Training in progress, step 600
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 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8edf1689671b5167eab01aefc02dc9a307f75355c75c8d77fb8cb4b0b6dfb354
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0094fe136b9c1e70d1ef9c0d70b1a85fa73d7f94c4be0cc01e1a29228d6be3c9
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6e54d439604df655963dbd916fa3bdee78851b9500a0f4ad6e95b84721cbcbb
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e15f6a202f08396e706f15d0499579279a80864fbd29912c70c6f4a169e2ba6
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -81,3 +81,44 @@
|
|
| 81 |
{"current_steps": 405, "total_steps": 1652, "loss": 0.1993, "lr": 3.7521242600626154e-05, "epoch": 1.7176220806794054, "percentage": 24.52, "elapsed_time": "4:17:20", "remaining_time": "13:12:20"}
|
| 82 |
{"current_steps": 410, "total_steps": 1652, "loss": 0.2471, "lr": 3.7418322781117e-05, "epoch": 1.7388535031847132, "percentage": 24.82, "elapsed_time": "4:20:28", "remaining_time": "13:09:03"}
|
| 83 |
{"current_steps": 415, "total_steps": 1652, "loss": 0.2065, "lr": 3.731345668561577e-05, "epoch": 1.7600849256900213, "percentage": 25.12, "elapsed_time": "4:23:38", "remaining_time": "13:05:49"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
{"current_steps": 405, "total_steps": 1652, "loss": 0.1993, "lr": 3.7521242600626154e-05, "epoch": 1.7176220806794054, "percentage": 24.52, "elapsed_time": "4:17:20", "remaining_time": "13:12:20"}
|
| 82 |
{"current_steps": 410, "total_steps": 1652, "loss": 0.2471, "lr": 3.7418322781117e-05, "epoch": 1.7388535031847132, "percentage": 24.82, "elapsed_time": "4:20:28", "remaining_time": "13:09:03"}
|
| 83 |
{"current_steps": 415, "total_steps": 1652, "loss": 0.2065, "lr": 3.731345668561577e-05, "epoch": 1.7600849256900213, "percentage": 25.12, "elapsed_time": "4:23:38", "remaining_time": "13:05:49"}
|
| 84 |
+
{"current_steps": 420, "total_steps": 1652, "loss": 0.1736, "lr": 3.720665603157464e-05, "epoch": 1.7813163481953291, "percentage": 25.42, "elapsed_time": "4:26:47", "remaining_time": "13:02:36"}
|
| 85 |
+
{"current_steps": 425, "total_steps": 1652, "loss": 0.219, "lr": 3.7097932752608096e-05, "epoch": 1.802547770700637, "percentage": 25.73, "elapsed_time": "4:29:56", "remaining_time": "12:59:20"}
|
| 86 |
+
{"current_steps": 430, "total_steps": 1652, "loss": 0.1986, "lr": 3.698729899715947e-05, "epoch": 1.8237791932059448, "percentage": 26.03, "elapsed_time": "4:33:06", "remaining_time": "12:56:07"}
|
| 87 |
+
{"current_steps": 435, "total_steps": 1652, "loss": 0.2078, "lr": 3.687476712714358e-05, "epoch": 1.8450106157112527, "percentage": 26.33, "elapsed_time": "4:36:15", "remaining_time": "12:52:53"}
|
| 88 |
+
{"current_steps": 440, "total_steps": 1652, "loss": 0.1934, "lr": 3.676034971656537e-05, "epoch": 1.8662420382165605, "percentage": 26.63, "elapsed_time": "4:39:24", "remaining_time": "12:49:38"}
|
| 89 |
+
{"current_steps": 445, "total_steps": 1652, "loss": 0.1917, "lr": 3.664405955011498e-05, "epoch": 1.8874734607218684, "percentage": 26.94, "elapsed_time": "4:42:33", "remaining_time": "12:46:22"}
|
| 90 |
+
{"current_steps": 450, "total_steps": 1652, "loss": 0.2353, "lr": 3.652590962173917e-05, "epoch": 1.9087048832271762, "percentage": 27.24, "elapsed_time": "4:45:41", "remaining_time": "12:43:05"}
|
| 91 |
+
{"current_steps": 455, "total_steps": 1652, "loss": 0.2091, "lr": 3.640591313318944e-05, "epoch": 1.929936305732484, "percentage": 27.54, "elapsed_time": "4:48:49", "remaining_time": "12:39:50"}
