Training in progress, step 1500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c22365f9f1922257bce2b624ba131f902a872d3af6a64b3fc1e949516f00f5ac
+oid sha256:fec5ddc66104a1242bea32d5992b492dff2bd120a511b7c3d1f150e9883748d1
 size 18516456

trainer_log.jsonl

@@ -321,3 +321,14 @@
 {"current_steps": 1445, "total_steps": 3400, "loss": 0.743, "lr": 6.623497346023418e-05, "epoch": 0.7442698944115375, "percentage": 42.5, "elapsed_time": "5:26:20", "remaining_time": "7:21:31", "throughput": 863.15, "total_tokens": 16901176}
 {"current_steps": 1450, "total_steps": 3400, "loss": 0.6291, "lr": 6.60047999954972e-05, "epoch": 0.7468452227659027, "percentage": 42.65, "elapsed_time": "5:27:23", "remaining_time": "7:20:17", "throughput": 863.37, "total_tokens": 16959632}
 {"current_steps": 1450, "total_steps": 3400, "eval_loss": 0.753077507019043, "epoch": 0.7468452227659027, "percentage": 42.65, "elapsed_time": "5:27:39", "remaining_time": "7:20:38", "throughput": 862.66, "total_tokens": 16959632}
+{"current_steps": 1455, "total_steps": 3400, "loss": 0.6533, "lr": 6.57742480148798e-05, "epoch": 0.7494205511202678, "percentage": 42.79, "elapsed_time": "5:28:47", "remaining_time": "7:19:30", "throughput": 862.67, "total_tokens": 17018072}
+{"current_steps": 1460, "total_steps": 3400, "loss": 0.7114, "lr": 6.554332297097031e-05, "epoch": 0.751995879474633, "percentage": 42.94, "elapsed_time": "5:29:50", "remaining_time": "7:18:16", "throughput": 862.87, "total_tokens": 17076560}
+{"current_steps": 1465, "total_steps": 3400, "loss": 0.6568, "lr": 6.53120303251801e-05, "epoch": 0.7545712078289982, "percentage": 43.09, "elapsed_time": "5:30:53", "remaining_time": "7:17:02", "throughput": 863.07, "total_tokens": 17135016}
+{"current_steps": 1470, "total_steps": 3400, "loss": 0.7016, "lr": 6.508037554761432e-05, "epoch": 0.7571465361833634, "percentage": 43.24, "elapsed_time": "5:31:56", "remaining_time": "7:15:49", "throughput": 863.26, "total_tokens": 17193496}
+{"current_steps": 1475, "total_steps": 3400, "loss": 0.6612, "lr": 6.484836411694267e-05, "epoch": 0.7597218645377286, "percentage": 43.38, "elapsed_time": "5:32:59", "remaining_time": "7:14:35", "throughput": 863.46, "total_tokens": 17251944}
+{"current_steps": 1480, "total_steps": 3400, "loss": 0.6115, "lr": 6.461600152026965e-05, "epoch": 0.7622971928920937, "percentage": 43.53, "elapsed_time": "5:34:03", "remaining_time": "7:13:22", "throughput": 863.65, "total_tokens": 17310456}
+{"current_steps": 1485, "total_steps": 3400, "loss": 0.6458, "lr": 6.438329325300499e-05, "epoch": 0.7648725212464589, "percentage": 43.68, "elapsed_time": "5:35:06", "remaining_time": "7:12:08", "throughput": 863.85, "total_tokens": 17368968}
+{"current_steps": 1490, "total_steps": 3400, "loss": 0.6434, "lr": 6.415024481873352e-05, "epoch": 0.7674478496008241, "percentage": 43.82, "elapsed_time": "5:36:09", "remaining_time": "7:10:55", "throughput": 864.04, "total_tokens": 17427424}
+{"current_steps": 1495, "total_steps": 3400, "loss": 0.5973, "lr": 6.391686172908506e-05, "epoch": 0.7700231779551893, "percentage": 43.97, "elapsed_time": "5:37:12", "remaining_time": "7:09:41", "throughput": 864.25, "total_tokens": 17485936}
+{"current_steps": 1500, "total_steps": 3400, "loss": 0.6021, "lr": 6.368314950360415e-05, "epoch": 0.7725985063095545, "percentage": 44.12, "elapsed_time": "5:38:15", "remaining_time": "7:08:27", "throughput": 864.44, "total_tokens": 17544440}
+{"current_steps": 1500, "total_steps": 3400, "eval_loss": 0.632923424243927, "epoch": 0.7725985063095545, "percentage": 44.12, "elapsed_time": "5:38:31", "remaining_time": "7:08:48", "throughput": 863.76, "total_tokens": 17544440}