Training in progress, step 2900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a330ed632b021642148062b09d22bb079b73a39c22d87b4a866893ac04d712
+oid sha256:1e2acd206b2dadd260ab38262d5014a0182f253ac5bb1be9e70b1fc1dcf9a565
 size 29034840

trainer_log.jsonl

@@ -628,3 +628,14 @@
 {"current_steps": 2845, "total_steps": 3400, "loss": 0.2709, "lr": 7.109663499981834e-06, "epoch": 0.7326809168168942, "percentage": 83.68, "elapsed_time": "1:30:40", "remaining_time": "0:17:41", "throughput": 5490.9, "total_tokens": 29875104}
 {"current_steps": 2850, "total_steps": 3400, "loss": 0.3024, "lr": 6.985195022814067e-06, "epoch": 0.7339685809940767, "percentage": 83.82, "elapsed_time": "1:32:05", "remaining_time": "0:17:46", "throughput": 5415.97, "total_tokens": 29928032}
 {"current_steps": 2850, "total_steps": 3400, "eval_loss": 0.47043517231941223, "epoch": 0.7339685809940767, "percentage": 83.82, "elapsed_time": "1:32:43", "remaining_time": "0:17:53", "throughput": 5379.51, "total_tokens": 29928032}
+{"current_steps": 2855, "total_steps": 3400, "loss": 0.3425, "lr": 6.861743852128233e-06, "epoch": 0.7352562451712593, "percentage": 83.97, "elapsed_time": "1:34:14", "remaining_time": "0:17:59", "throughput": 5301.85, "total_tokens": 29980608}
+{"current_steps": 2860, "total_steps": 3400, "loss": 0.3095, "lr": 6.7393129075627335e-06, "epoch": 0.7365439093484419, "percentage": 84.12, "elapsed_time": "1:35:40", "remaining_time": "0:18:03", "throughput": 5232.21, "total_tokens": 30033680}
+{"current_steps": 2865, "total_steps": 3400, "loss": 0.2894, "lr": 6.6179050846274515e-06, "epoch": 0.7378315735256246, "percentage": 84.26, "elapsed_time": "1:37:06", "remaining_time": "0:18:07", "throughput": 5163.75, "total_tokens": 30086016}
+{"current_steps": 2870, "total_steps": 3400, "loss": 0.3044, "lr": 6.497523254635296e-06, "epoch": 0.7391192377028071, "percentage": 84.41, "elapsed_time": "1:38:31", "remaining_time": "0:18:11", "throughput": 5098.52, "total_tokens": 30139216}
+{"current_steps": 2875, "total_steps": 3400, "loss": 0.3116, "lr": 6.37817026463432e-06, "epoch": 0.7404069018799897, "percentage": 84.56, "elapsed_time": "1:39:58", "remaining_time": "0:18:15", "throughput": 5033.54, "total_tokens": 30191240}
+{"current_steps": 2880, "total_steps": 3400, "loss": 0.3229, "lr": 6.25984893734034e-06, "epoch": 0.7416945660571723, "percentage": 84.71, "elapsed_time": "1:41:22", "remaining_time": "0:18:18", "throughput": 4972.02, "total_tokens": 30243680}
+{"current_steps": 2885, "total_steps": 3400, "loss": 0.2495, "lr": 6.142562071070179e-06, "epoch": 0.7429822302343548, "percentage": 84.85, "elapsed_time": "1:42:49", "remaining_time": "0:18:21", "throughput": 4911.03, "total_tokens": 30296376}
+{"current_steps": 2890, "total_steps": 3400, "loss": 0.3083, "lr": 6.026312439675552e-06, "epoch": 0.7442698944115375, "percentage": 85.0, "elapsed_time": "1:44:14", "remaining_time": "0:18:23", "throughput": 4852.82, "total_tokens": 30349864}
+{"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}