Auto upload zain 2026-08-12T19:22:26.649327
Browse files- zain/Activation/out/glu-waleed10-150L_run/training_log.jsonl +24 -0
- zain/Activation/wandb/debug-internal.log +40 -0
- zain/Activation/wandb/run-20260812_191207-w1cgnksl/files/output.log +26 -1
- zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug-internal.log +40 -0
- zain/Activation/wandb/run-20260812_191207-w1cgnksl/run-w1cgnksl.wandb +2 -2
zain/Activation/out/glu-waleed10-150L_run/training_log.jsonl
CHANGED
|
@@ -25,3 +25,27 @@
|
|
| 25 |
{"step": 360, "epoch": 0.024266936299292215, "timestamp": 1786562227.86508, "loss": 5.534560775756836, "grad_norm": 0.1875, "learning_rate": 0.005, "train/total_time_seconds": 131.27342559024692, "train/time_per_step_avg": 0.3643398737534881, "train/epoch_time_elapsed": 299.6833920404315, "train/estimated_remaining_minutes": 3.8895829804517605}
|
| 26 |
{"step": 380, "epoch": 0.02561509942703067, "timestamp": 1786562235.9926372, "loss": 5.449129104614258, "grad_norm": 0.66015625, "learning_rate": 0.005, "train/total_time_seconds": 138.37890404090285, "train/time_per_step_avg": 0.3613042406737804, "train/epoch_time_elapsed": 307.81094805151224, "train/estimated_remaining_minutes": 3.7629351098842005}
|
| 27 |
{"step": 400, "epoch": 0.026963262554769128, "timestamp": 1786562244.3724, "loss": 5.375603103637696, "grad_norm": 0.35546875, "learning_rate": 0.005, "train/total_time_seconds": 145.75075655430555, "train/time_per_step_avg": 0.36436228182166813, "train/epoch_time_elapsed": 316.1907127723098, "train/estimated_remaining_minutes": 3.643768913857639}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
{"step": 360, "epoch": 0.024266936299292215, "timestamp": 1786562227.86508, "loss": 5.534560775756836, "grad_norm": 0.1875, "learning_rate": 0.005, "train/total_time_seconds": 131.27342559024692, "train/time_per_step_avg": 0.3643398737534881, "train/epoch_time_elapsed": 299.6833920404315, "train/estimated_remaining_minutes": 3.8895829804517605}
|
| 26 |
{"step": 380, "epoch": 0.02561509942703067, "timestamp": 1786562235.9926372, "loss": 5.449129104614258, "grad_norm": 0.66015625, "learning_rate": 0.005, "train/total_time_seconds": 138.37890404090285, "train/time_per_step_avg": 0.3613042406737804, "train/epoch_time_elapsed": 307.81094805151224, "train/estimated_remaining_minutes": 3.7629351098842005}
|
| 27 |
{"step": 400, "epoch": 0.026963262554769128, "timestamp": 1786562244.3724, "loss": 5.375603103637696, "grad_norm": 0.35546875, "learning_rate": 0.005, "train/total_time_seconds": 145.75075655430555, "train/time_per_step_avg": 0.36436228182166813, "train/epoch_time_elapsed": 316.1907127723098, "train/estimated_remaining_minutes": 3.643768913857639}
|
| 28 |
+
{"step": 400, "epoch": 0.026963262554769128, "timestamp": 1786562265.7661924, "eval_loss": 5.315079689025879, "eval_runtime": 21.3923, "eval_samples_per_second": 445.348, "eval_steps_per_second": 3.506, "train/total_time_seconds": 145.75075655430555, "train/time_per_step_avg": 0.36436228182166813, "train/epoch_time_elapsed": 337.5845051333308, "train/estimated_remaining_minutes": 3.643768913857639}
|
| 29 |
+
{"step": 420, "epoch": 0.028311425682507583, "timestamp": 1786562274.101557, "loss": 5.217065048217774, "grad_norm": 1.0859375, "learning_rate": 0.005, "train/total_time_seconds": 153.08759658783674, "train/time_per_step_avg": 0.36430149983614685, "train/epoch_time_elapsed": 345.91986951231956, "train/estimated_remaining_minutes": 3.5234446833708457}
|
| 30 |
+
{"step": 440, "epoch": 0.02965958881024604, "timestamp": 1786562282.401063, "loss": 5.086183166503906, "grad_norm": 0.56640625, "learning_rate": 0.005, "train/total_time_seconds": 160.40237145125866, "train/time_per_step_avg": 0.36351748924702404, "train/epoch_time_elapsed": 354.2193754911423, "train/estimated_remaining_minutes": 3.4024745459357897}
|
| 31 |
+
{"step": 450, "epoch": 0.030333670374115267, "timestamp": 1786562307.9893155, "eval_loss": 4.963188171386719, "eval_runtime": 21.415, "eval_samples_per_second": 444.876, "eval_steps_per_second": 3.502, "train/total_time_seconds": 164.06709665060043, "train/time_per_step_avg": 0.3635347041860223, "train/epoch_time_elapsed": 379.8076265230775, "train/estimated_remaining_minutes": 3.342107524364083}
|
| 32 |
+
