Add checkpoint-1140

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a3ac6cfb77b6885d1ce0460557befb05818b85183d5005c90ee8407210be90
+size 4943385103

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92918813fc54ac10b16289f9b1c0dbe940f02f764efd9ed6ece8456e5d30eb18
+size 1465

special_tokens_map.json

@@ -12,6 +12,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "pad_token": "<|end_of_text|>"
+  }
 }

tokenizer_config.json

@@ -2058,6 +2058,5 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|end_of_text|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

trainer_state.json

@@ -31,24 +31,6 @@
       "eval_samples_per_second": 86.231,
       "eval_steps_per_second": 10.836,
       "step": 1140
-    },
-    {
-      "epoch": 1.0,
-      "step": 1140,
-      "total_flos": 1.3626163133939712e+16,
-      "train_loss": 2.4788927044784814,
-      "train_runtime": 196.8793,
-      "train_samples_per_second": 23.151,
-      "train_steps_per_second": 5.79
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.5619722863264766,
-      "eval_loss": 2.4340596199035645,
-      "eval_runtime": 13.1565,
-      "eval_samples_per_second": 86.497,
-      "eval_steps_per_second": 10.869,
-      "step": 1140
     }
   ],
   "logging_steps": 500,