Training in progress, step 2000

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad3594bcb3ff35f3f2e878e13876be354135b355ddc08a0bafcc51fa9e238692
+oid sha256:ef369bc6f133f918883659e41b1f1d54da5fade97c7980c94f475d0370c1ee7c
 size 29034840

trainer_log.jsonl

@@ -431,3 +431,14 @@
 {"current_steps": 1945, "total_steps": 3400, "loss": 0.3195, "lr": 4.225033414354908e-05, "epoch": 0.5009013649240278, "percentage": 57.21, "elapsed_time": "6:57:32", "remaining_time": "5:12:20", "throughput": 815.23, "total_tokens": 20423480}
 {"current_steps": 1950, "total_steps": 3400, "loss": 0.365, "lr": 4.201020783487464e-05, "epoch": 0.5021890291012104, "percentage": 57.35, "elapsed_time": "6:58:59", "remaining_time": "5:11:33", "throughput": 814.49, "total_tokens": 20476176}
 {"current_steps": 1950, "total_steps": 3400, "eval_loss": 0.4763557016849518, "epoch": 0.5021890291012104, "percentage": 57.35, "elapsed_time": "6:59:37", "remaining_time": "5:12:02", "throughput": 813.26, "total_tokens": 20476176}
+{"current_steps": 1955, "total_steps": 3400, "loss": 0.3723, "lr": 4.17702704859633e-05, "epoch": 0.503476693278393, "percentage": 57.5, "elapsed_time": "7:01:10", "remaining_time": "5:11:18", "throughput": 812.38, "total_tokens": 20529160}
+{"current_steps": 1960, "total_steps": 3400, "loss": 0.3637, "lr": 4.153052777136879e-05, "epoch": 0.5047643574555756, "percentage": 57.65, "elapsed_time": "7:02:38", "remaining_time": "5:10:30", "throughput": 811.61, "total_tokens": 20580864}
+{"current_steps": 1965, "total_steps": 3400, "loss": 0.3513, "lr": 4.1290985361041614e-05, "epoch": 0.5060520216327582, "percentage": 57.79, "elapsed_time": "7:04:04", "remaining_time": "5:09:41", "throughput": 810.93, "total_tokens": 20633720}
+{"current_steps": 1970, "total_steps": 3400, "loss": 0.3569, "lr": 4.105164892019514e-05, "epoch": 0.5073396858099408, "percentage": 57.94, "elapsed_time": "7:05:32", "remaining_time": "5:08:53", "throughput": 810.19, "total_tokens": 20685832}
+{"current_steps": 1975, "total_steps": 3400, "loss": 0.3072, "lr": 4.0812524109171476e-05, "epoch": 0.5086273499871233, "percentage": 58.09, "elapsed_time": "7:06:58", "remaining_time": "5:08:04", "throughput": 809.49, "total_tokens": 20737832}
+{"current_steps": 1980, "total_steps": 3400, "loss": 0.3884, "lr": 4.0573616583307705e-05, "epoch": 0.509915014164306, "percentage": 58.24, "elapsed_time": "7:08:26", "remaining_time": "5:07:15", "throughput": 808.8, "total_tokens": 20791184}
+{"current_steps": 1985, "total_steps": 3400, "loss": 0.3414, "lr": 4.033493199280202e-05, "epoch": 0.5112026783414886, "percentage": 58.38, "elapsed_time": "7:09:52", "remaining_time": "5:06:26", "throughput": 808.12, "total_tokens": 20843672}
+{"current_steps": 1990, "total_steps": 3400, "loss": 0.3545, "lr": 4.009647598258022e-05, "epoch": 0.5124903425186711, "percentage": 58.53, "elapsed_time": "7:11:20", "remaining_time": "5:05:37", "throughput": 807.39, "total_tokens": 20895760}
+{"current_steps": 1995, "total_steps": 3400, "loss": 0.3406, "lr": 3.985825419216207e-05, "epoch": 0.5137780066958537, "percentage": 58.68, "elapsed_time": "7:12:47", "remaining_time": "5:04:48", "throughput": 806.71, "total_tokens": 20948448}
+{"current_steps": 2000, "total_steps": 3400, "loss": 0.3814, "lr": 3.962027225552807e-05, "epoch": 0.5150656708730363, "percentage": 58.82, "elapsed_time": "7:14:15", "remaining_time": "5:03:58", "throughput": 806.05, "total_tokens": 21002032}
+{"current_steps": 2000, "total_steps": 3400, "eval_loss": 0.5097677707672119, "epoch": 0.5150656708730363, "percentage": 58.82, "elapsed_time": "7:14:53", "remaining_time": "5:04:25", "throughput": 804.87, "total_tokens": 21002032}