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 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a6b436cb508baba054ff9bf139e01549c013b0fbe21fe52ebfcee7b37000375
|
3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65154e1b2a59f015516cb07add8fb5ebeb9c0724f13a985544b028f288980c1c
|
3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d395b1a92eeca8efe013a6ee03743457331dbf5fa648226c8693dc1859054be9
|
3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:823c7c5df2d8ac48018a3a275859584ad1c2f13e9792b10dd4737156ffbda2b8
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -65,3 +65,70 @@
|
|
65 |
{"current_steps": 65, "total_steps": 335, "loss": 0.4238, "lr": 7.792447436995634e-05, "epoch": 0.9683426443202979, "percentage": 19.4, "elapsed_time": "2:44:45", "remaining_time": "11:24:24"}
|
66 |
{"current_steps": 66, "total_steps": 335, "loss": 0.4251, "lr": 7.778967648244807e-05, "epoch": 0.9832402234636871, "percentage": 19.7, "elapsed_time": "2:47:16", "remaining_time": "11:21:45"}
|
67 |
{"current_steps": 67, "total_steps": 335, "loss": 0.4227, "lr": 7.765076202038145e-05, "epoch": 0.9981378026070763, "percentage": 20.0, "elapsed_time": "2:49:45", "remaining_time": "11:19:02"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
{"current_steps": 65, "total_steps": 335, "loss": 0.4238, "lr": 7.792447436995634e-05, "epoch": 0.9683426443202979, "percentage": 19.4, "elapsed_time": "2:44:45", "remaining_time": "11:24:24"}
|
66 |
{"current_steps": 66, "total_steps": 335, "loss": 0.4251, "lr": 7.778967648244807e-05, "epoch": 0.9832402234636871, "percentage": 19.7, "elapsed_time": "2:47:16", "remaining_time": "11:21:45"}
|
67 |
{"current_steps": 67, "total_steps": 335, "loss": 0.4227, "lr": 7.765076202038145e-05, "epoch": 0.9981378026070763, "percentage": 20.0, "elapsed_time": "2:49:45", "remaining_time": "11:19:02"}
|
68 |
+
{"current_steps": 68, "total_steps": 335, "loss": 0.7678, "lr": 7.750774611624222e-05, "epoch": 1.0130353817504656, "percentage": 20.3, "elapsed_time": "2:53:48", "remaining_time": "11:22:26"}
|
69 |
+
{"current_steps": 69, "total_steps": 335, "loss": 0.4298, "lr": 7.736064434930193e-05, "epoch": 1.0279329608938548, "percentage": 20.6, "elapsed_time": "2:56:19", "remaining_time": "11:19:46"}
|
70 |
+
{"current_steps": 70, "total_steps": 335, "loss": 0.4051, "lr": 7.720947274392087e-05, "epoch": 1.042830540037244, "percentage": 20.9, "elapsed_time": "2:58:50", "remaining_time": "11:17:01"}
|
71 |
+
{"current_steps": 71, "total_steps": 335, "loss": 0.4149, "lr": 7.705424776780249e-05, "epoch": 1.0577281191806331, "percentage": 21.19, "elapsed_time": "3:01:22", "remaining_time": "11:14:22"}
|
72 |
+
{"current_steps": 72, "total_steps": 335, "loss": 0.4007, "lr": 7.689498633019941e-05, "epoch": 1.0726256983240223, "percentage": 21.49, "elapsed_time": "3:03:53", "remaining_time": "11:11:41"}
|
73 |
+
{"current_steps": 73, "total_steps": 335, "loss": 0.4116, "lr": 7.673170578007157e-05, "epoch": 1.0875232774674115, "percentage": 21.79, "elapsed_time": "3:06:23", "remaining_time": "11:08:58"}
|
74 |
+
