [00:18<00:08, 111MB/s, 88.1MB/s ]\n",
1243
+ "\n",
1244
+ "Processing Files (0 / 1) : 66% 1.77G/2.68G [00:18<00:07, 117MB/s, 88.5MB/s ]\n",
1245
+ "\n",
1246
+ "Processing Files (0 / 1) : 67% 1.79G/2.68G [00:18<00:07, 113MB/s, 89.0MB/s ]\n",
1247
+ "New Data Upload : 51% 68.1M/134M [00:18<00:16, 4.07MB/s, 6.68MB/s ]\u001b[A\n",
1248
+ "\n",
1249
+ " ...4fmqprp/model.safetensors: 67% 1.79G/2.68G [00:16<00:08, 109MB/s]\u001b[A\u001b[A\n",
1250
+ "\n",
1251
+ "Processing Files (0 / 1) : 68% 1.82G/2.68G [00:19<00:09, 89.2MB/s, 87.5MB/s ]\n",
1252
+ "New Data Upload : 52% 69.1M/134M [00:19<00:17, 3.65MB/s, 6.78MB/s ]\u001b[A\n",
1253
+ "\n",
1254
+ "Processing Files (0 / 1) : 69% 1.85G/2.68G [00:19<00:07, 106MB/s, 88.3MB/s ] \n",
1255
+ "New Data Upload : 52% 70.2M/134M [00:19<00:16, 3.93MB/s, 6.88MB/s ]\u001b[A\n",
1256
+ "\n",
1257
+ "Processing Files (0 / 1) : 69% 1.85G/2.68G [00:19<00:10, 81.7MB/s, 87.1MB/s ]\n",
1258
+ "New Data Upload : 54% 72.3M/134M [00:19<00:11, 5.23MB/s, 7.09MB/s ]\u001b[A\n",
1259
+ "\n",
1260
+ "Processing Files (0 / 1) : 70% 1.88G/2.68G [00:19<00:07, 104MB/s, 88.0MB/s ] \n",
1261
+ "New Data Upload : 55% 74.4M/134M [00:19<00:09, 6.39MB/s, 7.29MB/s ]\u001b[A\n",
1262
+ "\n",
1263
+ "Processing Files (0 / 1) : 72% 1.92G/2.68G [00:20<00:06, 121MB/s, 89.7MB/s ]\n",
1264
+ "New Data Upload : 58% 78.1M/134M [00:20<00:06, 9.24MB/s, 7.65MB/s ]\u001b[A\n",
1265
+ "\n",
1266
+ "Processing Files (0 / 1) : 73% 1.94G/2.68G [00:20<00:05, 123MB/s, 90.7MB/s ]\n",
1267
+ "New Data Upload : 61% 81.2M/134M [00:20<00:04, 10.9MB/s, 7.96MB/s ]\u001b[A\n",
1268
+ "\n",
1269
+ "Processing Files (0 / 1) : 74% 1.98G/2.68G [00:20<00:04, 143MB/s, 93.0MB/s ]\n",
1270
+ "New Data Upload : 61% 82.3M/134M [00:20<00:05, 9.37MB/s, 8.06MB/s ]\u001b[A\n",
1271
+ "\n",
1272
+ "Processing Files (0 / 1) : 75% 2.01G/2.68G [00:20<00:04, 141MB/s, 93.3MB/s ]\n",
1273
+ "New Data Upload : 64% 85.4M/134M [00:20<00:04, 11.1MB/s, 8.37MB/s ]\u001b[A\n",
1274
+ "\n",
1275
+ "Processing Files (0 / 1) : 76% 2.04G/2.68G [00:20<00:04, 148MB/s, 95.0MB/s ]\n",
1276
+ "New Data Upload : 66% 88.6M/134M [00:20<00:03, 12.5MB/s, 8.69MB/s ]\u001b[A\n",
1277
+ "\n",
1278
+ "Processing Files (0 / 1) : 77% 2.07G/2.68G [00:21<00:04, 144MB/s, 95.3MB/s ]\n",
1279
+ "New Data Upload : 69% 92.2M/134M [00:21<00:02, 14.2MB/s, 9.04MB/s ]\u001b[A\n",
1280
+ "\n",
1281
+ "Processing Files (0 / 1) : 78% 2.08G/2.68G [00:21<00:04, 124MB/s, 95.3MB/s ]\n",
1282
+ "New Data Upload : 48% 96.4M/201M [00:21<00:06, 16.2MB/s, 9.46MB/s ]\u001b[A\n",
1283
+ "\n",
1284
+ "Processing Files (0 / 1) : 78% 2.10G/2.68G [00:21<00:05, 110MB/s, 94.5MB/s ]\n",
1285
+ "New Data Upload : 50% 101M/201M [00:21<00:05, 17.6MB/s, 9.87MB/s ] \u001b[A\n",
1286
+ "\n",
1287
