Training in progress, epoch 3
Browse files
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4943162336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63f2ec7d43416d9730c5ff61a058324c5d2fe1f3e60fc0fcadc2ca66bcbb7c2b
|
3 |
size 4943162336
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999819336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ec61fa9b96de60336bcf5ffbde3aa0cdabc7d3565b1cb70d32569469f1d45bb
|
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:
|
3 |
size 4540516344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcea384ed6343e8a6536ad29060c1ad731cc7bb5b0d0ba0c72731d24d6bd2416
|
3 |
size 4540516344
|
trainer_log.jsonl
CHANGED
@@ -67,3 +67,36 @@
|
|
67 |
{"current_steps": 660, "total_steps": 1008, "loss": 0.4066, "lr": 1.7764836446824835e-06, "epoch": 1.9642857142857144, "percentage": 65.48, "elapsed_time": "5:55:07", "remaining_time": "3:07:15"}
|
68 |
{"current_steps": 670, "total_steps": 1008, "loss": 0.4039, "lr": 1.689164869002572e-06, "epoch": 1.994047619047619, "percentage": 66.47, "elapsed_time": "6:00:26", "remaining_time": "3:01:50"}
|
69 |
{"current_steps": 672, "total_steps": 1008, "eval_loss": 0.05654621869325638, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "6:05:22", "remaining_time": "3:02:41"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
{"current_steps": 660, "total_steps": 1008, "loss": 0.4066, "lr": 1.7764836446824835e-06, "epoch": 1.9642857142857144, "percentage": 65.48, "elapsed_time": "5:55:07", "remaining_time": "3:07:15"}
|
68 |
{"current_steps": 670, "total_steps": 1008, "loss": 0.4039, "lr": 1.689164869002572e-06, "epoch": 1.994047619047619, "percentage": 66.47, "elapsed_time": "6:00:26", "remaining_time": "3:01:50"}
|
69 |
{"current_steps": 672, "total_steps": 1008, "eval_loss": 0.05654621869325638, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "6:05:22", "remaining_time": "3:02:41"}
|
70 |
+
{"current_steps": 680, "total_steps": 1008, "loss": 0.355, "lr": 1.6029381269821607e-06, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "6:10:32", "remaining_time": "2:58:44"}
|
71 |
+
{"current_steps": 690, "total_steps": 1008, "loss": 0.342, "lr": 1.5179195488936505e-06, "epoch": 2.0535714285714284, "percentage": 68.45, "elapsed_time": "6:15:49", "remaining_time": "2:53:12"}
|
72 |
+
{"current_steps": 700, "total_steps": 1008, "loss": 0.3394, "lr": 1.4342236378529106e-06, "epoch": 2.0833333333333335, "percentage": 69.44, "elapsed_time": "6:21:09", "remaining_time": "2:47:42"}
|
73 |
+
{"current_steps": 710, "total_steps": 1008, "loss": 0.3363, "lr": 1.351963115606354e-06, "epoch": 2.113095238095238, "percentage": 70.44, "elapsed_time": "6:26:29", "remaining_time": "2:42:12"}
|
74 |
+
{"current_steps": 720, "total_steps": 1008, "loss": 0.3378, "lr": 1.2712487707171645e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "6:31:46", "remaining_time": "2:36:42"}
|
75 |
+
{"current_steps": 730, "total_steps": 1008, "loss": 0.338, "lr": 1.1921893093551324e-06, "epoch": 2.1726190476190474, "percentage": 72.42, "elapsed_time": "6:37:05", "remaining_time": "2:31:13"}
|
76 |
+
{"current_steps": 740, "total_steps": 1008, "loss": 0.3363, "lr": 1.1148912088910687e-06, "epoch": 2.2023809523809526, "percentage": 73.41, "elapsed_time": "6:42:23", "remaining_time": "2:25:43"}
|
77 |
+
{"current_steps": 750, "total_steps": 1008, "loss": 0.3393, "lr": 1.0394585744929605e-06, "epoch": 2.232142857142857, "percentage": 74.4, "elapsed_time": "6:47:41", "remaining_time": "2:20:14"}
|
78 |
+
{"current_steps": 760, "total_steps": 1008, "loss": 0.3401, "lr": 9.659929989170156e-07, "epoch": 2.261904761904762, "percentage": 75.4, "elapsed_time": "6:52:58", "remaining_time": "2:14:45"}
|
79 |
+
{"current_steps": 770, "total_steps": 1008, "loss": 0.3356, "lr": 8.945934256824218e-07, "epoch": 2.2916666666666665, "percentage": 76.39, "elapsed_time": "6:58:15", "remaining_time": "2:09:16"}
|
80 |
+
{"current_steps": 780, "total_steps": 1008, "loss": 0.3372, "lr": 8.253560158141111e-07, "epoch": 2.3214285714285716, "percentage": 77.38, "elapsed_time": "7:03:32", "remaining_time": "2:03:48"}
|
81 |
+
{"current_steps": 790, "total_steps": 1008, "loss": 0.3339, "lr": 7.583740183329769e-07, "epoch": 2.3511904761904763, "percentage": 78.37, "elapsed_time": "7:08:50", "remaining_time": "1:58:20"}
