Training in progress, step 2650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e9567b5b78ecaf7020aec03364d24598d915d5c6b4e0693a08fba051035ffc3
+oid sha256:bb670064f69799ca31ac4e8217d7e22011ba811f44d8295685d5e602a1b97e3a
 size 83945296

trainer_log.jsonl

@@ -310,3 +310,19 @@
 {"current_steps": 2590, "total_steps": 3295, "loss": 0.0157, "lr": 1.3313106828399147e-05, "epoch": 3.927962085308057, "percentage": 78.6, "elapsed_time": "7:48:50", "remaining_time": "2:07:37"}
 {"current_steps": 2600, "total_steps": 3295, "loss": 0.014, "lr": 1.2955223376303205e-05, "epoch": 3.943127962085308, "percentage": 78.91, "elapsed_time": "7:50:07", "remaining_time": "2:05:40"}
 {"current_steps": 2600, "total_steps": 3295, "eval_loss": 0.03850428760051727, "epoch": 3.943127962085308, "percentage": 78.91, "elapsed_time": "7:52:45", "remaining_time": "2:06:22"}
+{"current_steps": 2610, "total_steps": 3295, "loss": 0.0086, "lr": 1.2601498774309112e-05, "epoch": 3.9582938388625593, "percentage": 79.21, "elapsed_time": "7:54:07", "remaining_time": "2:04:26"}
+{"current_steps": 2620, "total_steps": 3295, "loss": 0.0106, "lr": 1.2251972733483612e-05, "epoch": 3.9734597156398106, "percentage": 79.51, "elapsed_time": "7:55:23", "remaining_time": "2:02:28"}
+{"current_steps": 2630, "total_steps": 3295, "loss": 0.0094, "lr": 1.19066844935399e-05, "epoch": 3.9886255924170615, "percentage": 79.82, "elapsed_time": "7:56:40", "remaining_time": "2:00:31"}
+{"current_steps": 2640, "total_steps": 3295, "loss": 0.0143, "lr": 1.156567281843241e-05, "epoch": 4.003791469194312, "percentage": 80.12, "elapsed_time": "7:57:56", "remaining_time": "1:58:34"}
+{"current_steps": 2650, "total_steps": 3295, "loss": 0.0086, "lr": 1.1228975992004842e-05, "epoch": 4.018957345971564, "percentage": 80.42, "elapsed_time": "7:59:13", "remaining_time": "1:56:38"}
+{"current_steps": 2650, "total_steps": 3295, "eval_loss": 0.04015021771192551, "epoch": 4.018957345971564, "percentage": 80.42, "elapsed_time": "8:01:51", "remaining_time": "1:57:16"}
+{"current_steps": 2660, "total_steps": 3295, "loss": 0.0056, "lr": 1.0896631813692377e-05, "epoch": 4.034123222748815, "percentage": 80.73, "elapsed_time": "8:03:12", "remaining_time": "1:55:21"}
+{"current_steps": 2670, "total_steps": 3295, "loss": 0.0049, "lr": 1.0568677594277899e-05, "epoch": 4.049289099526066, "percentage": 81.03, "elapsed_time": "8:04:29", "remaining_time": "1:53:24"}
+{"current_steps": 2680, "total_steps": 3295, "loss": 0.0036, "lr": 1.0245150151703509e-05, "epoch": 4.064454976303318, "percentage": 81.34, "elapsed_time": "8:05:46", "remaining_time": "1:51:28"}
+{"current_steps": 2690, "total_steps": 3295, "loss": 0.0055, "lr": 9.926085806936918e-06, "epoch": 4.079620853080569, "percentage": 81.64, "elapsed_time": "8:07:02", "remaining_time": "1:49:32"}
+{"current_steps": 2700, "total_steps": 3295, "loss": 0.005, "lr": 9.611520379894068e-06, "epoch": 4.0947867298578196, "percentage": 81.94, "elapsed_time": "8:08:19", "remaining_time": "1:47:36"}
+{"current_steps": 2700, "total_steps": 3295, "eval_loss": 0.043914105743169785, "epoch": 4.0947867298578196, "percentage": 81.94, "elapsed_time": "8:10:57", "remaining_time": "1:48:11"}
+{"current_steps": 2710, "total_steps": 3295, "loss": 0.0063, "lr": 9.301489185417578e-06, "epoch": 4.109952606635071, "percentage": 82.25, "elapsed_time": "8:12:17", "remaining_time": "1:46:16"}
+{"current_steps": 2720, "total_steps": 3295, "loss": 0.0043, "lr": 8.996027029312314e-06, "epoch": 4.125118483412322, "percentage": 82.55, "elapsed_time": "8:13:34", "remaining_time": "1:44:20"}
+{"current_steps": 2730, "total_steps": 3295, "loss": 0.0052, "lr": 8.695168204437721e-06, "epoch": 4.140284360189574, "percentage": 82.85, "elapsed_time": "8:14:50", "remaining_time": "1:42:24"}
+{"current_steps": 2740, "total_steps": 3295, "loss": 0.0039, "lr": 8.398946486858029e-06, "epoch": 4.155450236966825, "percentage": 83.16, "elapsed_time": "8:16:07", "remaining_time": "1:40:29"}