Upload 8 files

uploaded question generation model

config.json

@@ -0,0 +1,35 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "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
+    }
+  },
+  "total_flos": 48939573033566208,
+  "vocab_size": 50257
+}

log_history.json

@@ -0,0 +1,79 @@
+[
+  {
+    "loss": 1.9278494873046874,
+    "learning_rate": 4.554605380367005e-05,
+    "epoch": 0.2672367717797969,
+    "total_flos": 4360067088384000,
+    "step": 1000
+  },
+  {
+    "loss": 1.8067623291015624,
+    "learning_rate": 4.109210760734011e-05,
+    "epoch": 0.5344735435595938,
+    "total_flos": 8720134176768000,
+    "step": 2000
+  },
+  {
+    "loss": 1.77223828125,
+    "learning_rate": 3.663816141101016e-05,
+    "epoch": 0.8017103153393907,
+    "total_flos": 13080201265152000,
+    "step": 3000
+  },
+  {
+    "loss": 1.6007529296875,
+    "learning_rate": 3.2184215214680206e-05,
+    "epoch": 1.0689470871191875,
+    "total_flos": 17438088319991808,
+    "step": 4000
+  },
+  {
+    "loss": 1.21124267578125,
+    "learning_rate": 2.7730269018350257e-05,
+    "epoch": 1.3361838588989845,
+    "total_flos": 21798155408375808,
+    "step": 5000
+  },
+  {
+    "loss": 1.20527734375,
+    "learning_rate": 2.327632282202031e-05,
+    "epoch": 1.6034206306787815,
+    "total_flos": 26158222496759808,
+    "step": 6000
+  },
+  {
+    "loss": 1.1963974609375,
+    "learning_rate": 1.8822376625690362e-05,
+    "epoch": 1.8706574024585783,
+    "total_flos": 30518289585143808,
+    "step": 7000
+  },
+  {
+    "loss": 1.0101669921875,
+    "learning_rate": 1.4368430429360413e-05,
+    "epoch": 2.137894174238375,
+    "total_flos": 34876176639983616,
+    "step": 8000
+  },
+  {
+    "loss": 0.8346533203125,
+    "learning_rate": 9.914484233030466e-06,
+    "epoch": 2.405130946018172,
+    "total_flos": 39236243728367616,
+    "step": 9000
+  },
+  {
+    "loss": 0.820884765625,
+    "learning_rate": 5.4605380367005166e-06,
+    "epoch": 2.672367717797969,
+    "total_flos": 43596310816751616,
+    "step": 10000
+  },
+  {
+    "loss": 0.8244423828125,
+    "learning_rate": 1.0065918403705683e-06,
+    "epoch": 2.939604489577766,
+    "total_flos": 47956377905135616,
+    "step": 11000
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812604d8535b70584bb530a4a7365068bba2abf9705c1ed38757bb876c2e7fae
+size 1444531445

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0704aec2a78e868c904c4cb3e8727b2376af6371744f2b776628e2c6cdb3423c
+size 1333