Training in progress, step 2700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:827ad766e3a13984fdb182a9e1ff3663479a4a48e1ebea8bd0fa17625232d440
+oid sha256:87c5131642e0134183eead6ee8a652dcec18d08a73880b46e923d3ba034a1f2c
 size 18516456

trainer_log.jsonl

@@ -585,3 +585,14 @@
 {"current_steps": 2645, "total_steps": 3400, "loss": 0.3272, "lr": 1.2886177695085078e-05, "epoch": 1.3620911666237445, "percentage": 77.79, "elapsed_time": "9:48:12", "remaining_time": "2:47:54", "throughput": 876.38, "total_tokens": 30929824}
 {"current_steps": 2650, "total_steps": 3400, "loss": 0.2962, "lr": 1.2723678998574512e-05, "epoch": 1.3646664949781098, "percentage": 77.94, "elapsed_time": "9:49:16", "remaining_time": "2:46:46", "throughput": 876.46, "total_tokens": 30988344}
 {"current_steps": 2650, "total_steps": 3400, "eval_loss": 0.7657458186149597, "epoch": 1.3646664949781098, "percentage": 77.94, "elapsed_time": "9:49:32", "remaining_time": "2:46:51", "throughput": 876.06, "total_tokens": 30988344}
+{"current_steps": 2655, "total_steps": 3400, "loss": 0.3207, "lr": 1.2562061892553473e-05, "epoch": 1.367241823332475, "percentage": 78.09, "elapsed_time": "9:50:40", "remaining_time": "2:45:44", "throughput": 876.02, "total_tokens": 31046848}
+{"current_steps": 2660, "total_steps": 3400, "loss": 0.3001, "lr": 1.2401330199290367e-05, "epoch": 1.36981715168684, "percentage": 78.24, "elapsed_time": "9:51:44", "remaining_time": "2:44:37", "throughput": 876.11, "total_tokens": 31105352}
+{"current_steps": 2665, "total_steps": 3400, "loss": 0.2858, "lr": 1.224148772011346e-05, "epoch": 1.3723924800412053, "percentage": 78.38, "elapsed_time": "9:52:48", "remaining_time": "2:43:29", "throughput": 876.18, "total_tokens": 31163848}
+{"current_steps": 2670, "total_steps": 3400, "loss": 0.2338, "lr": 1.2082538235320929e-05, "epoch": 1.3749678083955703, "percentage": 78.53, "elapsed_time": "9:53:51", "remaining_time": "2:42:22", "throughput": 876.25, "total_tokens": 31222360}
+{"current_steps": 2675, "total_steps": 3400, "loss": 0.2212, "lr": 1.1924485504091565e-05, "epoch": 1.3775431367499356, "percentage": 78.68, "elapsed_time": "9:54:55", "remaining_time": "2:41:14", "throughput": 876.32, "total_tokens": 31280840}
+{"current_steps": 2680, "total_steps": 3400, "loss": 0.3131, "lr": 1.1767333264395736e-05, "epoch": 1.3801184651043008, "percentage": 78.82, "elapsed_time": "9:56:00", "remaining_time": "2:40:07", "throughput": 876.37, "total_tokens": 31339264}
+{"current_steps": 2685, "total_steps": 3400, "loss": 0.3616, "lr": 1.1611085232907132e-05, "epoch": 1.382693793458666, "percentage": 78.97, "elapsed_time": "9:57:04", "remaining_time": "2:38:59", "throughput": 876.42, "total_tokens": 31397744}
+{"current_steps": 2690, "total_steps": 3400, "loss": 0.3153, "lr": 1.14557451049147e-05, "epoch": 1.385269121813031, "percentage": 79.12, "elapsed_time": "9:58:09", "remaining_time": "2:37:52", "throughput": 876.48, "total_tokens": 31456240}
+{"current_steps": 2695, "total_steps": 3400, "loss": 0.3044, "lr": 1.1301316554235397e-05, "epoch": 1.3878444501673963, "percentage": 79.26, "elapsed_time": "9:59:13", "remaining_time": "2:36:45", "throughput": 876.53, "total_tokens": 31514744}
+{"current_steps": 2700, "total_steps": 3400, "loss": 0.3163, "lr": 1.114780323312724e-05, "epoch": 1.3904197785217616, "percentage": 79.41, "elapsed_time": "10:00:18", "remaining_time": "2:35:38", "throughput": 876.58, "total_tokens": 31573240}
+{"current_steps": 2700, "total_steps": 3400, "eval_loss": 0.7473158240318298, "epoch": 1.3904197785217616, "percentage": 79.41, "elapsed_time": "10:00:34", "remaining_time": "2:35:42", "throughput": 876.19, "total_tokens": 31573240}