{"step": 460, "epoch": 0.031007751937984496, "timestamp": 1786562311.9997342, "loss": 4.954313278198242, "grad_norm": 0.279296875, "learning_rate": 0.005, "train/total_time_seconds": 167.58300157263875, "train/time_per_step_avg": 0.36309575982391834, "train/epoch_time_elapsed": 383.81804628297687, "train/estimated_remaining_minutes": 3.2787978568559755}
|
| 33 |
+
{"step": 480, "epoch": 0.032355915065722954, "timestamp": 1786562320.3468804, "loss": 4.772397994995117, "grad_norm": 0.33984375, "learning_rate": 0.005, "train/total_time_seconds": 174.93495179340243, "train/time_per_step_avg": 0.3655604775249958, "train/epoch_time_elapsed": 392.16519249230623, "train/estimated_remaining_minutes": 3.1585477407142104}
|
| 34 |
+
{"step": 500, "epoch": 0.03370407819346141, "timestamp": 1786562328.4029014, "loss": 4.591049575805664, "grad_norm": 0.79296875, "learning_rate": 0.005, "train/total_time_seconds": 181.98964196816087, "train/time_per_step_avg": 0.36238885413855315, "train/epoch_time_elapsed": 400.22121372818947, "train/estimated_remaining_minutes": 3.033160699469348}
|
| 35 |
+
{"step": 500, "epoch": 0.03370407819346141, "timestamp": 1786562349.7974262, "eval_loss": 4.6361846923828125, "eval_runtime": 21.393, "eval_samples_per_second": 445.332, "eval_steps_per_second": 3.506, "train/total_time_seconds": 181.98964196816087, "train/time_per_step_avg": 0.36238885413855315, "train/epoch_time_elapsed": 421.6157380603254, "train/estimated_remaining_minutes": 3.033160699469348}
|
| 36 |
+
{"step": 520, "epoch": 0.03505224132119986, "timestamp": 1786562357.781215, "loss": 4.517485809326172, "grad_norm": 0.431640625, "learning_rate": 0.005, "train/total_time_seconds": 188.99753200635314, "train/time_per_step_avg": 0.359099354185164, "train/epoch_time_elapsed": 429.5995272435248, "train/estimated_remaining_minutes": 2.907654338559279}
|
| 37 |
+
{"step": 540, "epoch": 0.03640040444893832, "timestamp": 1786562366.143692, "loss": 4.398628234863281, "grad_norm": 0.5390625, "learning_rate": 0.005, "train/total_time_seconds": 196.36287999525666, "train/time_per_step_avg": 0.35960508543998004, "train/epoch_time_elapsed": 437.96200472489, "train/estimated_remaining_minutes": 2.7878680493153722}
|
| 38 |
+
{"step": 550, "epoch": 0.03707448601280755, "timestamp": 1786562391.6367283, "eval_loss": 4.3811798095703125, "eval_runtime": 21.3845, "eval_samples_per_second": 445.509, "eval_steps_per_second": 3.507, "train/total_time_seconds": 199.9754004739225, "train/time_per_step_avg": 0.3590830382332206, "train/epoch_time_elapsed": 463.45503959432244, "train/estimated_remaining_minutes": 2.7269372791898525}
|
| 39 |
+
{"step": 560, "epoch": 0.03774856757667678, "timestamp": 1786562395.6553323, "loss": 4.385685729980469, "grad_norm": 0.341796875, "learning_rate": 0.005, "train/total_time_seconds": 203.4931141473353, "train/time_per_step_avg": 0.3591011257469654, "train/epoch_time_elapsed": 467.473645016551, "train/estimated_remaining_minutes": 2.664790780500819}
|
| 40 |
+
{"step": 580, "epoch": 0.03909673070441524, "timestamp": 1786562403.8999777, "loss": 4.322913742065429, "grad_norm": 0.3984375, "learning_rate": 0.005, "train/total_time_seconds": 210.69783041253686, "train/time_per_step_avg": 0.35762878619134425, "train/epoch_time_elapsed": 475.71829026564956, "train/estimated_remaining_minutes": 2.542904849806479}
|
| 41 |
+
{"step": 600, "epoch": 0.04044489383215369, "timestamp": 1786562412.018503, "loss": 4.283470535278321, "grad_norm": 0.43359375, "learning_rate": 0.005, "train/total_time_seconds": 217.80533869937062, "train/time_per_step_avg": 0.35815696731209756, "train/epoch_time_elapsed": 483.836815148592, "train/estimated_remaining_minutes": 2.4200593188818957}
|
| 42 |
+
{"step": 600, "epoch": 0.04044489383215369, "timestamp": 1786562433.30201, "eval_loss": 4.249608039855957, "eval_runtime": 21.2819, "eval_samples_per_second": 447.658, "eval_steps_per_second": 3.524, "train/total_time_seconds": 217.80533869937062, "train/time_per_step_avg": 0.35815696731209756, "train/epoch_time_elapsed": 505.1203210763633, "train/estimated_remaining_minutes": 2.4200593188818957}
|
| 43 |
+
{"step": 620, "epoch": 0.04179305695989215, "timestamp": 1786562441.4187198, "loss": 4.265676116943359, "grad_norm": 0.58203125, "learning_rate": 0.005, "train/total_time_seconds": 224.89919234067202, "train/time_per_step_avg": 0.35901660334318874, "train/epoch_time_elapsed": 513.2370317876339, "train/estimated_remaining_minutes": 2.2973573411143913}
