Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9637897eed1592d2d482e3090638e19cf1f19ebaae7ca0874cfe9fa7a0f34af2
+oid sha256:810af82eabdcc28df7d1bf5eb9ac2a1f9cf690e08d76987aa6aef5043270f66e
 size 29034840

trainer_log.jsonl

@@ -42,3 +42,14 @@
 {"current_steps": 195, "total_steps": 3400, "loss": 0.7464, "lr": 9.998521935696953e-05, "epoch": 0.050218902910121044, "percentage": 5.74, "elapsed_time": "1:01:31", "remaining_time": "16:51:14", "throughput": 554.14, "total_tokens": 2045648}
 {"current_steps": 200, "total_steps": 3400, "loss": 0.7594, "lr": 9.997871633546257e-05, "epoch": 0.05150656708730363, "percentage": 5.88, "elapsed_time": "1:02:57", "remaining_time": "16:47:25", "throughput": 555.61, "total_tokens": 2099008}
 {"current_steps": 200, "total_steps": 3400, "eval_loss": 0.7274295687675476, "epoch": 0.05150656708730363, "percentage": 5.88, "elapsed_time": "1:03:35", "remaining_time": "16:57:35", "throughput": 550.06, "total_tokens": 2099008}
+{"current_steps": 205, "total_steps": 3400, "loss": 0.706, "lr": 9.997103130994296e-05, "epoch": 0.05279423126448622, "percentage": 6.03, "elapsed_time": "1:05:08", "remaining_time": "16:55:12", "throughput": 550.54, "total_tokens": 2151680}
+{"current_steps": 210, "total_steps": 3400, "loss": 0.7186, "lr": 9.996216446216267e-05, "epoch": 0.05408189544166881, "percentage": 6.18, "elapsed_time": "1:06:34", "remaining_time": "16:51:24", "throughput": 551.65, "total_tokens": 2203784}
+{"current_steps": 215, "total_steps": 3400, "loss": 0.7009, "lr": 9.995211600182397e-05, "epoch": 0.055369559618851406, "percentage": 6.32, "elapsed_time": "1:08:00", "remaining_time": "16:47:34", "throughput": 552.73, "total_tokens": 2255632}
+{"current_steps": 220, "total_steps": 3400, "loss": 0.6801, "lr": 9.994088616657444e-05, "epoch": 0.056657223796033995, "percentage": 6.47, "elapsed_time": "1:09:28", "remaining_time": "16:44:15", "throughput": 553.68, "total_tokens": 2308096}
+{"current_steps": 225, "total_steps": 3400, "loss": 0.7569, "lr": 9.992847522200133e-05, "epoch": 0.057944887973216584, "percentage": 6.62, "elapsed_time": "1:10:55", "remaining_time": "16:40:46", "throughput": 554.88, "total_tokens": 2361168}
+{"current_steps": 230, "total_steps": 3400, "loss": 0.7402, "lr": 9.99148834616253e-05, "epoch": 0.05923255215039917, "percentage": 6.76, "elapsed_time": "1:12:23", "remaining_time": "16:37:48", "throughput": 555.71, "total_tokens": 2413896}
+{"current_steps": 235, "total_steps": 3400, "loss": 0.7191, "lr": 9.990011120689351e-05, "epoch": 0.06052021632758177, "percentage": 6.91, "elapsed_time": "1:13:51", "remaining_time": "16:34:47", "throughput": 556.47, "total_tokens": 2466136}
+{"current_steps": 240, "total_steps": 3400, "loss": 0.7274, "lr": 9.988415880717194e-05, "epoch": 0.06180788050476436, "percentage": 7.06, "elapsed_time": "1:15:20", "remaining_time": "16:31:59", "throughput": 557.21, "total_tokens": 2518848}
+{"current_steps": 245, "total_steps": 3400, "loss": 0.7704, "lr": 9.986702663973722e-05, "epoch": 0.06309554468194695, "percentage": 7.21, "elapsed_time": "1:16:48", "remaining_time": "16:29:01", "throughput": 558.22, "total_tokens": 2572384}
+{"current_steps": 250, "total_steps": 3400, "loss": 0.7346, "lr": 9.98487151097676e-05, "epoch": 0.06438320885912954, "percentage": 7.35, "elapsed_time": "1:18:17", "remaining_time": "16:26:29", "throughput": 558.88, "total_tokens": 2625352}
+{"current_steps": 250, "total_steps": 3400, "eval_loss": 0.7181503176689148, "epoch": 0.06438320885912954, "percentage": 7.35, "elapsed_time": "1:18:55", "remaining_time": "16:34:29", "throughput": 554.38, "total_tokens": 2625352}