Training in progress, epoch 3
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:b95d2007cf9678b0631629c90e5ec895dea621909be558b1ddf384cbe5b27a3e
|
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 sha256:2a17565a015e785d3047eee83874a220d87055d9c3e6aeea56766dd4e5a6352e
|
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 sha256:3998932160aa35d4ecfa18518d59971a05549651c0db94fffdfb5cb858f9710a
|
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:db4b2c9735963d5cd92fc6208d578b23e0f6cc6d5ac033ea829070c43aaf4395
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -59,3 +59,32 @@
|
|
59 |
{"current_steps": 580, "total_steps": 882, "loss": 0.7399, "lr": 5e-06, "epoch": 1.9727891156462585, "percentage": 65.76, "elapsed_time": "9:25:25", "remaining_time": "4:54:24"}
|
60 |
{"current_steps": 588, "total_steps": 882, "eval_loss": 0.7747776508331299, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "9:38:24", "remaining_time": "4:49:12"}
|
61 |
{"current_steps": 590, "total_steps": 882, "loss": 0.7322, "lr": 5e-06, "epoch": 2.006802721088435, "percentage": 66.89, "elapsed_time": "9:41:32", "remaining_time": "4:47:48"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
{"current_steps": 580, "total_steps": 882, "loss": 0.7399, "lr": 5e-06, "epoch": 1.9727891156462585, "percentage": 65.76, "elapsed_time": "9:25:25", "remaining_time": "4:54:24"}
|
60 |
{"current_steps": 588, "total_steps": 882, "eval_loss": 0.7747776508331299, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "9:38:24", "remaining_time": "4:49:12"}
|
61 |
{"current_steps": 590, "total_steps": 882, "loss": 0.7322, "lr": 5e-06, "epoch": 2.006802721088435, "percentage": 66.89, "elapsed_time": "9:41:32", "remaining_time": "4:47:48"}
|
62 |
+
{"current_steps": 600, "total_steps": 882, "loss": 0.6959, "lr": 5e-06, "epoch": 2.0408163265306123, "percentage": 68.03, "elapsed_time": "9:51:12", "remaining_time": "4:37:51"}
|
63 |
+
{"current_steps": 610, "total_steps": 882, "loss": 0.6963, "lr": 5e-06, "epoch": 2.074829931972789, "percentage": 69.16, "elapsed_time": "10:00:51", "remaining_time": "4:27:55"}
|
64 |
+
{"current_steps": 620, "total_steps": 882, "loss": 0.6919, "lr": 5e-06, "epoch": 2.108843537414966, "percentage": 70.29, "elapsed_time": "10:10:30", "remaining_time": "4:17:59"}
|
65 |
+
{"current_steps": 630, "total_steps": 882, "loss": 0.6885, "lr": 5e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "10:20:09", "remaining_time": "4:08:03"}
|
66 |
+
{"current_steps": 640, "total_steps": 882, "loss": 0.696, "lr": 5e-06, "epoch": 2.17687074829932, "percentage": 72.56, "elapsed_time": "10:29:48", "remaining_time": "3:58:08"}
|
67 |
+
{"current_steps": 650, "total_steps": 882, "loss": 0.6937, "lr": 5e-06, "epoch": 2.2108843537414966, "percentage": 73.7, "elapsed_time": "10:39:27", "remaining_time": "3:48:14"}
|
68 |
+
{"current_steps": 660, "total_steps": 882, "loss": 0.6981, "lr": 5e-06, "epoch": 2.2448979591836733, "percentage": 74.83, "elapsed_time": "10:49:05", "remaining_time": "3:38:19"}
|
69 |
+
{"current_steps": 670, "total_steps": 882, "loss": 0.7015, "lr": 5e-06, "epoch": 2.2789115646258504, "percentage": 75.96, "elapsed_time": "10:58:45", "remaining_time": "3:28:26"}
|
70 |
+
{"current_steps": 680, "total_steps": 882, "loss": 0.7012, "lr": 5e-06, "epoch": 2.312925170068027, "percentage": 77.1, "elapsed_time": "11:08:25", "remaining_time": "3:18:33"}
|
71 |
+
{"current_steps": 690, "total_steps": 882, "loss": 0.6952, "lr": 5e-06, "epoch": 2.3469387755102042, "percentage": 78.23, "elapsed_time": "11:18:03", "remaining_time": "3:08:40"}
