Training in progress, step 1000
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 sha256:5dd4a65b5c002254a0c560428377889c0ea9df208353dbf5c02b137b62f2a836
|
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:d89ee2e1894edda17b39013f0836094f21362f1c4c15801d4f53c5dd5be3b243
|
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 sha256:7b16046f4231b9142e5380794f9283fc2524e0de9f122edce28ef18787484487
|
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 sha256:4f32a0d2b997c8f69fb6129ad7d3045f340e057a0d5c71b45bc8a702c36a53ac
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -58,3 +58,63 @@
|
|
58 |
{"current_steps": 490, "total_steps": 1548, "loss": 0.485, "lr": 8.63958979939235e-06, "epoch": 0.31640971829849057, "percentage": 31.65, "elapsed_time": "1:59:34", "remaining_time": "4:18:11"}
|
59 |
{"current_steps": 500, "total_steps": 1548, "loss": 0.4683, "lr": 8.56135286298822e-06, "epoch": 0.3228670594882557, "percentage": 32.3, "elapsed_time": "2:01:40", "remaining_time": "4:15:02"}
|
60 |
{"current_steps": 500, "total_steps": 1548, "eval_loss": 0.4224134683609009, "epoch": 0.3228670594882557, "percentage": 32.3, "elapsed_time": "2:03:32", "remaining_time": "4:18:56"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
{"current_steps": 490, "total_steps": 1548, "loss": 0.485, "lr": 8.63958979939235e-06, "epoch": 0.31640971829849057, "percentage": 31.65, "elapsed_time": "1:59:34", "remaining_time": "4:18:11"}
|
59 |
{"current_steps": 500, "total_steps": 1548, "loss": 0.4683, "lr": 8.56135286298822e-06, "epoch": 0.3228670594882557, "percentage": 32.3, "elapsed_time": "2:01:40", "remaining_time": "4:15:02"}
|
60 |
{"current_steps": 500, "total_steps": 1548, "eval_loss": 0.4224134683609009, "epoch": 0.3228670594882557, "percentage": 32.3, "elapsed_time": "2:03:32", "remaining_time": "4:18:56"}
|
61 |
+
{"current_steps": 510, "total_steps": 1548, "loss": 0.4983, "lr": 8.48130461105324e-06, "epoch": 0.3293244006780208, "percentage": 32.95, "elapsed_time": "2:06:59", "remaining_time": "4:18:26"}
|
62 |
+
{"current_steps": 520, "total_steps": 1548, "loss": 0.4568, "lr": 8.399485756386038e-06, "epoch": 0.3357817418677859, "percentage": 33.59, "elapsed_time": "2:09:04", "remaining_time": "4:15:10"}
|
63 |
+
{"current_steps": 530, "total_steps": 1548, "loss": 0.47, "lr": 8.315937912319493e-06, "epoch": 0.3422390830575511, "percentage": 34.24, "elapsed_time": "2:11:11", "remaining_time": "4:11:59"}
|
64 |
+
{"current_steps": 540, "total_steps": 1548, "loss": 0.4703, "lr": 8.23070357155605e-06, "epoch": 0.3486964242473162, "percentage": 34.88, "elapsed_time": "2:13:16", "remaining_time": "4:08:47"}
|
65 |
+
{"current_steps": 550, "total_steps": 1548, "loss": 0.4572, "lr": 8.143826084555809e-06, "epoch": 0.35515376543708127, "percentage": 35.53, "elapsed_time": "2:15:22", "remaining_time": "4:05:38"}
|
66 |
+
{"current_steps": 550, "total_steps": 1548, "eval_loss": 0.4135887324810028, "epoch": 0.35515376543708127, "percentage": 35.53, "elapsed_time": "2:17:14", "remaining_time": "4:09:01"}
|
67 |
+
{"current_steps": 560, "total_steps": 1548, "loss": 0.4639, "lr": 8.055349637488336e-06, "epoch": 0.3616111066268464, "percentage": 36.18, "elapsed_time": "2:19:20", "remaining_time": "4:05:50"}
|
68 |
+
{"current_steps": 570, "total_steps": 1548, "loss": 0.4606, "lr": 7.965319229759435e-06, "epoch": 0.3680684478166115, "percentage": 36.82, "elapsed_time": "2:21:26", "remaining_time": "4:02:41"}
|
69 |
+
