Training in progress, step 2450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2874dfb474adef2e86193b1ab18660860287a5e9abf08e0b2d06a88e2eefcb7a
+oid sha256:76ea3377531bb34d473bfe1ac7fb7435074a39aec464fce193b5f47faf92de11
 size 29034840

trainer_log.jsonl

@@ -530,3 +530,14 @@
 {"current_steps": 2395, "total_steps": 3400, "loss": 0.3482, "lr": 2.2044834691045873e-05, "epoch": 0.6167911408704609, "percentage": 70.44, "elapsed_time": "9:15:12", "remaining_time": "3:52:58", "throughput": 755.08, "total_tokens": 25153912}
 {"current_steps": 2400, "total_steps": 3400, "loss": 0.3445, "lr": 2.184356480489432e-05, "epoch": 0.6180788050476436, "percentage": 70.59, "elapsed_time": "9:16:40", "remaining_time": "3:51:56", "throughput": 754.67, "total_tokens": 25206168}
 {"current_steps": 2400, "total_steps": 3400, "eval_loss": 0.42807063460350037, "epoch": 0.6180788050476436, "percentage": 70.59, "elapsed_time": "9:17:18", "remaining_time": "3:52:12", "throughput": 753.81, "total_tokens": 25206168}
+{"current_steps": 2405, "total_steps": 3400, "loss": 0.3147, "lr": 2.1642960822587878e-05, "epoch": 0.6193664692248262, "percentage": 70.74, "elapsed_time": "9:18:51", "remaining_time": "3:51:12", "throughput": 753.28, "total_tokens": 25258880}
+{"current_steps": 2410, "total_steps": 3400, "loss": 0.3467, "lr": 2.1443027488440338e-05, "epoch": 0.6206541334020087, "percentage": 70.88, "elapsed_time": "9:20:19", "remaining_time": "3:50:10", "throughput": 752.87, "total_tokens": 25310976}
+{"current_steps": 2415, "total_steps": 3400, "loss": 0.3085, "lr": 2.124376953090456e-05, "epoch": 0.6219417975791913, "percentage": 71.03, "elapsed_time": "9:21:47", "remaining_time": "3:49:08", "throughput": 752.46, "total_tokens": 25363520}
+{"current_steps": 2420, "total_steps": 3400, "loss": 0.3376, "lr": 2.104519166246059e-05, "epoch": 0.623229461756374, "percentage": 71.18, "elapsed_time": "9:23:14", "remaining_time": "3:48:05", "throughput": 752.05, "total_tokens": 25415400}
+{"current_steps": 2425, "total_steps": 3400, "loss": 0.3312, "lr": 2.0847298579504344e-05, "epoch": 0.6245171259335566, "percentage": 71.32, "elapsed_time": "9:24:43", "remaining_time": "3:47:03", "throughput": 751.65, "total_tokens": 25468296}
+{"current_steps": 2430, "total_steps": 3400, "loss": 0.3282, "lr": 2.065009496223638e-05, "epoch": 0.6258047901107391, "percentage": 71.47, "elapsed_time": "9:26:10", "remaining_time": "3:46:00", "throughput": 751.27, "total_tokens": 25520816}
+{"current_steps": 2435, "total_steps": 3400, "loss": 0.321, "lr": 2.045358547455138e-05, "epoch": 0.6270924542879217, "percentage": 71.62, "elapsed_time": "9:27:38", "remaining_time": "3:44:57", "throughput": 750.87, "total_tokens": 25573416}
+{"current_steps": 2440, "total_steps": 3400, "loss": 0.33, "lr": 2.0257774763927655e-05, "epoch": 0.6283801184651043, "percentage": 71.76, "elapsed_time": "9:29:06", "remaining_time": "3:43:54", "throughput": 750.5, "total_tokens": 25626536}
+{"current_steps": 2445, "total_steps": 3400, "loss": 0.2833, "lr": 2.0062667461317426e-05, "epoch": 0.6296677826422868, "percentage": 71.91, "elapsed_time": "9:30:34", "remaining_time": "3:42:51", "throughput": 750.1, "total_tokens": 25679208}
+{"current_steps": 2450, "total_steps": 3400, "loss": 0.3413, "lr": 1.9868268181037185e-05, "epoch": 0.6309554468194695, "percentage": 72.06, "elapsed_time": "9:32:01", "remaining_time": "3:41:48", "throughput": 749.68, "total_tokens": 25730432}
+{"current_steps": 2450, "total_steps": 3400, "eval_loss": 0.46914541721343994, "epoch": 0.6309554468194695, "percentage": 72.06, "elapsed_time": "9:32:40", "remaining_time": "3:42:03", "throughput": 748.85, "total_tokens": 25730432}