Checkpoint @ step 10

checkpoints/checkpoint-10/model-00001-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a96bbc6eb1f3cf571740da941fed26e0a36bec28e1698a387fd2fa9cd5df8d9
+oid sha256:f27bba0d55f69f66eb1c562d7c21485447b04dbba720525ad5c54d5e4daf5ed6
 size 4833872608

checkpoints/checkpoint-10/model-00007-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e568c7dfef93fee0d2f5c341d146abecb756e18e013a468bd8b1cb72d0078ed7
+oid sha256:e72cb69ec6cb23e34cd034fbea08a2c92a0715064504809b2ba76f2ccb0a9a15
 size 3793700424

checkpoints/checkpoint-10/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c28a0e5d36d3f2a5e1bd801734be1cd4ec748c5cdcb18c7d2984cf5bfb9c8e8
+oid sha256:926b5e14b45db2ea8bb18e3879fd5f166f245be1ec70771f6a071e88fbc53fe4
 size 10745286048

checkpoints/checkpoint-10/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8d9fca1791d9576edc9f09a6774b69a0c5146425d721bccaa7a22726c18aff2
+oid sha256:9fcc894b6cda7763e969c5c40973539f655ffeba08490acac5b11be2290b176e
 size 1000

checkpoints/checkpoint-10/trainer_state.json

@@ -32,63 +32,63 @@
     {
       "epoch": 0.00012921009561547075,
       "grad_norm": 2216.217529296875,
-      "learning_rate": 0.0007588285868185887,
+      "learning_rate": 0.0007414014761921584,
       "loss": 9.8274,
       "step": 4
     },
     {
       "epoch": 0.00016151261951933844,
       "grad_norm": NaN,
-      "learning_rate": 0.0007588285868185887,
+      "learning_rate": 0.0007414014761921584,
       "loss": 4.9252,
       "step": 5
     },
     {
       "epoch": 0.00019381514342320613,
       "grad_norm": 287.1143798828125,
-      "learning_rate": 0.0007553215694261524,
+      "learning_rate": 0.0006874264578624801,
       "loss": 5.7305,
       "step": 6
     },
     {
       "epoch": 0.00022611766732707383,
-      "grad_norm": 39.2633056640625,
-      "learning_rate": 0.0007495005697511171,
-      "loss": 3.5258,
+      "grad_norm": 46.88080596923828,
+      "learning_rate": 0.0006033583958711398,
+      "loss": 3.511,
       "step": 7
     },
     {
       "epoch": 0.0002584201912309415,
-      "grad_norm": 277.8404846191406,
-      "learning_rate": 0.0007414014761921584,
-      "loss": 3.0963,
+      "grad_norm": 289.3145751953125,
+      "learning_rate": 0.0004974264578624801,
+      "loss": 3.0061,
       "step": 8
     },
     {
       "epoch": 0.0002907227151348092,
-      "grad_norm": 110.1237564086914,
-      "learning_rate": 0.000731074222354289,
-      "loss": 2.8809,
+      "grad_norm": 84.34556579589844,
+      "learning_rate": 0.00038,
+      "loss": 2.6551,
       "step": 9
     },
     {
       "epoch": 0.0003230252390386769,
-      "grad_norm": 59.39462661743164,
-      "learning_rate": 0.0007185824791915798,
-      "loss": 3.2668,
+      "grad_norm": 21.252391815185547,
+      "learning_rate": 0.00026257354213752004,
+      "loss": 3.1171,
       "step": 10
     },
     {
       "epoch": 0.0003230252390386769,
-      "eval_loss": 2.828110456466675,
-      "eval_runtime": 100.1319,
-      "eval_samples_per_second": 8.239,
-      "eval_steps_per_second": 1.039,
+      "eval_loss": 2.541130542755127,
+      "eval_runtime": 100.2286,
+      "eval_samples_per_second": 8.231,
+      "eval_steps_per_second": 1.038,
       "step": 10
     }
   ],
   "logging_steps": 1,
-  "max_steps": 40,
+  "max_steps": 10,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
@@ -99,7 +99,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }

checkpoints/checkpoint-10/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:463cb4a7907194af729afa3f301bd51a1435ad5d1910c75ddbd3e99796f5391a
+oid sha256:027ac376efe383ae62dd673f4d5276a475c946cee886227f5ba835bdff180ab2
 size 5304