{"current_steps": 580, "total_steps": 1548, "loss": 0.4764, "lr": 7.873780651124302e-06, "epoch": 0.3745257890063766, "percentage": 37.47, "elapsed_time": "2:23:33", "remaining_time": "3:59:35"}
|
70 |
+
{"current_steps": 590, "total_steps": 1548, "loss": 0.4473, "lr": 7.78078045839871e-06, "epoch": 0.3809831301961417, "percentage": 38.11, "elapsed_time": "2:25:38", "remaining_time": "3:56:28"}
|
71 |
+
{"current_steps": 600, "total_steps": 1548, "loss": 0.456, "lr": 7.686365951780071e-06, "epoch": 0.38744047138590687, "percentage": 38.76, "elapsed_time": "2:27:44", "remaining_time": "3:53:26"}
|
72 |
+
{"current_steps": 600, "total_steps": 1548, "eval_loss": 0.4034173786640167, "epoch": 0.38744047138590687, "percentage": 38.76, "elapsed_time": "2:29:36", "remaining_time": "3:56:22"}
|
73 |
+
{"current_steps": 610, "total_steps": 1548, "loss": 0.4416, "lr": 7.590585150790388e-06, "epoch": 0.39389781257567197, "percentage": 39.41, "elapsed_time": "2:31:42", "remaining_time": "3:53:17"}
|
74 |
+
{"current_steps": 620, "total_steps": 1548, "loss": 0.4652, "lr": 7.493486769853383e-06, "epoch": 0.40035515376543707, "percentage": 40.05, "elapsed_time": "2:33:47", "remaining_time": "3:50:11"}
|
75 |
+
{"current_steps": 630, "total_steps": 1548, "loss": 0.4558, "lr": 7.39512019351818e-06, "epoch": 0.4068124949552022, "percentage": 40.7, "elapsed_time": "2:35:52", "remaining_time": "3:47:07"}
|
76 |
+
{"current_steps": 640, "total_steps": 1548, "loss": 0.4351, "lr": 7.295535451342166e-06, "epoch": 0.4132698361449673, "percentage": 41.34, "elapsed_time": "2:37:57", "remaining_time": "3:44:06"}
|
77 |
+
{"current_steps": 650, "total_steps": 1548, "loss": 0.4606, "lr": 7.194783192445795e-06, "epoch": 0.4197271773347324, "percentage": 41.99, "elapsed_time": "2:40:03", "remaining_time": "3:41:07"}
|
78 |
+
{"current_steps": 650, "total_steps": 1548, "eval_loss": 0.39828598499298096, "epoch": 0.4197271773347324, "percentage": 41.99, "elapsed_time": "2:41:55", "remaining_time": "3:43:42"}
|
79 |
+
{"current_steps": 660, "total_steps": 1548, "loss": 0.4533, "lr": 7.092914659752286e-06, "epoch": 0.4261845185244975, "percentage": 42.64, "elapsed_time": "2:44:02", "remaining_time": "3:40:43"}
|
80 |
+
{"current_steps": 670, "total_steps": 1548, "loss": 0.4521, "lr": 6.989981663925301e-06, "epoch": 0.43264185971426267, "percentage": 43.28, "elapsed_time": "2:46:08", "remaining_time": "3:37:43"}
|
81 |
+
{"current_steps": 680, "total_steps": 1548, "loss": 0.4658, "lr": 6.886036557017881e-06, "epoch": 0.43909920090402776, "percentage": 43.93, "elapsed_time": "2:48:13", "remaining_time": "3:34:43"}
|
82 |
+
{"current_steps": 690, "total_steps": 1548, "loss": 0.4476, "lr": 6.781132205846019e-06, "epoch": 0.44555654209379286, "percentage": 44.57, "elapsed_time": "2:50:19", "remaining_time": "3:31:47"}
|
83 |
+
{"current_steps": 700, "total_steps": 1548, "loss": 0.4285, "lr": 6.675321965100431e-06, "epoch": 0.452013883283558, "percentage": 45.22, "elapsed_time": "2:52:25", "remaining_time": "3:28:53"}
|
84 |
+
{"current_steps": 700, "total_steps": 1548, "eval_loss": 0.38738012313842773, "epoch": 0.452013883283558, "percentage": 45.22, "elapsed_time": "2:54:17", "remaining_time": "3:31:08"}
|
85 |
+
{"current_steps": 710, "total_steps": 1548, "loss": 0.4381, "lr": 6.568659650210184e-06, "epoch": 0.4584712244733231, "percentage": 45.87, "elapsed_time": "2:56:23", "remaining_time": "3:28:11"}
|
86 |
+
