Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2c85a787e7a40a6739570825d5dac5d0da5dd949c5d42eed6ecb390485c0387
+oid sha256:ad376b0758013829099b368873eb5fd6337f67cf5e848a25b2b474b7983d6801
 size 2384234968

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac84b9582ff7b04d97c3564b5a701e65ff92f062e806c2f383748618a2ede63d
+oid sha256:a42c8ce6ec1d87a350b8754186e37b669ffc453a2365356e778b02dc08863a60
 size 4768662910

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49b78bc9f0d7e56e66d9414db603a96557a219cd78b5a76e7ebc4ea10e197295
+oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
 size 14244

trainer_state.json

@@ -11,109 +11,109 @@
   "log_history": [
     {
       "epoch": 0.14814814814814814,
-      "grad_norm": 5.238080978393555,
+      "grad_norm": 4.711470127105713,
       "learning_rate": 3.96e-06,
-      "loss": 1.4747,
+      "loss": 1.4337,
       "step": 100
     },
     {
       "epoch": 0.2962962962962963,
-      "grad_norm": 5.111464023590088,
+      "grad_norm": 4.751404285430908,
       "learning_rate": 7.960000000000002e-06,
-      "loss": 1.2339,
+      "loss": 1.2046,
       "step": 200
     },
     {
       "epoch": 0.4444444444444444,
-      "grad_norm": 4.6231770515441895,
+      "grad_norm": 4.166985988616943,
       "learning_rate": 1.196e-05,
-      "loss": 1.3136,
+      "loss": 1.2721,
       "step": 300
     },
     {
       "epoch": 0.5925925925925926,
-      "grad_norm": 4.638155460357666,
+      "grad_norm": 4.238899230957031,
       "learning_rate": 1.5960000000000003e-05,
-      "loss": 1.3179,
+      "loss": 1.2809,
       "step": 400
     },
     {
       "epoch": 0.7407407407407407,
-      "grad_norm": 4.396394729614258,
+      "grad_norm": 4.066563606262207,
       "learning_rate": 1.9960000000000002e-05,
-      "loss": 1.3025,
+      "loss": 1.2463,
       "step": 500
     },
     {
       "epoch": 0.8888888888888888,
-      "grad_norm": 2.8801891803741455,
+      "grad_norm": 3.029653787612915,
       "learning_rate": 1.87016393442623e-05,
-      "loss": 1.2734,
+      "loss": 1.2347,
       "step": 600
     },
     {
       "epoch": 1.0,
-      "eval_loss": 1.3948965072631836,
-      "eval_runtime": 179.2505,
-      "eval_samples_per_second": 3.347,
-      "eval_steps_per_second": 0.418,
+      "eval_loss": 1.3202142715454102,
+      "eval_runtime": 179.8462,
+      "eval_samples_per_second": 3.336,
+      "eval_steps_per_second": 0.417,
       "step": 675
     },
     {
       "epoch": 1.037037037037037,
-      "grad_norm": 4.732747554779053,
+      "grad_norm": 3.9755260944366455,
       "learning_rate": 1.7390163934426233e-05,
-      "loss": 1.2474,
+      "loss": 1.2086,
       "step": 700
     },
     {
       "epoch": 1.1851851851851851,
-      "grad_norm": 4.509610652923584,
+      "grad_norm": 4.08528995513916,
       "learning_rate": 1.6078688524590164e-05,
-      "loss": 1.0051,
+      "loss": 0.9801,
       "step": 800
     },
     {
       "epoch": 1.3333333333333333,
-      "grad_norm": 4.83737325668335,
+      "grad_norm": 4.117591381072998,
       "learning_rate": 1.47672131147541e-05,
-      "loss": 1.0629,
+      "loss": 1.0272,
       "step": 900
     },
     {
       "epoch": 1.4814814814814814,
-      "grad_norm": 5.032131671905518,
+      "grad_norm": 4.108471870422363,
       "learning_rate": 1.3455737704918036e-05,
-      "loss": 1.0543,
+      "loss": 1.0307,
       "step": 1000
     },
     {
       "epoch": 1.6296296296296298,
-      "grad_norm": 5.264540672302246,
+      "grad_norm": 4.6597161293029785,
       "learning_rate": 1.2144262295081968e-05,
-      "loss": 1.0929,
+      "loss": 1.0432,
       "step": 1100
     },
     {
       "epoch": 1.7777777777777777,
-      "grad_norm": 5.0603742599487305,
+      "grad_norm": 4.704660892486572,
       "learning_rate": 1.0832786885245903e-05,
-      "loss": 1.0502,
+      "loss": 1.0158,
       "step": 1200
     },
     {
       "epoch": 1.925925925925926,
-      "grad_norm": 5.43220853805542,
+      "grad_norm": 5.08992338180542,
       "learning_rate": 9.521311475409837e-06,
-      "loss": 1.0456,
+      "loss": 1.0238,
       "step": 1300
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.391052484512329,
-      "eval_runtime": 179.1632,
-      "eval_samples_per_second": 3.349,
-      "eval_steps_per_second": 0.419,
+      "eval_loss": 1.3168182373046875,
+      "eval_runtime": 179.8766,
+      "eval_samples_per_second": 3.336,
+      "eval_steps_per_second": 0.417,
       "step": 1350
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df73858dfad5311b29b2ac8a196a53ff9d692a10945cc7183c7586a3bd7becb3
+oid sha256:660b7cc6409839c5c5722f4d272744990cfd2568b71e11c72fb763d426f9a7fd
 size 5240