|
| 92 |
+
{"current_steps": 460, "total_steps": 1652, "loss": 0.202, "lr": 3.628408349254693e-05, "epoch": 1.951167728237792, "percentage": 27.85, "elapsed_time": "4:51:58", "remaining_time": "12:36:35"}
|
| 93 |
+
{"current_steps": 465, "total_steps": 1652, "loss": 0.2048, "lr": 3.616043431272417e-05, "epoch": 1.9723991507430998, "percentage": 28.15, "elapsed_time": "4:55:06", "remaining_time": "12:33:19"}
|
| 94 |
+
{"current_steps": 470, "total_steps": 1652, "loss": 0.2125, "lr": 3.603497940994407e-05, "epoch": 1.9936305732484076, "percentage": 28.45, "elapsed_time": "4:58:15", "remaining_time": "12:30:05"}
|
| 95 |
+
{"current_steps": 475, "total_steps": 1652, "loss": 0.1976, "lr": 3.59077328021961e-05, "epoch": 2.0127388535031847, "percentage": 28.75, "elapsed_time": "5:01:06", "remaining_time": "12:26:05"}
|
| 96 |
+
{"current_steps": 480, "total_steps": 1652, "loss": 0.2029, "lr": 3.577870870766997e-05, "epoch": 2.0339702760084926, "percentage": 29.06, "elapsed_time": "5:04:14", "remaining_time": "12:22:51"}
|
| 97 |
+
{"current_steps": 485, "total_steps": 1652, "loss": 0.1978, "lr": 3.5647921543166923e-05, "epoch": 2.0552016985138004, "percentage": 29.36, "elapsed_time": "5:07:23", "remaining_time": "12:19:39"}
|
| 98 |
+
{"current_steps": 490, "total_steps": 1652, "loss": 0.1965, "lr": 3.5515385922488846e-05, "epoch": 2.0764331210191083, "percentage": 29.66, "elapsed_time": "5:10:33", "remaining_time": "12:16:28"}
|
| 99 |
+
{"current_steps": 495, "total_steps": 1652, "loss": 0.1878, "lr": 3.5381116654805375e-05, "epoch": 2.097664543524416, "percentage": 29.96, "elapsed_time": "5:13:43", "remaining_time": "12:13:16"}
|
| 100 |
+
{"current_steps": 500, "total_steps": 1652, "loss": 0.1913, "lr": 3.524512874299912e-05, "epoch": 2.118895966029724, "percentage": 30.27, "elapsed_time": "5:16:52", "remaining_time": "12:10:05"}
|
| 101 |
+
{"current_steps": 505, "total_steps": 1652, "loss": 0.1988, "lr": 3.5107437381989325e-05, "epoch": 2.140127388535032, "percentage": 30.57, "elapsed_time": "5:20:01", "remaining_time": "12:06:52"}
|
| 102 |
+
{"current_steps": 510, "total_steps": 1652, "loss": 0.194, "lr": 3.4968057957034e-05, "epoch": 2.1613588110403397, "percentage": 30.87, "elapsed_time": "5:23:10", "remaining_time": "12:03:39"}
|
| 103 |
+
{"current_steps": 515, "total_steps": 1652, "loss": 0.1947, "lr": 3.482700604201086e-05, "epoch": 2.1825902335456475, "percentage": 31.17, "elapsed_time": "5:26:19", "remaining_time": "12:00:26"}
|
| 104 |
+
{"current_steps": 520, "total_steps": 1652, "loss": 0.2124, "lr": 3.4684297397677064e-05, "epoch": 2.2038216560509554, "percentage": 31.48, "elapsed_time": "5:29:27", "remaining_time": "11:57:12"}
|
| 105 |
+
{"current_steps": 525, "total_steps": 1652, "loss": 0.2005, "lr": 3.453994796990823e-05, "epoch": 2.225053078556263, "percentage": 31.78, "elapsed_time": "5:32:36", "remaining_time": "11:54:00"}
|
| 106 |
+
{"current_steps": 530, "total_steps": 1652, "loss": 0.1842, "lr": 3.439397388791662e-05, "epoch": 2.246284501061571, "percentage": 32.08, "elapsed_time": "5:35:46", "remaining_time": "11:50:48"}
|
| 107 |
+
{"current_steps": 535, "total_steps": 1652, "loss": 0.2108, "lr": 3.424639146244898e-05, "epoch": 2.267515923566879, "percentage": 32.38, "elapsed_time": "5:38:55", "remaining_time": "11:47:37"}
|
| 108 |
+