+ "Processing Files (0 / 1) : 79% 2.12G/2.68G [00:21<00:05, 103MB/s, 93.9MB/s ]\n",
1288
+ "New Data Upload : 52% 104M/201M [00:21<00:05, 17.8MB/s, 10.2MB/s ]\u001b[A\n",
1289
+ "\n",
1290
+ "Processing Files (0 / 1) : 80% 2.14G/2.68G [00:21<00:04, 111MB/s, 94.9MB/s ]\n",
1291
+ "New Data Upload : 53% 107M/201M [00:21<00:05, 17.1MB/s, 10.5MB/s ]\u001b[A\n",
1292
+ "\n",
1293
+ "Processing Files (0 / 1) : 81% 2.17G/2.68G [00:22<00:04, 119MB/s, 94.6MB/s ]\n",
1294
+ "New Data Upload : 55% 111M/201M [00:22<00:05, 17.7MB/s, 10.9MB/s ]\u001b[A\n",
1295
+ "\n",
1296
+ "Processing Files (0 / 1) : 82% 2.19G/2.68G [00:22<00:04, 112MB/s, 93.8MB/s ]\n",
1297
+ "New Data Upload : 57% 115M/201M [00:22<00:04, 17.9MB/s, 11.3MB/s ]\u001b[A\n",
1298
+ "\n",
1299
+ "Processing Files (0 / 1) : 82% 2.21G/2.68G [00:22<00:04, 107MB/s, 93.4MB/s ]\n",
1300
+ "New Data Upload : 59% 119M/201M [00:22<00:04, 18.8MB/s, 11.7MB/s ]\u001b[A\n",
1301
+ "\n",
1302
+ "Processing Files (0 / 1) : 83% 2.23G/2.68G [00:22<00:03, 116MB/s, 96.1MB/s ]\n",
1303
+ "New Data Upload : 61% 123M/201M [00:22<00:04, 19.4MB/s, 12.1MB/s ]\u001b[A\n",
1304
+ "\n",
1305
+ "Processing Files (0 / 1) : 84% 2.25G/2.68G [00:22<00:04, 106MB/s, 96.6MB/s ]\n",
1306
+ "New Data Upload : 62% 125M/201M [00:22<00:04, 16.7MB/s, 12.3MB/s ]\u001b[A\n",
1307
+ "\n",
1308
+ "Processing Files (0 / 1) : 85% 2.28G/2.68G [00:23<00:03, 112MB/s, 96.3MB/s ]\n",
1309
+ "New Data Upload : 63% 127M/201M [00:23<00:05, 14.1MB/s, 12.4MB/s ]\u001b[A\n",
1310
+ "\n",
1311
+ "Processing Files (0 / 1) : 86% 2.30G/2.68G [00:23<00:03, 109MB/s, 96.8MB/s ]\n",
1312
+ "New Data Upload : 66% 132M/201M [00:23<00:03, 17.8MB/s, 12.9MB/s ]\u001b[A\n",
1313
+ "\n",
1314
+ "Processing Files (0 / 1) : 87% 2.32G/2.68G [00:23<00:03, 108MB/s, 98.9MB/s ]\n",
1315
+ "New Data Upload : 69% 138M/201M [00:23<00:02, 21.9MB/s, 13.5MB/s ]\u001b[A\n",
1316
+ "\n",
1317
+ "Processing Files (0 / 1) : 87% 2.34G/2.68G [00:23<00:03, 106MB/s, 101MB/s ]\n",
1318
+ "New Data Upload : 71% 143M/201M [00:23<00:02, 22.5MB/s, 14.0MB/s ]\u001b[A\n",
1319
+ "\n",
1320
+ "Processing Files (0 / 1) : 88% 2.36G/2.68G [00:23<00:02, 110MB/s, 103MB/s ]\n",
1321
+ "New Data Upload : 72% 145M/201M [00:23<00:03, 18.1MB/s, 14.0MB/s ]\u001b[A\n",
1322
+ "\n",
1323
+ "Processing Files (0 / 1) : 89% 2.37G/2.68G [00:24<00:03, 95.0MB/s, 104MB/s ]\n",
1324
+ "New Data Upload : 73% 146M/201M [00:24<00:03, 15.0MB/s, 14.1MB/s ]\u001b[A\n",
1325
+ "\n",
1326
+ "Processing Files (0 / 1) : 89% 2.37G/2.68G [00:24<00:04, 69.1MB/s, 104MB/s ]\n",
1327
+ "New Data Upload : 74% 148M/201M [00:24<00:04, 12.9MB/s, 13.9MB/s ]\u001b[A\n",
1328
+ "\n",
1329
+ "Processing Files (0 / 1) : 89% 2.39G/2.68G [00:24<00:03, 71.9MB/s, 106MB/s ]\n",
1330
+ "\n",
1331
