Training in progress, step 1350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b791d45f5e8c5ec48a79f58002a2b81c7d9dc83eccb3702983e59a8069f0f5
+oid sha256:10b824529fcf1b1cc25b9074d2e972d61eae3cfa9d99a178c08c460258fd9cfb
 size 18516456

trainer_log.jsonl

@@ -288,3 +288,14 @@
 {"current_steps": 1295, "total_steps": 3400, "loss": 0.7443, "lr": 7.293751929833553e-05, "epoch": 0.667010043780582, "percentage": 38.09, "elapsed_time": "4:53:41", "remaining_time": "7:57:23", "throughput": 859.54, "total_tokens": 15146600}
 {"current_steps": 1300, "total_steps": 3400, "loss": 0.7724, "lr": 7.272118777828108e-05, "epoch": 0.6695853721349472, "percentage": 38.24, "elapsed_time": "4:54:44", "remaining_time": "7:56:07", "throughput": 859.78, "total_tokens": 15205064}
 {"current_steps": 1300, "total_steps": 3400, "eval_loss": 0.7189856171607971, "epoch": 0.6695853721349472, "percentage": 38.24, "elapsed_time": "4:55:00", "remaining_time": "7:56:33", "throughput": 859.0, "total_tokens": 15205064}
+{"current_steps": 1305, "total_steps": 3400, "loss": 0.7524, "lr": 7.250431889878455e-05, "epoch": 0.6721607004893124, "percentage": 38.38, "elapsed_time": "4:56:08", "remaining_time": "7:55:25", "throughput": 859.0, "total_tokens": 15263560}
+{"current_steps": 1310, "total_steps": 3400, "loss": 0.6748, "lr": 7.228691778882693e-05, "epoch": 0.6747360288436776, "percentage": 38.53, "elapsed_time": "4:57:11", "remaining_time": "7:54:09", "throughput": 859.25, "total_tokens": 15322016}
+{"current_steps": 1315, "total_steps": 3400, "loss": 0.7571, "lr": 7.20689895899765e-05, "epoch": 0.6773113571980427, "percentage": 38.68, "elapsed_time": "4:58:15", "remaining_time": "7:52:53", "throughput": 859.48, "total_tokens": 15380504}
+{"current_steps": 1320, "total_steps": 3400, "loss": 0.6615, "lr": 7.185053945626733e-05, "epoch": 0.6798866855524079, "percentage": 38.82, "elapsed_time": "4:59:18", "remaining_time": "7:51:37", "throughput": 859.72, "total_tokens": 15438944}
+{"current_steps": 1325, "total_steps": 3400, "loss": 0.7421, "lr": 7.163157255407732e-05, "epoch": 0.6824620139067731, "percentage": 38.97, "elapsed_time": "5:00:21", "remaining_time": "7:50:21", "throughput": 859.95, "total_tokens": 15497384}
+{"current_steps": 1330, "total_steps": 3400, "loss": 0.7886, "lr": 7.141209406200599e-05, "epoch": 0.6850373422611383, "percentage": 39.12, "elapsed_time": "5:01:24", "remaining_time": "7:49:06", "throughput": 860.19, "total_tokens": 15555856}
+{"current_steps": 1335, "total_steps": 3400, "loss": 0.7484, "lr": 7.1192109170752e-05, "epoch": 0.6876126706155035, "percentage": 39.26, "elapsed_time": "5:02:27", "remaining_time": "7:47:50", "throughput": 860.42, "total_tokens": 15614368}
+{"current_steps": 1340, "total_steps": 3400, "loss": 0.7086, "lr": 7.097162308299054e-05, "epoch": 0.6901879989698687, "percentage": 39.41, "elapsed_time": "5:03:30", "remaining_time": "7:46:34", "throughput": 860.66, "total_tokens": 15672864}
+{"current_steps": 1345, "total_steps": 3400, "loss": 0.7494, "lr": 7.07506410132501e-05, "epoch": 0.6927633273242338, "percentage": 39.56, "elapsed_time": "5:04:33", "remaining_time": "7:45:19", "throughput": 860.89, "total_tokens": 15731376}
+{"current_steps": 1350, "total_steps": 3400, "loss": 0.7278, "lr": 7.052916818778918e-05, "epoch": 0.695338655678599, "percentage": 39.71, "elapsed_time": "5:05:36", "remaining_time": "7:44:04", "throughput": 861.12, "total_tokens": 15789848}
+{"current_steps": 1350, "total_steps": 3400, "eval_loss": 0.712917685508728, "epoch": 0.695338655678599, "percentage": 39.71, "elapsed_time": "5:05:52", "remaining_time": "7:44:28", "throughput": 860.37, "total_tokens": 15789848}