sedrickkeh commited on
Commit
ed763e8
·
verified ·
1 Parent(s): 29ef45f

Training in progress, epoch 1

Browse files
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cb958d116f4f67871f0e2c5248baaaf348bef557f2b028a26c1437509703e75
3
  size 4949453792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1987a879580a51829b149912f4cc01fcb0dade975f8c8e1aa5035486f4702883
3
  size 4949453792
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:facfe2e5f99c6e0a88d68dd48cb81f901cc163b78898a6683ede2daa139f00dd
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e7540a73433512f9161dd484da652c45044dfbd9d54ac273e40efb3008447c
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c60e142583f5601dac6f8cadc3921a7f421787eb55cb66bec2f657a4644b9994
3
  size 4546807800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f2447bb3a2851c4a6c74cf03c3526bd6ad1b1f1d1e6f25b77aeb7030f539a6
3
  size 4546807800
trainer_log.jsonl CHANGED
@@ -48,3 +48,53 @@
48
  {"current_steps": 480, "total_steps": 1470, "loss": 0.2589, "lr": 4.1243951163035515e-06, "epoch": 0.978343949044586, "percentage": 32.65, "elapsed_time": "4:11:06", "remaining_time": "8:37:55"}
49
  {"current_steps": 490, "total_steps": 1470, "loss": 0.2567, "lr": 4.083960466269468e-06, "epoch": 0.9987261146496815, "percentage": 33.33, "elapsed_time": "4:16:20", "remaining_time": "8:32:41"}
50
  {"current_steps": 490, "total_steps": 1470, "eval_loss": 0.032234665006399155, "epoch": 0.9987261146496815, "percentage": 33.33, "elapsed_time": "4:22:09", "remaining_time": "8:44:18"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  {"current_steps": 480, "total_steps": 1470, "loss": 0.2589, "lr": 4.1243951163035515e-06, "epoch": 0.978343949044586, "percentage": 32.65, "elapsed_time": "4:11:06", "remaining_time": "8:37:55"}
49
  {"current_steps": 490, "total_steps": 1470, "loss": 0.2567, "lr": 4.083960466269468e-06, "epoch": 0.9987261146496815, "percentage": 33.33, "elapsed_time": "4:16:20", "remaining_time": "8:32:41"}
50
  {"current_steps": 490, "total_steps": 1470, "eval_loss": 0.032234665006399155, "epoch": 0.9987261146496815, "percentage": 33.33, "elapsed_time": "4:22:09", "remaining_time": "8:44:18"}
51
+ {"current_steps": 500, "total_steps": 1470, "loss": 0.1917, "lr": 4.042850272394296e-06, "epoch": 1.019108280254777, "percentage": 34.01, "elapsed_time": "4:28:12", "remaining_time": "8:40:19"}
52
+ {"current_steps": 510, "total_steps": 1470, "loss": 0.1828, "lr": 4.001085353689527e-06, "epoch": 1.0394904458598726, "percentage": 34.69, "elapsed_time": "4:33:25", "remaining_time": "8:34:41"}
53
+ {"current_steps": 520, "total_steps": 1470, "loss": 0.1823, "lr": 3.958686860732198e-06, "epoch": 1.0598726114649681, "percentage": 35.37, "elapsed_time": "4:38:40", "remaining_time": "8:29:07"}
54
+ {"current_steps": 530, "total_steps": 1470, "loss": 0.1824, "lr": 3.915676264953819e-06, "epoch": 1.0802547770700637, "percentage": 36.05, "elapsed_time": "4:43:55", "remaining_time": "8:23:34"}
55