+ "Processing Files (0 / 1) : 89% 2.39G/2.68G [00:24<00:05, 53.7MB/s, 106MB/s ]\n",
1332
+ "New Data Upload : 75% 150M/201M [00:24<00:05, 9.26MB/s, 14.0MB/s ]\u001b[A\n",
1333
+ "\n",
1334
+ "Processing Files (0 / 1) : 89% 2.39G/2.68G [00:24<00:07, 40.1MB/s, 106MB/s ]\n",
1335
+ "New Data Upload : 75% 152M/201M [00:24<00:05, 8.96MB/s, 14.0MB/s ]\u001b[A\n",
1336
+ "\n",
1337
+ "Processing Files (0 / 1) : 89% 2.40G/2.68G [00:25<00:09, 30.4MB/s, 105MB/s ]\n",
1338
+ "New Data Upload : 76% 153M/201M [00:25<00:05, 8.69MB/s, 13.7MB/s ]\u001b[A\n",
1339
+ "\n",
1340
+ "Processing Files (0 / 1) : 90% 2.41G/2.68G [00:25<00:05, 48.6MB/s, 105MB/s ]\n",
1341
+ "New Data Upload : 78% 156M/201M [00:25<00:04, 10.6MB/s, 13.5MB/s ]\u001b[A\n",
1342
+ "\n",
1343
+ "Processing Files (0 / 1) : 91% 2.45G/2.68G [00:25<00:02, 83.3MB/s, 107MB/s ]\n",
1344
+ "New Data Upload : 79% 158M/201M [00:25<00:04, 9.89MB/s, 13.2MB/s ]\u001b[A\n",
1345
+ "\n",
1346
+ "Processing Files (0 / 1) : 93% 2.48G/2.68G [00:25<00:01, 105MB/s, 110MB/s ] \n",
1347
+ "New Data Upload : 79% 160M/201M [00:25<00:04, 9.30MB/s, 12.9MB/s ]\u001b[A\n",
1348
+ "\n",
1349
+ "Processing Files (0 / 1) : 94% 2.51G/2.68G [00:25<00:01, 122MB/s, 111MB/s ]\n",
1350
+ "New Data Upload : 80% 161M/201M [00:25<00:04, 8.89MB/s, 12.6MB/s ]\u001b[A\n",
1351
+ "\n",
1352
+ "Processing Files (0 / 1) : 95% 2.54G/2.68G [00:26<00:01, 132MB/s, 111MB/s ]\n",
1353
+ "\n",
1354
+ "Processing Files (0 / 1) : 95% 2.55G/2.68G [00:26<00:01, 107MB/s, 109MB/s ]\n",
1355
+ "New Data Upload : 61% 163M/268M [00:26<00:14, 7.29MB/s, 12.2MB/s ]\u001b[A\n",
1356
+ "\n",
1357
+ "Processing Files (0 / 1) : 96% 2.57G/2.68G [00:26<00:00, 110MB/s, 109MB/s ]\n",
1358
+ "New Data Upload : 62% 166M/270M [00:26<00:11, 9.37MB/s, 12.0MB/s ]\u001b[A\n",
1359
+ "\n",
1360
+ "Processing Files (0 / 1) : 96% 2.58G/2.68G [00:26<00:01, 79.9MB/s, 106MB/s ]\n",
1361
+ "New Data Upload : 63% 168M/270M [00:26<00:10, 9.68MB/s, 11.7MB/s ]\u001b[A\n",
1362
+ "\n",
1363
+ "Processing Files (0 / 1) : 96% 2.58G/2.68G [00:26<00:01, 58.3MB/s, 103MB/s ]\n",
1364
+ "New Data Upload : 63% 170M/270M [00:26<00:10, 9.21MB/s, 11.3MB/s ]\u001b[A\n",
1365
+ "\n",
1366
+ "Processing Files (0 / 1) : 96% 2.58G/2.68G [00:27<00:02, 43.2MB/s, 100MB/s ]\n",
1367
+ "New Data Upload : 64% 172M/270M [00:27<00:11, 8.86MB/s, 10.8MB/s ]\u001b[A\n",
1368
+ "\n",
1369
+ "Processing Files (0 / 1) : 96% 2.58G/2.68G [00:27<00:02, 34.2MB/s, 97.1MB/s ]\n",
1370
+ "New Data Upload : 65% 174M/270M [00:27<00:09, 10.1MB/s, 10.6MB/s ]\u001b[A\n",
1371
+ "\n",
1372
+ "Processing Files (0 / 1) : 97% 2.58G/2.68G [00:27<00:03, 27.1MB/s, 94.6MB/s ]\n",
1373
+ "New Data Upload : 65% 176M/270M [00:27<00:09, 10.2MB/s, 10.8MB/s ]\u001b[A\n",
1374
+ "\n",
1375
