update finetune model

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "/data/home/hujie/workspace/hujie_project/progen/progen2/checkpoints/progen2-base",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "ProGenForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "progen",
+  "n_ctx": 2048,
+  "n_embd": 1536,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 27,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 48,
+  "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,
+      "temperature": 1.0
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 32
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db4ff8a5a778d23bb97367571c6b9eb17189938f38df135a0c94fe00fe25651
+size 6118617395

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b9a57090efa7fa2ef7877111db2395ad52eea5d505c9bddbf2c2184aa9e511
+size 3172548507

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefe9d404d10d02864bf3e3d7f2e1d9843a9e8b609ad32fe048d5f2e962b1ad1
+size 21579

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86df40b42690687e8d9b4a801e875079a578ff8d4f1ed7161c32d326cbe9258
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d74d510ce9a84ab31ccc5a93fd713c1c002dbf9dfe5088ff415b8172062acf
+size 623

tokenizer.json

@@ -0,0 +1,91 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "special": true,
+      "content": "<|pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 1,
+      "special": true,
+      "content": "<|bos|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    },
+    {
+      "id": 2,
+      "special": true,
+      "content": "<|eos|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true
+  },
+  "post_processor": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "vocab": {
+      "<|pad|>": 0,
+      "<|bos|>": 1,
+      "<|eos|>": 2,
+      "1": 3,
+      "2": 4,
+      "A": 5,
+      "B": 6,
+      "C": 7,
+      "D": 8,
+      "E": 9,
+      "F": 10,
+      "G": 11,
+      "H": 12,
+      "I": 13,
+      "K": 14,
+      "L": 15,
+      "M": 16,
+      "N": 17,
+      "O": 18,
+      "P": 19,
+      "Q": 20,
+      "R": 21,
+      "S": 22,
+      "T": 23,
+      "U": 24,
+      "V": 25,
+      "W": 26,
+      "X": 27,
+      "Y": 28,
+      "Z": 29
+    },
+    "merges": []
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc85a4f7a8665fc94131f3123c6e8f80a46ae5fd45e2b5da0e654dca160cdc76
+size 3439