|
| 44 |
+
{"step": 640, "epoch": 0.043141220087630605, "timestamp": 1786562449.4722443, "loss": 4.22065544128418, "grad_norm": 0.7578125, "learning_rate": 0.005, "train/total_time_seconds": 231.9734827466309, "train/time_per_step_avg": 0.35610602751374243, "train/epoch_time_elapsed": 521.2905562445521, "train/estimated_remaining_minutes": 2.1747514007496647}
|
| 45 |
+
{"step": 650, "epoch": 0.043815301651499834, "timestamp": 1786562474.9117076, "eval_loss": 4.480190277099609, "eval_runtime": 21.4147, "eval_samples_per_second": 444.882, "eval_steps_per_second": 3.502, "train/total_time_seconds": 235.51181496307254, "train/time_per_step_avg": 0.3553641448915005, "train/epoch_time_elapsed": 546.7300181873143, "train/estimated_remaining_minutes": 2.1135675701814205}
|
| 46 |
+
{"step": 660, "epoch": 0.044489383215369056, "timestamp": 1786562478.9174032, "loss": 4.3253837585449215, "grad_norm": 1.75, "learning_rate": 0.005, "train/total_time_seconds": 239.02991192415357, "train/time_per_step_avg": 0.35536797776818274, "train/epoch_time_elapsed": 550.735714904964, "train/estimated_remaining_minutes": 2.0522770215710158}
|
| 47 |
+
{"step": 680, "epoch": 0.045837546343107514, "timestamp": 1786562487.2779944, "loss": 4.34516487121582, "grad_norm": 0.50390625, "learning_rate": 0.005, "train/total_time_seconds": 246.3985892534256, "train/time_per_step_avg": 0.3570075884088874, "train/epoch_time_elapsed": 559.0963061153889, "train/estimated_remaining_minutes": 1.9325379549288282}
|
| 48 |
+
{"step": 700, "epoch": 0.04718570947084597, "timestamp": 1786562495.3207486, "loss": 4.221965408325195, "grad_norm": 1.4765625, "learning_rate": 0.005, "train/total_time_seconds": 253.456104490906, "train/time_per_step_avg": 0.35650765791535377, "train/epoch_time_elapsed": 567.1390607245266, "train/estimated_remaining_minutes": 1.8104007463636145}
|
| 49 |
+
{"step": 700, "epoch": 0.04718570947084597, "timestamp": 1786562516.6689005, "eval_loss": 4.238162517547607, "eval_runtime": 21.3466, "eval_samples_per_second": 446.3, "eval_steps_per_second": 3.513, "train/total_time_seconds": 253.456104490906, "train/time_per_step_avg": 0.35650765791535377, "train/epoch_time_elapsed": 588.4872120581567, "train/estimated_remaining_minutes": 1.8104007463636145}
|
| 50 |
+
{"step": 720, "epoch": 0.04853387259858443, "timestamp": 1786562524.9873672, "loss": 4.538877868652344, "grad_norm": 2.96875, "learning_rate": 0.005, "train/total_time_seconds": 260.77417112514377, "train/time_per_step_avg": 0.3587497878447175, "train/epoch_time_elapsed": 596.805680077523, "train/estimated_remaining_minutes": 1.6902029609963023}
|
| 51 |
+
{"step": 740, "epoch": 0.04988203572632288, "timestamp": 1786562533.3492465, "loss": 4.674048614501953, "grad_norm": 2.53125, "learning_rate": 0.005, "train/total_time_seconds": 268.12411511316895, "train/time_per_step_avg": 0.3615063236653805, "train/epoch_time_elapsed": 605.1675585322082, "train/estimated_remaining_minutes": 1.57009616958162}
|
zain/Activation/wandb/debug-internal.log
CHANGED
|
@@ -49,3 +49,43 @@
|
|
| 49 |
{"time":"2026-08-12T19:17:09.215007025Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 50 |
{"time":"2026-08-12T19:17:24.060863895Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":25,"history_lines":1,"events_offset":40,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 51 |
{"time":"2026-08-12T19:17:24.188633325Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
{"time":"2026-08-12T19:17:09.215007025Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 50 |
{"time":"2026-08-12T19:17:24.060863895Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":25,"history_lines":1,"events_offset":40,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 51 |
{"time":"2026-08-12T19:17:24.188633325Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 52 |
+
{"time":"2026-08-12T19:17:39.060792481Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":26,"history_lines":1,"events_offset":42,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 53 |
+
{"time":"2026-08-12T19:17:39.210094375Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 54 |
+
{"time":"2026-08-12T19:17:54.061471204Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":27,"history_lines":1,"events_offset":44,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 55 |