+ "Processing Files (0 / 1) : 97% 2.59G/2.68G [00:27<00:04, 21.0MB/s, 92.0MB/s ]\n",
1376
+ "New Data Upload : 66% 178M/270M [00:27<00:09, 9.19MB/s, 10.9MB/s ]\u001b[A\n",
1377
+ "\n",
1378
+ "Processing Files (0 / 1) : 97% 2.59G/2.68G [00:27<00:04, 21.0MB/s, 89.7MB/s ]\n",
1379
+ "New Data Upload : 68% 182M/270M [00:27<00:06, 12.7MB/s, 11.3MB/s ]\u001b[A\n",
1380
+ "\n",
1381
+ "Processing Files (0 / 1) : 97% 2.59G/2.68G [00:28<00:05, 17.1MB/s, 90.0MB/s ]\n",
1382
+ "New Data Upload : 68% 184M/270M [00:28<00:07, 11.3MB/s, 11.5MB/s ]\u001b[A\n",
1383
+ "\n",
1384
+ "Processing Files (0 / 1) : 97% 2.60G/2.68G [00:28<00:04, 19.1MB/s, 88.2MB/s ]\n",
1385
+ "New Data Upload : 70% 188M/270M [00:28<00:05, 15.0MB/s, 11.9MB/s ]\u001b[A\n",
1386
+ "\n",
1387
+ "Processing Files (0 / 1) : 97% 2.60G/2.68G [00:28<00:05, 15.8MB/s, 86.3MB/s ]\n",
1388
+ "New Data Upload : 70% 190M/270M [00:28<00:06, 12.9MB/s, 12.0MB/s ]\u001b[A\n",
1389
+ "\n",
1390
+ "Processing Files (0 / 1) : 97% 2.60G/2.68G [00:28<00:04, 18.2MB/s, 84.2MB/s ]\n",
1391
+ "New Data Upload : 72% 195M/270M [00:28<00:04, 16.2MB/s, 12.5MB/s ]\u001b[A\n",
1392
+ "\n",
1393
+ "Processing Files (0 / 1) : 97% 2.61G/2.68G [00:28<00:03, 19.9MB/s, 82.0MB/s ]\n",
1394
+ "New Data Upload : 74% 199M/270M [00:28<00:03, 18.5MB/s, 12.9MB/s ]\u001b[A\n",
1395
+ "\n",
1396
+ "Processing Files (0 / 1) : 98% 2.61G/2.68G [00:29<00:02, 23.5MB/s, 80.6MB/s ]\n",
1397
+ "New Data Upload : 76% 206M/270M [00:29<00:02, 22.5MB/s, 13.5MB/s ]\u001b[A\n",
1398
+ "\n",
1399
+ "Processing Files (0 / 1) : 98% 2.62G/2.68G [00:29<00:02, 22.8MB/s, 81.0MB/s ]\n",
1400
+ "New Data Upload : 78% 210M/270M [00:29<00:02, 22.1MB/s, 13.9MB/s ]\u001b[A\n",
1401
+ "\n",
1402
+ "Processing Files (0 / 1) : 98% 2.62G/2.68G [00:29<00:02, 21.5MB/s, 79.1MB/s ]\n",
1403
+ "New Data Upload : 79% 214M/270M [00:29<00:02, 21.0MB/s, 14.2MB/s ]\u001b[A\n",
1404
+ "\n",
1405
+ "Processing Files (0 / 1) : 98% 2.63G/2.68G [00:29<00:02, 21.4MB/s, 76.3MB/s ]\n",
1406
+ "New Data Upload : 81% 218M/270M [00:29<00:02, 21.1MB/s, 14.5MB/s ]\u001b[A\n",
1407
+ "\n",
1408
+ "Processing Files (0 / 1) : 98% 2.63G/2.68G [00:29<00:01, 23.8MB/s, 76.7MB/s ]\n",
1409
+ "New Data Upload : 83% 224M/270M [00:29<00:01, 23.5MB/s, 14.9MB/s ]\u001b[A\n",
1410
+ "\n",
1411
+ "Processing Files (0 / 1) : 98% 2.63G/2.68G [00:30<00:02, 19.0MB/s, 73.6MB/s ]\n",
1412
+ "New Data Upload : 84% 225M/270M [00:30<00:02, 18.8MB/s, 14.8MB/s ]\u001b[A\n",
1413
+ "\n",
1414
+ "Processing Files (0 / 1) : 99% 2.64G/2.68G [00:30<00:01, 20.5MB/s, 70.9MB/s ]\n",
1415
+ "New Data Upload : 85% 230M/270M [00:30<00:01, 20.3MB/s, 14.9MB/s ]\u001b[A\n",
1416
+ "\n",
1417
+ "Processing Files (0 / 1) : 99% 2.64G/2.68G [00:30<00:01, 23.9MB/s, 68.9MB/s ]\n",
1418
+ "New Data Upload : 88% 237M/270M [00:30<00:01, 23.8MB/s, 15.2MB/s ]\u001b[A\n",
