Training in progress, step 2950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2acd206b2dadd260ab38262d5014a0182f253ac5bb1be9e70b1fc1dcf9a565
+oid sha256:728e00b9bd6d98b9b5a2353e9d15e1290fa4bfd90b752c01f9851f89b2b4a800
 size 29034840

trainer_log.jsonl

@@ -639,3 +639,14 @@
 {"current_steps": 2895, "total_steps": 3400, "loss": 0.3252, "lr": 5.911102792477357e-06, "epoch": 0.7455575585887201, "percentage": 85.15, "elapsed_time": "1:45:40", "remaining_time": "0:18:26", "throughput": 4794.9, "total_tokens": 30402248}
 {"current_steps": 2900, "total_steps": 3400, "loss": 0.3167, "lr": 5.796935854200763e-06, "epoch": 0.7468452227659027, "percentage": 85.29, "elapsed_time": "1:47:05", "remaining_time": "0:18:27", "throughput": 4739.89, "total_tokens": 30455480}
 {"current_steps": 2900, "total_steps": 3400, "eval_loss": 0.46323254704475403, "epoch": 0.7468452227659027, "percentage": 85.29, "elapsed_time": "1:47:43", "remaining_time": "0:18:34", "throughput": 4711.68, "total_tokens": 30455480}
+{"current_steps": 2905, "total_steps": 3400, "loss": 0.3063, "lr": 5.683814324910685e-06, "epoch": 0.7481328869430852, "percentage": 85.44, "elapsed_time": "1:49:16", "remaining_time": "0:18:37", "throughput": 4652.91, "total_tokens": 30507096}
+{"current_steps": 2910, "total_steps": 3400, "loss": 0.2694, "lr": 5.571740879947979e-06, "epoch": 0.7494205511202678, "percentage": 85.59, "elapsed_time": "1:50:42", "remaining_time": "0:18:38", "throughput": 4600.55, "total_tokens": 30558760}
+{"current_steps": 2915, "total_steps": 3400, "loss": 0.2578, "lr": 5.4607181698661634e-06, "epoch": 0.7507082152974505, "percentage": 85.74, "elapsed_time": "1:52:09", "remaining_time": "0:18:39", "throughput": 4549.02, "total_tokens": 30612024}
+{"current_steps": 2920, "total_steps": 3400, "loss": 0.3526, "lr": 5.35074882036869e-06, "epoch": 0.751995879474633, "percentage": 85.88, "elapsed_time": "1:53:35", "remaining_time": "0:18:40", "throughput": 4499.42, "total_tokens": 30665272}
+{"current_steps": 2925, "total_steps": 3400, "loss": 0.2965, "lr": 5.241835432246889e-06, "epoch": 0.7532835436518156, "percentage": 86.03, "elapsed_time": "1:55:02", "remaining_time": "0:18:40", "throughput": 4450.28, "total_tokens": 30717104}
+{"current_steps": 2930, "total_steps": 3400, "loss": 0.3122, "lr": 5.133980581318459e-06, "epoch": 0.7545712078289982, "percentage": 86.18, "elapsed_time": "1:56:28", "remaining_time": "0:18:41", "throughput": 4402.63, "total_tokens": 30769656}
+{"current_steps": 2935, "total_steps": 3400, "loss": 0.2968, "lr": 5.027186818366542e-06, "epoch": 0.7558588720061807, "percentage": 86.32, "elapsed_time": "1:57:55", "remaining_time": "0:18:41", "throughput": 4356.08, "total_tokens": 30822016}
+{"current_steps": 2940, "total_steps": 3400, "loss": 0.3536, "lr": 4.921456669079366e-06, "epoch": 0.7571465361833634, "percentage": 86.47, "elapsed_time": "1:59:22", "remaining_time": "0:18:40", "throughput": 4310.46, "total_tokens": 30873336}
+{"current_steps": 2945, "total_steps": 3400, "loss": 0.2721, "lr": 4.816792633990569e-06, "epoch": 0.758434200360546, "percentage": 86.62, "elapsed_time": "2:00:48", "remaining_time": "0:18:39", "throughput": 4266.31, "total_tokens": 30926104}
+{"current_steps": 2950, "total_steps": 3400, "loss": 0.2899, "lr": 4.713197188420026e-06, "epoch": 0.7597218645377286, "percentage": 86.76, "elapsed_time": "2:02:15", "remaining_time": "0:18:39", "throughput": 4222.93, "total_tokens": 30979312}
+{"current_steps": 2950, "total_steps": 3400, "eval_loss": 0.4720001518726349, "epoch": 0.7597218645377286, "percentage": 86.76, "elapsed_time": "2:02:54", "remaining_time": "0:18:44", "throughput": 4200.85, "total_tokens": 30979312}