Training in progress, step 2850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656b339f848f4a5e39a2f325df5573bc98a1ce1de9df8113a07cd8eeae54367e
+oid sha256:01a330ed632b021642148062b09d22bb079b73a39c22d87b4a866893ac04d712
 size 29034840

trainer_log.jsonl

@@ -617,3 +617,14 @@
 {"current_steps": 2795, "total_steps": 3400, "loss": 0.308, "lr": 8.409640695783443e-06, "epoch": 0.7198042750450683, "percentage": 82.21, "elapsed_time": "1:15:40", "remaining_time": "0:16:22", "throughput": 6464.36, "total_tokens": 29349664}
 {"current_steps": 2800, "total_steps": 3400, "loss": 0.3567, "lr": 8.275164992077556e-06, "epoch": 0.7210919392222508, "percentage": 82.35, "elapsed_time": "1:17:08", "remaining_time": "0:16:31", "throughput": 6353.06, "total_tokens": 29402040}
 {"current_steps": 2800, "total_steps": 3400, "eval_loss": 0.4282406270503998, "epoch": 0.7210919392222508, "percentage": 82.35, "elapsed_time": "1:17:46", "remaining_time": "0:16:39", "throughput": 6301.28, "total_tokens": 29402040}
+{"current_steps": 2805, "total_steps": 3400, "loss": 0.2538, "lr": 8.141676086873572e-06, "epoch": 0.7223796033994334, "percentage": 82.5, "elapsed_time": "1:19:16", "remaining_time": "0:16:49", "throughput": 6192.3, "total_tokens": 29455456}
+{"current_steps": 2810, "total_steps": 3400, "loss": 0.3374, "lr": 8.009177137203794e-06, "epoch": 0.723667267576616, "percentage": 82.65, "elapsed_time": "1:20:42", "remaining_time": "0:16:56", "throughput": 6093.0, "total_tokens": 29507136}
+{"current_steps": 2815, "total_steps": 3400, "loss": 0.3303, "lr": 7.877671276687898e-06, "epoch": 0.7249549317537987, "percentage": 82.79, "elapsed_time": "1:22:07", "remaining_time": "0:17:03", "throughput": 5998.8, "total_tokens": 29558760}
+{"current_steps": 2820, "total_steps": 3400, "loss": 0.2834, "lr": 7.747161615458902e-06, "epoch": 0.7262425959309812, "percentage": 82.94, "elapsed_time": "1:23:34", "remaining_time": "0:17:11", "throughput": 5905.78, "total_tokens": 29612000}
+{"current_steps": 2825, "total_steps": 3400, "loss": 0.2746, "lr": 7.617651240089546e-06, "epoch": 0.7275302601081638, "percentage": 83.09, "elapsed_time": "1:24:58", "remaining_time": "0:17:17", "throughput": 5817.99, "total_tokens": 29664472}
+{"current_steps": 2830, "total_steps": 3400, "loss": 0.315, "lr": 7.489143213519301e-06, "epoch": 0.7288179242853464, "percentage": 83.24, "elapsed_time": "1:26:24", "remaining_time": "0:17:24", "throughput": 5731.65, "total_tokens": 29716440}
+{"current_steps": 2835, "total_steps": 3400, "loss": 0.2877, "lr": 7.361640574981937e-06, "epoch": 0.7301055884625289, "percentage": 83.38, "elapsed_time": "1:27:49", "remaining_time": "0:17:30", "throughput": 5648.99, "total_tokens": 29769248}
+{"current_steps": 2840, "total_steps": 3400, "loss": 0.2953, "lr": 7.2351463399336735e-06, "epoch": 0.7313932526397116, "percentage": 83.53, "elapsed_time": "1:29:14", "remaining_time": "0:17:35", "throughput": 5569.15, "total_tokens": 29821968}
+{"current_steps": 2845, "total_steps": 3400, "loss": 0.2709, "lr": 7.109663499981834e-06, "epoch": 0.7326809168168942, "percentage": 83.68, "elapsed_time": "1:30:40", "remaining_time": "0:17:41", "throughput": 5490.9, "total_tokens": 29875104}
+{"current_steps": 2850, "total_steps": 3400, "loss": 0.3024, "lr": 6.985195022814067e-06, "epoch": 0.7339685809940767, "percentage": 83.82, "elapsed_time": "1:32:05", "remaining_time": "0:17:46", "throughput": 5415.97, "total_tokens": 29928032}
+{"current_steps": 2850, "total_steps": 3400, "eval_loss": 0.47043517231941223, "epoch": 0.7339685809940767, "percentage": 83.82, "elapsed_time": "1:32:43", "remaining_time": "0:17:53", "throughput": 5379.51, "total_tokens": 29928032}