Training in progress, step 2450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdf5f54c0020018c5eca1b4c1055878f2c1e58bfa3f188c951ed0eed9b279f0d
+oid sha256:dcb059e4fc556edf0deec1236fbeb6b876aa7055fe07000f0612ab6a0a9c5f0c
 size 18516456

trainer_log.jsonl

@@ -530,3 +530,14 @@
 {"current_steps": 2395, "total_steps": 3400, "loss": 0.4267, "lr": 2.2044834691045873e-05, "epoch": 1.2333247489054855, "percentage": 70.44, "elapsed_time": "8:53:34", "remaining_time": "3:43:53", "throughput": 874.81, "total_tokens": 28006112}
 {"current_steps": 2400, "total_steps": 3400, "loss": 0.3486, "lr": 2.184356480489432e-05, "epoch": 1.2359000772598505, "percentage": 70.59, "elapsed_time": "8:54:37", "remaining_time": "3:42:45", "throughput": 874.91, "total_tokens": 28064552}
 {"current_steps": 2400, "total_steps": 3400, "eval_loss": 0.7410638928413391, "epoch": 1.2359000772598505, "percentage": 70.59, "elapsed_time": "8:54:53", "remaining_time": "3:42:52", "throughput": 874.47, "total_tokens": 28064552}
+{"current_steps": 2405, "total_steps": 3400, "loss": 0.2416, "lr": 2.1642960822587878e-05, "epoch": 1.2384754056142158, "percentage": 70.74, "elapsed_time": "8:56:01", "remaining_time": "3:41:45", "throughput": 874.43, "total_tokens": 28123016}
+{"current_steps": 2410, "total_steps": 3400, "loss": 0.3007, "lr": 2.1443027488440338e-05, "epoch": 1.241050733968581, "percentage": 70.88, "elapsed_time": "8:57:04", "remaining_time": "3:40:37", "throughput": 874.53, "total_tokens": 28181464}
+{"current_steps": 2415, "total_steps": 3400, "loss": 0.2655, "lr": 2.124376953090456e-05, "epoch": 1.2436260623229463, "percentage": 71.03, "elapsed_time": "8:58:08", "remaining_time": "3:39:29", "throughput": 874.63, "total_tokens": 28239920}
+{"current_steps": 2420, "total_steps": 3400, "loss": 0.3075, "lr": 2.104519166246059e-05, "epoch": 1.2462013906773113, "percentage": 71.18, "elapsed_time": "8:59:11", "remaining_time": "3:38:20", "throughput": 874.73, "total_tokens": 28298432}
+{"current_steps": 2425, "total_steps": 3400, "loss": 0.3537, "lr": 2.0847298579504344e-05, "epoch": 1.2487767190316765, "percentage": 71.32, "elapsed_time": "9:00:14", "remaining_time": "3:37:12", "throughput": 874.83, "total_tokens": 28356904}
+{"current_steps": 2430, "total_steps": 3400, "loss": 0.2993, "lr": 2.065009496223638e-05, "epoch": 1.2513520473860418, "percentage": 71.47, "elapsed_time": "9:01:17", "remaining_time": "3:36:04", "throughput": 874.93, "total_tokens": 28415384}
+{"current_steps": 2435, "total_steps": 3400, "loss": 0.2752, "lr": 2.045358547455138e-05, "epoch": 1.2539273757404068, "percentage": 71.62, "elapsed_time": "9:02:20", "remaining_time": "3:34:56", "throughput": 875.02, "total_tokens": 28473848}
+{"current_steps": 2440, "total_steps": 3400, "loss": 0.2975, "lr": 2.0257774763927655e-05, "epoch": 1.256502704094772, "percentage": 71.76, "elapsed_time": "9:03:23", "remaining_time": "3:33:47", "throughput": 875.12, "total_tokens": 28532312}
+{"current_steps": 2445, "total_steps": 3400, "loss": 0.4051, "lr": 2.0062667461317426e-05, "epoch": 1.2590780324491373, "percentage": 71.91, "elapsed_time": "9:04:27", "remaining_time": "3:32:39", "throughput": 875.22, "total_tokens": 28590784}
+{"current_steps": 2450, "total_steps": 3400, "loss": 0.2966, "lr": 1.9868268181037185e-05, "epoch": 1.2616533608035025, "percentage": 72.06, "elapsed_time": "9:05:30", "remaining_time": "3:31:31", "throughput": 875.32, "total_tokens": 28649256}
+{"current_steps": 2450, "total_steps": 3400, "eval_loss": 0.7485548853874207, "epoch": 1.2616533608035025, "percentage": 72.06, "elapsed_time": "9:05:46", "remaining_time": "3:31:37", "throughput": 874.89, "total_tokens": 28649256}