Upload folder using huggingface_hub

checkpoint-1400/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67267547f1d2b6c7640f9b9a6d678612bb187e133080a876f715c2e22b848454
+oid sha256:7471e7503097821eb7cedd03029765d8c6d340f64a530fcacf1b70d8280cc43e
 size 402763

checkpoint-1400/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fe14eea3a51c61a652dc1a0c3a843c1a5310626d7b42f10aad4470d4d42bc84
+oid sha256:e7f4a4bed170f65dac3b0aeae3d2a5f812fa425e4f7fc45556f7fdc55987af2d
 size 62314258

checkpoint-1400/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cdf1a1a5aa1d6ce60e2b75c3ae17e1a0d7a15339cd844971d4798625dd644a2
+oid sha256:543a6952dfe815e824a9d4b10abd2434f4f2a650c28d1aabc5602d81b60d9a50
 size 14645

checkpoint-1400/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-1400/trainer_state.json

@@ -11,53 +11,53 @@
   "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
     },
     {
       "epoch": 0.28762080073630925,
-      "grad_norm": 0.6826881766319275,
+      "grad_norm": 0.7992149591445923,
       "learning_rate": 0.0001455717901518638,
-      "loss": 3.856,
+      "loss": 3.3575,
       "step": 1250
     }
   ],