Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5882616c1aae0f7724d7bd34885022e27ded9c71106c2e5c79aa443754359b2c
+oid sha256:4263bb12f6f7b00cc787ca42acd9f1e6041bdb37b46a99592b1d88d1273c92df
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:842486dc4798da8d9a24f55e6fb0df5984e1c83e8cebb625d1502eb92eb84884
+oid sha256:065a237bd8ad8cf4066a0afbd6671f6cf69d55d76e49496adcc09264f8b3bbd6
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f8dec8e74d6a2b105b6c505a8970b29659411a6b494585e79f37bf3ecfbb0f
+oid sha256:1b20f4b185827c975fe4e2de6775d96c941617e3f433e2eb70eade3664ee43cf
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1278fc2ed69ef661b65f3f4650b90f1867233d89bc97fe37b276924d356941b
+oid sha256:5a5c5a9e6108759a35e812818c4fd3367f3fc176e91d00d7c4bcb115b7790adc
 size 1168138808

trainer_log.jsonl

@@ -16,3 +16,20 @@
 {"current_steps": 160, "total_steps": 501, "loss": 0.7727, "lr": 5e-06, "epoch": 0.9538002980625931, "percentage": 31.94, "elapsed_time": "2:34:10", "remaining_time": "5:28:36"}
 {"current_steps": 167, "total_steps": 501, "eval_loss": 0.7674793601036072, "epoch": 0.9955290611028316, "percentage": 33.33, "elapsed_time": "2:44:37", "remaining_time": "5:29:14"}
 {"current_steps": 170, "total_steps": 501, "loss": 0.7832, "lr": 5e-06, "epoch": 1.0134128166915053, "percentage": 33.93, "elapsed_time": "2:47:58", "remaining_time": "5:27:03"}
+{"current_steps": 180, "total_steps": 501, "loss": 0.7342, "lr": 5e-06, "epoch": 1.0730253353204173, "percentage": 35.93, "elapsed_time": "2:57:35", "remaining_time": "5:16:42"}
+{"current_steps": 190, "total_steps": 501, "loss": 0.7264, "lr": 5e-06, "epoch": 1.1326378539493294, "percentage": 37.92, "elapsed_time": "3:07:13", "remaining_time": "5:06:26"}
+{"current_steps": 200, "total_steps": 501, "loss": 0.7249, "lr": 5e-06, "epoch": 1.1922503725782414, "percentage": 39.92, "elapsed_time": "3:16:52", "remaining_time": "4:56:17"}
+{"current_steps": 210, "total_steps": 501, "loss": 0.733, "lr": 5e-06, "epoch": 1.2518628912071534, "percentage": 41.92, "elapsed_time": "3:26:28", "remaining_time": "4:46:06"}
+{"current_steps": 220, "total_steps": 501, "loss": 0.7219, "lr": 5e-06, "epoch": 1.3114754098360657, "percentage": 43.91, "elapsed_time": "3:36:07", "remaining_time": "4:36:02"}
+{"current_steps": 230, "total_steps": 501, "loss": 0.7208, "lr": 5e-06, "epoch": 1.3710879284649775, "percentage": 45.91, "elapsed_time": "3:45:46", "remaining_time": "4:26:01"}
+{"current_steps": 240, "total_steps": 501, "loss": 0.7188, "lr": 5e-06, "epoch": 1.4307004470938898, "percentage": 47.9, "elapsed_time": "3:55:24", "remaining_time": "4:16:00"}
+{"current_steps": 250, "total_steps": 501, "loss": 0.7192, "lr": 5e-06, "epoch": 1.4903129657228018, "percentage": 49.9, "elapsed_time": "4:05:03", "remaining_time": "4:06:01"}
+{"current_steps": 260, "total_steps": 501, "loss": 0.7245, "lr": 5e-06, "epoch": 1.5499254843517138, "percentage": 51.9, "elapsed_time": "4:14:42", "remaining_time": "3:56:05"}
+{"current_steps": 270, "total_steps": 501, "loss": 0.7263, "lr": 5e-06, "epoch": 1.6095380029806259, "percentage": 53.89, "elapsed_time": "4:24:21", "remaining_time": "3:46:10"}
+{"current_steps": 280, "total_steps": 501, "loss": 0.7203, "lr": 5e-06, "epoch": 1.669150521609538, "percentage": 55.89, "elapsed_time": "4:34:01", "remaining_time": "3:36:16"}
+{"current_steps": 290, "total_steps": 501, "loss": 0.7217, "lr": 5e-06, "epoch": 1.7287630402384502, "percentage": 57.88, "elapsed_time": "4:43:41", "remaining_time": "3:26:24"}
+{"current_steps": 300, "total_steps": 501, "loss": 0.7267, "lr": 5e-06, "epoch": 1.788375558867362, "percentage": 59.88, "elapsed_time": "4:53:21", "remaining_time": "3:16:33"}
+{"current_steps": 310, "total_steps": 501, "loss": 0.7179, "lr": 5e-06, "epoch": 1.8479880774962743, "percentage": 61.88, "elapsed_time": "5:03:02", "remaining_time": "3:06:42"}
+{"current_steps": 320, "total_steps": 501, "loss": 0.7196, "lr": 5e-06, "epoch": 1.9076005961251863, "percentage": 63.87, "elapsed_time": "5:12:41", "remaining_time": "2:56:51"}
+{"current_steps": 330, "total_steps": 501, "loss": 0.7274, "lr": 5e-06, "epoch": 1.9672131147540983, "percentage": 65.87, "elapsed_time": "5:22:20", "remaining_time": "2:47:01"}
+{"current_steps": 335, "total_steps": 501, "eval_loss": 0.7537275552749634, "epoch": 1.9970193740685542, "percentage": 66.87, "elapsed_time": "5:30:31", "remaining_time": "2:43:46"}