Training in progress, step 1500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63bdf97cbdcbe4d5216e9c0ce613d425d968ff354386ba05cd27adff5ef1275e
+oid sha256:b0263e90dbe014ac70c526fa71d2fd7a1bebb2c4fe954d285088a83f154c10e0
 size 29034840

trainer_log.jsonl

@@ -321,3 +321,14 @@
 {"current_steps": 1445, "total_steps": 3400, "loss": 0.3876, "lr": 6.623497346023418e-05, "epoch": 0.37213494720576873, "percentage": 42.5, "elapsed_time": "4:23:55", "remaining_time": "5:57:05", "throughput": 957.94, "total_tokens": 15169880}
 {"current_steps": 1450, "total_steps": 3400, "loss": 0.4065, "lr": 6.60047999954972e-05, "epoch": 0.37342261138295135, "percentage": 42.65, "elapsed_time": "4:25:23", "remaining_time": "5:56:54", "throughput": 955.96, "total_tokens": 15222568}
 {"current_steps": 1450, "total_steps": 3400, "eval_loss": 0.4395444095134735, "epoch": 0.37342261138295135, "percentage": 42.65, "elapsed_time": "4:26:02", "remaining_time": "5:57:46", "throughput": 953.66, "total_tokens": 15222568}
+{"current_steps": 1455, "total_steps": 3400, "loss": 0.4231, "lr": 6.57742480148798e-05, "epoch": 0.3747102755601339, "percentage": 42.79, "elapsed_time": "4:27:34", "remaining_time": "5:57:41", "throughput": 951.44, "total_tokens": 15275288}
+{"current_steps": 1460, "total_steps": 3400, "loss": 0.4301, "lr": 6.554332297097031e-05, "epoch": 0.3759979397373165, "percentage": 42.94, "elapsed_time": "4:29:02", "remaining_time": "5:57:29", "throughput": 949.54, "total_tokens": 15328072}
+{"current_steps": 1465, "total_steps": 3400, "loss": 0.446, "lr": 6.53120303251801e-05, "epoch": 0.3772856039144991, "percentage": 43.09, "elapsed_time": "4:30:30", "remaining_time": "5:57:17", "throughput": 947.56, "total_tokens": 15379120}
+{"current_steps": 1470, "total_steps": 3400, "loss": 0.3764, "lr": 6.508037554761432e-05, "epoch": 0.3785732680916817, "percentage": 43.24, "elapsed_time": "4:31:57", "remaining_time": "5:57:04", "throughput": 945.66, "total_tokens": 15431104}
+{"current_steps": 1475, "total_steps": 3400, "loss": 0.4423, "lr": 6.484836411694267e-05, "epoch": 0.3798609322688643, "percentage": 43.38, "elapsed_time": "4:33:25", "remaining_time": "5:56:50", "throughput": 943.75, "total_tokens": 15482816}
+{"current_steps": 1480, "total_steps": 3400, "loss": 0.4439, "lr": 6.461600152026965e-05, "epoch": 0.3811485964460469, "percentage": 43.53, "elapsed_time": "4:34:52", "remaining_time": "5:56:35", "throughput": 941.94, "total_tokens": 15534896}
+{"current_steps": 1485, "total_steps": 3400, "loss": 0.4408, "lr": 6.438329325300499e-05, "epoch": 0.38243626062322944, "percentage": 43.68, "elapsed_time": "4:36:20", "remaining_time": "5:56:22", "throughput": 940.09, "total_tokens": 15587496}
+{"current_steps": 1490, "total_steps": 3400, "loss": 0.4086, "lr": 6.415024481873352e-05, "epoch": 0.38372392480041206, "percentage": 43.82, "elapsed_time": "4:37:47", "remaining_time": "5:56:05", "throughput": 938.33, "total_tokens": 15639672}
+{"current_steps": 1495, "total_steps": 3400, "loss": 0.4489, "lr": 6.391686172908506e-05, "epoch": 0.38501158897759463, "percentage": 43.97, "elapsed_time": "4:39:16", "remaining_time": "5:55:51", "throughput": 936.55, "total_tokens": 15693120}
+{"current_steps": 1500, "total_steps": 3400, "loss": 0.4338, "lr": 6.368314950360415e-05, "epoch": 0.38629925315477726, "percentage": 44.12, "elapsed_time": "4:40:42", "remaining_time": "5:55:34", "throughput": 934.81, "total_tokens": 15744848}
+{"current_steps": 1500, "total_steps": 3400, "eval_loss": 0.45475366711616516, "epoch": 0.38629925315477726, "percentage": 44.12, "elapsed_time": "4:41:21", "remaining_time": "5:56:22", "throughput": 932.68, "total_tokens": 15744848}