1419
+ "\n",
1420
+ "Processing Files (0 / 1) : 99% 2.65G/2.68G [00:30<00:01, 21.5MB/s, 65.5MB/s ]\n",
1421
+ "New Data Upload : 89% 240M/270M [00:30<00:01, 21.4MB/s, 15.4MB/s ]\u001b[A\n",
1422
+ "\n",
1423
+ "Processing Files (0 / 1) : 99% 2.65G/2.68G [00:30<00:01, 19.8MB/s, 63.2MB/s ]\n",
1424
+ "New Data Upload : 90% 243M/270M [00:30<00:01, 19.8MB/s, 15.4MB/s ]\u001b[A\n",
1425
+ "\n",
1426
+ "Processing Files (0 / 1) : 99% 2.65G/2.68G [00:31<00:01, 18.7MB/s, 60.2MB/s ]\n",
1427
+ "New Data Upload : 91% 246M/270M [00:31<00:01, 18.6MB/s, 15.4MB/s ]\u001b[A\n",
1428
+ "\n",
1429
+ "Processing Files (0 / 1) : 99% 2.66G/2.68G [00:31<00:01, 17.8MB/s, 57.9MB/s ]\n",
1430
+ "New Data Upload : 93% 249M/270M [00:31<00:01, 17.8MB/s, 15.4MB/s ]\u001b[A\n",
1431
+ "\n",
1432
+ "Processing Files (0 / 1) : 99% 2.66G/2.68G [00:31<00:00, 17.3MB/s, 56.7MB/s ]\n",
1433
+ "New Data Upload : 94% 253M/270M [00:31<00:00, 17.3MB/s, 15.3MB/s ]\u001b[A\n",
1434
+ "\n",
1435
+ " ...4fmqprp/model.safetensors: 99% 2.66G/2.68G [00:28<00:00, 91.3MB/s]\u001b[A\u001b[A\n",
1436
+ "\n",
1437
+ "Processing Files (0 / 1) : 99% 2.66G/2.68G [00:31<00:01, 13.0MB/s, 53.8MB/s ]\n",
1438
+ "New Data Upload : 95% 256M/270M [00:31<00:01, 13.0MB/s, 14.8MB/s ]\u001b[A\n",
1439
+ "\n",
1440
+ "Processing Files (0 / 1) : 100% 2.67G/2.68G [00:32<00:00, 14.2MB/s, 51.6MB/s ]\n",
1441
+ "New Data Upload : 96% 259M/270M [00:32<00:00, 14.2MB/s, 14.9MB/s ]\u001b[A\n",
1442
+ "\n",
1443
+ "Processing Files (0 / 1) : 100% 2.67G/2.68G [00:32<00:00, 14.7MB/s, 49.2MB/s ]\n",
1444
+ "New Data Upload : 97% 263M/270M [00:32<00:00, 14.7MB/s, 14.8MB/s ]\u001b[A\n",
1445
+ "\n",
1446
+ "Processing Files (0 / 1) : 100% 2.67G/2.68G [00:32<00:00, 15.0MB/s, 47.7MB/s ]\n",
1447
+ "New Data Upload : 99% 266M/270M [00:32<00:00, 15.0MB/s, 14.8MB/s ]\u001b[A\n",
1448
+ "\n",
1449
+ "Processing Files (0 / 1) : 100% 2.68G/2.68G [00:32<00:00, 15.3MB/s, 46.1MB/s ]\n",
1450
+ "New Data Upload : 100% 269M/270M [00:32<00:00, 15.3MB/s, 14.7MB/s ]\u001b[A\n",
1451
+ "\n",
1452
+ "Processing Files (0 / 1) : 100% 2.68G/2.68G [00:32<00:00, 11.7MB/s, 43.5MB/s ]\n",
1453
+ "New Data Upload : 100% 269M/270M [00:32<00:00, 11.7MB/s, 14.3MB/s ]\u001b[A\n",
1454
+ "\n",
1455
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:30<00:00, 87.6MB/s]\u001b[A\u001b[A\n",
1456
+ "\n",
1457
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:30<00:00, 87.1MB/s]\u001b[A\u001b[A\n",
1458
+ "\n",
1459
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:30<00:00, 86.5MB/s]\u001b[A\u001b[A\n",
1460
+ "\n",
1461
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:30<00:00, 85.9MB/s]\u001b[A\u001b[A\n",
1462
+ "\n",
1463
