Training in progress, step 2900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1404e60fabb5103dbe434a7e9d7d0543eaa50c6cb487e2d805559319b22760ea
+oid sha256:f49768fb6efa912a563fdf9c78311249a1d28fb66c672197a06fe3282fb5f3cb
 size 18516456

trainer_log.jsonl

@@ -629,3 +629,14 @@
 {"current_steps": 2845, "total_steps": 3400, "loss": 0.2671, "lr": 7.109663499981834e-06, "epoch": 1.4651043007983517, "percentage": 83.68, "elapsed_time": "10:32:15", "remaining_time": "2:03:20", "throughput": 877.0, "total_tokens": 33269320}
 {"current_steps": 2850, "total_steps": 3400, "loss": 0.2848, "lr": 6.985195022814067e-06, "epoch": 1.467679629152717, "percentage": 83.82, "elapsed_time": "10:33:18", "remaining_time": "2:02:13", "throughput": 877.07, "total_tokens": 33327720}
 {"current_steps": 2850, "total_steps": 3400, "eval_loss": 0.8045337796211243, "epoch": 1.467679629152717, "percentage": 83.82, "elapsed_time": "10:33:34", "remaining_time": "2:02:16", "throughput": 876.71, "total_tokens": 33327720}
+{"current_steps": 2855, "total_steps": 3400, "loss": 0.2811, "lr": 6.861743852128233e-06, "epoch": 1.4702549575070822, "percentage": 83.97, "elapsed_time": "10:34:42", "remaining_time": "2:01:09", "throughput": 876.68, "total_tokens": 33386160}
+{"current_steps": 2860, "total_steps": 3400, "loss": 0.2394, "lr": 6.7393129075627335e-06, "epoch": 1.4728302858614473, "percentage": 84.12, "elapsed_time": "10:35:45", "remaining_time": "2:00:02", "throughput": 876.76, "total_tokens": 33444648}
+{"current_steps": 2865, "total_steps": 3400, "loss": 0.243, "lr": 6.6179050846274515e-06, "epoch": 1.4754056142158125, "percentage": 84.26, "elapsed_time": "10:36:49", "remaining_time": "1:58:55", "throughput": 876.84, "total_tokens": 33503144}
+{"current_steps": 2870, "total_steps": 3400, "loss": 0.242, "lr": 6.497523254635296e-06, "epoch": 1.4779809425701778, "percentage": 84.41, "elapsed_time": "10:37:52", "remaining_time": "1:57:47", "throughput": 876.92, "total_tokens": 33561600}
+{"current_steps": 2875, "total_steps": 3400, "loss": 0.1864, "lr": 6.37817026463432e-06, "epoch": 1.4805562709245428, "percentage": 84.56, "elapsed_time": "10:38:55", "remaining_time": "1:56:40", "throughput": 877.0, "total_tokens": 33620056}
+{"current_steps": 2880, "total_steps": 3400, "loss": 0.2406, "lr": 6.25984893734034e-06, "epoch": 1.483131599278908, "percentage": 84.71, "elapsed_time": "10:39:58", "remaining_time": "1:55:32", "throughput": 877.09, "total_tokens": 33678512}
+{"current_steps": 2885, "total_steps": 3400, "loss": 0.2287, "lr": 6.142562071070179e-06, "epoch": 1.4857069276332733, "percentage": 84.85, "elapsed_time": "10:41:01", "remaining_time": "1:54:25", "throughput": 877.17, "total_tokens": 33736960}
+{"current_steps": 2890, "total_steps": 3400, "loss": 0.2643, "lr": 6.026312439675552e-06, "epoch": 1.4882822559876385, "percentage": 85.0, "elapsed_time": "10:42:04", "remaining_time": "1:53:18", "throughput": 877.25, "total_tokens": 33795416}
+{"current_steps": 2895, "total_steps": 3400, "loss": 0.2956, "lr": 5.911102792477357e-06, "epoch": 1.4908575843420036, "percentage": 85.15, "elapsed_time": "10:43:07", "remaining_time": "1:52:11", "throughput": 877.32, "total_tokens": 33853936}
+{"current_steps": 2900, "total_steps": 3400, "loss": 0.29, "lr": 5.796935854200763e-06, "epoch": 1.4934329126963688, "percentage": 85.29, "elapsed_time": "10:44:10", "remaining_time": "1:51:03", "throughput": 877.41, "total_tokens": 33912440}
+{"current_steps": 2900, "total_steps": 3400, "eval_loss": 0.8113046884536743, "epoch": 1.4934329126963688, "percentage": 85.29, "elapsed_time": "10:44:26", "remaining_time": "1:51:06", "throughput": 877.04, "total_tokens": 33912440}