{"current_steps": 74, "total_steps": 335, "loss": 0.4008, "lr": 7.656442390419622e-05, "epoch": 1.1024208566108007, "percentage": 22.09, "elapsed_time": "3:08:53", "remaining_time": "11:06:15"}
|
75 |
+
{"current_steps": 75, "total_steps": 335, "loss": 0.3935, "lr": 7.63931589252304e-05, "epoch": 1.1173184357541899, "percentage": 22.39, "elapsed_time": "3:11:24", "remaining_time": "11:03:32"}
|
76 |
+
{"current_steps": 76, "total_steps": 335, "loss": 0.3983, "lr": 7.621792949972588e-05, "epoch": 1.132216014897579, "percentage": 22.69, "elapsed_time": "3:13:55", "remaining_time": "11:00:51"}
|
77 |
+
{"current_steps": 77, "total_steps": 335, "loss": 0.4092, "lr": 7.603875471609677e-05, "epoch": 1.1471135940409685, "percentage": 22.99, "elapsed_time": "3:16:25", "remaining_time": "10:58:09"}
|
78 |
+
{"current_steps": 78, "total_steps": 335, "loss": 0.3988, "lr": 7.585565409254025e-05, "epoch": 1.1620111731843576, "percentage": 23.28, "elapsed_time": "3:18:56", "remaining_time": "10:55:28"}
|
79 |
+
{"current_steps": 79, "total_steps": 335, "loss": 0.4049, "lr": 7.566864757491027e-05, "epoch": 1.1769087523277468, "percentage": 23.58, "elapsed_time": "3:21:27", "remaining_time": "10:52:48"}
|
80 |
+
{"current_steps": 80, "total_steps": 335, "loss": 0.3991, "lr": 7.547775553454485e-05, "epoch": 1.191806331471136, "percentage": 23.88, "elapsed_time": "3:23:57", "remaining_time": "10:50:06"}
|
81 |
+
{"current_steps": 81, "total_steps": 335, "loss": 0.4015, "lr": 7.528299876604689e-05, "epoch": 1.2067039106145252, "percentage": 24.18, "elapsed_time": "3:26:28", "remaining_time": "10:47:28"}
|
82 |
+
{"current_steps": 82, "total_steps": 335, "loss": 0.3948, "lr": 7.508439848501899e-05, "epoch": 1.2216014897579144, "percentage": 24.48, "elapsed_time": "3:28:59", "remaining_time": "10:44:47"}
|
83 |
+
{"current_steps": 83, "total_steps": 335, "loss": 0.3946, "lr": 7.488197632575232e-05, "epoch": 1.2364990689013036, "percentage": 24.78, "elapsed_time": "3:31:31", "remaining_time": "10:42:11"}
|
84 |
+
{"current_steps": 84, "total_steps": 335, "loss": 0.3925, "lr": 7.467575433886989e-05, "epoch": 1.2513966480446927, "percentage": 25.07, "elapsed_time": "3:34:03", "remaining_time": "10:39:36"}
|
85 |
+
{"current_steps": 85, "total_steps": 335, "loss": 0.3944, "lr": 7.44657549889246e-05, "epoch": 1.266294227188082, "percentage": 25.37, "elapsed_time": "3:36:34", "remaining_time": "10:36:59"}
|
86 |
+
{"current_steps": 86, "total_steps": 335, "loss": 0.395, "lr": 7.425200115195193e-05, "epoch": 1.2811918063314711, "percentage": 25.67, "elapsed_time": "3:39:04", "remaining_time": "10:34:19"}
|
87 |
+
{"current_steps": 87, "total_steps": 335, "loss": 0.3896, "lr": 7.403451611297808e-05, "epoch": 1.2960893854748603, "percentage": 25.97, "elapsed_time": "3:41:35", "remaining_time": "10:31:40"}
|
88 |
+
{"current_steps": 88, "total_steps": 335, "loss": 0.3972, "lr": 7.381332356348343e-05, "epoch": 1.3109869646182495, "percentage": 26.27, "elapsed_time": "3:44:05", "remaining_time": "10:29:00"}
|
89 |
+
