Training in progress, step 1600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1764f403b39c14f233fd2d6443f410cab81d66e3cc9f1d476e6e55a6642ff67
+oid sha256:af1a6642ef8e6fc99c76eecc34b9716928e3cb77cbad5191e812f07407a40f6e
 size 29034840

trainer_log.jsonl

@@ -343,3 +343,14 @@
 {"current_steps": 1545, "total_steps": 3400, "loss": 0.3965, "lr": 6.156584283609359e-05, "epoch": 0.39788823074942054, "percentage": 45.44, "elapsed_time": "4:54:43", "remaining_time": "5:53:51", "throughput": 917.09, "total_tokens": 16217192}
 {"current_steps": 1550, "total_steps": 3400, "loss": 0.3872, "lr": 6.132914447489137e-05, "epoch": 0.39917589492660316, "percentage": 45.59, "elapsed_time": "4:56:11", "remaining_time": "5:53:30", "throughput": 915.52, "total_tokens": 16269896}
 {"current_steps": 1550, "total_steps": 3400, "eval_loss": 0.4416767656803131, "epoch": 0.39917589492660316, "percentage": 45.59, "elapsed_time": "4:56:49", "remaining_time": "5:54:16", "throughput": 913.54, "total_tokens": 16269896}
+{"current_steps": 1555, "total_steps": 3400, "loss": 0.4593, "lr": 6.109217817775139e-05, "epoch": 0.4004635591037857, "percentage": 45.74, "elapsed_time": "4:58:22", "remaining_time": "5:54:01", "throughput": 911.73, "total_tokens": 16322496}
+{"current_steps": 1560, "total_steps": 3400, "loss": 0.4865, "lr": 6.085494954896156e-05, "epoch": 0.40175122328096835, "percentage": 45.88, "elapsed_time": "4:59:50", "remaining_time": "5:53:39", "throughput": 910.22, "total_tokens": 16375320}
+{"current_steps": 1565, "total_steps": 3400, "loss": 0.4422, "lr": 6.061746419901388e-05, "epoch": 0.4030388874581509, "percentage": 46.03, "elapsed_time": "5:01:17", "remaining_time": "5:53:16", "throughput": 908.76, "total_tokens": 16428096}
+{"current_steps": 1570, "total_steps": 3400, "loss": 0.3538, "lr": 6.0379727744471936e-05, "epoch": 0.4043265516353335, "percentage": 46.18, "elapsed_time": "5:02:45", "remaining_time": "5:52:53", "throughput": 907.26, "total_tokens": 16480832}
+{"current_steps": 1575, "total_steps": 3400, "loss": 0.3923, "lr": 6.014174580783794e-05, "epoch": 0.4056142158125161, "percentage": 46.32, "elapsed_time": "5:04:12", "remaining_time": "5:52:29", "throughput": 905.86, "total_tokens": 16534016}
+{"current_steps": 1580, "total_steps": 3400, "loss": 0.3967, "lr": 5.990352401741981e-05, "epoch": 0.4069018799896987, "percentage": 46.47, "elapsed_time": "5:05:40", "remaining_time": "5:52:06", "throughput": 904.34, "total_tokens": 16586216}
+{"current_steps": 1585, "total_steps": 3400, "loss": 0.4212, "lr": 5.9665068007197976e-05, "epoch": 0.4081895441668813, "percentage": 46.62, "elapsed_time": "5:07:07", "remaining_time": "5:51:41", "throughput": 902.97, "total_tokens": 16639312}
+{"current_steps": 1590, "total_steps": 3400, "loss": 0.3489, "lr": 5.94263834166923e-05, "epoch": 0.40947720834406387, "percentage": 46.76, "elapsed_time": "5:08:35", "remaining_time": "5:51:17", "throughput": 901.53, "total_tokens": 16692328}
+{"current_steps": 1595, "total_steps": 3400, "loss": 0.4105, "lr": 5.918747589082853e-05, "epoch": 0.41076487252124644, "percentage": 46.91, "elapsed_time": "5:10:02", "remaining_time": "5:50:51", "throughput": 900.15, "total_tokens": 16745088}
+{"current_steps": 1600, "total_steps": 3400, "loss": 0.3914, "lr": 5.8948351079804875e-05, "epoch": 0.41205253669842906, "percentage": 47.06, "elapsed_time": "5:11:30", "remaining_time": "5:50:26", "throughput": 898.78, "total_tokens": 16798768}
+{"current_steps": 1600, "total_steps": 3400, "eval_loss": 0.4657597243785858, "epoch": 0.41205253669842906, "percentage": 47.06, "elapsed_time": "5:12:08", "remaining_time": "5:51:10", "throughput": 896.94, "total_tokens": 16798768}