Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d3a6b4c46831cd8c1810b0e7e62f8df2c1f59d51f078be6eeada7e2f8b66a6f
+oid sha256:847dc02f3b38aa7e51f0cacbe1b2b80cb29380793b7bf43a6cf5d1d1b94b455c
 size 4903351912

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8e7d2165c972659fcdf972726afe841189fdbce3be21f4f03c078fe14c8204
+oid sha256:98d2c3d23b2d39fab6fc5b5326e3c2a31e0765bee6f6567aede4042b437aa53e
 size 4947570872

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78682608a9eefe579d96b02436606bb2c5d1b626beeff357efa02023c79e74b7
+oid sha256:80bfa8f575ce1b25b91c01f7da9ec0bbaa16bc12948a7636470294a65576e7ee
 size 4962221464

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb531babee48b91e142934d7e7dda1033c6b3664c84dc210e6a651cb706fadfb
+oid sha256:7cb16e3955e4d8454bd444cfc5cd2f4c17c1b3009e33b760fb4c8da32cefafb1
 size 3670322200

trainer_log.jsonl

@@ -43,3 +43,48 @@
 {"current_steps": 430, "total_steps": 1329, "loss": 0.591, "learning_rate": 4.291488888871734e-06, "epoch": 0.9703808180535967, "percentage": 32.36, "elapsed_time": "10:41:29", "remaining_time": "22:21:09"}
 {"current_steps": 440, "total_steps": 1329, "loss": 0.5957, "learning_rate": 4.245626907435755e-06, "epoch": 0.9929478138222849, "percentage": 33.11, "elapsed_time": "10:56:25", "remaining_time": "22:06:16"}
 {"current_steps": 443, "total_steps": 1329, "eval_loss": 0.5937371253967285, "epoch": 0.9997179125528914, "percentage": 33.33, "elapsed_time": "11:12:31", "remaining_time": "22:25:02"}
+{"current_steps": 450, "total_steps": 1329, "loss": 0.6093, "learning_rate": 4.198595042234199e-06, "epoch": 1.0155148095909732, "percentage": 33.86, "elapsed_time": "11:24:03", "remaining_time": "22:16:11"}
+{"current_steps": 460, "total_steps": 1329, "loss": 0.5388, "learning_rate": 4.150425742513609e-06, "epoch": 1.0380818053596614, "percentage": 34.61, "elapsed_time": "11:38:56", "remaining_time": "22:00:23"}
+{"current_steps": 470, "total_steps": 1329, "loss": 0.5538, "learning_rate": 4.101152242284071e-06, "epoch": 1.0606488011283497, "percentage": 35.36, "elapsed_time": "11:53:48", "remaining_time": "21:44:35"}
+{"current_steps": 480, "total_steps": 1329, "loss": 0.5413, "learning_rate": 4.050808537389682e-06, "epoch": 1.0832157968970382, "percentage": 36.12, "elapsed_time": "12:08:44", "remaining_time": "21:28:58"}
+{"current_steps": 490, "total_steps": 1329, "loss": 0.5516, "learning_rate": 3.999429362053397e-06, "epoch": 1.1057827926657264, "percentage": 36.87, "elapsed_time": "12:23:42", "remaining_time": "21:13:24"}
+{"current_steps": 500, "total_steps": 1329, "loss": 0.5497, "learning_rate": 3.947050164912446e-06, "epoch": 1.1283497884344147, "percentage": 37.62, "elapsed_time": "12:38:36", "remaining_time": "20:57:47"}
+{"current_steps": 510, "total_steps": 1329, "loss": 0.5506, "learning_rate": 3.893707084560831e-06, "epoch": 1.150916784203103, "percentage": 38.37, "elapsed_time": "12:53:29", "remaining_time": "20:42:08"}
+{"current_steps": 520, "total_steps": 1329, "loss": 0.5428, "learning_rate": 3.839436924615808e-06, "epoch": 1.1734837799717912, "percentage": 39.13, "elapsed_time": "13:08:25", "remaining_time": "20:26:37"}
+{"current_steps": 530, "total_steps": 1329, "loss": 0.5485, "learning_rate": 3.784277128325532e-06, "epoch": 1.1960507757404795, "percentage": 39.88, "elapsed_time": "13:23:22", "remaining_time": "20:11:08"}
+{"current_steps": 540, "total_steps": 1329, "loss": 0.5458, "learning_rate": 3.7282657527354014e-06, "epoch": 1.2186177715091677, "percentage": 40.63, "elapsed_time": "13:38:18", "remaining_time": "19:55:38"}