+
{"time":"2026-08-12T19:17:54.199418171Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 56 |
+
{"time":"2026-08-12T19:18:09.061000182Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":28,"history_lines":2,"events_offset":46,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 57 |
+
{"time":"2026-08-12T19:18:09.209093897Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 58 |
+
{"time":"2026-08-12T19:18:24.060763863Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":48,"events_lines":2,"console_offset":3,"console_lines":1}
|
| 59 |
+
{"time":"2026-08-12T19:18:24.1773145Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 60 |
+
{"time":"2026-08-12T19:18:39.061681015Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":30,"history_lines":2,"events_offset":50,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 61 |
+
{"time":"2026-08-12T19:18:39.213849305Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 62 |
+
{"time":"2026-08-12T19:18:54.061564717Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":32,"history_lines":2,"events_offset":52,"events_lines":2,"console_offset":3,"console_lines":1}
|
| 63 |
+
{"time":"2026-08-12T19:18:54.183311031Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 64 |
+
{"time":"2026-08-12T19:19:09.06124697Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":54,"events_lines":2,"console_offset":11,"console_lines":25}
|
| 65 |
+
{"time":"2026-08-12T19:19:09.197160601Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 66 |
+
{"time":"2026-08-12T19:19:24.061371815Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":34,"history_lines":2,"events_offset":56,"events_lines":2,"console_offset":36,"console_lines":2}
|
| 67 |
+
{"time":"2026-08-12T19:19:24.169446986Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 68 |
+
{"time":"2026-08-12T19:19:39.061619239Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":36,"history_lines":1,"events_offset":58,"events_lines":2,"console_offset":38,"console_lines":1}
|
| 69 |
+
{"time":"2026-08-12T19:19:39.184700489Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 70 |
+
{"time":"2026-08-12T19:19:54.061005576Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":37,"history_lines":1,"events_offset":60,"events_lines":2,"console_offset":39,"console_lines":1}
|
| 71 |
+
{"time":"2026-08-12T19:19:54.203579208Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 72 |
+
{"time":"2026-08-12T19:20:09.061544887Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":38,"history_lines":2,"events_offset":62,"events_lines":2,"console_offset":40,"console_lines":2}
|
| 73 |
+
{"time":"2026-08-12T19:20:09.209145123Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 74 |
+
{"time":"2026-08-12T19:20:24.061085273Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":40,"history_lines":1,"events_offset":64,"events_lines":2,"console_offset":42,"console_lines":1}
|
| 75 |
+
{"time":"2026-08-12T19:20:24.180324215Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 76 |
+
{"time":"2026-08-12T19:20:39.061567669Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":41,"history_lines":1,"events_offset":66,"events_lines":2,"console_offset":43,"console_lines":1}
|
| 77 |
+
{"time":"2026-08-12T19:20:39.187049132Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 78 |
+
{"time":"2026-08-12T19:20:54.060876869Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":42,"history_lines":2,"events_offset":68,"events_lines":2,"console_offset":44,"console_lines":2}
|
| 79 |
+
{"time":"2026-08-12T19:20:54.208534847Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 80 |
+
{"time":"2026-08-12T19:21:09.061014024Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":70,"events_lines":2}
|
| 81 |
+
{"time":"2026-08-12T19:21:09.205590728Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 82 |
+
{"time":"2026-08-12T19:21:24.061230217Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":44,"history_lines":2,"events_offset":72,"events_lines":2,"console_offset":46,"console_lines":2}
|
| 83 |
+
{"time":"2026-08-12T19:21:24.169771183Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 84 |
+
{"time":"2026-08-12T19:21:39.061283547Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":46,"history_lines":2,"events_offset":74,"events_lines":2,"console_offset":48,"console_lines":2}
