Training in progress, step 2200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2cc1f16a485d3e450e8a2a866e3d76b5149212ac068f60cacb581a8329cec2
+oid sha256:76b20ab8c2a7403c32454801b8a1cf7e477efa58783a51bc7e3abf420b274c08
 size 18516456

trainer_log.jsonl

@@ -475,3 +475,14 @@
 {"current_steps": 2145, "total_steps": 3400, "loss": 0.3848, "lr": 3.284822657536856e-05, "epoch": 1.1045583311872265, "percentage": 63.09, "elapsed_time": "7:59:11", "remaining_time": "4:40:22", "throughput": 872.37, "total_tokens": 25082248}
 {"current_steps": 2150, "total_steps": 3400, "loss": 0.3699, "lr": 3.262002716103897e-05, "epoch": 1.1071336595415915, "percentage": 63.24, "elapsed_time": "8:00:15", "remaining_time": "4:39:12", "throughput": 872.49, "total_tokens": 25140752}
 {"current_steps": 2150, "total_steps": 3400, "eval_loss": 0.8523861169815063, "epoch": 1.1071336595415915, "percentage": 63.24, "elapsed_time": "8:00:31", "remaining_time": "4:39:22", "throughput": 872.0, "total_tokens": 25140752}
+{"current_steps": 2155, "total_steps": 3400, "loss": 0.3154, "lr": 3.2392238785630386e-05, "epoch": 1.1097089878959567, "percentage": 63.38, "elapsed_time": "8:01:38", "remaining_time": "4:38:15", "throughput": 871.98, "total_tokens": 25199208}
+{"current_steps": 2160, "total_steps": 3400, "loss": 0.3915, "lr": 3.216486683637146e-05, "epoch": 1.112284316250322, "percentage": 63.53, "elapsed_time": "8:02:41", "remaining_time": "4:37:06", "throughput": 872.11, "total_tokens": 25257680}
+{"current_steps": 2165, "total_steps": 3400, "loss": 0.3675, "lr": 3.1937916690642356e-05, "epoch": 1.114859644604687, "percentage": 63.68, "elapsed_time": "8:03:44", "remaining_time": "4:35:56", "throughput": 872.23, "total_tokens": 25316200}
+{"current_steps": 2170, "total_steps": 3400, "loss": 0.4047, "lr": 3.1711393715847476e-05, "epoch": 1.1174349729590523, "percentage": 63.82, "elapsed_time": "8:04:47", "remaining_time": "4:34:47", "throughput": 872.35, "total_tokens": 25374656}
+{"current_steps": 2175, "total_steps": 3400, "loss": 0.4155, "lr": 3.14853032692886e-05, "epoch": 1.1200103013134175, "percentage": 63.97, "elapsed_time": "8:05:50", "remaining_time": "4:33:38", "throughput": 872.47, "total_tokens": 25433168}
+{"current_steps": 2180, "total_steps": 3400, "loss": 0.3966, "lr": 3.125965069803811e-05, "epoch": 1.1225856296677827, "percentage": 64.12, "elapsed_time": "8:06:53", "remaining_time": "4:32:29", "throughput": 872.59, "total_tokens": 25491664}
+{"current_steps": 2185, "total_steps": 3400, "loss": 0.3068, "lr": 3.103444133881261e-05, "epoch": 1.1251609580221478, "percentage": 64.26, "elapsed_time": "8:07:57", "remaining_time": "4:31:19", "throughput": 872.7, "total_tokens": 25550128}
+{"current_steps": 2190, "total_steps": 3400, "loss": 0.386, "lr": 3.080968051784666e-05, "epoch": 1.127736286376513, "percentage": 64.41, "elapsed_time": "8:09:00", "remaining_time": "4:30:10", "throughput": 872.82, "total_tokens": 25608624}
+{"current_steps": 2195, "total_steps": 3400, "loss": 0.3898, "lr": 3.058537355076683e-05, "epoch": 1.1303116147308783, "percentage": 64.56, "elapsed_time": "8:10:03", "remaining_time": "4:29:01", "throughput": 872.93, "total_tokens": 25667128}
+{"current_steps": 2200, "total_steps": 3400, "loss": 0.4016, "lr": 3.0361525742465973e-05, "epoch": 1.1328869430852433, "percentage": 64.71, "elapsed_time": "8:11:06", "remaining_time": "4:27:52", "throughput": 873.04, "total_tokens": 25725560}
+{"current_steps": 2200, "total_steps": 3400, "eval_loss": 0.7534744143486023, "epoch": 1.1328869430852433, "percentage": 64.71, "elapsed_time": "8:11:22", "remaining_time": "4:28:01", "throughput": 872.57, "total_tokens": 25725560}