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:30<00:00, 85.4MB/s]\u001b[A\u001b[A\n",
1464
+ "\n",
1465
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:31<00:00, 84.8MB/s]\u001b[A\u001b[A\n",
1466
+ "\n",
1467
+ "Processing Files (1 / 1) : 100% 2.68G/2.68G [00:34<00:00, 3.10MB/s, 29.8MB/s ]\n",
1468
+ "New Data Upload : 100% 270M/270M [00:34<00:00, 3.10MB/s, 12.1MB/s ]\u001b[A\n",
1469
+ "\n",
1470
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:31<00:00, 83.8MB/s]\u001b[A\u001b[A\n",
1471
+ "\n",
1472
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:31<00:00, 83.2MB/s]\u001b[A\u001b[A\n",
1473
+ "\n",
1474
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:31<00:00, 82.7MB/s]\u001b[A\u001b[A\n",
1475
+ "\n",
1476
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:32<00:00, 82.2MB/s]\u001b[A\u001b[A\n",
1477
+ "\n",
1478
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:32<00:00, 81.7MB/s]\u001b[A\u001b[A\n",
1479
+ "\n",
1480
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:32<00:00, 81.2MB/s]\u001b[A\u001b[A\n",
1481
+ "\n",
1482
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:32<00:00, 80.7MB/s]\u001b[A\u001b[A\n",
1483
+ "\n",
1484
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:32<00:00, 80.2MB/s]\u001b[A\u001b[A\n",
1485
+ "\n",
1486
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:33<00:00, 79.7MB/s]\u001b[A\u001b[A\n",
1487
+ "\n",
1488
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:33<00:00, 79.2MB/s]\u001b[A\u001b[A\n",
1489
+ "\n",
1490
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:33<00:00, 78.8MB/s]\u001b[A\u001b[A\n",
1491
+ "\n",
1492
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:33<00:00, 78.4MB/s]\u001b[A\u001b[A\n",
1493
+ "\n",
1494
+ "Processing Files (1 / 1) : 100% 2.68G/2.68G [00:36<00:00, 72.8MB/s, 10.1MB/s ]\n",
1495
+ "New Data Upload : 100% 270M/270M [00:36<00:00, 7.33MB/s, 10.1MB/s ]\n",
1496
+ " ...4fmqprp/model.safetensors: 100% 2.68G/2.68G [00:33<00:00, 78.3MB/s]\n",
1497
+ "\n",
1498
+ "README.md: 100% 690/690 [00:00<00:00, 5.23MB/s]\n",
1499
+ "Processing Files (0 / 0) : | | 0.00B / 0.00B \n",
1500
+ "New Data Upload : | | 0.00B / 0.00B \u001b[A\n",
1501
+ "\n",
1502
+ " ...mp5ah361yo/tokenizer.json: 100% 11.4M/11.4M [00:00<?, ?B/s]\u001b[A\u001b[A\n",
1503
+ "\n",
1504
+ "Processing Files (1 / 1) : 100% 11.4M/11.4M [00:00<00:00, 17.0MB/s, 28.6MB/s ]\n",
1505
+ "\n",
1506
+ " ...mp5ah361yo/tokenizer.json: 100% 11.4M/11.4M [00:00<?, ?B/s]\u001b[A\u001b[A\n",
1507
+ "\n",
1508
+ " ...mp5ah361yo/tokenizer.json: 100% 11.4M/11.4M [00:00<?, ?B/s]\u001b[A\u001b[A\n",
1509
+ "\n",
1510
+ " ...mp5ah361yo/tokenizer.json: 100% 11.4M/11.4M [00:00<?, ?B/s]\u001b[A\u001b[A\n",
1511
+ "\n",
1512
+ " ...mp5ah361yo/tokenizer.json: 100% 11.4M/11.4M [00:00<?, ?B/s]\u001b[A\u001b[A\n",
