Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7156b16f127d3e2296e6ada4ebf9cbb8c48381f16d088d0a874a522c40e99a16
+oid sha256:55382d84797424bf555d465074d1d58ecfa91cc23250d3509fdb9cd78d1cbeff
 size 29034840

trainer_log.jsonl

@@ -97,3 +97,14 @@
 {"current_steps": 445, "total_steps": 3882, "loss": 0.901, "lr": 9.886986419356246e-05, "epoch": 0.22920422353850115, "percentage": 11.46, "elapsed_time": "2:17:43", "remaining_time": "17:43:40", "throughput": 629.89, "total_tokens": 5204800}
 {"current_steps": 450, "total_steps": 3882, "loss": 0.9062, "lr": 9.88243864560762e-05, "epoch": 0.23177955189286634, "percentage": 11.59, "elapsed_time": "2:19:17", "remaining_time": "17:42:16", "throughput": 629.8, "total_tokens": 5263304}
 {"current_steps": 450, "total_steps": 3882, "eval_loss": 0.9007609486579895, "epoch": 0.23177955189286634, "percentage": 11.59, "elapsed_time": "2:19:37", "remaining_time": "17:44:55", "throughput": 628.23, "total_tokens": 5263304}
+{"current_steps": 455, "total_steps": 3882, "loss": 0.8891, "lr": 9.877802252293474e-05, "epoch": 0.23435488024723153, "percentage": 11.72, "elapsed_time": "2:21:18", "remaining_time": "17:44:17", "throughput": 627.69, "total_tokens": 5321760}
+{"current_steps": 460, "total_steps": 3882, "loss": 0.9026, "lr": 9.873077323567488e-05, "epoch": 0.2369302086015967, "percentage": 11.85, "elapsed_time": "2:22:49", "remaining_time": "17:42:31", "throughput": 627.82, "total_tokens": 5380224}
+{"current_steps": 465, "total_steps": 3882, "loss": 0.8707, "lr": 9.868263945190312e-05, "epoch": 0.23950553695596188, "percentage": 11.98, "elapsed_time": "2:24:21", "remaining_time": "17:40:47", "throughput": 627.93, "total_tokens": 5438704}
+{"current_steps": 470, "total_steps": 3882, "loss": 0.9051, "lr": 9.863362204528024e-05, "epoch": 0.24208086531032708, "percentage": 12.11, "elapsed_time": "2:25:54", "remaining_time": "17:39:10", "throughput": 627.96, "total_tokens": 5497208}
+{"current_steps": 475, "total_steps": 3882, "loss": 0.8711, "lr": 9.858372190550533e-05, "epoch": 0.24465619366469224, "percentage": 12.24, "elapsed_time": "2:27:28", "remaining_time": "17:37:43", "throughput": 627.9, "total_tokens": 5555704}
+{"current_steps": 480, "total_steps": 3882, "loss": 0.885, "lr": 9.853293993829969e-05, "epoch": 0.24723152201905743, "percentage": 12.36, "elapsed_time": "2:29:00", "remaining_time": "17:36:05", "throughput": 627.95, "total_tokens": 5614160}
+{"current_steps": 485, "total_steps": 3882, "loss": 0.8615, "lr": 9.848127706539039e-05, "epoch": 0.24980685037342262, "percentage": 12.49, "elapsed_time": "2:30:31", "remaining_time": "17:34:16", "throughput": 628.11, "total_tokens": 5672640}
+{"current_steps": 490, "total_steps": 3882, "loss": 0.9057, "lr": 9.842873422449354e-05, "epoch": 0.2523821787277878, "percentage": 12.62, "elapsed_time": "2:32:01", "remaining_time": "17:32:21", "throughput": 628.32, "total_tokens": 5731072}
+{"current_steps": 495, "total_steps": 3882, "loss": 0.8818, "lr": 9.837531236929726e-05, "epoch": 0.254957507082153, "percentage": 12.75, "elapsed_time": "2:33:31", "remaining_time": "17:30:30", "throughput": 628.5, "total_tokens": 5789544}
+{"current_steps": 500, "total_steps": 3882, "loss": 0.8576, "lr": 9.832101246944439e-05, "epoch": 0.25753283543651817, "percentage": 12.88, "elapsed_time": "2:35:02", "remaining_time": "17:28:38", "throughput": 628.68, "total_tokens": 5848048}
+{"current_steps": 500, "total_steps": 3882, "eval_loss": 0.8268976211547852, "epoch": 0.25753283543651817, "percentage": 12.88, "elapsed_time": "2:35:21", "remaining_time": "17:30:51", "throughput": 627.36, "total_tokens": 5848048}