|
| 85 |
+
{"time":"2026-08-12T19:21:39.17408722Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 86 |
+
{"time":"2026-08-12T19:21:54.061571591Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":76,"events_lines":2}
|
| 87 |
+
{"time":"2026-08-12T19:21:54.160013406Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 88 |
+
{"time":"2026-08-12T19:22:09.061421365Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":48,"history_lines":2,"events_offset":78,"events_lines":2,"console_offset":50,"console_lines":2}
|
| 89 |
+
{"time":"2026-08-12T19:22:09.255653996Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 90 |
+
{"time":"2026-08-12T19:22:24.061485993Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":50,"history_lines":1,"events_offset":80,"events_lines":2,"console_offset":52,"console_lines":1}
|
| 91 |
+
{"time":"2026-08-12T19:22:24.206976463Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
zain/Activation/wandb/run-20260812_191207-w1cgnksl/files/output.log
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
|
| 2 |
{'loss': '7.957', 'grad_norm': '1.258', 'learning_rate': '0.000475', 'epoch': '0.001348', 'train/total_time_seconds': '7.735', 'train/time_per_step_avg': '0.3868', 'train/epoch_time_elapsed': '8.817', 'train/estimated_remaining_minutes': '6.317'}
|
| 3 |
{'loss': '6.816', 'grad_norm': '0.8672', 'learning_rate': '0.000975', 'epoch': '0.002696', 'train/total_time_seconds': '15.15', 'train/time_per_step_avg': '0.3787', 'train/epoch_time_elapsed': '17.24', 'train/estimated_remaining_minutes': '6.059'}
|
| 4 |
|
|
@@ -26,3 +26,28 @@
|
|
| 26 |
{'eval_loss': '5.538', 'eval_runtime': '21.44', 'eval_samples_per_second': '444.3', 'eval_steps_per_second': '3.498', 'epoch': '0.02359', 'train/total_time_seconds': '127.7', 'train/time_per_step_avg': '0.364', 'train/epoch_time_elapsed': '295.6', 'train/estimated_remaining_minutes': '3.953'}
|
| 27 |
{'loss': '5.535', 'grad_norm': '0.1875', 'learning_rate': '0.005', 'epoch': '0.02427', 'train/total_time_seconds': '131.3', 'train/time_per_step_avg': '0.3643', 'train/epoch_time_elapsed': '299.7', 'train/estimated_remaining_minutes': '3.89'}
|
| 28 |
{'loss': '5.449', 'grad_norm': '0.6602', 'learning_rate': '0.005', 'epoch': '0.02562', 'train/total_time_seconds': '138.4', 'train/time_per_step_avg': '0.3613', 'train/epoch_time_elapsed': '307.8', 'train/estimated_remaining_minutes': '3.763'}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
{'loss': '7.957', 'grad_norm': '1.258', 'learning_rate': '0.000475', 'epoch': '0.001348', 'train/total_time_seconds': '7.735', 'train/time_per_step_avg': '0.3868', 'train/epoch_time_elapsed': '8.817', 'train/estimated_remaining_minutes': '6.317'}
|
| 3 |
{'loss': '6.816', 'grad_norm': '0.8672', 'learning_rate': '0.000975', 'epoch': '0.002696', 'train/total_time_seconds': '15.15', 'train/time_per_step_avg': '0.3787', 'train/epoch_time_elapsed': '17.24', 'train/estimated_remaining_minutes': '6.059'}
|
| 4 |
|
|
|
|
| 26 |
{'eval_loss': '5.538', 'eval_runtime': '21.44', 'eval_samples_per_second': '444.3', 'eval_steps_per_second': '3.498', 'epoch': '0.02359', 'train/total_time_seconds': '127.7', 'train/time_per_step_avg': '0.364', 'train/epoch_time_elapsed': '295.6', 'train/estimated_remaining_minutes': '3.953'}
|
| 27 |
{'loss': '5.535', 'grad_norm': '0.1875', 'learning_rate': '0.005', 'epoch': '0.02427', 'train/total_time_seconds': '131.3', 'train/time_per_step_avg': '0.3643', 'train/epoch_time_elapsed': '299.7', 'train/estimated_remaining_minutes': '3.89'}
|
| 28 |
{'loss': '5.449', 'grad_norm': '0.6602', 'learning_rate': '0.005', 'epoch': '0.02562', 'train/total_time_seconds': '138.4', 'train/time_per_step_avg': '0.3613', 'train/epoch_time_elapsed': '307.8', 'train/estimated_remaining_minutes': '3.763'}
|
| 29 |
+
{'loss': '5.376', 'grad_norm': '0.3555', 'learning_rate': '0.005', 'epoch': '0.02696', 'train/total_time_seconds': '145.8', 'train/time_per_step_avg': '0.3644', 'train/epoch_time_elapsed': '316.2', 'train/estimated_remaining_minutes': '3.644'}
|
| 30 |
+
{'eval_loss': '5.315', 'eval_runtime': '21.39', 'eval_samples_per_second': '445.3', 'eval_steps_per_second': '3.506', 'epoch': '0.02696', 'train/total_time_seconds': '145.8', 'train/time_per_step_avg': '0.3644', 'train/epoch_time_elapsed': '337.6', 'train/estimated_remaining_minutes': '3.644'}
