Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3afc1bf1736e352cd21d7d89b219c95215802812e6421113fac1918375d204f
+oid sha256:635163bcb7a7d1d963ff50b7c0dcd8a0776dae208395df6140a9524a8faef878
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89e5a555b996990113b0a6a61a8707e25370c6beecb986b9912bd77bf40298fa
+oid sha256:6ad75a633044b8702576ee6127b12e4b40d60593c099bf33784f09efe7bbab9b
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d1f919bca3b0a1980bb83b7f2c8120fcde2df2d550516d865ed89db7b8842d
+oid sha256:a40b16a0702a4acdc8fd02aa8e11e91edd4faac79c5a8c3a395358ce2b985283
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a157761bcbcf9ac596a814edc82cabd1459cfdae2584c2bfef8ad5c74b1dac
+oid sha256:36d85f05f0906df5f631e9742da0b5d97026a6e62691de0522a431cbd6dc6af6
 size 1089994880

trainer_log.jsonl

@@ -10,3 +10,13 @@
 {"current_steps": 10, "total_steps": 70, "loss": 0.8179, "lr": 1.9888308262251286e-05, "epoch": 0.96, "percentage": 14.29, "elapsed_time": "0:20:14", "remaining_time": "2:01:27"}
 {"current_steps": 11, "total_steps": 70, "loss": 0.7918, "lr": 1.9801724878485438e-05, "epoch": 1.056, "percentage": 15.71, "elapsed_time": "0:22:56", "remaining_time": "2:03:00"}
 {"current_steps": 12, "total_steps": 70, "loss": 0.7592, "lr": 1.969077286229078e-05, "epoch": 1.152, "percentage": 17.14, "elapsed_time": "0:24:58", "remaining_time": "2:00:44"}
+{"current_steps": 13, "total_steps": 70, "loss": 0.7785, "lr": 1.955572805786141e-05, "epoch": 1.248, "percentage": 18.57, "elapsed_time": "0:26:54", "remaining_time": "1:57:58"}
+{"current_steps": 14, "total_steps": 70, "loss": 0.7622, "lr": 1.9396926207859085e-05, "epoch": 1.3439999999999999, "percentage": 20.0, "elapsed_time": "0:28:58", "remaining_time": "1:55:53"}
+{"current_steps": 15, "total_steps": 70, "loss": 0.735, "lr": 1.921476211870408e-05, "epoch": 1.44, "percentage": 21.43, "elapsed_time": "0:30:47", "remaining_time": "1:52:55"}
+{"current_steps": 16, "total_steps": 70, "loss": 0.7301, "lr": 1.900968867902419e-05, "epoch": 1.536, "percentage": 22.86, "elapsed_time": "0:32:50", "remaining_time": "1:50:49"}
+{"current_steps": 17, "total_steps": 70, "loss": 0.7429, "lr": 1.8782215733702286e-05, "epoch": 1.6320000000000001, "percentage": 24.29, "elapsed_time": "0:34:53", "remaining_time": "1:48:46"}
+{"current_steps": 18, "total_steps": 70, "loss": 0.7215, "lr": 1.8532908816321557e-05, "epoch": 1.728, "percentage": 25.71, "elapsed_time": "0:36:51", "remaining_time": "1:46:28"}
+{"current_steps": 19, "total_steps": 70, "loss": 0.7171, "lr": 1.826238774315995e-05, "epoch": 1.8239999999999998, "percentage": 27.14, "elapsed_time": "0:38:55", "remaining_time": "1:44:29"}
+{"current_steps": 20, "total_steps": 70, "loss": 0.6891, "lr": 1.7971325072229227e-05, "epoch": 1.92, "percentage": 28.57, "elapsed_time": "0:40:54", "remaining_time": "1:42:15"}
+{"current_steps": 21, "total_steps": 70, "loss": 0.6961, "lr": 1.766044443118978e-05, "epoch": 2.016, "percentage": 30.0, "elapsed_time": "0:43:34", "remaining_time": "1:41:39"}
+{"current_steps": 22, "total_steps": 70, "loss": 0.649, "lr": 1.7330518718298263e-05, "epoch": 2.112, "percentage": 31.43, "elapsed_time": "0:45:11", "remaining_time": "1:38:36"}