Training in progress, epoch 0

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a408ee0f8fdb3e845bdb3339ada61d40292f2f09d48e453fad3847ad65d08edd
+oid sha256:f73af9c9815025c776edd898d2ca84f85b66177201d71e077a4222de0d0263c8
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232a3909840e01cc819ae08e59016d4cfb3b3cf013b2da08dd7592daee29abc1
+oid sha256:9c9f1293543ed073ee9b7f5bd5515c8d718d60f3c514347fecb617feb251f5a5
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:114355d06f32f87480540f3c0905736dbe4dcc326abd785be23f5e115c2c31f2
+oid sha256:0764a2cd606279de276256cb40513c531714b1cc2fd8f7fce649c8a974080031
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41ce1392103035fe42f43626e1a974ceee688ee2fa40cff3da8b52332a9bf0c8
+oid sha256:05cd31b01e13f84942474e2064c6282e11c00e9969e287e09088608857a85c2a
 size 1089994880

trainer_log.jsonl

@@ -179,3 +179,20 @@
 {"current_steps": 179, "total_steps": 180, "loss": 0.4959, "lr": 7.521182059946342e-09, "epoch": 4.937931034482759, "percentage": 99.44, "elapsed_time": "5:14:45", "remaining_time": "0:01:45"}
 {"current_steps": 180, "total_steps": 180, "loss": 0.4928, "lr": 0.0, "epoch": 4.9655172413793105, "percentage": 100.0, "elapsed_time": "5:16:27", "remaining_time": "0:00:00"}
 {"current_steps": 180, "total_steps": 180, "epoch": 4.9655172413793105, "percentage": 100.0, "elapsed_time": "5:19:20", "remaining_time": "0:00:00"}
+{"current_steps": 181, "total_steps": 975, "loss": 0.4737, "lr": 7.82449679849362e-05, "epoch": 0.92672, "percentage": 18.56, "elapsed_time": "0:01:08", "remaining_time": "0:04:59"}
+{"current_steps": 182, "total_steps": 975, "loss": 0.4816, "lr": 7.82027447626706e-05, "epoch": 0.93184, "percentage": 18.67, "elapsed_time": "0:02:09", "remaining_time": "0:09:22"}
+{"current_steps": 183, "total_steps": 975, "loss": 0.5019, "lr": 7.816003131630129e-05, "epoch": 0.93696, "percentage": 18.77, "elapsed_time": "0:03:10", "remaining_time": "0:13:44"}
+{"current_steps": 184, "total_steps": 975, "loss": 0.7558, "lr": 7.811682819393448e-05, "epoch": 0.94208, "percentage": 18.87, "elapsed_time": "0:04:03", "remaining_time": "0:17:24"}
+{"current_steps": 185, "total_steps": 975, "loss": 0.6467, "lr": 7.807313594995996e-05, "epoch": 0.9472, "percentage": 18.97, "elapsed_time": "0:05:01", "remaining_time": "0:21:26"}
+{"current_steps": 186, "total_steps": 975, "loss": 0.626, "lr": 7.802895514504404e-05, "epoch": 0.95232, "percentage": 19.08, "elapsed_time": "0:05:46", "remaining_time": "0:24:30"}
+{"current_steps": 187, "total_steps": 975, "loss": 0.6328, "lr": 7.798428634612227e-05, "epoch": 0.95744, "percentage": 19.18, "elapsed_time": "0:06:38", "remaining_time": "0:27:58"}
+{"current_steps": 188, "total_steps": 975, "loss": 0.6009, "lr": 7.79391301263923e-05, "epoch": 0.96256, "percentage": 19.28, "elapsed_time": "0:07:32", "remaining_time": "0:31:35"}
+{"current_steps": 189, "total_steps": 975, "loss": 0.6328, "lr": 7.789348706530638e-05, "epoch": 0.96768, "percentage": 19.38, "elapsed_time": "0:08:27", "remaining_time": "0:35:11"}
+{"current_steps": 190, "total_steps": 975, "loss": 0.632, "lr": 7.784735774856401e-05, "epoch": 0.9728, "percentage": 19.49, "elapsed_time": "0:09:13", "remaining_time": "0:38:07"}
+{"current_steps": 191, "total_steps": 975, "loss": 0.6104, "lr": 7.780074276810442e-05, "epoch": 0.97792, "percentage": 19.59, "elapsed_time": "0:10:00", "remaining_time": "0:41:03"}
+{"current_steps": 192, "total_steps": 975, "loss": 0.6136, "lr": 7.775364272209896e-05, "epoch": 0.98304, "percentage": 19.69, "elapsed_time": "0:10:46", "remaining_time": "0:43:57"}
+{"current_steps": 193, "total_steps": 975, "loss": 0.6537, "lr": 7.77060582149434e-05, "epoch": 0.98816, "percentage": 19.79, "elapsed_time": "0:11:36", "remaining_time": "0:47:01"}
+{"current_steps": 194, "total_steps": 975, "loss": 0.6299, "lr": 7.76579898572502e-05, "epoch": 0.99328, "percentage": 19.9, "elapsed_time": "0:12:30", "remaining_time": "0:50:19"}
+{"current_steps": 195, "total_steps": 975, "loss": 0.6234, "lr": 7.76094382658407e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "0:13:28", "remaining_time": "0:53:55"}
+{"current_steps": 196, "total_steps": 975, "loss": 0.5981, "lr": 7.756040406373716e-05, "epoch": 1.00352, "percentage": 20.1, "elapsed_time": "0:15:53", "remaining_time": "1:03:11"}
+{"current_steps": 197, "total_steps": 975, "loss": 0.6131, "lr": 7.751088788015478e-05, "epoch": 1.00864, "percentage": 20.21, "elapsed_time": "0:16:49", "remaining_time": "1:06:27"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888ab675100e2cc806286253779336d6dfde2a3ced9ba04af2c0abb1e49fd4fd
-size 7416
+oid sha256:0e21f6e32259d05900f7d8d89a6e089c83f75c28c622d6f1e23294c2e259a81f
+size 7480