+{"current_steps": 550, "total_steps": 1329, "loss": 0.5507, "learning_rate": 3.671441442430908e-06, "epoch": 1.2411847672778562, "percentage": 41.38, "elapsed_time": "13:53:14", "remaining_time": "19:40:10"}
+{"current_steps": 560, "total_steps": 1329, "loss": 0.5521, "learning_rate": 3.6138434028751334e-06, "epoch": 1.2637517630465445, "percentage": 42.14, "elapsed_time": "14:08:11", "remaining_time": "19:24:44"}
+{"current_steps": 570, "total_steps": 1329, "loss": 0.549, "learning_rate": 3.555511373359255e-06, "epoch": 1.2863187588152327, "percentage": 42.89, "elapsed_time": "14:23:05", "remaining_time": "19:09:16"}
+{"current_steps": 580, "total_steps": 1329, "loss": 0.5489, "learning_rate": 3.496485599584756e-06, "epoch": 1.308885754583921, "percentage": 43.64, "elapsed_time": "14:37:59", "remaining_time": "18:53:48"}
+{"current_steps": 590, "total_steps": 1329, "loss": 0.5487, "learning_rate": 3.4368068058962357e-06, "epoch": 1.3314527503526092, "percentage": 44.39, "elapsed_time": "14:52:54", "remaining_time": "18:38:24"}
+{"current_steps": 600, "total_steps": 1329, "loss": 0.5542, "learning_rate": 3.376516167183983e-06, "epoch": 1.3540197461212977, "percentage": 45.15, "elapsed_time": "15:07:49", "remaining_time": "18:23:00"}
+{"current_steps": 610, "total_steps": 1329, "loss": 0.5459, "learning_rate": 3.315655280475704e-06, "epoch": 1.376586741889986, "percentage": 45.9, "elapsed_time": "15:22:43", "remaining_time": "18:07:36"}
+{"current_steps": 620, "total_steps": 1329, "loss": 0.5502, "learning_rate": 3.2542661362369925e-06, "epoch": 1.3991537376586742, "percentage": 46.65, "elapsed_time": "15:37:38", "remaining_time": "17:52:14"}
+{"current_steps": 630, "total_steps": 1329, "loss": 0.5479, "learning_rate": 3.1923910894003598e-06, "epoch": 1.4217207334273625, "percentage": 47.4, "elapsed_time": "15:52:32", "remaining_time": "17:36:52"}
+{"current_steps": 640, "total_steps": 1329, "loss": 0.5471, "learning_rate": 3.1300728301427947e-06, "epoch": 1.4442877291960508, "percentage": 48.16, "elapsed_time": "16:07:26", "remaining_time": "17:21:30"}
+{"current_steps": 650, "total_steps": 1329, "loss": 0.5479, "learning_rate": 3.0673543544320354e-06, "epoch": 1.466854724964739, "percentage": 48.91, "elapsed_time": "16:22:20", "remaining_time": "17:06:10"}
+{"current_steps": 660, "total_steps": 1329, "loss": 0.5515, "learning_rate": 3.00427893436185e-06, "epoch": 1.4894217207334273, "percentage": 49.66, "elapsed_time": "16:37:14", "remaining_time": "16:50:50"}
+{"current_steps": 670, "total_steps": 1329, "loss": 0.5459, "learning_rate": 2.9408900882968174e-06, "epoch": 1.5119887165021155, "percentage": 50.41, "elapsed_time": "16:52:07", "remaining_time": "16:35:30"}
+{"current_steps": 680, "total_steps": 1329, "loss": 0.5402, "learning_rate": 2.8772315508471893e-06, "epoch": 1.5345557122708038, "percentage": 51.17, "elapsed_time": "17:07:03", "remaining_time": "16:20:14"}
+{"current_steps": 690, "total_steps": 1329, "loss": 0.5417, "learning_rate": 2.8133472426945584e-06, "epoch": 1.5571227080394923, "percentage": 51.92, "elapsed_time": "17:21:56", "remaining_time": "16:04:55"}
+{"current_steps": 700, "total_steps": 1329, "loss": 0.546, "learning_rate": 2.749281240289151e-06, "epoch": 1.5796897038081805, "percentage": 52.67, "elapsed_time": "17:36:52", "remaining_time": "15:49:40"}
+{"current_steps": 710, "total_steps": 1329, "loss": 0.5486, "learning_rate": 2.6850777454396342e-06, "epoch": 1.6022566995768688, "percentage": 53.42, "elapsed_time": "17:51:47", "remaining_time": "15:34:25"}
