update model to ckpoint 3500

config.json

@@ -75,7 +75,7 @@
   },
   "tokenizer_class": "GPT2Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.21.2",
+  "transformers_version": "4.23.1",
   "use_cache": true,
   "vocab_size": 50257,
   "window_size": 256

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b232536af60507a394a732d320251cec01cebde2695b4d7ffeb75813013c6d
+oid sha256:4b3977a25a38d65c8381c63b8d549e59b819ec5bec1ed892867ce834555f874b
 size 9996970517

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60e8f61f907fc510242f5d47d1d607f83ea067904be0cd552f5189458b28070
+oid sha256:547fc177de3ba4ba268864c8128f9b4e05b1196e8a8bdaa44b45d6450e33611f
 size 742637631

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe4f7564f56a1ffa25a5c606d62664ceee4525fae7d67da25c48a37122eeeaf
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c8325f2941fb440a70e076145fff814af3bb9cb14c7d849f105ea262a5d6cf
+size 623

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7115339655820856,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.872915819438796e-06,
+      "loss": 3.1058,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.745831638877592e-06,
+      "loss": 3.0496,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.618747458316389e-06,
+      "loss": 3.0295,
+      "step": 1500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.491663277755185e-06,
+      "loss": 3.0068,
+      "step": 2000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.364579097193982e-06,
+      "loss": 2.9939,
+      "step": 2500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.237494916632778e-06,
+      "loss": 2.9796,
+      "step": 3000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.110410736071574e-06,
+      "loss": 2.977,
+      "step": 3500
+    }
+  ],
+  "max_steps": 19672,
+  "num_train_epochs": 4,
+  "total_flos": 2.1653725642752e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f78c8e67b3b7439ebcbe37dd17e41efe401bc444f002524a38db641fee291db5
-size 3311
+oid sha256:dc7808aebc878ce0f5e2093106139820e524f70e98790daf3c56abdbf1b0d8b6
+size 3375