|
| 31 |
+
{'loss': '5.217', 'grad_norm': '1.086', 'learning_rate': '0.005', 'epoch': '0.02831', 'train/total_time_seconds': '153.1', 'train/time_per_step_avg': '0.3643', 'train/epoch_time_elapsed': '345.9', 'train/estimated_remaining_minutes': '3.523'}
|
| 32 |
+
{'loss': '5.086', 'grad_norm': '0.5664', 'learning_rate': '0.005', 'epoch': '0.02966', 'train/total_time_seconds': '160.4', 'train/time_per_step_avg': '0.3635', 'train/epoch_time_elapsed': '354.2', 'train/estimated_remaining_minutes': '3.402'}
|
| 33 |
+
{'eval_loss': '4.963', 'eval_runtime': '21.41', 'eval_samples_per_second': '444.9', 'eval_steps_per_second': '3.502', 'epoch': '0.03033', 'train/total_time_seconds': '164.1', 'train/time_per_step_avg': '0.3635', 'train/epoch_time_elapsed': '379.8', 'train/estimated_remaining_minutes': '3.342'}
|
| 34 |
+
{'loss': '4.954', 'grad_norm': '0.2793', 'learning_rate': '0.005', 'epoch': '0.03101', 'train/total_time_seconds': '167.6', 'train/time_per_step_avg': '0.3631', 'train/epoch_time_elapsed': '383.8', 'train/estimated_remaining_minutes': '3.279'}
|
| 35 |
+
{'loss': '4.772', 'grad_norm': '0.3398', 'learning_rate': '0.005', 'epoch': '0.03236', 'train/total_time_seconds': '174.9', 'train/time_per_step_avg': '0.3656', 'train/epoch_time_elapsed': '392.2', 'train/estimated_remaining_minutes': '3.159'}
|
| 36 |
+
{'loss': '4.591', 'grad_norm': '0.793', 'learning_rate': '0.005', 'epoch': '0.0337', 'train/total_time_seconds': '182', 'train/time_per_step_avg': '0.3624', 'train/epoch_time_elapsed': '400.2', 'train/estimated_remaining_minutes': '3.033'}
|
| 37 |
+
{'eval_loss': '4.636', 'eval_runtime': '21.39', 'eval_samples_per_second': '445.3', 'eval_steps_per_second': '3.506', 'epoch': '0.0337', 'train/total_time_seconds': '182', 'train/time_per_step_avg': '0.3624', 'train/epoch_time_elapsed': '421.6', 'train/estimated_remaining_minutes': '3.033'}
|
| 38 |
+
{'loss': '4.517', 'grad_norm': '0.4316', 'learning_rate': '0.005', 'epoch': '0.03505', 'train/total_time_seconds': '189', 'train/time_per_step_avg': '0.3591', 'train/epoch_time_elapsed': '429.6', 'train/estimated_remaining_minutes': '2.908'}
|
| 39 |
+
{'loss': '4.399', 'grad_norm': '0.5391', 'learning_rate': '0.005', 'epoch': '0.0364', 'train/total_time_seconds': '196.4', 'train/time_per_step_avg': '0.3596', 'train/epoch_time_elapsed': '438', 'train/estimated_remaining_minutes': '2.788'}
|
| 40 |
+
{'eval_loss': '4.381', 'eval_runtime': '21.38', 'eval_samples_per_second': '445.5', 'eval_steps_per_second': '3.507', 'epoch': '0.03707', 'train/total_time_seconds': '200', 'train/time_per_step_avg': '0.3591', 'train/epoch_time_elapsed': '463.5', 'train/estimated_remaining_minutes': '2.727'}
|
| 41 |
+
{'loss': '4.386', 'grad_norm': '0.3418', 'learning_rate': '0.005', 'epoch': '0.03775', 'train/total_time_seconds': '203.5', 'train/time_per_step_avg': '0.3591', 'train/epoch_time_elapsed': '467.5', 'train/estimated_remaining_minutes': '2.665'}
|
| 42 |
+
{'loss': '4.323', 'grad_norm': '0.3984', 'learning_rate': '0.005', 'epoch': '0.0391', 'train/total_time_seconds': '210.7', 'train/time_per_step_avg': '0.3576', 'train/epoch_time_elapsed': '475.7', 'train/estimated_remaining_minutes': '2.543'}
|
| 43 |
+
{'loss': '4.283', 'grad_norm': '0.4336', 'learning_rate': '0.005', 'epoch': '0.04044', 'train/total_time_seconds': '217.8', 'train/time_per_step_avg': '0.3582', 'train/epoch_time_elapsed': '483.8', 'train/estimated_remaining_minutes': '2.42'}
|
| 44 |
+
{'eval_loss': '4.25', 'eval_runtime': '21.28', 'eval_samples_per_second': '447.7', 'eval_steps_per_second': '3.524', 'epoch': '0.04044', 'train/total_time_seconds': '217.8', 'train/time_per_step_avg': '0.3582', 'train/epoch_time_elapsed': '505.1', 'train/estimated_remaining_minutes': '2.42'}
|
| 45 |
+
{'loss': '4.266', 'grad_norm': '0.582', 'learning_rate': '0.005', 'epoch': '0.04179', 'train/total_time_seconds': '224.9', 'train/time_per_step_avg': '0.359', 'train/epoch_time_elapsed': '513.2', 'train/estimated_remaining_minutes': '2.297'}
|
| 46 |
+
{'loss': '4.221', 'grad_norm': '0.7578', 'learning_rate': '0.005', 'epoch': '0.04314', 'train/total_time_seconds': '232', 'train/time_per_step_avg': '0.3561', 'train/epoch_time_elapsed': '521.3', 'train/estimated_remaining_minutes': '2.175'}
|
| 47 |
+
