Upload folder using huggingface_hub

checkpoint-1050/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2efb683d1596318bd5d460ab10fe133d2d265accfad9800db712dc09aa179f60
+oid sha256:98fd5044314627e437dc2b7cdda294e48e3c4963a768af47d181b6e425a41dcc
 size 402763

checkpoint-1050/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d22db40534b825bfb6e2e3a1be52f795fedaf4e7a7685d37a2181fdd6d4a304d
+oid sha256:cd8a29d89acc6af99d387344d32386020a6920163d2db254b78b02b7a902ed79
 size 62314258

checkpoint-1050/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321ac564783ecdca53102cf6b6549daa0a313bec83709a52ea07029f85b930f5
+oid sha256:879d73f7b526f4773e67571faa23d0381f777afe5786d66898ad1914dcb91306
 size 14645

checkpoint-1050/tokenizer_config.json

@@ -935,6 +935,6 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
-  "tokenizer_class": "T5Tokenizer",
+  "tokenizer_class": "T5TokenizerFast",
   "unk_token": "<unk>"
 }

checkpoint-1050/trainer_state.json

@@ -11,46 +11,46 @@
   "log_history": [
     {
       "epoch": 0.05752416014726185,
-      "grad_norm": 0.5827537775039673,
+      "grad_norm": 0.6941567659378052,
       "learning_rate": 0.00016513000460193283,
-      "loss": 5.0544,
+      "loss": 3.417,
       "step": 250
     },
     {
       "epoch": 0.1150483202945237,
-      "grad_norm": 0.5847251415252686,
+      "grad_norm": 0.739392101764679,
       "learning_rate": 0.00016024045098941557,
-      "loss": 4.2362,
+      "loss": 3.3994,
       "step": 500
     },
     {
       "epoch": 0.1150483202945237,
-      "eval_loss": 3.4322922229766846,
-      "eval_runtime": 35.9031,
-      "eval_samples_per_second": 109.74,
-      "eval_steps_per_second": 3.231,
+      "eval_loss": 2.832693576812744,
+      "eval_runtime": 34.8026,
+      "eval_samples_per_second": 113.21,
+      "eval_steps_per_second": 3.333,
       "step": 500
     },
     {
       "epoch": 0.17257248044178555,
-      "grad_norm": 0.6557937264442444,
+      "grad_norm": 0.7630258202552795,
       "learning_rate": 0.0001553508973768983,
-      "loss": 4.0566,
+      "loss": 3.3881,
       "step": 750
     },
     {
       "epoch": 0.2300966405890474,
-      "grad_norm": 0.6734243631362915,
+      "grad_norm": 0.745369553565979,
       "learning_rate": 0.00015046134376438104,
-      "loss": 3.9349,
+      "loss": 3.3655,
       "step": 1000
     },
     {
       "epoch": 0.2300966405890474,
-      "eval_loss": 3.1976470947265625,
-      "eval_runtime": 35.3562,
-      "eval_samples_per_second": 111.437,
-      "eval_steps_per_second": 3.281,
+      "eval_loss": 2.821577548980713,
+      "eval_runtime": 34.6743,
+      "eval_samples_per_second": 113.629,
+      "eval_steps_per_second": 3.345,
       "step": 1000
     }
   ],