Training in progress, step 40, checkpoint

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b907ba68261a733495a2decc931e4839e4907e6e52a97528b167a0a5a0ebd392
+oid sha256:681a208ef373053824021017b27708b23a588064e7003361364981ae70fa09cc
 size 4943178720

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf95b6219ea0c58409934588c2a66dc9c8321e127f35cf06df02c3acd88afc0e
+oid sha256:b3b773cef476437d526f7c17ec504cec44088b25420cde09e2273e473904f2e5
 size 4999819336

last-checkpoint/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76053a4a789be6b616ea43ab19cf1a53cfc29041a95eebbb8627e860734e1f52
+oid sha256:64e632ea54fafa03fa867d58aa1615bc784b20c0be1d236538bd55ebff650daa
 size 4540532728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22617f0b8389a6d4fa5a7e5e259a2a6e9ac793955c55c10b715b8d4f9596c212
+oid sha256:fe9951bfdfc286622c846de580f1aec65c1e44f78aa8094a852f758e9ef7b3ca
 size 14710155092

last-checkpoint/trainer_state.json

@@ -11,37 +11,37 @@
     {
       "epoch": 0.019230769230769232,
       "eval_loss": 1.8673125505447388,
-      "eval_runtime": 15.1011,
-      "eval_samples_per_second": 99.397,
-      "eval_steps_per_second": 6.225,
+      "eval_runtime": 14.8131,
+      "eval_samples_per_second": 101.329,
+      "eval_steps_per_second": 6.346,
       "step": 1
     },
     {
       "epoch": 0.19230769230769232,
-      "grad_norm": 36.0,
+      "grad_norm": 29.625,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 2.4526,
+      "loss": 2.4447,
       "step": 10
     },
     {
       "epoch": 0.38461538461538464,
-      "grad_norm": 231.0,
+      "grad_norm": 246.0,
       "learning_rate": 0.00013333333333333334,
-      "loss": 2.8068,
+      "loss": 3.8293,
       "step": 20
     },
     {
       "epoch": 0.5769230769230769,
-      "grad_norm": 105.0,
+      "grad_norm": 96.5,
       "learning_rate": 0.0002,
-      "loss": 6.5887,
+      "loss": 6.931,
       "step": 30
     },
     {
       "epoch": 0.7692307692307693,
-      "grad_norm": 67.0,
+      "grad_norm": 804.0,
       "learning_rate": 0.00019984815164333163,
-      "loss": 9.409,
+      "loss": 11.6713,
       "step": 40
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b41a9fb463c0db3738bb35eb54493dd7cd16792db1e56184a9c9b31d58bd7b14
+oid sha256:0acef938a7d9ffe7b10254d7cbe4256ddc2dc212f47d8b0cfb76c4ad76b57933
 size 6776