Training in progress, step 2550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51ba4cb036f96637ea50997962c817be8981b7c185736e25bcaea373e2187935
+oid sha256:1423743ef577d043d7175f7e7d833ad5439113f93d35aae3b6833a3cf0e1cb32
 size 29034840

trainer_log.jsonl

@@ -560,3 +560,14 @@
 {"current_steps": 2495, "total_steps": 6770, "loss": 0.2456, "lr": 7.473866081494896e-05, "epoch": 0.7370753323485968, "percentage": 36.85, "elapsed_time": "4:13:49", "remaining_time": "7:14:53", "throughput": 1701.25, "total_tokens": 25908544}
 {"current_steps": 2500, "total_steps": 6770, "loss": 0.2382, "lr": 7.463245613687695e-05, "epoch": 0.7385524372230429, "percentage": 36.93, "elapsed_time": "4:15:15", "remaining_time": "7:15:59", "throughput": 1695.04, "total_tokens": 25961056}
 {"current_steps": 2500, "total_steps": 6770, "eval_loss": 0.2542795240879059, "epoch": 0.7385524372230429, "percentage": 36.93, "elapsed_time": "4:15:35", "remaining_time": "7:16:32", "throughput": 1692.92, "total_tokens": 25961056}
+{"current_steps": 2505, "total_steps": 6770, "loss": 0.2843, "lr": 7.452610450181865e-05, "epoch": 0.740029542097489, "percentage": 37.0, "elapsed_time": "4:17:07", "remaining_time": "7:17:45", "throughput": 1686.15, "total_tokens": 26012232}
+{"current_steps": 2510, "total_steps": 6770, "loss": 0.2376, "lr": 7.441960654426687e-05, "epoch": 0.741506646971935, "percentage": 37.08, "elapsed_time": "4:18:33", "remaining_time": "7:18:49", "throughput": 1680.12, "total_tokens": 26064432}
+{"current_steps": 2515, "total_steps": 6770, "loss": 0.2464, "lr": 7.431296289958735e-05, "epoch": 0.7429837518463811, "percentage": 37.15, "elapsed_time": "4:20:00", "remaining_time": "7:19:54", "throughput": 1674.0, "total_tokens": 26115856}
+{"current_steps": 2520, "total_steps": 6770, "loss": 0.2793, "lr": 7.4206174204015e-05, "epoch": 0.7444608567208272, "percentage": 37.22, "elapsed_time": "4:21:27", "remaining_time": "7:20:56", "throughput": 1668.04, "total_tokens": 26167176}
+{"current_steps": 2525, "total_steps": 6770, "loss": 0.2141, "lr": 7.409924109465011e-05, "epoch": 0.7459379615952733, "percentage": 37.3, "elapsed_time": "4:22:53", "remaining_time": "7:21:58", "throughput": 1662.21, "total_tokens": 26219144}
+{"current_steps": 2530, "total_steps": 6770, "loss": 0.2137, "lr": 7.399216420945453e-05, "epoch": 0.7474150664697193, "percentage": 37.37, "elapsed_time": "4:24:19", "remaining_time": "7:22:58", "throughput": 1656.57, "total_tokens": 26271712}
+{"current_steps": 2535, "total_steps": 6770, "loss": 0.2177, "lr": 7.388494418724789e-05, "epoch": 0.7488921713441654, "percentage": 37.44, "elapsed_time": "4:25:44", "remaining_time": "7:23:57", "throughput": 1650.91, "total_tokens": 26323656}
+{"current_steps": 2540, "total_steps": 6770, "loss": 0.2762, "lr": 7.377758166770377e-05, "epoch": 0.7503692762186115, "percentage": 37.52, "elapsed_time": "4:27:09", "remaining_time": "7:24:55", "throughput": 1645.38, "total_tokens": 26375392}
+{"current_steps": 2545, "total_steps": 6770, "loss": 0.2794, "lr": 7.367007729134588e-05, "epoch": 0.7518463810930576, "percentage": 37.59, "elapsed_time": "4:28:37", "remaining_time": "7:25:56", "throughput": 1639.64, "total_tokens": 26426080}
+{"current_steps": 2550, "total_steps": 6770, "loss": 0.2364, "lr": 7.356243169954426e-05, "epoch": 0.7533234859675036, "percentage": 37.67, "elapsed_time": "4:30:02", "remaining_time": "7:26:53", "throughput": 1634.17, "total_tokens": 26477208}
+{"current_steps": 2550, "total_steps": 6770, "eval_loss": 0.38712552189826965, "epoch": 0.7533234859675036, "percentage": 37.67, "elapsed_time": "4:30:21", "remaining_time": "7:27:24", "throughput": 1632.25, "total_tokens": 26477208}