{"current_steps": 89, "total_steps": 335, "loss": 0.3947, "lr": 7.358844759882168e-05, "epoch": 1.3258845437616387, "percentage": 26.57, "elapsed_time": "3:46:35", "remaining_time": "10:26:19"}
|
90 |
+
{"current_steps": 90, "total_steps": 335, "loss": 0.3924, "lr": 7.335991271559512e-05, "epoch": 1.3407821229050279, "percentage": 26.87, "elapsed_time": "3:49:06", "remaining_time": "10:23:40"}
|
91 |
+
{"current_steps": 91, "total_steps": 335, "loss": 0.3802, "lr": 7.312774380898608e-05, "epoch": 1.355679702048417, "percentage": 27.16, "elapsed_time": "3:51:37", "remaining_time": "10:21:02"}
|
92 |
+
{"current_steps": 92, "total_steps": 335, "loss": 0.3921, "lr": 7.289196617004499e-05, "epoch": 1.3705772811918062, "percentage": 27.46, "elapsed_time": "3:54:08", "remaining_time": "10:18:26"}
|
93 |
+
{"current_steps": 93, "total_steps": 335, "loss": 0.3852, "lr": 7.265260548293535e-05, "epoch": 1.3854748603351954, "percentage": 27.76, "elapsed_time": "3:56:39", "remaining_time": "10:15:50"}
|
94 |
+
{"current_steps": 94, "total_steps": 335, "loss": 0.3864, "lr": 7.24096878221359e-05, "epoch": 1.4003724394785848, "percentage": 28.06, "elapsed_time": "3:59:11", "remaining_time": "10:13:14"}
|
95 |
+
{"current_steps": 95, "total_steps": 335, "loss": 0.3917, "lr": 7.216323964960013e-05, "epoch": 1.415270018621974, "percentage": 28.36, "elapsed_time": "4:01:40", "remaining_time": "10:10:34"}
|
96 |
+
{"current_steps": 96, "total_steps": 335, "loss": 0.3889, "lr": 7.191328781187374e-05, "epoch": 1.4301675977653632, "percentage": 28.66, "elapsed_time": "4:04:11", "remaining_time": "10:07:56"}
|
97 |
+
{"current_steps": 97, "total_steps": 335, "loss": 0.3976, "lr": 7.165985953717017e-05, "epoch": 1.4450651769087524, "percentage": 28.96, "elapsed_time": "4:06:41", "remaining_time": "10:05:17"}
|
98 |
+
{"current_steps": 98, "total_steps": 335, "loss": 0.3991, "lr": 7.140298243240444e-05, "epoch": 1.4599627560521415, "percentage": 29.25, "elapsed_time": "4:09:13", "remaining_time": "10:02:42"}
|
99 |
+
{"current_steps": 99, "total_steps": 335, "loss": 0.395, "lr": 7.114268448018589e-05, "epoch": 1.4748603351955307, "percentage": 29.55, "elapsed_time": "4:11:45", "remaining_time": "10:00:08"}
|
100 |
+
{"current_steps": 100, "total_steps": 335, "loss": 0.3904, "lr": 7.087899403576992e-05, "epoch": 1.48975791433892, "percentage": 29.85, "elapsed_time": "4:14:16", "remaining_time": "9:57:33"}
|
101 |
+
{"current_steps": 101, "total_steps": 335, "loss": 0.3809, "lr": 7.06119398239691e-05, "epoch": 1.504655493482309, "percentage": 30.15, "elapsed_time": "4:16:47", "remaining_time": "9:54:56"}
|
102 |
+
{"current_steps": 102, "total_steps": 335, "loss": 0.3962, "lr": 7.034155093602413e-05, "epoch": 1.5195530726256983, "percentage": 30.45, "elapsed_time": "4:19:17", "remaining_time": "9:52:19"}
|
103 |
+
{"current_steps": 103, "total_steps": 335, "loss": 0.3976, "lr": 7.006785682643479e-05, "epoch": 1.5344506517690877, "percentage": 30.75, "elapsed_time": "4:21:48", "remaining_time": "9:49:41"}
|
104 |
+
{"current_steps": 104, "total_steps": 335, "loss": 0.3917, "lr": 6.979088730975128e-05, "epoch": 1.5493482309124769, "percentage": 31.04, "elapsed_time": "4:24:18", "remaining_time": "9:47:05"}