1513
+ "\n",
1514
+ " ...mp5ah361yo/tokenizer.json: 100% 11.4M/11.4M [00:00<?, ?B/s]\u001b[A\u001b[A\n",
1515
+ "\n",
1516
+ " ...mp5ah361yo/tokenizer.json: 100% 11.4M/11.4M [00:01<?, ?B/s]\u001b[A\u001b[A\n",
1517
+ "\n",
1518
+ " ...mp5ah361yo/tokenizer.json: 100% 11.4M/11.4M [00:01<?, ?B/s]\u001b[A\u001b[A\n",
1519
+ "\n",
1520
+ " ...mp5ah361yo/tokenizer.json: 100% 11.4M/11.4M [00:01<?, ?B/s]\u001b[A\u001b[A\n",
1521
+ "\n",
1522
+ " ...mp5ah361yo/tokenizer.json: 100% 11.4M/11.4M [00:01<?, ?B/s]\u001b[A\u001b[A\n",
1523
+ "\n",
1524
+ "Processing Files (1 / 1) : 100% 11.4M/11.4M [00:02<00:00, 4.62MB/s, 5.19MB/s ]\n",
1525
+ "New Data Upload : | | 0.00B / 0.00B, 0.00B/s \n",
1526
+ " ...mp5ah361yo/tokenizer.json: 100% 11.4M/11.4M [00:01<?, ?B/s]\n",
1527
+ "[OK] Model pushed -> https://huggingface.co/OGrohit/logtriage-sre-agent\n",
1528
+ "\n",
1529
+ "============================================================\n",
1530
+ "[OK] TRAINING COMPLETE\n",
1531
+ "============================================================\n",
1532
+ " Reward curve: reward_curve.png\n",
1533
+ " Trained model: ./logtriage-trained\n",
1534
+ " HF Hub: https://huggingface.co/OGrohit/logtriage-sre-agent\n",
1535
+ "\n",
1536
+ " Use reward_curve.png in your demo slide.\n",
1537
+ " This image is 20% of your judging score.\n",
1538
+ "\n",
1539
+ " 0% 0/10 [06:19<?, ?it/s]\n"
1540
+ ]
1541
+ }
1542
+ ]
1543
+ },
1544
+ {
1545
+ "cell_type": "code",
1546
+ "source": [
1547
+ "!python merge_curves.py"
1548
+ ],
1549
+ "metadata": {
1550
+ "colab": {
1551
+ "base_uri": "https://localhost:8080/"
1552
+ },
1553
+ "id": "RMalsurHCPU3",
1554
+ "outputId": "e4e405b1-d1ff-40ad-955f-a3c976db6bc6"
1555
+ },
1556
+ "execution_count": 6,
1557
+ "outputs": [
1558
+ {
1559
+ "output_type": "stream",
1560
+ "name": "stdout",
1561
+ "text": [
1562
+ "\n",
1563
+ "=== merge_curves.py ===\n",
1564
+ "Checkpoint dir : ./phase2_checkpoints\n",
1565
+ "Output : reward_curve.png\n",
1566
+ "\n",
1567
+ "[OK] single_crash: loaded 25 episodes from single_crash_ep25.json\n",
1568
+ " single_crash:\n",
1569
+ " First 10 avg : +0.180\n",
1570
+ " Last 10 avg : +0.145\n",
1571
+ " Improvement : -0.035\n",
1572
+ "[OK] cascading_failure: loaded 25 episodes from cascading_failure_ep25.json\n",
1573
+ " cascading_failure:\n",
1574
+ " First 10 avg : +0.090\n",
1575
+ " Last 10 avg : +0.185\n",
1576
+ " Improvement : +0.095\n",
1577
+ "[OK] silent_degradation: loaded 25 episodes from silent_degradation_ep25.json\n",
1578
+ " silent_degradation:\n",
1579
+ " First 10 avg : +0.180\n",
1580
+ " Last 10 avg : +0.210\n",
1581
+ " Improvement : +0.030\n",
1582
+ "\n",
1583
+ "[OK] Saved: reward_curve.png\n",
1584
+ " Open with: start reward_curve.png\n",
