Training in progress, epoch 1
Browse files
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51cf127615d757efee1e29c3e73a7e76f4b88bd2a2e7b385ce6b2cc5df1be3f7
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b46ec1ebd0412177bec08de468657eae6e7fef870dee73155a330c1f74a423d5
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15a2fa6e1186479655d84c6eb31f6ce5897f21b491b92e72ac00b25e8911d361
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:484917bc923450416fabd11a1ac56a1f20e57d593f697747d0c981e16ec11f65
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -57,3 +57,63 @@
|
|
57 |
{"current_steps": 570, "total_steps": 1755, "loss": 0.8147, "lr": 5e-06, "epoch": 0.9737347853939782, "percentage": 32.48, "elapsed_time": "9:09:40", "remaining_time": "19:02:44"}
|
58 |
{"current_steps": 580, "total_steps": 1755, "loss": 0.8146, "lr": 5e-06, "epoch": 0.9908178518043989, "percentage": 33.05, "elapsed_time": "9:19:21", "remaining_time": "18:53:10"}
|
59 |
{"current_steps": 585, "total_steps": 1755, "eval_loss": 0.8145768046379089, "epoch": 0.9993593850096092, "percentage": 33.33, "elapsed_time": "9:34:54", "remaining_time": "19:09:48"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
{"current_steps": 570, "total_steps": 1755, "loss": 0.8147, "lr": 5e-06, "epoch": 0.9737347853939782, "percentage": 32.48, "elapsed_time": "9:09:40", "remaining_time": "19:02:44"}
|
58 |
{"current_steps": 580, "total_steps": 1755, "loss": 0.8146, "lr": 5e-06, "epoch": 0.9908178518043989, "percentage": 33.05, "elapsed_time": "9:19:21", "remaining_time": "18:53:10"}
|
59 |
{"current_steps": 585, "total_steps": 1755, "eval_loss": 0.8145768046379089, "epoch": 0.9993593850096092, "percentage": 33.33, "elapsed_time": "9:34:54", "remaining_time": "19:09:48"}
|
60 |
+
{"current_steps": 590, "total_steps": 1755, "loss": 0.8416, "lr": 5e-06, "epoch": 1.0079009182148195, "percentage": 33.62, "elapsed_time": "9:40:33", "remaining_time": "19:06:21"}
|
61 |
+
{"current_steps": 600, "total_steps": 1755, "loss": 0.7786, "lr": 5e-06, "epoch": 1.0249839846252402, "percentage": 34.19, "elapsed_time": "9:50:14", "remaining_time": "18:56:13"}
|
62 |
+
{"current_steps": 610, "total_steps": 1755, "loss": 0.7689, "lr": 5e-06, "epoch": 1.0420670510356609, "percentage": 34.76, "elapsed_time": "9:59:52", "remaining_time": "18:45:59"}
|
63 |
+
{"current_steps": 620, "total_steps": 1755, "loss": 0.774, "lr": 5e-06, "epoch": 1.0591501174460816, "percentage": 35.33, "elapsed_time": "10:09:31", "remaining_time": "18:35:48"}
|
64 |
+
{"current_steps": 630, "total_steps": 1755, "loss": 0.7727, "lr": 5e-06, "epoch": 1.0762331838565022, "percentage": 35.9, "elapsed_time": "10:19:11", "remaining_time": "18:25:41"}
|
65 |
+
{"current_steps": 640, "total_steps": 1755, "loss": 0.7723, "lr": 5e-06, "epoch": 1.093316250266923, "percentage": 36.47, "elapsed_time": "10:28:51", "remaining_time": "18:15:34"}
|
66 |
+
{"current_steps": 650, "total_steps": 1755, "loss": 0.7761, "lr": 5e-06, "epoch": 1.1103993166773436, "percentage": 37.04, "elapsed_time": "10:38:28", "remaining_time": "18:05:24"}
|
67 |
+
{"current_steps": 660, "total_steps": 1755, "loss": 0.7791, "lr": 5e-06, "epoch": 1.1274823830877643, "percentage": 37.61, "elapsed_time": "10:48:08", "remaining_time": "17:55:18"}
|
68 |
+