+ {"current_steps": 540, "total_steps": 1470, "loss": 0.1835, "lr": 3.8720753477668174e-06, "epoch": 1.1006369426751592, "percentage": 36.73, "elapsed_time": "4:49:07", "remaining_time": "8:17:56"}
56
+ {"current_steps": 550, "total_steps": 1470, "loss": 0.1838, "lr": 3.8279061895340065e-06, "epoch": 1.1210191082802548, "percentage": 37.41, "elapsed_time": "4:54:21", "remaining_time": "8:12:22"}
57
+ {"current_steps": 560, "total_steps": 1470, "loss": 0.1799, "lr": 3.783191158386649e-06, "epoch": 1.1414012738853503, "percentage": 38.1, "elapsed_time": "4:59:34", "remaining_time": "8:06:49"}
58
+ {"current_steps": 570, "total_steps": 1470, "loss": 0.1797, "lr": 3.7379528988968004e-06, "epoch": 1.1617834394904458, "percentage": 38.78, "elapsed_time": "5:04:47", "remaining_time": "8:01:15"}
59
+ {"current_steps": 580, "total_steps": 1470, "loss": 0.1814, "lr": 3.6922143206096463e-06, "epoch": 1.1821656050955414, "percentage": 39.46, "elapsed_time": "5:10:02", "remaining_time": "7:55:45"}
60
+ {"current_steps": 590, "total_steps": 1470, "loss": 0.1814, "lr": 3.645998586441664e-06, "epoch": 1.202547770700637, "percentage": 40.14, "elapsed_time": "5:15:16", "remaining_time": "7:50:14"}
61
+ {"current_steps": 600, "total_steps": 1470, "loss": 0.1828, "lr": 3.5993291009504583e-06, "epoch": 1.2229299363057324, "percentage": 40.82, "elapsed_time": "5:20:28", "remaining_time": "7:44:41"}
62
+ {"current_steps": 610, "total_steps": 1470, "loss": 0.1842, "lr": 3.5522294984822414e-06, "epoch": 1.243312101910828, "percentage": 41.5, "elapsed_time": "5:25:42", "remaining_time": "7:39:12"}
63
+ {"current_steps": 620, "total_steps": 1470, "loss": 0.1824, "lr": 3.504723631202927e-06, "epoch": 1.2636942675159235, "percentage": 42.18, "elapsed_time": "5:30:54", "remaining_time": "7:33:40"}
64
+ {"current_steps": 630, "total_steps": 1470, "loss": 0.1833, "lr": 3.4568355570189293e-06, "epoch": 1.284076433121019, "percentage": 42.86, "elapsed_time": "5:36:08", "remaining_time": "7:28:10"}
65
+ {"current_steps": 640, "total_steps": 1470, "loss": 0.1822, "lr": 3.4085895273937616e-06, "epoch": 1.3044585987261146, "percentage": 43.54, "elapsed_time": "5:41:22", "remaining_time": "7:22:42"}
66
+ {"current_steps": 650, "total_steps": 1470, "loss": 0.1801, "lr": 3.3600099750666186e-06, "epoch": 1.3248407643312101, "percentage": 44.22, "elapsed_time": "5:46:36", "remaining_time": "7:17:15"}
67
+ {"current_steps": 660, "total_steps": 1470, "loss": 0.1811, "lr": 3.3111215016791615e-06, "epoch": 1.3452229299363057, "percentage": 44.9, "elapsed_time": "5:51:50", "remaining_time": "7:11:48"}
68
+ {"current_steps": 670, "total_steps": 1470, "loss": 0.1816, "lr": 3.2619488653167524e-06, "epoch": 1.3656050955414012, "percentage": 45.58, "elapsed_time": "5:57:06", "remaining_time": "7:06:23"}
69
+ {"current_steps": 680, "total_steps": 1470, "loss": 0.1813, "lr": 3.2125169679704816e-06, "epoch": 1.385987261146497, "percentage": 46.26, "elapsed_time": "6:02:22", "remaining_time": "7:00:59"}
70
+ {"current_steps": 690, "total_steps": 1470, "loss": 0.1779, "lr": 3.1628508429263055e-06, "epoch": 1.4063694267515925, "percentage": 46.94, "elapsed_time": "6:07:36", "remaining_time": "6:55:33"}
