Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "uer/gpt2-chinese-cluecorpussmall",
+  "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,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "output_past": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "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": 320
+    }
+  },
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12345051e4e45302dc6b15cdb8d58a67c0ec1ce6c6a97fcf7385ac678f844aff
+size 420912233

runs/Feb04_16-44-14_ZkkzWz/1675529632.85752/events.out.tfevents.1675529632.ZkkzWz.458.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dfc0a469a069020023c2583191dac1e0fd62d43e7d4ddca0b4c2c8c185b3522
+size 5715

runs/Feb04_16-44-14_ZkkzWz/events.out.tfevents.1675529632.ZkkzWz.458.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60783b1ca153ad75a94ac112be591d8d66054082696347958371174ade3db936
+size 4381

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faaeb203fb1c9355c38323360631a5f485706e8490e18e0ac69f9fe07c6acad6
+size 3503