{'eval_loss': '4.48', 'eval_runtime': '21.41', 'eval_samples_per_second': '444.9', 'eval_steps_per_second': '3.502', 'epoch': '0.04382', 'train/total_time_seconds': '235.5', 'train/time_per_step_avg': '0.3554', 'train/epoch_time_elapsed': '546.7', 'train/estimated_remaining_minutes': '2.114'}
|
| 48 |
+
{'loss': '4.325', 'grad_norm': '1.75', 'learning_rate': '0.005', 'epoch': '0.04449', 'train/total_time_seconds': '239', 'train/time_per_step_avg': '0.3554', 'train/epoch_time_elapsed': '550.7', 'train/estimated_remaining_minutes': '2.052'}
|
| 49 |
+
{'loss': '4.345', 'grad_norm': '0.5039', 'learning_rate': '0.005', 'epoch': '0.04584', 'train/total_time_seconds': '246.4', 'train/time_per_step_avg': '0.357', 'train/epoch_time_elapsed': '559.1', 'train/estimated_remaining_minutes': '1.933'}
|
| 50 |
+
{'loss': '4.222', 'grad_norm': '1.477', 'learning_rate': '0.005', 'epoch': '0.04719', 'train/total_time_seconds': '253.5', 'train/time_per_step_avg': '0.3565', 'train/epoch_time_elapsed': '567.1', 'train/estimated_remaining_minutes': '1.81'}
|
| 51 |
+
{'eval_loss': '4.238', 'eval_runtime': '21.35', 'eval_samples_per_second': '446.3', 'eval_steps_per_second': '3.513', 'epoch': '0.04719', 'train/total_time_seconds': '253.5', 'train/time_per_step_avg': '0.3565', 'train/epoch_time_elapsed': '588.5', 'train/estimated_remaining_minutes': '1.81'}
|
| 52 |
+
{'loss': '4.539', 'grad_norm': '2.969', 'learning_rate': '0.005', 'epoch': '0.04853', 'train/total_time_seconds': '260.8', 'train/time_per_step_avg': '0.3587', 'train/epoch_time_elapsed': '596.8', 'train/estimated_remaining_minutes': '1.69'}
|
| 53 |
+
{'loss': '4.674', 'grad_norm': '2.531', 'learning_rate': '0.005', 'epoch': '0.04988', 'train/total_time_seconds': '268.1', 'train/time_per_step_avg': '0.3615', 'train/epoch_time_elapsed': '605.2', 'train/estimated_remaining_minutes': '1.57'}
|
zain/Activation/wandb/run-20260812_191207-w1cgnksl/logs/debug-internal.log
CHANGED
|
@@ -49,3 +49,43 @@
|
|
| 49 |
{"time":"2026-08-12T19:17:09.215007025Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 50 |
{"time":"2026-08-12T19:17:24.060863895Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":25,"history_lines":1,"events_offset":40,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 51 |
{"time":"2026-08-12T19:17:24.188633325Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
{"time":"2026-08-12T19:17:09.215007025Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 50 |
{"time":"2026-08-12T19:17:24.060863895Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":25,"history_lines":1,"events_offset":40,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 51 |
{"time":"2026-08-12T19:17:24.188633325Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 52 |
+
{"time":"2026-08-12T19:17:39.060792481Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":26,"history_lines":1,"events_offset":42,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 53 |
+
{"time":"2026-08-12T19:17:39.210094375Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 54 |
+
{"time":"2026-08-12T19:17:54.061471204Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":27,"history_lines":1,"events_offset":44,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 55 |
+
{"time":"2026-08-12T19:17:54.199418171Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 56 |
+
{"time":"2026-08-12T19:18:09.061000182Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":28,"history_lines":2,"events_offset":46,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 57 |
+
{"time":"2026-08-12T19:18:09.209093897Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 58 |
+
{"time":"2026-08-12T19:18:24.060763863Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":48,"events_lines":2,"console_offset":3,"console_lines":1}
|
| 59 |
+
{"time":"2026-08-12T19:18:24.1773145Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 60 |
+
{"time":"2026-08-12T19:18:39.061681015Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":30,"history_lines":2,"events_offset":50,"events_lines":2,"console_offset":0,"console_lines":1}
|
| 61 |
+
{"time":"2026-08-12T19:18:39.213849305Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 62 |
+
{"time":"2026-08-12T19:18:54.061564717Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":32,"history_lines":2,"events_offset":52,"events_lines":2,"console_offset":3,"console_lines":1}
|