|
105 |
+
{"current_steps": 105, "total_steps": 335, "loss": 0.3858, "lr": 6.951067255732655e-05, "epoch": 1.564245810055866, "percentage": 31.34, "elapsed_time": "4:26:50", "remaining_time": "9:44:30"}
|
106 |
+
{"current_steps": 106, "total_steps": 335, "loss": 0.3864, "lr": 6.92272430940295e-05, "epoch": 1.5791433891992552, "percentage": 31.64, "elapsed_time": "4:29:22", "remaining_time": "9:41:57"}
|
107 |
+
{"current_steps": 107, "total_steps": 335, "loss": 0.3883, "lr": 6.894062979491987e-05, "epoch": 1.5940409683426444, "percentage": 31.94, "elapsed_time": "4:31:54", "remaining_time": "9:39:22"}
|
108 |
+
{"current_steps": 108, "total_steps": 335, "loss": 0.386, "lr": 6.865086388188476e-05, "epoch": 1.6089385474860336, "percentage": 32.24, "elapsed_time": "4:34:24", "remaining_time": "9:36:46"}
|
109 |
+
{"current_steps": 109, "total_steps": 335, "loss": 0.39, "lr": 6.835797692023774e-05, "epoch": 1.6238361266294228, "percentage": 32.54, "elapsed_time": "4:36:55", "remaining_time": "9:34:09"}
|
110 |
+
{"current_steps": 110, "total_steps": 335, "loss": 0.3872, "lr": 6.806200081528008e-05, "epoch": 1.638733705772812, "percentage": 32.84, "elapsed_time": "4:39:27", "remaining_time": "9:31:37"}
|
111 |
+
{"current_steps": 111, "total_steps": 335, "loss": 0.3813, "lr": 6.776296780882537e-05, "epoch": 1.6536312849162011, "percentage": 33.13, "elapsed_time": "4:41:57", "remaining_time": "9:29:00"}
|
112 |
+
{"current_steps": 112, "total_steps": 335, "loss": 0.3812, "lr": 6.746091047568716e-05, "epoch": 1.6685288640595903, "percentage": 33.43, "elapsed_time": "4:44:29", "remaining_time": "9:26:26"}
|
113 |
+
{"current_steps": 113, "total_steps": 335, "loss": 0.3835, "lr": 6.715586172013054e-05, "epoch": 1.6834264432029795, "percentage": 33.73, "elapsed_time": "4:47:00", "remaining_time": "9:23:51"}
|
114 |
+
{"current_steps": 114, "total_steps": 335, "loss": 0.3813, "lr": 6.684785477228777e-05, "epoch": 1.6983240223463687, "percentage": 34.03, "elapsed_time": "4:49:31", "remaining_time": "9:21:16"}
|
115 |
+
{"current_steps": 115, "total_steps": 335, "loss": 0.3852, "lr": 6.653692318453831e-05, "epoch": 1.7132216014897579, "percentage": 34.33, "elapsed_time": "4:52:03", "remaining_time": "9:18:42"}
|
116 |
+
{"current_steps": 116, "total_steps": 335, "loss": 0.3913, "lr": 6.622310082785384e-05, "epoch": 1.728119180633147, "percentage": 34.63, "elapsed_time": "4:54:33", "remaining_time": "9:16:06"}
|
117 |
+
{"current_steps": 117, "total_steps": 335, "loss": 0.3827, "lr": 6.590642188810869e-05, "epoch": 1.7430167597765363, "percentage": 34.93, "elapsed_time": "4:57:04", "remaining_time": "9:13:30"}
|
118 |
+
{"current_steps": 118, "total_steps": 335, "loss": 0.3744, "lr": 6.558692086235565e-05, "epoch": 1.7579143389199254, "percentage": 35.22, "elapsed_time": "4:59:34", "remaining_time": "9:10:55"}
|
119 |
+
{"current_steps": 119, "total_steps": 335, "loss": 0.3811, "lr": 6.526463255506828e-05, "epoch": 1.7728119180633146, "percentage": 35.52, "elapsed_time": "5:02:06", "remaining_time": "9:08:22"}