{"current_steps": 670, "total_steps": 1755, "loss": 0.7737, "lr": 5e-06, "epoch": 1.144565449498185, "percentage": 38.18, "elapsed_time": "10:57:48", "remaining_time": "17:45:15"}
|
69 |
+
{"current_steps": 680, "total_steps": 1755, "loss": 0.7665, "lr": 5e-06, "epoch": 1.1616485159086056, "percentage": 38.75, "elapsed_time": "11:07:29", "remaining_time": "17:35:13"}
|
70 |
+
{"current_steps": 690, "total_steps": 1755, "loss": 0.7742, "lr": 5e-06, "epoch": 1.1787315823190263, "percentage": 39.32, "elapsed_time": "11:17:10", "remaining_time": "17:25:12"}
|
71 |
+
{"current_steps": 700, "total_steps": 1755, "loss": 0.7738, "lr": 5e-06, "epoch": 1.195814648729447, "percentage": 39.89, "elapsed_time": "11:26:49", "remaining_time": "17:15:08"}
|
72 |
+
{"current_steps": 710, "total_steps": 1755, "loss": 0.7745, "lr": 5e-06, "epoch": 1.2128977151398677, "percentage": 40.46, "elapsed_time": "11:36:29", "remaining_time": "17:05:07"}
|
73 |
+
{"current_steps": 720, "total_steps": 1755, "loss": 0.7749, "lr": 5e-06, "epoch": 1.2299807815502883, "percentage": 41.03, "elapsed_time": "11:46:09", "remaining_time": "16:55:06"}
|
74 |
+
{"current_steps": 730, "total_steps": 1755, "loss": 0.7761, "lr": 5e-06, "epoch": 1.247063847960709, "percentage": 41.6, "elapsed_time": "11:55:48", "remaining_time": "16:45:04"}
|
75 |
+
{"current_steps": 740, "total_steps": 1755, "loss": 0.7733, "lr": 5e-06, "epoch": 1.2641469143711297, "percentage": 42.17, "elapsed_time": "12:05:29", "remaining_time": "16:35:05"}
|
76 |
+
{"current_steps": 750, "total_steps": 1755, "loss": 0.7751, "lr": 5e-06, "epoch": 1.2812299807815504, "percentage": 42.74, "elapsed_time": "12:15:06", "remaining_time": "16:25:02"}
|
77 |
+
{"current_steps": 760, "total_steps": 1755, "loss": 0.7749, "lr": 5e-06, "epoch": 1.298313047191971, "percentage": 43.3, "elapsed_time": "12:24:46", "remaining_time": "16:15:03"}
|
78 |
+
{"current_steps": 770, "total_steps": 1755, "loss": 0.7741, "lr": 5e-06, "epoch": 1.3153961136023917, "percentage": 43.87, "elapsed_time": "12:34:26", "remaining_time": "16:05:06"}
|
79 |
+
{"current_steps": 780, "total_steps": 1755, "loss": 0.7784, "lr": 5e-06, "epoch": 1.3324791800128124, "percentage": 44.44, "elapsed_time": "12:44:04", "remaining_time": "15:55:05"}
|
80 |
+
{"current_steps": 790, "total_steps": 1755, "loss": 0.7758, "lr": 5e-06, "epoch": 1.349562246423233, "percentage": 45.01, "elapsed_time": "12:53:43", "remaining_time": "15:45:06"}
|
81 |
+
{"current_steps": 800, "total_steps": 1755, "loss": 0.7733, "lr": 5e-06, "epoch": 1.3666453128336538, "percentage": 45.58, "elapsed_time": "13:03:21", "remaining_time": "15:35:07"}
|
82 |
+
{"current_steps": 810, "total_steps": 1755, "loss": 0.7739, "lr": 5e-06, "epoch": 1.3837283792440744, "percentage": 46.15, "elapsed_time": "13:13:00", "remaining_time": "15:25:10"}
|
83 |
+
{"current_steps": 820, "total_steps": 1755, "loss": 0.7744, "lr": 5e-06, "epoch": 1.4008114456544951, "percentage": 46.72, "elapsed_time": "13:22:38", "remaining_time": "15:15:12"}
|
84 |
+
{"current_steps": 830, "total_steps": 1755, "loss": 0.7703, "lr": 5e-06, "epoch": 1.4178945120649158, "percentage": 47.29, "elapsed_time": "13:32:18", "remaining_time": "15:05:17"}
|
85 |
+