1585
+ " Push with: git add reward_curve.png && git commit -m 'feat: 3-task reward curve' && git push\n"
1586
+ ]
1587
+ }
1588
+ ]
1589
+ },
1590
+ {
1591
+ "cell_type": "code",
1592
+ "source": [
1593
+ " from google.colab import files\n",
1594
+ " files.download(\"reward_curve.png\")"
1595
+ ],
1596
+ "metadata": {
1597
+ "colab": {
1598
+ "base_uri": "https://localhost:8080/",
1599
+ "height": 17
1600
+ },
1601
+ "id": "jMipwtccCUBG",
1602
+ "outputId": "425ced85-97bf-48c8-ec8a-c85fb720258d"
1603
+ },
1604
+ "execution_count": 7,
1605
+ "outputs": [
1606
+ {
1607
+ "output_type": "display_data",
1608
+ "data": {
1609
+ "text/plain": [
1610
+ "<IPython.core.display.Javascript object>"
1611
+ ],
1612
+ "application/javascript": [
1613
+ "\n",
1614
+ " async function download(id, filename, size) {\n",
1615
+ " if (!google.colab.kernel.accessAllowed) {\n",
1616
+ " return;\n",
1617
+ " }\n",
1618
+ " const div = document.createElement('div');\n",
1619
+ " const label = document.createElement('label');\n",
1620
+ " label.textContent = `Downloading \"${filename}\": `;\n",
1621
+ " div.appendChild(label);\n",
1622
+ " const progress = document.createElement('progress');\n",
1623
+ " progress.max = size;\n",
1624
+ " div.appendChild(progress);\n",
1625
+ " document.body.appendChild(div);\n",
1626
+ "\n",
1627
+ " const buffers = [];\n",
1628
+ " let downloaded = 0;\n",
1629
+ "\n",
1630
+ " const channel = await google.colab.kernel.comms.open(id);\n",
1631
+ " // Send a message to notify the kernel that we're ready.\n",
1632
+ " channel.send({})\n",
1633
+ "\n",
1634
+ " for await (const message of channel.messages) {\n",
1635
+ " // Send a message to notify the kernel that we're ready.\n",
1636
+ " channel.send({})\n",
1637
+ " if (message.buffers) {\n",
1638
+ " for (const buffer of message.buffers) {\n",
1639
+ " buffers.push(buffer);\n",
1640
+ " downloaded += buffer.byteLength;\n",
1641
+ " progress.value = downloaded;\n",
1642
+ " }\n",
1643
+ " }\n",
1644
+ " }\n",
1645
+ " const blob = new Blob(buffers, {type: 'application/binary'});\n",
1646
+ " const a = document.createElement('a');\n",
1647
+ " a.href = window.URL.createObjectURL(blob);\n",
1648
+ " a.download = filename;\n",
1649
+ " div.appendChild(a);\n",
1650
+ " a.click();\n",
1651
+ " div.remove();\n",
1652
+ " }\n",
1653
+ " "
1654
+ ]
1655
+ },
1656
+ "metadata": {}
1657
+ },
1658
+ {
1659
+ "output_type": "display_data",
1660
+ "data": {
1661
+ "text/plain": [
1662
+ "<IPython.core.display.Javascript object>"
1663
+ ],
1664
+ "application/javascript": [
1665
+ "download(\"download_1efc715d-f3eb-4702-86d0-e541c09e6c15\", \"reward_curve.png\", 268703)"
1666
+ ]
1667
+ },
1668
+ "metadata": {}
1669
+ }
1670
+ ]
1671
+ }
1672
+ ]
1673
+ }