|
120 |
+
{"current_steps": 120, "total_steps": 335, "loss": 0.3758, "lr": 6.493959207434934e-05, "epoch": 1.7877094972067038, "percentage": 35.82, "elapsed_time": "5:04:37", "remaining_time": "9:05:47"}
|
121 |
+
{"current_steps": 121, "total_steps": 335, "loss": 0.3853, "lr": 6.461183482810646e-05, "epoch": 1.802607076350093, "percentage": 36.12, "elapsed_time": "5:07:09", "remaining_time": "9:03:13"}
|
122 |
+
{"current_steps": 122, "total_steps": 335, "loss": 0.3882, "lr": 6.42813965201949e-05, "epoch": 1.8175046554934822, "percentage": 36.42, "elapsed_time": "5:09:41", "remaining_time": "9:00:41"}
|
123 |
+
{"current_steps": 123, "total_steps": 335, "loss": 0.3858, "lr": 6.394831314652835e-05, "epoch": 1.8324022346368714, "percentage": 36.72, "elapsed_time": "5:12:15", "remaining_time": "8:58:12"}
|
124 |
+
{"current_steps": 124, "total_steps": 335, "loss": 0.3856, "lr": 6.361262099115761e-05, "epoch": 1.8472998137802608, "percentage": 37.01, "elapsed_time": "5:14:50", "remaining_time": "8:55:44"}
|
125 |
+
{"current_steps": 125, "total_steps": 335, "loss": 0.3849, "lr": 6.327435662231812e-05, "epoch": 1.86219739292365, "percentage": 37.31, "elapsed_time": "5:17:20", "remaining_time": "8:53:08"}
|
126 |
+
{"current_steps": 126, "total_steps": 335, "loss": 0.3866, "lr": 6.293355688844637e-05, "epoch": 1.8770949720670391, "percentage": 37.61, "elapsed_time": "5:19:51", "remaining_time": "8:50:33"}
|
127 |
+
{"current_steps": 127, "total_steps": 335, "loss": 0.3737, "lr": 6.259025891416594e-05, "epoch": 1.8919925512104283, "percentage": 37.91, "elapsed_time": "5:22:21", "remaining_time": "8:47:57"}
|
128 |
+
{"current_steps": 128, "total_steps": 335, "loss": 0.3741, "lr": 6.224450009624332e-05, "epoch": 1.9068901303538175, "percentage": 38.21, "elapsed_time": "5:24:51", "remaining_time": "8:45:21"}
|
129 |
+
{"current_steps": 129, "total_steps": 335, "loss": 0.3767, "lr": 6.18963180995141e-05, "epoch": 1.9217877094972067, "percentage": 38.51, "elapsed_time": "5:27:21", "remaining_time": "8:42:46"}
|
130 |
+
{"current_steps": 130, "total_steps": 335, "loss": 0.3857, "lr": 6.154575085278012e-05, "epoch": 1.9366852886405959, "percentage": 38.81, "elapsed_time": "5:29:52", "remaining_time": "8:40:10"}
|
131 |
+
{"current_steps": 131, "total_steps": 335, "loss": 0.3806, "lr": 6.119283654467761e-05, "epoch": 1.9515828677839853, "percentage": 39.1, "elapsed_time": "5:32:22", "remaining_time": "8:37:35"}
|
132 |
+
{"current_steps": 132, "total_steps": 335, "loss": 0.3802, "lr": 6.083761361951722e-05, "epoch": 1.9664804469273744, "percentage": 39.4, "elapsed_time": "5:34:53", "remaining_time": "8:35:00"}
|
133 |
+
{"current_steps": 133, "total_steps": 335, "loss": 0.3773, "lr": 6.048012077309612e-05, "epoch": 1.9813780260707636, "percentage": 39.7, "elapsed_time": "5:37:24", "remaining_time": "8:32:27"}
|
134 |
+
{"current_steps": 134, "total_steps": 335, "loss": 0.3832, "lr": 6.01203969484827e-05, "epoch": 1.9962756052141528, "percentage": 40.0, "elapsed_time": "5:39:53", "remaining_time": "8:29:50"}
|