{"current_steps": 840, "total_steps": 1755, "loss": 0.7701, "lr": 5e-06, "epoch": 1.4349775784753362, "percentage": 47.86, "elapsed_time": "13:41:56", "remaining_time": "14:55:19"}
|
86 |
+
{"current_steps": 850, "total_steps": 1755, "loss": 0.7687, "lr": 5e-06, "epoch": 1.452060644885757, "percentage": 48.43, "elapsed_time": "13:51:35", "remaining_time": "14:45:24"}
|
87 |
+
{"current_steps": 860, "total_steps": 1755, "loss": 0.7694, "lr": 5e-06, "epoch": 1.4691437112961776, "percentage": 49.0, "elapsed_time": "14:01:14", "remaining_time": "14:35:28"}
|
88 |
+
{"current_steps": 870, "total_steps": 1755, "loss": 0.7713, "lr": 5e-06, "epoch": 1.4862267777065983, "percentage": 49.57, "elapsed_time": "14:10:55", "remaining_time": "14:25:35"}
|
89 |
+
{"current_steps": 880, "total_steps": 1755, "loss": 0.7687, "lr": 5e-06, "epoch": 1.503309844117019, "percentage": 50.14, "elapsed_time": "14:20:34", "remaining_time": "14:15:41"}
|
90 |
+
{"current_steps": 890, "total_steps": 1755, "loss": 0.7719, "lr": 5e-06, "epoch": 1.5203929105274396, "percentage": 50.71, "elapsed_time": "14:30:14", "remaining_time": "14:05:47"}
|
91 |
+
{"current_steps": 900, "total_steps": 1755, "loss": 0.7704, "lr": 5e-06, "epoch": 1.5374759769378603, "percentage": 51.28, "elapsed_time": "14:39:54", "remaining_time": "13:55:54"}
|
92 |
+
{"current_steps": 910, "total_steps": 1755, "loss": 0.7681, "lr": 5e-06, "epoch": 1.554559043348281, "percentage": 51.85, "elapsed_time": "14:49:29", "remaining_time": "13:45:57"}
|
93 |
+
{"current_steps": 920, "total_steps": 1755, "loss": 0.772, "lr": 5e-06, "epoch": 1.5716421097587017, "percentage": 52.42, "elapsed_time": "14:59:08", "remaining_time": "13:36:03"}
|
94 |
+
{"current_steps": 930, "total_steps": 1755, "loss": 0.7736, "lr": 5e-06, "epoch": 1.5887251761691223, "percentage": 52.99, "elapsed_time": "15:08:48", "remaining_time": "13:26:12"}
|
95 |
+
{"current_steps": 940, "total_steps": 1755, "loss": 0.7724, "lr": 5e-06, "epoch": 1.605808242579543, "percentage": 53.56, "elapsed_time": "15:18:27", "remaining_time": "13:16:19"}
|
96 |
+
{"current_steps": 950, "total_steps": 1755, "loss": 0.7711, "lr": 5e-06, "epoch": 1.6228913089899637, "percentage": 54.13, "elapsed_time": "15:28:05", "remaining_time": "13:06:25"}
|
97 |
+
{"current_steps": 960, "total_steps": 1755, "loss": 0.7715, "lr": 5e-06, "epoch": 1.6399743754003844, "percentage": 54.7, "elapsed_time": "15:37:45", "remaining_time": "12:56:34"}
|
98 |
+
{"current_steps": 970, "total_steps": 1755, "loss": 0.7783, "lr": 5e-06, "epoch": 1.657057441810805, "percentage": 55.27, "elapsed_time": "15:47:23", "remaining_time": "12:46:42"}
|
99 |
+
{"current_steps": 980, "total_steps": 1755, "loss": 0.7721, "lr": 5e-06, "epoch": 1.6741405082212257, "percentage": 55.84, "elapsed_time": "15:57:04", "remaining_time": "12:36:52"}
|
100 |
+
{"current_steps": 990, "total_steps": 1755, "loss": 0.7718, "lr": 5e-06, "epoch": 1.6912235746316464, "percentage": 56.41, "elapsed_time": "16:06:44", "remaining_time": "12:27:01"}
|
101 |
+
{"current_steps": 1000, "total_steps": 1755, "loss": 0.7741, "lr": 5e-06, "epoch": 1.708306641042067, "percentage": 56.98, "elapsed_time": "16:16:21", "remaining_time": "12:17:09"}
|
102 |
+
{"current_steps": 1010, "total_steps": 1755, "loss": 0.771, "lr": 5e-06, "epoch": 1.7253897074524878, "percentage": 57.55, "elapsed_time": "16:25:59", "remaining_time": "12:07:17"}