| 63 |
+
{"time":"2026-08-12T19:18:54.183311031Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 64 |
+
{"time":"2026-08-12T19:19:09.06124697Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":54,"events_lines":2,"console_offset":11,"console_lines":25}
|
| 65 |
+
{"time":"2026-08-12T19:19:09.197160601Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 66 |
+
{"time":"2026-08-12T19:19:24.061371815Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":34,"history_lines":2,"events_offset":56,"events_lines":2,"console_offset":36,"console_lines":2}
|
| 67 |
+
{"time":"2026-08-12T19:19:24.169446986Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 68 |
+
{"time":"2026-08-12T19:19:39.061619239Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":36,"history_lines":1,"events_offset":58,"events_lines":2,"console_offset":38,"console_lines":1}
|
| 69 |
+
{"time":"2026-08-12T19:19:39.184700489Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 70 |
+
{"time":"2026-08-12T19:19:54.061005576Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":37,"history_lines":1,"events_offset":60,"events_lines":2,"console_offset":39,"console_lines":1}
|
| 71 |
+
{"time":"2026-08-12T19:19:54.203579208Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 72 |
+
{"time":"2026-08-12T19:20:09.061544887Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":38,"history_lines":2,"events_offset":62,"events_lines":2,"console_offset":40,"console_lines":2}
|
| 73 |
+
{"time":"2026-08-12T19:20:09.209145123Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 74 |
+
{"time":"2026-08-12T19:20:24.061085273Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":40,"history_lines":1,"events_offset":64,"events_lines":2,"console_offset":42,"console_lines":1}
|
| 75 |
+
{"time":"2026-08-12T19:20:24.180324215Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 76 |
+
{"time":"2026-08-12T19:20:39.061567669Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":41,"history_lines":1,"events_offset":66,"events_lines":2,"console_offset":43,"console_lines":1}
|
| 77 |
+
{"time":"2026-08-12T19:20:39.187049132Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 78 |
+
{"time":"2026-08-12T19:20:54.060876869Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":42,"history_lines":2,"events_offset":68,"events_lines":2,"console_offset":44,"console_lines":2}
|
| 79 |
+
{"time":"2026-08-12T19:20:54.208534847Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 80 |
+
{"time":"2026-08-12T19:21:09.061014024Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":70,"events_lines":2}
|
| 81 |
+
{"time":"2026-08-12T19:21:09.205590728Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 82 |
+
{"time":"2026-08-12T19:21:24.061230217Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":44,"history_lines":2,"events_offset":72,"events_lines":2,"console_offset":46,"console_lines":2}
|
| 83 |
+
{"time":"2026-08-12T19:21:24.169771183Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 84 |
+
{"time":"2026-08-12T19:21:39.061283547Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":46,"history_lines":2,"events_offset":74,"events_lines":2,"console_offset":48,"console_lines":2}
|
| 85 |
+
{"time":"2026-08-12T19:21:39.17408722Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 86 |
+
{"time":"2026-08-12T19:21:54.061571591Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":76,"events_lines":2}
|
| 87 |
+
{"time":"2026-08-12T19:21:54.160013406Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 88 |
+
{"time":"2026-08-12T19:22:09.061421365Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":48,"history_lines":2,"events_offset":78,"events_lines":2,"console_offset":50,"console_lines":2}
|
| 89 |
+
{"time":"2026-08-12T19:22:09.255653996Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 90 |
+
{"time":"2026-08-12T19:22:24.061485993Z","level":"INFO","msg":"filestream: sending request","total_files":4,"history_offset":50,"history_lines":1,"events_offset":80,"events_lines":2,"console_offset":52,"console_lines":1}
|
| 91 |
+
{"time":"2026-08-12T19:22:24.206976463Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
zain/Activation/wandb/run-20260812_191207-w1cgnksl/run-w1cgnksl.wandb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f5123013c00348f1dd3280fbc20d8fa62ae3795a0bb7f4bb77992bc29e1cc4a
|
| 3 |
+
size 655360
|