{"current_steps": 720, "total_steps": 1548, "loss": 0.4264, "lr": 6.461199509972001e-06, "epoch": 0.4649285656630882, "percentage": 46.51, "elapsed_time": "2:58:30", "remaining_time": "3:25:16"}
|
87 |
+
{"current_steps": 730, "total_steps": 1548, "loss": 0.4143, "lr": 6.35299619895914e-06, "epoch": 0.47138590685285336, "percentage": 47.16, "elapsed_time": "3:00:35", "remaining_time": "3:22:21"}
|
88 |
+
{"current_steps": 740, "total_steps": 1548, "loss": 0.4364, "lr": 6.244104749723916e-06, "epoch": 0.47784324804261846, "percentage": 47.8, "elapsed_time": "3:02:39", "remaining_time": "3:19:26"}
|
89 |
+
{"current_steps": 750, "total_steps": 1548, "loss": 0.4499, "lr": 6.134580544807951e-06, "epoch": 0.48430058923238356, "percentage": 48.45, "elapsed_time": "3:04:45", "remaining_time": "3:16:34"}
|
90 |
+
{"current_steps": 750, "total_steps": 1548, "eval_loss": 0.38058942556381226, "epoch": 0.48430058923238356, "percentage": 48.45, "elapsed_time": "3:06:37", "remaining_time": "3:18:33"}
|
91 |
+
{"current_steps": 760, "total_steps": 1548, "loss": 0.4374, "lr": 6.024479288574448e-06, "epoch": 0.49075793042214866, "percentage": 49.1, "elapsed_time": "3:08:42", "remaining_time": "3:15:39"}
|
92 |
+
{"current_steps": 770, "total_steps": 1548, "loss": 0.4201, "lr": 5.9138569788767645e-06, "epoch": 0.4972152716119138, "percentage": 49.74, "elapsed_time": "3:10:47", "remaining_time": "3:12:46"}
|
93 |
+
{"current_steps": 780, "total_steps": 1548, "loss": 0.4201, "lr": 5.802769878577729e-06, "epoch": 0.5036726128016789, "percentage": 50.39, "elapsed_time": "3:12:55", "remaining_time": "3:09:57"}
|
94 |
+
{"current_steps": 790, "total_steps": 1548, "loss": 0.4258, "lr": 5.691274486934166e-06, "epoch": 0.510129953991444, "percentage": 51.03, "elapsed_time": "3:15:00", "remaining_time": "3:07:06"}
|
95 |
+
{"current_steps": 800, "total_steps": 1548, "loss": 0.4198, "lr": 5.579427510861194e-06, "epoch": 0.5165872951812092, "percentage": 51.68, "elapsed_time": "3:17:06", "remaining_time": "3:04:17"}
|
96 |
+
{"current_steps": 800, "total_steps": 1548, "eval_loss": 0.36852195858955383, "epoch": 0.5165872951812092, "percentage": 51.68, "elapsed_time": "3:18:57", "remaining_time": "3:06:01"}
|
97 |
+
{"current_steps": 810, "total_steps": 1548, "loss": 0.4268, "lr": 5.4672858360909e-06, "epoch": 0.5230446363709742, "percentage": 52.33, "elapsed_time": "3:21:02", "remaining_time": "3:03:10"}
|
98 |
+
{"current_steps": 820, "total_steps": 1548, "loss": 0.4219, "lr": 5.35490649824008e-06, "epoch": 0.5295019775607394, "percentage": 52.97, "elapsed_time": "3:23:09", "remaining_time": "3:00:22"}
|
99 |
+
{"current_steps": 830, "total_steps": 1548, "loss": 0.4447, "lr": 5.242346653801739e-06, "epoch": 0.5359593187505045, "percentage": 53.62, "elapsed_time": "3:25:15", "remaining_time": "2:57:33"}
|
100 |
+
{"current_steps": 840, "total_steps": 1548, "loss": 0.4225, "lr": 5.129663551075109e-06, "epoch": 0.5424166599402696, "percentage": 54.26, "elapsed_time": "3:27:20", "remaining_time": "2:54:45"}
|
101 |
+
{"current_steps": 850, "total_steps": 1548, "loss": 0.4208, "lr": 5.016914501048988e-06, "epoch": 0.5488740011300347, "percentage": 54.91, "elapsed_time": "3:29:28", "remaining_time": "2:52:00"}
|
102 |
+
{"current_steps": 850, "total_steps": 1548, "eval_loss": 0.366115003824234, "epoch": 0.5488740011300347, "percentage": 54.91, "elapsed_time": "3:31:20", "remaining_time": "2:53:32"}
|
103 |
+
{"current_steps": 860, "total_steps": 1548, "loss": 0.415, "lr": 4.904156848253184e-06, "epoch": 0.5553313423197999, "percentage": 55.56, "elapsed_time": "3:33:27", "remaining_time": "2:50:46"}
