Model save

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.9360857009887695,
-    "eval_runtime": 142.4328,
+    "eval_loss": 0.9360852241516113,
+    "eval_runtime": 142.4913,
     "eval_samples": 23110,
-    "eval_samples_per_second": 108.339,
-    "eval_steps_per_second": 1.699,
-    "train_loss": 0.07633444366105106,
-    "train_runtime": 563.397,
+    "eval_samples_per_second": 108.294,
+    "eval_steps_per_second": 1.698,
+    "train_loss": 0.07633398782222643,
+    "train_runtime": 563.604,
     "train_samples": 207865,
-    "train_samples_per_second": 247.474,
-    "train_steps_per_second": 1.935
+    "train_samples_per_second": 247.383,
+    "train_steps_per_second": 1.934
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 0.9360857009887695,
-    "eval_runtime": 142.4328,
+    "eval_loss": 0.9360852241516113,
+    "eval_runtime": 142.4913,
     "eval_samples": 23110,
-    "eval_samples_per_second": 108.339,
-    "eval_steps_per_second": 1.699
+    "eval_samples_per_second": 108.294,
+    "eval_steps_per_second": 1.698
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f785798732c7ef26d34f5056ed95c789cca31876fc2729a8688e91a64f158975
+oid sha256:d962f5f669d3b46ec1ee3f616d374040c5b5341d94e31eb87c37b783850a6941
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177eaac08f7ca90baa649f6c2eb979843b9bdd29897c8f18f53902c60c19df52
+oid sha256:70645b2075d65260c14c0cd5b6587092bf6ad7baf2ec58bacb170f20d06b8453
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e07e16b881fdcd0767315f89c90e17b12c08f7fa9626f3a9c98af34ef8e11de
+oid sha256:44584b41e975a724de8f368833fca905f60dd80bdc3307178aab1a1b9ca18e07
 size 4540516344

runs/Jan04_11-14-47_ip-26-0-173-202/events.out.tfevents.1704366960.ip-26-0-173-202.768748.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd81d94fbac36a437fc4f0ee2b90ef0985a241c1709771aec78e28d8d52ca9e3
+size 7882

runs/Jan04_11-14-47_ip-26-0-173-202/events.out.tfevents.1704367666.ip-26-0-173-202.768748.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432bf01d585d5a919362be4a588de1d99f432349fe1d563ac4f6d96a799a4f21
+size 359

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.07633444366105106,
-    "train_runtime": 563.397,
+    "train_loss": 0.07633398782222643,
+    "train_runtime": 563.604,
     "train_samples": 207865,
-    "train_samples_per_second": 247.474,
-    "train_steps_per_second": 1.935
+    "train_samples_per_second": 247.383,
+    "train_steps_per_second": 1.934
 }

trainer_state.json

@@ -1217,13 +1217,13 @@
     {
       "epoch": 0.92,
       "learning_rate": 2.985942075541848e-07,
-      "loss": 0.9267,
+      "loss": 0.9266,
       "step": 1005
     },
     {
       "epoch": 0.93,
       "learning_rate": 2.646499188279328e-07,
-      "loss": 0.9119,
+      "loss": 0.912,
       "step": 1010
     },
     {
@@ -1283,7 +1283,7 @@
     {
       "epoch": 0.97,
       "learning_rate": 3.735843446830867e-08,
-      "loss": 0.9228,
+      "loss": 0.9227,
       "step": 1060
     },
     {
@@ -1301,7 +1301,7 @@
     {
       "epoch": 0.99,
       "learning_rate": 9.343974109685684e-09,
-      "loss": 0.9278,
+      "loss": 0.9277,
       "step": 1075
     },
     {
@@ -1324,9 +1324,9 @@
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.9360857009887695,
-      "eval_runtime": 143.3612,
-      "eval_samples_per_second": 107.637,
+      "eval_loss": 0.9360852241516113,
+      "eval_runtime": 143.326,
+      "eval_samples_per_second": 107.664,
       "eval_steps_per_second": 1.688,
       "step": 1090
     },
@@ -1334,10 +1334,10 @@
       "epoch": 1.0,
       "step": 1090,
       "total_flos": 456447649382400.0,
-      "train_loss": 0.07633444366105106,
-      "train_runtime": 563.397,
-      "train_samples_per_second": 247.474,
-      "train_steps_per_second": 1.935
+      "train_loss": 0.07633398782222643,
+      "train_runtime": 563.604,
+      "train_samples_per_second": 247.383,
+      "train_steps_per_second": 1.934
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0691346a7ead143f31dee13e381834e39d381f00c48ab175103779bd8ed770fd
+oid sha256:ebb8b817065113f0d4164ec672e5ca229a3f452e5837c978813720b0f6564d8e
 size 5880