Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2db4665f73a81067323c6e1fe3ce6f20f13701e1f5b75374bb3028914965ce
+oid sha256:a5c9bd309f09bbc0db2507c2579c285c61e442698dc76fca08031eac9372dec2
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b7a1d76edd17f58b72b10a87b25de3b47b417c8f3ebe8889f922c52a50eb6e4
+oid sha256:d27502b8a0f063f838b49f24df41f083ef19933eaf3b757f75134d1a728a3afb
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0726a4f44f1570ca984fd8ac93eaa5cff5ed9de2b548195a2c5e96bef958f59e
+oid sha256:11a9a0bbd2466019520e897f24193ae317e90607d3d4d932699db1f9db00f621
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738ef48df46f96764e2a8273f0c597b75b940f15bd6d6ba0b96c693de6e1b7b0
+oid sha256:4ee412f5c6bd76d07c3cf01a36cc3eb42e0fddbac3085f2846e3ce4db263e846
 size 1089994880

trainer_log.jsonl

@@ -33,3 +33,37 @@
 {"current_steps": 330, "total_steps": 682, "loss": 0.6401, "learning_rate": 5e-06, "epoch": 0.9656181419166057, "percentage": 48.39, "elapsed_time": "4:47:13", "remaining_time": "5:06:22"}
 {"current_steps": 340, "total_steps": 682, "loss": 0.6361, "learning_rate": 5e-06, "epoch": 0.9948792977322605, "percentage": 49.85, "elapsed_time": "4:55:55", "remaining_time": "4:57:40"}
 {"current_steps": 341, "total_steps": 682, "eval_loss": 0.6406120657920837, "epoch": 0.9978054133138259, "percentage": 50.0, "elapsed_time": "5:02:50", "remaining_time": "5:02:50"}
+{"current_steps": 350, "total_steps": 682, "loss": 0.6512, "learning_rate": 5e-06, "epoch": 1.025237746891002, "percentage": 51.32, "elapsed_time": "5:11:26", "remaining_time": "4:55:25"}
+{"current_steps": 360, "total_steps": 682, "loss": 0.6053, "learning_rate": 5e-06, "epoch": 1.054498902706657, "percentage": 52.79, "elapsed_time": "5:20:08", "remaining_time": "4:46:21"}
+{"current_steps": 370, "total_steps": 682, "loss": 0.6087, "learning_rate": 5e-06, "epoch": 1.0837600585223117, "percentage": 54.25, "elapsed_time": "5:28:51", "remaining_time": "4:37:18"}
+{"current_steps": 380, "total_steps": 682, "loss": 0.6061, "learning_rate": 5e-06, "epoch": 1.1130212143379663, "percentage": 55.72, "elapsed_time": "5:37:34", "remaining_time": "4:28:17"}
+{"current_steps": 390, "total_steps": 682, "loss": 0.6114, "learning_rate": 5e-06, "epoch": 1.142282370153621, "percentage": 57.18, "elapsed_time": "5:46:17", "remaining_time": "4:19:16"}
+{"current_steps": 400, "total_steps": 682, "loss": 0.6129, "learning_rate": 5e-06, "epoch": 1.1715435259692757, "percentage": 58.65, "elapsed_time": "5:54:59", "remaining_time": "4:10:15"}
+{"current_steps": 410, "total_steps": 682, "loss": 0.6125, "learning_rate": 5e-06, "epoch": 1.2008046817849305, "percentage": 60.12, "elapsed_time": "6:03:42", "remaining_time": "4:01:17"}
+{"current_steps": 420, "total_steps": 682, "loss": 0.6007, "learning_rate": 5e-06, "epoch": 1.2300658376005853, "percentage": 61.58, "elapsed_time": "6:12:24", "remaining_time": "3:52:18"}
+{"current_steps": 430, "total_steps": 682, "loss": 0.6108, "learning_rate": 5e-06, "epoch": 1.2593269934162399, "percentage": 63.05, "elapsed_time": "6:21:07", "remaining_time": "3:43:21"}
+{"current_steps": 440, "total_steps": 682, "loss": 0.6036, "learning_rate": 5e-06, "epoch": 1.2885881492318947, "percentage": 64.52, "elapsed_time": "6:29:49", "remaining_time": "3:34:24"}
+{"current_steps": 450, "total_steps": 682, "loss": 0.6073, "learning_rate": 5e-06, "epoch": 1.3178493050475493, "percentage": 65.98, "elapsed_time": "6:38:32", "remaining_time": "3:25:28"}
+{"current_steps": 460, "total_steps": 682, "loss": 0.6049, "learning_rate": 5e-06, "epoch": 1.347110460863204, "percentage": 67.45, "elapsed_time": "6:47:14", "remaining_time": "3:16:32"}
+{"current_steps": 470, "total_steps": 682, "loss": 0.6023, "learning_rate": 5e-06, "epoch": 1.3763716166788589, "percentage": 68.91, "elapsed_time": "6:55:56", "remaining_time": "3:07:37"}