|
104 |
+
{"current_steps": 870, "total_steps": 1548, "loss": 0.4238, "lr": 4.791447941592896e-06, "epoch": 0.5617886835095649, "percentage": 56.2, "elapsed_time": "3:35:34", "remaining_time": "2:48:00"}
|
105 |
+
{"current_steps": 880, "total_steps": 1548, "loss": 0.4075, "lr": 4.678845105180886e-06, "epoch": 0.56824602469933, "percentage": 56.85, "elapsed_time": "3:37:41", "remaining_time": "2:45:14"}
|
106 |
+
{"current_steps": 890, "total_steps": 1548, "loss": 0.4042, "lr": 4.566405609182247e-06, "epoch": 0.5747033658890952, "percentage": 57.49, "elapsed_time": "3:39:46", "remaining_time": "2:42:29"}
|
107 |
+
{"current_steps": 900, "total_steps": 1548, "loss": 0.4379, "lr": 4.454186640686607e-06, "epoch": 0.5811607070788603, "percentage": 58.14, "elapsed_time": "3:41:52", "remaining_time": "2:39:44"}
|
108 |
+
{"current_steps": 900, "total_steps": 1548, "eval_loss": 0.3636697232723236, "epoch": 0.5811607070788603, "percentage": 58.14, "elapsed_time": "3:43:44", "remaining_time": "2:41:05"}
|
109 |
+
{"current_steps": 910, "total_steps": 1548, "loss": 0.4009, "lr": 4.3422452746226e-06, "epoch": 0.5876180482686254, "percentage": 58.79, "elapsed_time": "3:45:49", "remaining_time": "2:38:19"}
|
110 |
+
{"current_steps": 920, "total_steps": 1548, "loss": 0.4368, "lr": 4.230638444729368e-06, "epoch": 0.5940753894583906, "percentage": 59.43, "elapsed_time": "3:47:53", "remaining_time": "2:35:33"}
|
111 |
+
{"current_steps": 930, "total_steps": 1548, "loss": 0.4047, "lr": 4.1194229145998795e-06, "epoch": 0.6005327306481556, "percentage": 60.08, "elapsed_time": "3:49:58", "remaining_time": "2:32:49"}
|
112 |
+
{"current_steps": 940, "total_steps": 1548, "loss": 0.3952, "lr": 4.008655248810787e-06, "epoch": 0.6069900718379208, "percentage": 60.72, "elapsed_time": "3:52:05", "remaining_time": "2:30:07"}
|
113 |
+
{"current_steps": 950, "total_steps": 1548, "loss": 0.4075, "lr": 3.898391784153494e-06, "epoch": 0.6134474130276858, "percentage": 61.37, "elapsed_time": "3:54:10", "remaining_time": "2:27:24"}
|
114 |
+
{"current_steps": 950, "total_steps": 1548, "eval_loss": 0.3558257520198822, "epoch": 0.6134474130276858, "percentage": 61.37, "elapsed_time": "3:56:02", "remaining_time": "2:28:35"}
|
115 |
+
{"current_steps": 960, "total_steps": 1548, "loss": 0.405, "lr": 3.788688600981085e-06, "epoch": 0.619904754217451, "percentage": 62.02, "elapsed_time": "3:58:08", "remaining_time": "2:25:51"}
|
116 |
+
{"current_steps": 970, "total_steps": 1548, "loss": 0.417, "lr": 3.679601494685679e-06, "epoch": 0.6263620954072161, "percentage": 62.66, "elapsed_time": "4:00:15", "remaining_time": "2:23:09"}
|
117 |
+
{"current_steps": 980, "total_steps": 1548, "loss": 0.4077, "lr": 3.571185947320712e-06, "epoch": 0.6328194365969811, "percentage": 63.31, "elapsed_time": "4:02:22", "remaining_time": "2:20:28"}
|
118 |
+
{"current_steps": 990, "total_steps": 1548, "loss": 0.3983, "lr": 3.4634970993825854e-06, "epoch": 0.6392767777867463, "percentage": 63.95, "elapsed_time": "4:04:29", "remaining_time": "2:17:48"}
|
119 |
+
{"current_steps": 1000, "total_steps": 1548, "loss": 0.4121, "lr": 3.356589721766034e-06, "epoch": 0.6457341189765115, "percentage": 64.6, "elapsed_time": "4:06:34", "remaining_time": "2:15:07"}
|
120 |
+
{"current_steps": 1000, "total_steps": 1548, "eval_loss": 0.35134828090667725, "epoch": 0.6457341189765115, "percentage": 64.6, "elapsed_time": "4:08:26", "remaining_time": "2:16:08"}
|