Training in progress, step 500

.gitignore

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

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "IDEA-CCNL/Wenzhong-GPT2-110M",
+  "activation_function": "gelu_fast",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "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,
+  "tokenizer_class": "GPT2TokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50258
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea569aa7c27a94afa2509340ebab964e23b21c8d1f3ba48f898db665e12a1aa8
+size 510401085

runs/May01_08-47-25_node13/1682930853.3170443/events.out.tfevents.1682930853.node13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d91559f279e2cbe966e1b55e1c1cae68d04761d79f3c42b0a7f6269df1e3384
+size 5603

runs/May01_08-47-25_node13/events.out.tfevents.1682930853.node13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73a5e58c224e10d582126fa8e71179f1030df88a8ca59bf3b81eb9606b2bcac
+size 4172

runs/May01_08-50-18_node13/1682931023.6832337/events.out.tfevents.1682931023.node13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70c19f1f363272770b289160495b7738d611a9d2feb13f76b6806f532aa9ea8
+size 5603

runs/May01_08-50-18_node13/events.out.tfevents.1682931023.node13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebb955edc812b0cf2962ffcb381d2d82c24d218fb9b309914950f2f8e5f2511
+size 4172

runs/May01_12-41-55_node13/1682944920.765208/events.out.tfevents.1682944920.node13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b52f199db2842989370e1e60ca9003ed5cadae3af525467f3bc3d8ac517a1bd
+size 5603

runs/May01_12-41-55_node13/events.out.tfevents.1682944920.node13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4740683686d1b09e753046dbd1eb01aaad3a7b3ccf2bd46015b09810c4d7e1d
+size 4172

runs/May01_15-10-20_node13/1682953825.8277748/events.out.tfevents.1682953825.node13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8366b6372a0f977a48065a974c629b447b19b6d9c75a63797af36e31123ef6b6
+size 5603

runs/May01_15-10-20_node13/events.out.tfevents.1682953825.node13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd99b2be241a4d7d5463b3eb7ad5264d2a21d2e788f2cd7a7c7f4b9e941f554
+size 4172

runs/May01_15-14-22_node13/1682954067.9161758/events.out.tfevents.1682954067.node13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d70adfbbd93a583500febfc367943f0a0fb369473ab02ef625f71a392cd11b1b
+size 5603

runs/May01_15-14-22_node13/events.out.tfevents.1682954067.node13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eac22c5bfba65b8cef8a56e07fcb05a73dee9ed737ad2df5caf5e25e3d80bdb
+size 4172

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394085eb8bbcb95faddad939ecad0528ea2408cb361f7b47a48cb0eaba8a0e0c
+size 3643