Model save

README.md

@@ -49,15 +49,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.7095        | 0.09  | 1    | 1.7013          |
+| 1.7095        | 0.09  | 1    | 1.7015          |
 | 1.7095        | 1.07  | 2    | 1.6854          |
 | 1.7095        | 2.06  | 3    | 1.6635          |
-| 1.7095        | 3.04  | 4    | 1.6378          |
-| 1.6715        | 4.02  | 5    | 1.6107          |
+| 1.7095        | 3.04  | 4    | 1.6377          |
+| 1.6715        | 4.02  | 5    | 1.6106          |
 | 1.6715        | 5.1   | 7    | 1.5584          |
-| 1.6715        | 6.08  | 8    | 1.5345          |
-| 1.6715        | 7.06  | 9    | 1.5133          |
-| 1.5588        | 8.05  | 10   | 1.4934          |
+| 1.6715        | 6.08  | 8    | 1.5344          |
+| 1.6715        | 7.06  | 9    | 1.5132          |
+| 1.5588        | 8.05  | 10   | 1.4933          |
 | 1.5588        | 9.03  | 11   | 1.4756          |
 
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ca5ccdfab3e7b33d87a3f17cf5babcc7eb5f9f741a0ee2885fd1e7aeb00147
+oid sha256:666cc01e681b40ccae20914c7fad0fdcd73f72ed3f8d6b3d3d5f94c4575a253e
 size 218138576

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 9.03,
-    "eval_loss": 1.475583791732788,
-    "eval_runtime": 6.3363,
+    "eval_loss": 1.4756207466125488,
+    "eval_runtime": 6.3444,
     "eval_samples": 294,
-    "eval_samples_per_second": 46.399,
-    "eval_steps_per_second": 5.839,
-    "train_loss": 1.714235695925626,
-    "train_runtime": 4134.2039,
+    "eval_samples_per_second": 46.34,
+    "eval_steps_per_second": 5.832,
+    "train_loss": 1.7142409628087825,
+    "train_runtime": 4135.8024,
     "train_samples": 5895,
-    "train_samples_per_second": 14.259,
+    "train_samples_per_second": 14.254,
     "train_steps_per_second": 0.027
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.03,
-    "eval_loss": 1.475583791732788,
-    "eval_runtime": 6.3363,
+    "eval_loss": 1.4756207466125488,
+    "eval_runtime": 6.3444,
     "eval_samples": 294,
-    "eval_samples_per_second": 46.399,
-    "eval_steps_per_second": 5.839
+    "eval_samples_per_second": 46.34,
+    "eval_steps_per_second": 5.832
 }

runs/Dec14_13-56-05_s4311/events.out.tfevents.1702562244.s4311.817937.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13bceaa2d273b3b12db226f49a3c79e6f99213d1bbb2e09a5be1614520450aa
+size 7724

runs/Dec14_13-56-05_s4311/events.out.tfevents.1702566386.s4311.817937.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6655036fa20dec055f217bb8032aa555a529d2f754efb3e8a781fcff26d559ac
+size 354

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.03,
-    "train_loss": 1.714235695925626,
-    "train_runtime": 4134.2039,
+    "train_loss": 1.7142409628087825,
+    "train_runtime": 4135.8024,
     "train_samples": 5895,
-    "train_samples_per_second": 14.259,
+    "train_samples_per_second": 14.254,
     "train_steps_per_second": 0.027
 }

