End of training

.gitignore

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

config.json

@@ -0,0 +1,41 @@
+{
+ "_name_or_path": "jed351/gpt2-tiny-zh-hk",
+ "activation_function": "gelu_new",
+ "architectures": [
+ "GPT2LMHeadModel"
+ ],
+ "attn_pdrop": 0.1,
+ "bos_token_id": 101,
+ "embd_pdrop": 0.1,
+ "eos_token_id": 102,
+ "gradient_checkpointing": false,
+ "initializer_range": 0.02,
+ "layer_norm_epsilon": 1e-05,
+ "model_type": "gpt2",
+ "n_ctx": 1024,
+ "n_embd": 312,
+ "n_head": 12,
+ "n_inner": null,
+ "n_layer": 4,
+ "n_positions": 1024,
+ "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": 50
+ }
+ },
+ "tokenizer_class": "BertTokenizerFast",
+ "torch_dtype": "float32",
+ "transformers_version": "4.26.0",
+ "use_cache": true,
+ "vocab_size": 21253
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 101,
+ "eos_token_id": 102,
+ "transformers_version": "4.26.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f123b3185eabb3b15f0fa0a576e5ac5fbb69ecc18d8cfef40919db469883fce
+size 50771749

runs/Jan27_15-18-48_5da115df40b1/1674832742.7173645/events.out.tfevents.1674832742.5da115df40b1.552.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d5c38e1984e3f9ba21d51c4ac290079e776d4e1beda8e6f4821e7f7facbf94b
+size 5677

runs/Jan27_15-18-48_5da115df40b1/events.out.tfevents.1674832742.5da115df40b1.552.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0cbfb236ddc5858aa26744ce9260deb06f9aa0c89ecc0892a0790348a244709
+size 8494

runs/Jan27_15-18-48_5da115df40b1/events.out.tfevents.1674835201.5da115df40b1.552.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998838b7693a9d2ff8841a1bc21b8ae129d7680c745ef1e1b9362bc347310d45
+size 311

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72fa1131049ba7baa363ac0e063a87f1055da9e93f2dfc4251fe04425500d689
+size 3515