+{"current_steps": 720, "total_steps": 1329, "loss": 0.5563, "learning_rate": 2.620781054816457e-06, "epoch": 1.6248236953455573, "percentage": 54.18, "elapsed_time": "18:06:42", "remaining_time": "15:19:10"}
+{"current_steps": 730, "total_steps": 1329, "loss": 0.5393, "learning_rate": 2.5564355293897154e-06, "epoch": 1.6473906911142455, "percentage": 54.93, "elapsed_time": "18:21:37", "remaining_time": "15:03:55"}
+{"current_steps": 740, "total_steps": 1329, "loss": 0.5546, "learning_rate": 2.49208556382268e-06, "epoch": 1.6699576868829338, "percentage": 55.68, "elapsed_time": "18:36:32", "remaining_time": "14:48:42"}
+{"current_steps": 750, "total_steps": 1329, "loss": 0.5461, "learning_rate": 2.427775555842057e-06, "epoch": 1.692524682651622, "percentage": 56.43, "elapsed_time": "18:51:27", "remaining_time": "14:33:29"}
+{"current_steps": 760, "total_steps": 1329, "loss": 0.5448, "learning_rate": 2.3635498756061458e-06, "epoch": 1.7150916784203103, "percentage": 57.19, "elapsed_time": "19:06:22", "remaining_time": "14:18:16"}
+{"current_steps": 770, "total_steps": 1329, "loss": 0.545, "learning_rate": 2.299452835092016e-06, "epoch": 1.7376586741889986, "percentage": 57.94, "elapsed_time": "19:21:15", "remaining_time": "14:03:02"}
+{"current_steps": 780, "total_steps": 1329, "loss": 0.5411, "learning_rate": 2.2355286575228257e-06, "epoch": 1.7602256699576868, "percentage": 58.69, "elapsed_time": "19:36:12", "remaining_time": "13:47:52"}
+{"current_steps": 790, "total_steps": 1329, "loss": 0.5441, "learning_rate": 2.1718214468563717e-06, "epoch": 1.782792665726375, "percentage": 59.44, "elapsed_time": "19:51:08", "remaining_time": "13:32:41"}
+{"current_steps": 800, "total_steps": 1329, "loss": 0.5388, "learning_rate": 2.108375157355931e-06, "epoch": 1.8053596614950633, "percentage": 60.2, "elapsed_time": "20:06:05", "remaining_time": "13:17:31"}
+{"current_steps": 810, "total_steps": 1329, "loss": 0.5494, "learning_rate": 2.0452335632643795e-06, "epoch": 1.8279266572637518, "percentage": 60.95, "elapsed_time": "20:21:03", "remaining_time": "13:02:22"}
+{"current_steps": 820, "total_steps": 1329, "loss": 0.5363, "learning_rate": 1.9824402286025154e-06, "epoch": 1.85049365303244, "percentage": 61.7, "elapsed_time": "20:36:00", "remaining_time": "12:47:13"}
+{"current_steps": 830, "total_steps": 1329, "loss": 0.5481, "learning_rate": 1.92003847711242e-06, "epoch": 1.8730606488011283, "percentage": 62.45, "elapsed_time": "20:50:56", "remaining_time": "12:32:04"}
+{"current_steps": 840, "total_steps": 1329, "loss": 0.5483, "learning_rate": 1.8580713623666068e-06, "epoch": 1.8956276445698168, "percentage": 63.21, "elapsed_time": "21:05:53", "remaining_time": "12:16:55"}
+{"current_steps": 850, "total_steps": 1329, "loss": 0.5358, "learning_rate": 1.7965816380635584e-06, "epoch": 1.918194640338505, "percentage": 63.96, "elapsed_time": "21:20:50", "remaining_time": "12:01:47"}
+{"current_steps": 860, "total_steps": 1329, "loss": 0.5409, "learning_rate": 1.7356117285301693e-06, "epoch": 1.9407616361071933, "percentage": 64.71, "elapsed_time": "21:35:45", "remaining_time": "11:46:38"}
+{"current_steps": 870, "total_steps": 1329, "loss": 0.5475, "learning_rate": 1.675203699451431e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:50:40", "remaining_time": "11:31:29"}
+{"current_steps": 880, "total_steps": 1329, "loss": 0.5451, "learning_rate": 1.6153992288475608e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:05:35", "remaining_time": "11:16:21"}
+{"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5835120677947998, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:26:19", "remaining_time": "11:13:09"}