71
+ {"current_steps": 700, "total_steps": 1470, "loss": 0.1802, "lr": 3.112975642087696e-06, "epoch": 1.426751592356688, "percentage": 47.62, "elapsed_time": "6:12:50", "remaining_time": "6:50:08"}
72
+ {"current_steps": 710, "total_steps": 1470, "loss": 0.1814, "lr": 3.0629166232382244e-06, "epoch": 1.4471337579617836, "percentage": 48.3, "elapsed_time": "6:18:05", "remaining_time": "6:44:43"}
73
+ {"current_steps": 720, "total_steps": 1470, "loss": 0.1824, "lr": 3.012699137250523e-06, "epoch": 1.467515923566879, "percentage": 48.98, "elapsed_time": "6:23:18", "remaining_time": "6:39:17"}
74
+ {"current_steps": 730, "total_steps": 1470, "loss": 0.1796, "lr": 2.962348615248099e-06, "epoch": 1.4878980891719746, "percentage": 49.66, "elapsed_time": "6:28:34", "remaining_time": "6:33:53"}
75
+ {"current_steps": 740, "total_steps": 1470, "loss": 0.181, "lr": 2.9118905557265194e-06, "epoch": 1.5082802547770702, "percentage": 50.34, "elapsed_time": "6:33:47", "remaining_time": "6:28:28"}
76
+ {"current_steps": 750, "total_steps": 1470, "loss": 0.1803, "lr": 2.861350511640466e-06, "epoch": 1.5286624203821657, "percentage": 51.02, "elapsed_time": "6:38:59", "remaining_time": "6:23:01"}
77
+ {"current_steps": 760, "total_steps": 1470, "loss": 0.1798, "lr": 2.81075407746322e-06, "epoch": 1.5490445859872612, "percentage": 51.7, "elapsed_time": "6:44:13", "remaining_time": "6:17:37"}
78
+ {"current_steps": 770, "total_steps": 1470, "loss": 0.1794, "lr": 2.760126876225113e-06, "epoch": 1.5694267515923568, "percentage": 52.38, "elapsed_time": "6:49:28", "remaining_time": "6:12:15"}
79
+ {"current_steps": 780, "total_steps": 1470, "loss": 0.1784, "lr": 2.7094945465375237e-06, "epoch": 1.5898089171974523, "percentage": 53.06, "elapsed_time": "6:54:42", "remaining_time": "6:06:51"}
80
+ {"current_steps": 790, "total_steps": 1470, "loss": 0.1796, "lr": 2.6588827296089765e-06, "epoch": 1.6101910828025479, "percentage": 53.74, "elapsed_time": "6:59:55", "remaining_time": "6:01:27"}
81
+ {"current_steps": 800, "total_steps": 1470, "loss": 0.1778, "lr": 2.608317056259933e-06, "epoch": 1.6305732484076434, "percentage": 54.42, "elapsed_time": "7:05:09", "remaining_time": "5:56:04"}
82
+ {"current_steps": 810, "total_steps": 1470, "loss": 0.1818, "lr": 2.557823133942836e-06, "epoch": 1.650955414012739, "percentage": 55.1, "elapsed_time": "7:10:23", "remaining_time": "5:50:41"}
83
+ {"current_steps": 820, "total_steps": 1470, "loss": 0.1818, "lr": 2.507426533773994e-06, "epoch": 1.6713375796178345, "percentage": 55.78, "elapsed_time": "7:15:38", "remaining_time": "5:45:19"}
84
+ {"current_steps": 830, "total_steps": 1470, "loss": 0.1785, "lr": 2.4571527775838637e-06, "epoch": 1.69171974522293, "percentage": 56.46, "elapsed_time": "7:20:52", "remaining_time": "5:39:56"}
85
+ {"current_steps": 840, "total_steps": 1470, "loss": 0.1767, "lr": 2.407027324992293e-06, "epoch": 1.7121019108280255, "percentage": 57.14, "elapsed_time": "7:26:05", "remaining_time": "5:34:34"}
