Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:096ec6ac552983ab43d0dda5561e3c9cff60e44de3fd4a3fec86968c5bde5ddb
+oid sha256:eb916bc0b450690c5e1afe6c478d1f897fd1dc2540cccd22b8199c13e8660d5e
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17de6457729f707f5e7b14bdd33d194535fbb8ea2db9898ff992b0d385b7e0fa
+oid sha256:205275e417a966a8cd58a598695091a241244a6cebc379faddd50b03106eeb79
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0346b3d13149088937a90cf9250412b91f716cc09bb44e039341c8ec827aaf70
+oid sha256:afaa6cb5402a003f3641db27c880ade415548dfbf5ae9acb41e6ce09266e08e0
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d77716a96c8918c7275c8585b9be3e90a6a09717e76a6ff1a8d424f26029f920
+oid sha256:70c7698e8de6d3d99fe6e5ba20dc8dd518071a276ca7e9acc72343f32321d607
 size 1089994880

trainer_log.jsonl

@@ -43,3 +43,47 @@
 {"current_steps": 430, "total_steps": 1314, "loss": 0.6369, "learning_rate": 3.7394247038917094e-06, "epoch": 0.98005698005698, "percentage": 32.72, "elapsed_time": "6:17:30", "remaining_time": "12:56:05"}
 {"current_steps": 438, "total_steps": 1314, "eval_loss": 0.6274411082267761, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:32:18", "remaining_time": "13:04:37"}
 {"current_steps": 440, "total_steps": 1314, "loss": 0.6504, "learning_rate": 3.697123519458545e-06, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:34:44", "remaining_time": "13:04:06"}
+{"current_steps": 450, "total_steps": 1314, "loss": 0.6094, "learning_rate": 3.654822335025381e-06, "epoch": 1.0262108262108263, "percentage": 34.25, "elapsed_time": "6:43:34", "remaining_time": "12:54:51"}
+{"current_steps": 460, "total_steps": 1314, "loss": 0.603, "learning_rate": 3.612521150592217e-06, "epoch": 1.049002849002849, "percentage": 35.01, "elapsed_time": "6:52:21", "remaining_time": "12:45:33"}
+{"current_steps": 470, "total_steps": 1314, "loss": 0.604, "learning_rate": 3.5702199661590524e-06, "epoch": 1.0717948717948718, "percentage": 35.77, "elapsed_time": "7:01:08", "remaining_time": "12:36:15"}
+{"current_steps": 480, "total_steps": 1314, "loss": 0.6114, "learning_rate": 3.5279187817258886e-06, "epoch": 1.0945868945868946, "percentage": 36.53, "elapsed_time": "7:09:56", "remaining_time": "12:27:01"}
+{"current_steps": 490, "total_steps": 1314, "loss": 0.6165, "learning_rate": 3.4856175972927248e-06, "epoch": 1.1173789173789175, "percentage": 37.29, "elapsed_time": "7:18:42", "remaining_time": "12:17:44"}
+{"current_steps": 500, "total_steps": 1314, "loss": 0.6062, "learning_rate": 3.4433164128595605e-06, "epoch": 1.1401709401709401, "percentage": 38.05, "elapsed_time": "7:27:29", "remaining_time": "12:08:30"}
+{"current_steps": 510, "total_steps": 1314, "loss": 0.6039, "learning_rate": 3.4010152284263963e-06, "epoch": 1.162962962962963, "percentage": 38.81, "elapsed_time": "7:36:17", "remaining_time": "11:59:19"}
+{"current_steps": 520, "total_steps": 1314, "loss": 0.6095, "learning_rate": 3.358714043993232e-06, "epoch": 1.1857549857549858, "percentage": 39.57, "elapsed_time": "7:45:05", "remaining_time": "11:50:09"}
+{"current_steps": 530, "total_steps": 1314, "loss": 0.6025, "learning_rate": 3.3164128595600682e-06, "epoch": 1.2085470085470085, "percentage": 40.33, "elapsed_time": "7:53:52", "remaining_time": "11:40:57"}
+{"current_steps": 540, "total_steps": 1314, "loss": 0.6127, "learning_rate": 3.2741116751269036e-06, "epoch": 1.2313390313390313, "percentage": 41.1, "elapsed_time": "8:02:38", "remaining_time": "11:31:46"}
