upload model

config.json

@@ -0,0 +1,40 @@
+{
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "vocab_size": 50257
+}

log_history.json

@@ -0,0 +1,65 @@
+[
+  {
+    "loss": 1.6234498291015624,
+    "learning_rate": 4.4444444444444447e-05,
+    "epoch": 0.2222222222222222,
+    "total_flos": 9511281623040000,
+    "step": 500
+  },
+  {
+    "loss": 1.4528057861328125,
+    "learning_rate": 3.888888888888889e-05,
+    "epoch": 0.4444444444444444,
+    "total_flos": 19022563246080000,
+    "step": 1000
+  },
+  {
+    "loss": 1.400372802734375,
+    "learning_rate": 3.3333333333333335e-05,
+    "epoch": 0.6666666666666666,
+    "total_flos": 28533844869120000,
+    "step": 1500
+  },
+  {
+    "loss": 1.364806640625,
+    "learning_rate": 2.777777777777778e-05,
+    "epoch": 0.8888888888888888,
+    "total_flos": 38045126492160000,
+    "step": 2000
+  },
+  {
+    "loss": 1.25629931640625,
+    "learning_rate": 2.2222222222222223e-05,
+    "epoch": 1.1111111111111112,
+    "total_flos": 47556408115200000,
+    "step": 2500
+  },
+  {
+    "loss": 1.16014453125,
+    "learning_rate": 1.6666666666666667e-05,
+    "epoch": 1.3333333333333333,
+    "total_flos": 57067689738240000,
+    "step": 3000
+  },
+  {
+    "loss": 1.15758203125,
+    "learning_rate": 1.1111111111111112e-05,
+    "epoch": 1.5555555555555556,
+    "total_flos": 66578971361280000,
+    "step": 3500
+  },
+  {
+    "loss": 1.133671875,
+    "learning_rate": 5.555555555555556e-06,
+    "epoch": 1.7777777777777777,
+    "total_flos": 76090252984320000,
+    "step": 4000
+  },
+  {
+    "loss": 1.144353515625,
+    "learning_rate": 0.0,
+    "epoch": 2.0,
+    "total_flos": 85601534607360000,
+    "step": 4500
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:192e53af10e5c981cec5a9fa42b247f5f81475b43159a7b6e12e326b993a0c36
+size 3134064907

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:331287a9d88ccf6fa7f6d78024b658b4102684f11fdc6c9af0758afbb8a1a169
+size 1839