Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612d49951e5ec8f596c5ecefe56acb19d263838a622d9726119b4d0cb48c7d6d
+oid sha256:ddbe250b5e430ad15bd2c4e4c5c0b0a412978920534f4e8c05636cdd7400d3fd
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85bfeb9f8d2a3bb33d24dc3dbbe07f744dd4dd3c4bac7da6277d788123c31678
+oid sha256:cd69ee98aac11e3d2755d4e5d0535a1bde0fb26703f7d1c0cf32efd2ef103ea5
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ca95a4711ff1287c4eff69008425e7967f72e319f137ccff048a521b9ca95c
+oid sha256:85cb6329e57420899c5be4a80221221e12dccbec9c17b3a3417c2cbfcf89ce33
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e67292e396f365b9897a6869a06a6136984b6e7b1132dc15e3b7e3b233f6f4a
+oid sha256:87a9bd28372d16bc978c5d536782d15382f6d40df64ec418a65be0ce5c433b52
 size 1168138808

trainer_log.jsonl

@@ -61,3 +61,34 @@
 {"current_steps": 600, "total_steps": 912, "loss": 0.5331, "learning_rate": 5e-06, "epoch": 1.9688269073010665, "percentage": 65.79, "elapsed_time": "4:55:54", "remaining_time": "2:33:52"}
 {"current_steps": 609, "total_steps": 912, "eval_loss": 0.5679268836975098, "epoch": 1.9983593109105824, "percentage": 66.78, "elapsed_time": "5:03:16", "remaining_time": "2:30:53"}
 {"current_steps": 610, "total_steps": 912, "loss": 0.5258, "learning_rate": 5e-06, "epoch": 2.0016406890894176, "percentage": 66.89, "elapsed_time": "5:04:30", "remaining_time": "2:30:45"}
+{"current_steps": 620, "total_steps": 912, "loss": 0.4982, "learning_rate": 5e-06, "epoch": 2.0344544708777685, "percentage": 67.98, "elapsed_time": "5:09:24", "remaining_time": "2:25:43"}
+{"current_steps": 630, "total_steps": 912, "loss": 0.4856, "learning_rate": 5e-06, "epoch": 2.06726825266612, "percentage": 69.08, "elapsed_time": "5:14:17", "remaining_time": "2:20:40"}
+{"current_steps": 640, "total_steps": 912, "loss": 0.49, "learning_rate": 5e-06, "epoch": 2.100082034454471, "percentage": 70.18, "elapsed_time": "5:19:10", "remaining_time": "2:15:38"}
+{"current_steps": 650, "total_steps": 912, "loss": 0.49, "learning_rate": 5e-06, "epoch": 2.132895816242822, "percentage": 71.27, "elapsed_time": "5:24:03", "remaining_time": "2:10:37"}
+{"current_steps": 660, "total_steps": 912, "loss": 0.4926, "learning_rate": 5e-06, "epoch": 2.165709598031173, "percentage": 72.37, "elapsed_time": "5:28:55", "remaining_time": "2:05:35"}
+{"current_steps": 670, "total_steps": 912, "loss": 0.4876, "learning_rate": 5e-06, "epoch": 2.198523379819524, "percentage": 73.46, "elapsed_time": "5:33:48", "remaining_time": "2:00:34"}
+{"current_steps": 680, "total_steps": 912, "loss": 0.4878, "learning_rate": 5e-06, "epoch": 2.2313371616078754, "percentage": 74.56, "elapsed_time": "5:38:41", "remaining_time": "1:55:33"}
+{"current_steps": 690, "total_steps": 912, "loss": 0.4944, "learning_rate": 5e-06, "epoch": 2.2641509433962264, "percentage": 75.66, "elapsed_time": "5:43:34", "remaining_time": "1:50:32"}
+{"current_steps": 700, "total_steps": 912, "loss": 0.4966, "learning_rate": 5e-06, "epoch": 2.2969647251845773, "percentage": 76.75, "elapsed_time": "5:48:27", "remaining_time": "1:45:31"}
+{"current_steps": 710, "total_steps": 912, "loss": 0.49, "learning_rate": 5e-06, "epoch": 2.3297785069729287, "percentage": 77.85, "elapsed_time": "5:53:20", "remaining_time": "1:40:31"}
+{"current_steps": 720, "total_steps": 912, "loss": 0.5036, "learning_rate": 5e-06, "epoch": 2.3625922887612796, "percentage": 78.95, "elapsed_time": "5:58:13", "remaining_time": "1:35:31"}
+{"current_steps": 730, "total_steps": 912, "loss": 0.4927, "learning_rate": 5e-06, "epoch": 2.395406070549631, "percentage": 80.04, "elapsed_time": "6:03:06", "remaining_time": "1:30:31"}