|
82 |
+
{"current_steps": 800, "total_steps": 1008, "loss": 0.3366, "lr": 6.93737644667995e-07, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "7:14:09", "remaining_time": "1:52:52"}
|
83 |
+
{"current_steps": 810, "total_steps": 1008, "loss": 0.3359, "lr": 6.315339471593646e-07, "epoch": 2.4107142857142856, "percentage": 80.36, "elapsed_time": "7:19:27", "remaining_time": "1:47:25"}
|
84 |
+
{"current_steps": 820, "total_steps": 1008, "loss": 0.3344, "lr": 5.718467018163243e-07, "epoch": 2.4404761904761907, "percentage": 81.35, "elapsed_time": "7:24:45", "remaining_time": "1:41:58"}
|
85 |
+
{"current_steps": 830, "total_steps": 1008, "loss": 0.3362, "lr": 5.147562954875269e-07, "epoch": 2.4702380952380953, "percentage": 82.34, "elapsed_time": "7:30:02", "remaining_time": "1:36:30"}
|
86 |
+
{"current_steps": 840, "total_steps": 1008, "loss": 0.3337, "lr": 4.6033961759594045e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "7:35:19", "remaining_time": "1:31:03"}
|
87 |
+
{"current_steps": 850, "total_steps": 1008, "loss": 0.3363, "lr": 4.0866995658409155e-07, "epoch": 2.5297619047619047, "percentage": 84.33, "elapsed_time": "7:40:38", "remaining_time": "1:25:37"}
|
88 |
+
{"current_steps": 860, "total_steps": 1008, "loss": 0.3362, "lr": 3.598169012091049e-07, "epoch": 2.5595238095238093, "percentage": 85.32, "elapsed_time": "7:45:58", "remaining_time": "1:20:11"}
|
89 |
+
{"current_steps": 870, "total_steps": 1008, "loss": 0.3394, "lr": 3.1384624682049144e-07, "epoch": 2.5892857142857144, "percentage": 86.31, "elapsed_time": "7:51:17", "remaining_time": "1:14:45"}
|
90 |
+
{"current_steps": 880, "total_steps": 1008, "loss": 0.3343, "lr": 2.708199067468939e-07, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "7:56:34", "remaining_time": "1:09:19"}
|
91 |
+
{"current_steps": 890, "total_steps": 1008, "loss": 0.3358, "lr": 2.3079582891115144e-07, "epoch": 2.6488095238095237, "percentage": 88.29, "elapsed_time": "8:01:51", "remaining_time": "1:03:53"}
|
92 |
+
{"current_steps": 900, "total_steps": 1008, "loss": 0.3343, "lr": 1.9382791778596864e-07, "epoch": 2.678571428571429, "percentage": 89.29, "elapsed_time": "8:07:09", "remaining_time": "0:58:27"}
|
93 |
+
{"current_steps": 910, "total_steps": 1008, "loss": 0.3348, "lr": 1.5996596179531365e-07, "epoch": 2.7083333333333335, "percentage": 90.28, "elapsed_time": "8:12:29", "remaining_time": "0:53:02"}
|
94 |
+
{"current_steps": 920, "total_steps": 1008, "loss": 0.3375, "lr": 1.2925556625931174e-07, "epoch": 2.738095238095238, "percentage": 91.27, "elapsed_time": "8:17:49", "remaining_time": "0:47:37"}
|
95 |
+
{"current_steps": 930, "total_steps": 1008, "loss": 0.336, "lr": 1.0173809197295075e-07, "epoch": 2.767857142857143, "percentage": 92.26, "elapsed_time": "8:23:06", "remaining_time": "0:42:11"}
|
96 |
+
{"current_steps": 940, "total_steps": 1008, "loss": 0.3339, "lr": 7.7450599501315e-08, "epoch": 2.7976190476190474, "percentage": 93.25, "elapsed_time": "8:28:23", "remaining_time": "0:36:46"}
|
97 |
+
{"current_steps": 950, "total_steps": 1008, "loss": 0.335, "lr": 5.6425799266375534e-08, "epoch": 2.8273809523809526, "percentage": 94.25, "elapsed_time": "8:33:41", "remaining_time": "0:31:21"}
|
98 |
+
{"current_steps": 960, "total_steps": 1008, "loss": 0.334, "lr": 3.869200749255703e-08, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "8:38:59", "remaining_time": "0:25:56"}
|
99 |
+
{"current_steps": 970, "total_steps": 1008, "loss": 0.3327, "lr": 2.427310807041561e-08, "epoch": 2.886904761904762, "percentage": 96.23, "elapsed_time": "8:44:17", "remaining_time": "0:20:32"}
|
100 |
+
{"current_steps": 980, "total_steps": 1008, "loss": 0.3313, "lr": 1.3188520389787462e-08, "epoch": 2.9166666666666665, "percentage": 97.22, "elapsed_time": "8:49:34", "remaining_time": "0:15:07"}
|
101 |
+
{"current_steps": 990, "total_steps": 1008, "loss": 0.336, "lr": 5.453173185734073e-09, "epoch": 2.946428571428571, "percentage": 98.21, "elapsed_time": "8:54:51", "remaining_time": "0:09:43"}
|
102 |
+
{"current_steps": 1000, "total_steps": 1008, "loss": 0.3325, "lr": 1.0774844325039946e-09, "epoch": 2.9761904761904763, "percentage": 99.21, "elapsed_time": "9:00:10", "remaining_time": "0:04:19"}
|