Training in progress, step 500

.ipynb_checkpoints/config-checkpoint.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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:033666951259fd334f0a4bc234a6930606cb06db96215cee3bd0f492482c2cf8
+oid sha256:7a70c63ef4cfbcd87896fef1e8f9987284c9ccbc3af344a68c41a99d75453b8a
 size 420912233

runs/Feb06_08-10-02_PYAOGW/1675671011.8129454/events.out.tfevents.1675671011.PYAOGW.11444.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c7ca9cab3066ea761fd4e4f11c0a54662c6f93fbfb4370f4f3ca3333c1af54
+size 5715

runs/Feb06_08-10-02_PYAOGW/events.out.tfevents.1675671011.PYAOGW.11444.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f8db2d9253c156026ac7de542408b970ac6f9c376c2e88549136959b214cd7
+size 4381

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f7c482d865a1624342d5ebd65e6bcb7275a459034f24826e8c1143365e9dda5
+oid sha256:4e17330ccf3dbaeee3610639eddc19285cd13f4d014e6da0c1696140dead245c
 size 3503