86
+ {"current_steps": 850, "total_steps": 1470, "loss": 0.1764, "lr": 2.357075560515267e-06, "epoch": 1.732484076433121, "percentage": 57.82, "elapsed_time": "7:31:17", "remaining_time": "5:29:10"}
87
+ {"current_steps": 860, "total_steps": 1470, "loss": 0.1766, "lr": 2.3073227807096903e-06, "epoch": 1.7528662420382166, "percentage": 58.5, "elapsed_time": "7:36:28", "remaining_time": "5:23:46"}
88
+ {"current_steps": 870, "total_steps": 1470, "loss": 0.1776, "lr": 2.2577941813627137e-06, "epoch": 1.7732484076433122, "percentage": 59.18, "elapsed_time": "7:41:40", "remaining_time": "5:18:23"}
89
+ {"current_steps": 880, "total_steps": 1470, "loss": 0.1763, "lr": 2.2085148447320886e-06, "epoch": 1.7936305732484077, "percentage": 59.86, "elapsed_time": "7:46:52", "remaining_time": "5:13:01"}
90
+ {"current_steps": 890, "total_steps": 1470, "loss": 0.1761, "lr": 2.1595097268440215e-06, "epoch": 1.8140127388535032, "percentage": 60.54, "elapsed_time": "7:52:07", "remaining_time": "5:07:40"}
91
+ {"current_steps": 900, "total_steps": 1470, "loss": 0.1756, "lr": 2.110803644854949e-06, "epoch": 1.8343949044585988, "percentage": 61.22, "elapsed_time": "7:57:21", "remaining_time": "5:02:19"}
92
+ {"current_steps": 910, "total_steps": 1470, "loss": 0.1754, "lr": 2.062421264483641e-06, "epoch": 1.8547770700636943, "percentage": 61.9, "elapsed_time": "8:02:34", "remaining_time": "4:56:58"}
93
+ {"current_steps": 920, "total_steps": 1470, "loss": 0.1764, "lr": 2.0143870875199952e-06, "epoch": 1.8751592356687898, "percentage": 62.59, "elapsed_time": "8:07:47", "remaining_time": "4:51:37"}
94
+ {"current_steps": 930, "total_steps": 1470, "loss": 0.1742, "lr": 1.9667254394168497e-06, "epoch": 1.8955414012738854, "percentage": 63.27, "elapsed_time": "8:13:01", "remaining_time": "4:46:16"}
95
+ {"current_steps": 940, "total_steps": 1470, "loss": 0.1795, "lr": 1.9194604569710933e-06, "epoch": 1.915923566878981, "percentage": 63.95, "elapsed_time": "8:18:14", "remaining_time": "4:40:55"}
96
+ {"current_steps": 950, "total_steps": 1470, "loss": 0.1748, "lr": 1.8726160761003172e-06, "epoch": 1.9363057324840764, "percentage": 64.63, "elapsed_time": "8:23:25", "remaining_time": "4:35:33"}
97
+ {"current_steps": 960, "total_steps": 1470, "loss": 0.1761, "lr": 1.8262160197211954e-06, "epoch": 1.956687898089172, "percentage": 65.31, "elapsed_time": "8:28:38", "remaining_time": "4:30:12"}
98
+ {"current_steps": 970, "total_steps": 1470, "loss": 0.174, "lr": 1.780283785735729e-06, "epoch": 1.9770700636942675, "percentage": 65.99, "elapsed_time": "8:33:50", "remaining_time": "4:24:52"}
99
+ {"current_steps": 980, "total_steps": 1470, "loss": 0.1749, "lr": 1.734842635131455e-06, "epoch": 1.997452229299363, "percentage": 66.67, "elapsed_time": "8:39:05", "remaining_time": "4:19:32"}
100
+ {"current_steps": 981, "total_steps": 1470, "eval_loss": 0.030678020790219307, "epoch": 1.9994904458598726, "percentage": 66.73, "elapsed_time": "8:45:18", "remaining_time": "4:21:51"}