Training in progress, step 1700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e0b4a2fc40fdec8a180c4d25ce929ba82f7ef789cad9b7a31fd3f14719a2c9
+oid sha256:40488b690d3cbb62aef973e623da597fed2f1f503eac48f0d6e9e0140377208a
 size 29034840

trainer_log.jsonl

@@ -365,3 +365,14 @@
 {"current_steps": 1645, "total_steps": 3400, "loss": 0.372, "lr": 5.6787384668786994e-05, "epoch": 0.42364151429307234, "percentage": 48.38, "elapsed_time": "5:25:19", "remaining_time": "5:47:04", "throughput": 884.74, "total_tokens": 17269344}
 {"current_steps": 1650, "total_steps": 3400, "loss": 0.3755, "lr": 5.654639883131178e-05, "epoch": 0.42492917847025496, "percentage": 48.53, "elapsed_time": "5:26:46", "remaining_time": "5:46:34", "throughput": 883.55, "total_tokens": 17323232}
 {"current_steps": 1650, "total_steps": 3400, "eval_loss": 0.4726848006248474, "epoch": 0.42492917847025496, "percentage": 48.53, "elapsed_time": "5:27:24", "remaining_time": "5:47:15", "throughput": 881.82, "total_tokens": 17323232}
+{"current_steps": 1655, "total_steps": 3400, "loss": 0.3972, "lr": 5.6305258170538676e-05, "epoch": 0.42621684264743753, "percentage": 48.68, "elapsed_time": "5:28:56", "remaining_time": "5:46:50", "throughput": 880.35, "total_tokens": 17375432}
+{"current_steps": 1660, "total_steps": 3400, "loss": 0.3988, "lr": 5.606396838947988e-05, "epoch": 0.42750450682462016, "percentage": 48.82, "elapsed_time": "5:30:23", "remaining_time": "5:46:19", "throughput": 879.13, "total_tokens": 17427832}
+{"current_steps": 1665, "total_steps": 3400, "loss": 0.4247, "lr": 5.582253519467432e-05, "epoch": 0.4287921710018027, "percentage": 48.97, "elapsed_time": "5:31:51", "remaining_time": "5:45:48", "throughput": 877.87, "total_tokens": 17480056}
+{"current_steps": 1670, "total_steps": 3400, "loss": 0.386, "lr": 5.558096429605263e-05, "epoch": 0.43007983517898535, "percentage": 49.12, "elapsed_time": "5:33:18", "remaining_time": "5:45:16", "throughput": 876.74, "total_tokens": 17533192}
+{"current_steps": 1675, "total_steps": 3400, "loss": 0.4487, "lr": 5.533926140680221e-05, "epoch": 0.4313674993561679, "percentage": 49.26, "elapsed_time": "5:34:46", "remaining_time": "5:44:45", "throughput": 875.48, "total_tokens": 17585000}
+{"current_steps": 1680, "total_steps": 3400, "loss": 0.3878, "lr": 5.509743224323203e-05, "epoch": 0.4326551635333505, "percentage": 49.41, "elapsed_time": "5:36:14", "remaining_time": "5:44:15", "throughput": 874.26, "total_tokens": 17638152}
+{"current_steps": 1685, "total_steps": 3400, "loss": 0.3333, "lr": 5.485548252463749e-05, "epoch": 0.4339428277105331, "percentage": 49.56, "elapsed_time": "5:37:47", "remaining_time": "5:43:48", "throughput": 872.86, "total_tokens": 17690656}
+{"current_steps": 1690, "total_steps": 3400, "loss": 0.464, "lr": 5.4613417973165106e-05, "epoch": 0.4352304918877157, "percentage": 49.71, "elapsed_time": "5:39:19", "remaining_time": "5:43:20", "throughput": 871.45, "total_tokens": 17742112}
+{"current_steps": 1695, "total_steps": 3400, "loss": 0.4374, "lr": 5.4371244313677225e-05, "epoch": 0.4365181560648983, "percentage": 49.85, "elapsed_time": "5:40:50", "remaining_time": "5:42:50", "throughput": 870.12, "total_tokens": 17793968}
+{"current_steps": 1700, "total_steps": 3400, "loss": 0.3796, "lr": 5.4128967273616625e-05, "epoch": 0.43780582024208087, "percentage": 50.0, "elapsed_time": "5:42:16", "remaining_time": "5:42:16", "throughput": 868.97, "total_tokens": 17845600}
+{"current_steps": 1700, "total_steps": 3400, "eval_loss": 0.4555380642414093, "epoch": 0.43780582024208087, "percentage": 50.0, "elapsed_time": "5:42:54", "remaining_time": "5:42:54", "throughput": 867.36, "total_tokens": 17845600}