{"current_steps": 540, "total_steps": 1652, "loss": 0.2073, "lr": 3.409721718396395e-05, "epoch": 2.2887473460721868, "percentage": 32.69, "elapsed_time": "5:42:04", "remaining_time": "11:44:25"}
|
| 109 |
+
{"current_steps": 545, "total_steps": 1652, "loss": 0.2136, "lr": 3.394646772078951e-05, "epoch": 2.3099787685774946, "percentage": 32.99, "elapsed_time": "5:45:13", "remaining_time": "11:41:13"}
|
| 110 |
+
{"current_steps": 550, "total_steps": 1652, "loss": 0.1953, "lr": 3.379415991726047e-05, "epoch": 2.3312101910828025, "percentage": 33.29, "elapsed_time": "5:48:22", "remaining_time": "11:38:00"}
|
| 111 |
+
{"current_steps": 555, "total_steps": 1652, "loss": 0.2001, "lr": 3.3640310791836375e-05, "epoch": 2.3524416135881103, "percentage": 33.6, "elapsed_time": "5:51:31", "remaining_time": "11:34:49"}
|
| 112 |
+
{"current_steps": 560, "total_steps": 1652, "loss": 0.2171, "lr": 3.348493753519987e-05, "epoch": 2.373673036093418, "percentage": 33.9, "elapsed_time": "5:54:38", "remaining_time": "11:31:34"}
|
| 113 |
+
{"current_steps": 565, "total_steps": 1652, "loss": 0.1966, "lr": 3.332805750833588e-05, "epoch": 2.394904458598726, "percentage": 34.2, "elapsed_time": "5:57:47", "remaining_time": "11:28:20"}
|
| 114 |
+
{"current_steps": 570, "total_steps": 1652, "loss": 0.187, "lr": 3.3169688240591735e-05, "epoch": 2.416135881104034, "percentage": 34.5, "elapsed_time": "6:00:56", "remaining_time": "11:25:08"}
|
| 115 |
+
{"current_steps": 575, "total_steps": 1652, "loss": 0.1826, "lr": 3.300984742771849e-05, "epoch": 2.4373673036093417, "percentage": 34.81, "elapsed_time": "6:04:05", "remaining_time": "11:21:57"}
|
| 116 |
+
{"current_steps": 580, "total_steps": 1652, "loss": 0.2016, "lr": 3.284855292989363e-05, "epoch": 2.4585987261146496, "percentage": 35.11, "elapsed_time": "6:07:14", "remaining_time": "11:18:46"}
|
| 117 |
+
{"current_steps": 585, "total_steps": 1652, "loss": 0.1907, "lr": 3.268582276972549e-05, "epoch": 2.4798301486199574, "percentage": 35.41, "elapsed_time": "6:10:23", "remaining_time": "11:15:34"}
|
| 118 |
+
{"current_steps": 590, "total_steps": 1652, "loss": 0.2006, "lr": 3.252167513023934e-05, "epoch": 2.5010615711252653, "percentage": 35.71, "elapsed_time": "6:13:33", "remaining_time": "11:12:24"}
|
| 119 |
+
{"current_steps": 595, "total_steps": 1652, "loss": 0.1982, "lr": 3.2356128352845794e-05, "epoch": 2.522292993630573, "percentage": 36.02, "elapsed_time": "6:16:43", "remaining_time": "11:09:14"}
|
| 120 |
+
{"current_steps": 600, "total_steps": 1652, "loss": 0.1869, "lr": 3.218920093529129e-05, "epoch": 2.543524416135881, "percentage": 36.32, "elapsed_time": "6:19:53", "remaining_time": "11:06:04"}
|
| 121 |
+
{"current_steps": 605, "total_steps": 1652, "loss": 0.1757, "lr": 3.202091152959126e-05, "epoch": 2.564755838641189, "percentage": 36.62, "elapsed_time": "6:24:12", "remaining_time": "11:04:53"}
|
| 122 |
+
{"current_steps": 610, "total_steps": 1652, "loss": 0.1775, "lr": 3.1851278939945974e-05, "epoch": 2.5859872611464967, "percentage": 36.92, "elapsed_time": "6:27:20", "remaining_time": "11:01:40"}
|
| 123 |
+
{"current_steps": 615, "total_steps": 1652, "loss": 0.2035, "lr": 3.1680322120639436e-05, "epoch": 2.6072186836518045, "percentage": 37.23, "elapsed_time": "6:30:29", "remaining_time": "10:58:26"}
|
| 124 |
+
{"current_steps": 620, "total_steps": 1652, "loss": 0.1815, "lr": 3.150806017392145e-05, "epoch": 2.6284501061571124, "percentage": 37.53, "elapsed_time": "6:33:39", "remaining_time": "10:55:15"}
|