Training in progress, step 143

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c94e5f35bfe3e146d0823b10bb721b0dd0bdc5aeddc5b4f6d9309fd21c7d91d
+oid sha256:024543e6a3320fa2965e7dbc1e152a1d144bdf5f42099dba3322f8a53c8a5fa5
 size 335717200

trainer_log.jsonl

@@ -36,3 +36,10 @@
 {"current_steps": 130, "total_steps": 249, "eval_loss": 0.35231098532676697, "epoch": 0.5220883534136547, "percentage": 52.21, "elapsed_time": "0:00:39", "remaining_time": "0:00:36", "throughput": 578.36, "total_tokens": 23056}
 {"current_steps": 135, "total_steps": 249, "loss": 0.3499, "lr": 2.6051562213206632e-05, "epoch": 0.5421686746987951, "percentage": 54.22, "elapsed_time": "0:00:41", "remaining_time": "0:00:35", "throughput": 571.58, "total_tokens": 23840}
 {"current_steps": 140, "total_steps": 249, "loss": 0.3637, "lr": 2.429884359310328e-05, "epoch": 0.5622489959839357, "percentage": 56.22, "elapsed_time": "0:00:42", "remaining_time": "0:00:32", "throughput": 590.67, "total_tokens": 24832}
+{"current_steps": 143, "total_steps": 249, "eval_loss": 0.3550644516944885, "epoch": 0.5742971887550201, "percentage": 57.43, "elapsed_time": "0:00:42", "remaining_time": "0:00:31", "throughput": 591.19, "total_tokens": 25312}
+{"current_steps": 145, "total_steps": 249, "loss": 0.3785, "lr": 2.2549571491760986e-05, "epoch": 0.5823293172690763, "percentage": 58.23, "elapsed_time": "0:00:45", "remaining_time": "0:00:32", "throughput": 560.26, "total_tokens": 25648}
+{"current_steps": 150, "total_steps": 249, "loss": 0.3394, "lr": 2.0812344417381595e-05, "epoch": 0.6024096385542169, "percentage": 60.24, "elapsed_time": "0:00:46", "remaining_time": "0:00:30", "throughput": 574.55, "total_tokens": 26496}
+{"current_steps": 155, "total_steps": 249, "loss": 0.3938, "lr": 1.909570167110415e-05, "epoch": 0.6224899598393574, "percentage": 62.25, "elapsed_time": "0:00:46", "remaining_time": "0:00:28", "throughput": 589.65, "total_tokens": 27392}
+{"current_steps": 156, "total_steps": 249, "eval_loss": 0.3516700565814972, "epoch": 0.6265060240963856, "percentage": 62.65, "elapsed_time": "0:00:47", "remaining_time": "0:00:28", "throughput": 584.93, "total_tokens": 27552}
+{"current_steps": 160, "total_steps": 249, "loss": 0.3667, "lr": 1.7408081372259632e-05, "epoch": 0.642570281124498, "percentage": 64.26, "elapsed_time": "0:00:48", "remaining_time": "0:00:27", "throughput": 580.26, "total_tokens": 28272}
+{"current_steps": 165, "total_steps": 249, "loss": 0.3198, "lr": 1.5757778980982626e-05, "epoch": 0.6626506024096386, "percentage": 66.27, "elapsed_time": "0:00:49", "remaining_time": "0:00:24", "throughput": 594.93, "total_tokens": 29184}