Training in progress, step 450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:519addb7c2ccddb2bb04acac1bf357ce6be904b2c9ab029829133da4e8c89699
+oid sha256:b66f09b5eb3e2b8e820ab8703bfb62caadc5f14fec5d8d4c4a11402660014d23
 size 18516456

trainer_log.jsonl

@@ -90,3 +90,14 @@
 {"current_steps": 395, "total_steps": 3400, "loss": 0.8851, "lr": 9.88074796551666e-05, "epoch": 0.20345093999484934, "percentage": 11.62, "elapsed_time": "1:33:05", "remaining_time": "11:48:14", "throughput": 827.08, "total_tokens": 4619944}
 {"current_steps": 400, "total_steps": 3400, "loss": 0.9004, "lr": 9.875411350104744e-05, "epoch": 0.20602626834921453, "percentage": 11.76, "elapsed_time": "1:34:12", "remaining_time": "11:46:36", "throughput": 827.62, "total_tokens": 4678384}
 {"current_steps": 400, "total_steps": 3400, "eval_loss": 0.9086406826972961, "epoch": 0.20602626834921453, "percentage": 11.76, "elapsed_time": "1:34:29", "remaining_time": "11:48:42", "throughput": 825.17, "total_tokens": 4678384}
+{"current_steps": 405, "total_steps": 3400, "loss": 0.8976, "lr": 9.86995943049533e-05, "epoch": 0.2086015967035797, "percentage": 11.91, "elapsed_time": "1:35:41", "remaining_time": "11:47:40", "throughput": 824.99, "total_tokens": 4736904}
+{"current_steps": 410, "total_steps": 3400, "loss": 0.9134, "lr": 9.864392335627117e-05, "epoch": 0.2111769250579449, "percentage": 12.06, "elapsed_time": "1:36:49", "remaining_time": "11:46:04", "throughput": 825.49, "total_tokens": 4795376}
+{"current_steps": 415, "total_steps": 3400, "loss": 0.8955, "lr": 9.858710197162721e-05, "epoch": 0.21375225341231008, "percentage": 12.21, "elapsed_time": "1:37:56", "remaining_time": "11:44:26", "throughput": 826.02, "total_tokens": 4853880}
+{"current_steps": 420, "total_steps": 3400, "loss": 0.9014, "lr": 9.852913149485556e-05, "epoch": 0.21632758176667524, "percentage": 12.35, "elapsed_time": "1:39:02", "remaining_time": "11:42:46", "throughput": 826.59, "total_tokens": 4912360}
+{"current_steps": 425, "total_steps": 3400, "loss": 0.9065, "lr": 9.847001329696653e-05, "epoch": 0.21890291012104043, "percentage": 12.5, "elapsed_time": "1:40:09", "remaining_time": "11:41:08", "throughput": 827.12, "total_tokens": 4970872}
+{"current_steps": 430, "total_steps": 3400, "loss": 0.8952, "lr": 9.840974877611422e-05, "epoch": 0.22147823847540563, "percentage": 12.65, "elapsed_time": "1:41:17", "remaining_time": "11:39:33", "throughput": 827.59, "total_tokens": 5029304}
+{"current_steps": 435, "total_steps": 3400, "loss": 0.9106, "lr": 9.834833935756344e-05, "epoch": 0.2240535668297708, "percentage": 12.79, "elapsed_time": "1:42:25", "remaining_time": "11:38:11", "throughput": 827.83, "total_tokens": 5087800}
+{"current_steps": 440, "total_steps": 3400, "loss": 0.8996, "lr": 9.828578649365601e-05, "epoch": 0.22662889518413598, "percentage": 12.94, "elapsed_time": "1:43:34", "remaining_time": "11:36:48", "throughput": 828.08, "total_tokens": 5146312}
+{"current_steps": 445, "total_steps": 3400, "loss": 0.8999, "lr": 9.822209166377635e-05, "epoch": 0.22920422353850115, "percentage": 13.09, "elapsed_time": "1:44:43", "remaining_time": "11:35:24", "throughput": 828.35, "total_tokens": 5204800}
+{"current_steps": 450, "total_steps": 3400, "loss": 0.9076, "lr": 9.815725637431662e-05, "epoch": 0.23177955189286634, "percentage": 13.24, "elapsed_time": "1:45:53", "remaining_time": "11:34:08", "throughput": 828.45, "total_tokens": 5263304}
+{"current_steps": 450, "total_steps": 3400, "eval_loss": 0.8962157368659973, "epoch": 0.23177955189286634, "percentage": 13.24, "elapsed_time": "1:46:10", "remaining_time": "11:36:01", "throughput": 826.21, "total_tokens": 5263304}