+{"current_steps": 740, "total_steps": 912, "loss": 0.4983, "learning_rate": 5e-06, "epoch": 2.428219852337982, "percentage": 81.14, "elapsed_time": "6:07:59", "remaining_time": "1:25:31"}
+{"current_steps": 750, "total_steps": 912, "loss": 0.4949, "learning_rate": 5e-06, "epoch": 2.4610336341263332, "percentage": 82.24, "elapsed_time": "6:12:51", "remaining_time": "1:20:32"}
+{"current_steps": 760, "total_steps": 912, "loss": 0.5014, "learning_rate": 5e-06, "epoch": 2.493847415914684, "percentage": 83.33, "elapsed_time": "6:17:43", "remaining_time": "1:15:32"}
+{"current_steps": 770, "total_steps": 912, "loss": 0.4978, "learning_rate": 5e-06, "epoch": 2.526661197703035, "percentage": 84.43, "elapsed_time": "6:22:36", "remaining_time": "1:10:33"}
+{"current_steps": 780, "total_steps": 912, "loss": 0.4969, "learning_rate": 5e-06, "epoch": 2.5594749794913865, "percentage": 85.53, "elapsed_time": "6:27:29", "remaining_time": "1:05:34"}
+{"current_steps": 790, "total_steps": 912, "loss": 0.497, "learning_rate": 5e-06, "epoch": 2.5922887612797374, "percentage": 86.62, "elapsed_time": "6:32:22", "remaining_time": "1:00:35"}
+{"current_steps": 800, "total_steps": 912, "loss": 0.4881, "learning_rate": 5e-06, "epoch": 2.6251025430680883, "percentage": 87.72, "elapsed_time": "6:37:15", "remaining_time": "0:55:36"}
+{"current_steps": 810, "total_steps": 912, "loss": 0.4986, "learning_rate": 5e-06, "epoch": 2.6579163248564397, "percentage": 88.82, "elapsed_time": "6:42:08", "remaining_time": "0:50:38"}
+{"current_steps": 820, "total_steps": 912, "loss": 0.4937, "learning_rate": 5e-06, "epoch": 2.690730106644791, "percentage": 89.91, "elapsed_time": "6:47:01", "remaining_time": "0:45:40"}
+{"current_steps": 830, "total_steps": 912, "loss": 0.5017, "learning_rate": 5e-06, "epoch": 2.723543888433142, "percentage": 91.01, "elapsed_time": "6:51:54", "remaining_time": "0:40:41"}
+{"current_steps": 840, "total_steps": 912, "loss": 0.4997, "learning_rate": 5e-06, "epoch": 2.756357670221493, "percentage": 92.11, "elapsed_time": "6:56:47", "remaining_time": "0:35:43"}
+{"current_steps": 850, "total_steps": 912, "loss": 0.4975, "learning_rate": 5e-06, "epoch": 2.7891714520098443, "percentage": 93.2, "elapsed_time": "7:01:40", "remaining_time": "0:30:45"}
+{"current_steps": 860, "total_steps": 912, "loss": 0.4932, "learning_rate": 5e-06, "epoch": 2.821985233798195, "percentage": 94.3, "elapsed_time": "7:06:33", "remaining_time": "0:25:47"}
+{"current_steps": 870, "total_steps": 912, "loss": 0.5005, "learning_rate": 5e-06, "epoch": 2.854799015586546, "percentage": 95.39, "elapsed_time": "7:11:26", "remaining_time": "0:20:49"}
+{"current_steps": 880, "total_steps": 912, "loss": 0.4996, "learning_rate": 5e-06, "epoch": 2.8876127973748975, "percentage": 96.49, "elapsed_time": "7:16:19", "remaining_time": "0:15:51"}
+{"current_steps": 890, "total_steps": 912, "loss": 0.5018, "learning_rate": 5e-06, "epoch": 2.9204265791632484, "percentage": 97.59, "elapsed_time": "7:21:11", "remaining_time": "0:10:54"}
+{"current_steps": 900, "total_steps": 912, "loss": 0.4993, "learning_rate": 5e-06, "epoch": 2.9532403609516, "percentage": 98.68, "elapsed_time": "7:26:04", "remaining_time": "0:05:56"}
+{"current_steps": 910, "total_steps": 912, "loss": 0.4973, "learning_rate": 5e-06, "epoch": 2.9860541427399507, "percentage": 99.78, "elapsed_time": "7:30:57", "remaining_time": "0:00:59"}
+{"current_steps": 912, "total_steps": 912, "eval_loss": 0.5682421326637268, "epoch": 2.992616899097621, "percentage": 100.0, "elapsed_time": "7:35:41", "remaining_time": "0:00:00"}