+{"current_steps": 480, "total_steps": 682, "loss": 0.6031, "learning_rate": 5e-06, "epoch": 1.4056327724945135, "percentage": 70.38, "elapsed_time": "7:04:38", "remaining_time": "2:58:42"}
+{"current_steps": 490, "total_steps": 682, "loss": 0.6095, "learning_rate": 5e-06, "epoch": 1.4348939283101683, "percentage": 71.85, "elapsed_time": "7:13:21", "remaining_time": "2:49:48"}
+{"current_steps": 500, "total_steps": 682, "loss": 0.5978, "learning_rate": 5e-06, "epoch": 1.464155084125823, "percentage": 73.31, "elapsed_time": "7:22:03", "remaining_time": "2:40:54"}
+{"current_steps": 510, "total_steps": 682, "loss": 0.6059, "learning_rate": 5e-06, "epoch": 1.4934162399414777, "percentage": 74.78, "elapsed_time": "7:30:46", "remaining_time": "2:32:01"}
+{"current_steps": 520, "total_steps": 682, "loss": 0.6082, "learning_rate": 5e-06, "epoch": 1.5226773957571325, "percentage": 76.25, "elapsed_time": "7:39:29", "remaining_time": "2:23:08"}
+{"current_steps": 530, "total_steps": 682, "loss": 0.6068, "learning_rate": 5e-06, "epoch": 1.5519385515727873, "percentage": 77.71, "elapsed_time": "7:48:12", "remaining_time": "2:14:16"}
+{"current_steps": 540, "total_steps": 682, "loss": 0.6134, "learning_rate": 5e-06, "epoch": 1.5811997073884418, "percentage": 79.18, "elapsed_time": "7:56:56", "remaining_time": "2:05:24"}
+{"current_steps": 550, "total_steps": 682, "loss": 0.6044, "learning_rate": 5e-06, "epoch": 1.6104608632040964, "percentage": 80.65, "elapsed_time": "8:05:39", "remaining_time": "1:56:33"}
+{"current_steps": 560, "total_steps": 682, "loss": 0.6061, "learning_rate": 5e-06, "epoch": 1.6397220190197512, "percentage": 82.11, "elapsed_time": "8:14:23", "remaining_time": "1:47:42"}
+{"current_steps": 570, "total_steps": 682, "loss": 0.5968, "learning_rate": 5e-06, "epoch": 1.668983174835406, "percentage": 83.58, "elapsed_time": "8:23:07", "remaining_time": "1:38:51"}
+{"current_steps": 580, "total_steps": 682, "loss": 0.6061, "learning_rate": 5e-06, "epoch": 1.6982443306510606, "percentage": 85.04, "elapsed_time": "8:31:50", "remaining_time": "1:30:00"}
+{"current_steps": 590, "total_steps": 682, "loss": 0.6063, "learning_rate": 5e-06, "epoch": 1.7275054864667154, "percentage": 86.51, "elapsed_time": "8:40:34", "remaining_time": "1:21:10"}
+{"current_steps": 600, "total_steps": 682, "loss": 0.6032, "learning_rate": 5e-06, "epoch": 1.7567666422823702, "percentage": 87.98, "elapsed_time": "8:49:17", "remaining_time": "1:12:20"}
+{"current_steps": 610, "total_steps": 682, "loss": 0.6056, "learning_rate": 5e-06, "epoch": 1.7860277980980248, "percentage": 89.44, "elapsed_time": "8:57:58", "remaining_time": "1:03:29"}
+{"current_steps": 620, "total_steps": 682, "loss": 0.6061, "learning_rate": 5e-06, "epoch": 1.8152889539136796, "percentage": 90.91, "elapsed_time": "9:06:41", "remaining_time": "0:54:40"}
+{"current_steps": 630, "total_steps": 682, "loss": 0.6052, "learning_rate": 5e-06, "epoch": 1.8445501097293344, "percentage": 92.38, "elapsed_time": "9:15:24", "remaining_time": "0:45:50"}
+{"current_steps": 640, "total_steps": 682, "loss": 0.6, "learning_rate": 5e-06, "epoch": 1.873811265544989, "percentage": 93.84, "elapsed_time": "9:24:06", "remaining_time": "0:37:01"}
+{"current_steps": 650, "total_steps": 682, "loss": 0.6057, "learning_rate": 5e-06, "epoch": 1.9030724213606436, "percentage": 95.31, "elapsed_time": "9:32:49", "remaining_time": "0:28:12"}
+{"current_steps": 660, "total_steps": 682, "loss": 0.6062, "learning_rate": 5e-06, "epoch": 1.9323335771762986, "percentage": 96.77, "elapsed_time": "9:41:29", "remaining_time": "0:19:22"}
+{"current_steps": 670, "total_steps": 682, "loss": 0.595, "learning_rate": 5e-06, "epoch": 1.9615947329919532, "percentage": 98.24, "elapsed_time": "9:50:11", "remaining_time": "0:10:34"}
+{"current_steps": 680, "total_steps": 682, "loss": 0.6095, "learning_rate": 5e-06, "epoch": 1.9908558888076078, "percentage": 99.71, "elapsed_time": "9:58:54", "remaining_time": "0:01:45"}