|
103 |
+
{"current_steps": 1020, "total_steps": 1755, "loss": 0.7728, "lr": 5e-06, "epoch": 1.7424727738629084, "percentage": 58.12, "elapsed_time": "16:35:38", "remaining_time": "11:57:26"}
|
104 |
+
{"current_steps": 1030, "total_steps": 1755, "loss": 0.7702, "lr": 5e-06, "epoch": 1.759555840273329, "percentage": 58.69, "elapsed_time": "16:45:16", "remaining_time": "11:47:35"}
|
105 |
+
{"current_steps": 1040, "total_steps": 1755, "loss": 0.7695, "lr": 5e-06, "epoch": 1.7766389066837496, "percentage": 59.26, "elapsed_time": "16:54:53", "remaining_time": "11:37:44"}
|
106 |
+
{"current_steps": 1050, "total_steps": 1755, "loss": 0.7713, "lr": 5e-06, "epoch": 1.7937219730941703, "percentage": 59.83, "elapsed_time": "17:04:27", "remaining_time": "11:27:50"}
|
107 |
+
{"current_steps": 1060, "total_steps": 1755, "loss": 0.7707, "lr": 5e-06, "epoch": 1.810805039504591, "percentage": 60.4, "elapsed_time": "17:14:04", "remaining_time": "11:18:00"}
|
108 |
+
{"current_steps": 1070, "total_steps": 1755, "loss": 0.767, "lr": 5e-06, "epoch": 1.8278881059150116, "percentage": 60.97, "elapsed_time": "17:23:42", "remaining_time": "11:08:09"}
|
109 |
+
{"current_steps": 1080, "total_steps": 1755, "loss": 0.7739, "lr": 5e-06, "epoch": 1.8449711723254323, "percentage": 61.54, "elapsed_time": "17:33:21", "remaining_time": "10:58:20"}
|
110 |
+
{"current_steps": 1090, "total_steps": 1755, "loss": 0.7697, "lr": 5e-06, "epoch": 1.862054238735853, "percentage": 62.11, "elapsed_time": "17:43:00", "remaining_time": "10:48:32"}
|
111 |
+
{"current_steps": 1100, "total_steps": 1755, "loss": 0.7715, "lr": 5e-06, "epoch": 1.8791373051462736, "percentage": 62.68, "elapsed_time": "17:52:40", "remaining_time": "10:38:44"}
|
112 |
+
{"current_steps": 1110, "total_steps": 1755, "loss": 0.7715, "lr": 5e-06, "epoch": 1.8962203715566943, "percentage": 63.25, "elapsed_time": "18:02:20", "remaining_time": "10:28:55"}
|
113 |
+
{"current_steps": 1120, "total_steps": 1755, "loss": 0.776, "lr": 5e-06, "epoch": 1.913303437967115, "percentage": 63.82, "elapsed_time": "18:11:59", "remaining_time": "10:19:07"}
|
114 |
+
{"current_steps": 1130, "total_steps": 1755, "loss": 0.7689, "lr": 5e-06, "epoch": 1.9303865043775357, "percentage": 64.39, "elapsed_time": "18:21:39", "remaining_time": "10:09:19"}
|
115 |
+
{"current_steps": 1140, "total_steps": 1755, "loss": 0.7691, "lr": 5e-06, "epoch": 1.9474695707879563, "percentage": 64.96, "elapsed_time": "18:31:18", "remaining_time": "9:59:31"}
|
116 |
+
{"current_steps": 1150, "total_steps": 1755, "loss": 0.7684, "lr": 5e-06, "epoch": 1.964552637198377, "percentage": 65.53, "elapsed_time": "18:40:55", "remaining_time": "9:49:42"}
|
117 |
+
{"current_steps": 1160, "total_steps": 1755, "loss": 0.7651, "lr": 5e-06, "epoch": 1.9816357036087977, "percentage": 66.1, "elapsed_time": "18:50:33", "remaining_time": "9:39:54"}
|
118 |
+
{"current_steps": 1170, "total_steps": 1755, "loss": 0.7679, "lr": 5e-06, "epoch": 1.9987187700192184, "percentage": 66.67, "elapsed_time": "19:00:11", "remaining_time": "9:30:05"}
|
119 |
+
{"current_steps": 1170, "total_steps": 1755, "eval_loss": 0.8001261949539185, "epoch": 1.9987187700192184, "percentage": 66.67, "elapsed_time": "19:11:14", "remaining_time": "9:35:37"}
|