Model save

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/bootpin/huggingface/runs/ff380p97)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/bootpin/huggingface/runs/lg4lg76q)
 
 This model was trained with SFT.
 

all_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.7142857142857144,
     "total_flos": 1113549778714624.0,
     "train_loss": 19.26901610692342,
-    "train_runtime": 77.6776,
+    "train_runtime": 77.567,
     "train_samples": 460341,
-    "train_samples_per_second": 1.442,
+    "train_samples_per_second": 1.444,
     "train_steps_per_second": 0.077
 }

runs/Apr03_05-08-32_afc374fd6ab1/events.out.tfevents.1743656920.afc374fd6ab1.9900.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7b9a0e5cb79be57a28cb69d61c1fa76f9cbe0886caedbb850997caf72b7bf0
+size 7065

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.7142857142857144,
     "total_flos": 1113549778714624.0,
     "train_loss": 19.26901610692342,
-    "train_runtime": 77.6776,
+    "train_runtime": 77.567,
     "train_samples": 460341,
-    "train_samples_per_second": 1.442,
+    "train_samples_per_second": 1.444,
     "train_steps_per_second": 0.077
 }

trainer_state.json

@@ -18,9 +18,9 @@
     {
       "epoch": 0.8571428571428571,
       "eval_loss": 17.570310592651367,
-      "eval_runtime": 0.39,
-      "eval_samples_per_second": 5.128,
-      "eval_steps_per_second": 2.564,
+      "eval_runtime": 0.3894,
+      "eval_samples_per_second": 5.136,
+      "eval_steps_per_second": 2.568,
       "step": 3
     },
     {
@@ -33,9 +33,9 @@
     {
       "epoch": 1.7142857142857144,
       "eval_loss": 13.667020797729492,
-      "eval_runtime": 0.3966,
-      "eval_samples_per_second": 5.043,
-      "eval_steps_per_second": 2.522,
+      "eval_runtime": 0.4014,
+      "eval_samples_per_second": 4.983,
+      "eval_steps_per_second": 2.491,
       "step": 6
     },
     {
@@ -43,8 +43,8 @@
       "step": 6,
       "total_flos": 1113549778714624.0,
       "train_loss": 19.26901610692342,
-      "train_runtime": 77.6776,
-      "train_samples_per_second": 1.442,
+      "train_runtime": 77.567,
+      "train_samples_per_second": 1.444,
       "train_steps_per_second": 0.077
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f22119c867c9141f858801ffc816aee08d01b4f35b0812e21f6d9367d4093e5
+oid sha256:faa19ffaf1e2ddc9132de277ead37eb9ac3104cc1baaf3c94cbde2c2fa8781b7
 size 7160