trainer_state.json

@@ -16,34 +16,34 @@
     },
     {
       "epoch": 0.09,
-      "eval_loss": 1.7013005018234253,
-      "eval_runtime": 6.3689,
-      "eval_samples_per_second": 46.162,
-      "eval_steps_per_second": 5.809,
+      "eval_loss": 1.701454997062683,
+      "eval_runtime": 6.3744,
+      "eval_samples_per_second": 46.122,
+      "eval_steps_per_second": 5.804,
       "step": 1
     },
     {
       "epoch": 1.07,
-      "eval_loss": 1.6853851079940796,
-      "eval_runtime": 6.3663,
-      "eval_samples_per_second": 46.181,
-      "eval_steps_per_second": 5.812,
+      "eval_loss": 1.6854428052902222,
+      "eval_runtime": 6.363,
+      "eval_samples_per_second": 46.204,
+      "eval_steps_per_second": 5.815,
       "step": 2
     },
     {
       "epoch": 2.06,
-      "eval_loss": 1.6635044813156128,
-      "eval_runtime": 6.3573,
-      "eval_samples_per_second": 46.246,
-      "eval_steps_per_second": 5.82,
+      "eval_loss": 1.6634844541549683,
+      "eval_runtime": 6.3663,
+      "eval_samples_per_second": 46.181,
+      "eval_steps_per_second": 5.812,
       "step": 3
     },
     {
       "epoch": 3.04,
-      "eval_loss": 1.6378282308578491,
-      "eval_runtime": 6.3598,
-      "eval_samples_per_second": 46.228,
-      "eval_steps_per_second": 5.818,
+      "eval_loss": 1.6377184391021729,
+      "eval_runtime": 6.3346,
+      "eval_samples_per_second": 46.412,
+      "eval_steps_per_second": 5.841,
       "step": 4
     },
     {
@@ -54,34 +54,34 @@
     },
     {
       "epoch": 4.02,
-      "eval_loss": 1.610694408416748,
-      "eval_runtime": 6.3454,
-      "eval_samples_per_second": 46.333,
-      "eval_steps_per_second": 5.831,
+      "eval_loss": 1.6106265783309937,
+      "eval_runtime": 6.3433,
+      "eval_samples_per_second": 46.348,
+      "eval_steps_per_second": 5.833,
       "step": 5
     },
     {
       "epoch": 5.1,
-      "eval_loss": 1.5584030151367188,
-      "eval_runtime": 6.3281,
-      "eval_samples_per_second": 46.459,
-      "eval_steps_per_second": 5.847,
+      "eval_loss": 1.5584189891815186,
+      "eval_runtime": 6.3627,
+      "eval_samples_per_second": 46.206,
+      "eval_steps_per_second": 5.815,
       "step": 7
     },
     {
       "epoch": 6.08,
-      "eval_loss": 1.5344550609588623,
-      "eval_runtime": 6.3648,
-      "eval_samples_per_second": 46.192,
-      "eval_steps_per_second": 5.813,
+      "eval_loss": 1.5343831777572632,
+      "eval_runtime": 6.3403,
+      "eval_samples_per_second": 46.37,
+      "eval_steps_per_second": 5.836,
       "step": 8
     },
     {
       "epoch": 7.06,
-      "eval_loss": 1.5132712125778198,
-      "eval_runtime": 6.3444,
-      "eval_samples_per_second": 46.34,
-      "eval_steps_per_second": 5.832,
+      "eval_loss": 1.5131820440292358,
+      "eval_runtime": 6.3297,
+      "eval_samples_per_second": 46.448,
+      "eval_steps_per_second": 5.845,
       "step": 9
     },
     {
@@ -92,27 +92,27 @@
     },
     {
       "epoch": 8.05,
-      "eval_loss": 1.493425965309143,
-      "eval_runtime": 6.3668,
-      "eval_samples_per_second": 46.177,
-      "eval_steps_per_second": 5.811,
+      "eval_loss": 1.4932821989059448,
+      "eval_runtime": 6.3196,
+      "eval_samples_per_second": 46.522,
+      "eval_steps_per_second": 5.855,
       "step": 10
     },
     {
       "epoch": 9.03,
-      "eval_loss": 1.475648283958435,
-      "eval_runtime": 6.352,
-      "eval_samples_per_second": 46.285,
-      "eval_steps_per_second": 5.825,
+      "eval_loss": 1.4755805730819702,
+      "eval_runtime": 6.3502,
+      "eval_samples_per_second": 46.298,
+      "eval_steps_per_second": 5.827,
       "step": 11
     },
     {
       "epoch": 9.03,
       "step": 11,
       "total_flos": 5.3091621472200294e+17,
-      "train_loss": 1.714235695925626,
-      "train_runtime": 4134.2039,
-      "train_samples_per_second": 14.259,
+      "train_loss": 1.7142409628087825,
+      "train_runtime": 4135.8024,
+      "train_samples_per_second": 14.254,
       "train_steps_per_second": 0.027
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06d3d120ec42d827abe951b3cebbab8012a29481eaf1f3e3baf37f66d3ab56b7
+oid sha256:82f9cbd5ae020148e5023e8a94238eb6d948e2533fd584833fd423ac94f00345
 size 4664