+{"current_steps": 550, "total_steps": 1314, "loss": 0.6091, "learning_rate": 3.2318104906937397e-06, "epoch": 1.2541310541310542, "percentage": 41.86, "elapsed_time": "8:11:26", "remaining_time": "11:22:38"}
+{"current_steps": 560, "total_steps": 1314, "loss": 0.6107, "learning_rate": 3.1895093062605755e-06, "epoch": 1.2769230769230768, "percentage": 42.62, "elapsed_time": "8:20:14", "remaining_time": "11:13:31"}
+{"current_steps": 570, "total_steps": 1314, "loss": 0.6046, "learning_rate": 3.1472081218274113e-06, "epoch": 1.2997150997150997, "percentage": 43.38, "elapsed_time": "8:29:02", "remaining_time": "11:04:26"}
+{"current_steps": 580, "total_steps": 1314, "loss": 0.6029, "learning_rate": 3.1049069373942474e-06, "epoch": 1.3225071225071225, "percentage": 44.14, "elapsed_time": "8:37:49", "remaining_time": "10:55:19"}
+{"current_steps": 590, "total_steps": 1314, "loss": 0.6028, "learning_rate": 3.062605752961083e-06, "epoch": 1.3452991452991454, "percentage": 44.9, "elapsed_time": "8:46:37", "remaining_time": "10:46:14"}
+{"current_steps": 600, "total_steps": 1314, "loss": 0.6083, "learning_rate": 3.0203045685279194e-06, "epoch": 1.368091168091168, "percentage": 45.66, "elapsed_time": "8:55:25", "remaining_time": "10:37:09"}
+{"current_steps": 610, "total_steps": 1314, "loss": 0.6084, "learning_rate": 2.9780033840947547e-06, "epoch": 1.390883190883191, "percentage": 46.42, "elapsed_time": "9:04:14", "remaining_time": "10:28:06"}
+{"current_steps": 620, "total_steps": 1314, "loss": 0.611, "learning_rate": 2.935702199661591e-06, "epoch": 1.4136752136752135, "percentage": 47.18, "elapsed_time": "9:12:58", "remaining_time": "10:18:58"}
+{"current_steps": 630, "total_steps": 1314, "loss": 0.6088, "learning_rate": 2.8934010152284262e-06, "epoch": 1.4364672364672364, "percentage": 47.95, "elapsed_time": "9:21:44", "remaining_time": "10:09:53"}
+{"current_steps": 640, "total_steps": 1314, "loss": 0.6036, "learning_rate": 2.8510998307952624e-06, "epoch": 1.4592592592592593, "percentage": 48.71, "elapsed_time": "9:30:31", "remaining_time": "10:00:50"}
+{"current_steps": 650, "total_steps": 1314, "loss": 0.6013, "learning_rate": 2.808798646362098e-06, "epoch": 1.4820512820512821, "percentage": 49.47, "elapsed_time": "9:39:18", "remaining_time": "9:51:46"}
+{"current_steps": 660, "total_steps": 1314, "loss": 0.6012, "learning_rate": 2.7664974619289344e-06, "epoch": 1.504843304843305, "percentage": 50.23, "elapsed_time": "9:48:06", "remaining_time": "9:42:45"}
+{"current_steps": 670, "total_steps": 1314, "loss": 0.6088, "learning_rate": 2.72419627749577e-06, "epoch": 1.5276353276353276, "percentage": 50.99, "elapsed_time": "9:56:54", "remaining_time": "9:33:44"}
+{"current_steps": 680, "total_steps": 1314, "loss": 0.5973, "learning_rate": 2.681895093062606e-06, "epoch": 1.5504273504273505, "percentage": 51.75, "elapsed_time": "10:05:41", "remaining_time": "9:24:43"}
+{"current_steps": 690, "total_steps": 1314, "loss": 0.6012, "learning_rate": 2.639593908629442e-06, "epoch": 1.573219373219373, "percentage": 52.51, "elapsed_time": "10:14:29", "remaining_time": "9:15:42"}
+{"current_steps": 700, "total_steps": 1314, "loss": 0.617, "learning_rate": 2.5972927241962774e-06, "epoch": 1.596011396011396, "percentage": 53.27, "elapsed_time": "10:23:16", "remaining_time": "9:06:41"}
+{"current_steps": 710, "total_steps": 1314, "loss": 0.6039, "learning_rate": 2.5549915397631136e-06, "epoch": 1.6188034188034188, "percentage": 54.03, "elapsed_time": "10:32:04", "remaining_time": "8:57:42"}