|
72 |
+
{"current_steps": 700, "total_steps": 882, "loss": 0.6953, "lr": 5e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "11:27:42", "remaining_time": "2:58:48"}
|
73 |
+
{"current_steps": 710, "total_steps": 882, "loss": 0.6997, "lr": 5e-06, "epoch": 2.4149659863945576, "percentage": 80.5, "elapsed_time": "11:37:20", "remaining_time": "2:48:56"}
|
74 |
+
{"current_steps": 720, "total_steps": 882, "loss": 0.6947, "lr": 5e-06, "epoch": 2.4489795918367347, "percentage": 81.63, "elapsed_time": "11:46:57", "remaining_time": "2:39:04"}
|
75 |
+
{"current_steps": 730, "total_steps": 882, "loss": 0.7002, "lr": 5e-06, "epoch": 2.4829931972789114, "percentage": 82.77, "elapsed_time": "11:56:36", "remaining_time": "2:29:12"}
|
76 |
+
{"current_steps": 740, "total_steps": 882, "loss": 0.7, "lr": 5e-06, "epoch": 2.5170068027210886, "percentage": 83.9, "elapsed_time": "12:06:14", "remaining_time": "2:19:21"}
|
77 |
+
{"current_steps": 750, "total_steps": 882, "loss": 0.6977, "lr": 5e-06, "epoch": 2.5510204081632653, "percentage": 85.03, "elapsed_time": "12:15:52", "remaining_time": "2:09:30"}
|
78 |
+
{"current_steps": 760, "total_steps": 882, "loss": 0.6972, "lr": 5e-06, "epoch": 2.5850340136054424, "percentage": 86.17, "elapsed_time": "12:25:31", "remaining_time": "1:59:40"}
|
79 |
+
{"current_steps": 770, "total_steps": 882, "loss": 0.6988, "lr": 5e-06, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "12:35:10", "remaining_time": "1:49:50"}
|
80 |
+
{"current_steps": 780, "total_steps": 882, "loss": 0.6977, "lr": 5e-06, "epoch": 2.6530612244897958, "percentage": 88.44, "elapsed_time": "12:44:48", "remaining_time": "1:40:00"}
|
81 |
+
{"current_steps": 790, "total_steps": 882, "loss": 0.6987, "lr": 5e-06, "epoch": 2.687074829931973, "percentage": 89.57, "elapsed_time": "12:54:26", "remaining_time": "1:30:11"}
|
82 |
+
{"current_steps": 800, "total_steps": 882, "loss": 0.6982, "lr": 5e-06, "epoch": 2.7210884353741496, "percentage": 90.7, "elapsed_time": "13:04:03", "remaining_time": "1:20:22"}
|
83 |
+
{"current_steps": 810, "total_steps": 882, "loss": 0.7006, "lr": 5e-06, "epoch": 2.7551020408163263, "percentage": 91.84, "elapsed_time": "13:13:42", "remaining_time": "1:10:33"}
|
84 |
+
{"current_steps": 820, "total_steps": 882, "loss": 0.7038, "lr": 5e-06, "epoch": 2.7891156462585034, "percentage": 92.97, "elapsed_time": "13:23:20", "remaining_time": "1:00:44"}
|
85 |
+
{"current_steps": 830, "total_steps": 882, "loss": 0.7031, "lr": 5e-06, "epoch": 2.8231292517006805, "percentage": 94.1, "elapsed_time": "13:32:57", "remaining_time": "0:50:55"}
|
86 |
+
{"current_steps": 840, "total_steps": 882, "loss": 0.7001, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "13:42:35", "remaining_time": "0:41:07"}
|
87 |
+
{"current_steps": 850, "total_steps": 882, "loss": 0.6999, "lr": 5e-06, "epoch": 2.891156462585034, "percentage": 96.37, "elapsed_time": "13:52:13", "remaining_time": "0:31:19"}
|
88 |
+
{"current_steps": 860, "total_steps": 882, "loss": 0.7007, "lr": 5e-06, "epoch": 2.925170068027211, "percentage": 97.51, "elapsed_time": "14:01:53", "remaining_time": "0:21:32"}
|
89 |
+
{"current_steps": 870, "total_steps": 882, "loss": 0.7029, "lr": 5e-06, "epoch": 2.9591836734693877, "percentage": 98.64, "elapsed_time": "14:11:30", "remaining_time": "0:11:44"}
|
90 |
+
{"current_steps": 880, "total_steps": 882, "loss": 0.7006, "lr": 5e-06, "epoch": 2.9931972789115644, "percentage": 99.77, "elapsed_time": "14:21:09", "remaining_time": "0:01:57"}
|