+{"current_steps": 720, "total_steps": 1314, "loss": 0.6083, "learning_rate": 2.5126903553299493e-06, "epoch": 1.6415954415954417, "percentage": 54.79, "elapsed_time": "10:40:51", "remaining_time": "8:48:42"}
+{"current_steps": 730, "total_steps": 1314, "loss": 0.6014, "learning_rate": 2.470389170896785e-06, "epoch": 1.6643874643874645, "percentage": 55.56, "elapsed_time": "10:49:39", "remaining_time": "8:39:43"}
+{"current_steps": 740, "total_steps": 1314, "loss": 0.6023, "learning_rate": 2.4280879864636213e-06, "epoch": 1.6871794871794872, "percentage": 56.32, "elapsed_time": "10:58:24", "remaining_time": "8:30:42"}
+{"current_steps": 750, "total_steps": 1314, "loss": 0.5995, "learning_rate": 2.385786802030457e-06, "epoch": 1.7099715099715098, "percentage": 57.08, "elapsed_time": "11:07:12", "remaining_time": "8:21:44"}
+{"current_steps": 760, "total_steps": 1314, "loss": 0.6038, "learning_rate": 2.343485617597293e-06, "epoch": 1.7327635327635327, "percentage": 57.84, "elapsed_time": "11:16:00", "remaining_time": "8:12:46"}
+{"current_steps": 770, "total_steps": 1314, "loss": 0.6003, "learning_rate": 2.3011844331641286e-06, "epoch": 1.7555555555555555, "percentage": 58.6, "elapsed_time": "11:24:48", "remaining_time": "8:03:48"}
+{"current_steps": 780, "total_steps": 1314, "loss": 0.6074, "learning_rate": 2.2588832487309648e-06, "epoch": 1.7783475783475784, "percentage": 59.36, "elapsed_time": "11:33:35", "remaining_time": "7:54:50"}
+{"current_steps": 790, "total_steps": 1314, "loss": 0.6048, "learning_rate": 2.2165820642978005e-06, "epoch": 1.8011396011396013, "percentage": 60.12, "elapsed_time": "11:42:23", "remaining_time": "7:45:53"}
+{"current_steps": 800, "total_steps": 1314, "loss": 0.5916, "learning_rate": 2.1742808798646363e-06, "epoch": 1.823931623931624, "percentage": 60.88, "elapsed_time": "11:51:11", "remaining_time": "7:36:56"}
+{"current_steps": 810, "total_steps": 1314, "loss": 0.5995, "learning_rate": 2.1319796954314725e-06, "epoch": 1.8467236467236468, "percentage": 61.64, "elapsed_time": "12:00:01", "remaining_time": "7:28:00"}
+{"current_steps": 820, "total_steps": 1314, "loss": 0.5972, "learning_rate": 2.0896785109983082e-06, "epoch": 1.8695156695156694, "percentage": 62.4, "elapsed_time": "12:08:50", "remaining_time": "7:19:04"}
+{"current_steps": 830, "total_steps": 1314, "loss": 0.601, "learning_rate": 2.047377326565144e-06, "epoch": 1.8923076923076922, "percentage": 63.17, "elapsed_time": "12:17:37", "remaining_time": "7:10:08"}
+{"current_steps": 840, "total_steps": 1314, "loss": 0.6057, "learning_rate": 2.0050761421319797e-06, "epoch": 1.915099715099715, "percentage": 63.93, "elapsed_time": "12:26:25", "remaining_time": "7:01:11"}
+{"current_steps": 850, "total_steps": 1314, "loss": 0.6036, "learning_rate": 1.9627749576988155e-06, "epoch": 1.937891737891738, "percentage": 64.69, "elapsed_time": "12:35:11", "remaining_time": "6:52:14"}
+{"current_steps": 860, "total_steps": 1314, "loss": 0.6048, "learning_rate": 1.9204737732656517e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:43:59", "remaining_time": "6:43:18"}
+{"current_steps": 870, "total_steps": 1314, "loss": 0.6024, "learning_rate": 1.8781725888324874e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:52:48", "remaining_time": "6:34:23"}
+{"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6210305690765381, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:06:18", "remaining_time": "6:31:48"}