Training in progress, step 500

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 50258,
+  "<|im_start|>": 50257
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "openai-community/gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50257,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50258,
+  "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,
+  "pad_token_id": 50258,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 50259
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b71366fc1b2c3e7d5418b42967e2e63db9cc6e392d7a6e9f6b27d5996ea5d4
+size 497780352

runs/Sep02_02-49-45_057cf5e5754d/events.out.tfevents.1725245405.057cf5e5754d.14781.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:969f3d83ee590e88b1f63536db63d1a5ecc26fddcf8d83bc8b6c251f646ace78
+size 45268

runs/Sep02_03-15-07_057cf5e5754d/events.out.tfevents.1725246912.057cf5e5754d.14781.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1185f02da1db6e7e3b8369e87ab325a6645f0caf6b057aa5ce6d701292d258ab
+size 7617

runs/Sep02_03-30-31_057cf5e5754d/events.out.tfevents.1725247835.057cf5e5754d.33715.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a74fb71a32a007df80a936fca96d810d1f0d1bceeae131986e42d1e5bdd354
+size 6956

runs/Sep02_03-59-55_057cf5e5754d/events.out.tfevents.1725249627.057cf5e5754d.40651.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8711dd90e379d524ee73a13657e6c4260312cbb652f866924529faed55f1d2
+size 5689

runs/Sep02_04-01-25_057cf5e5754d/events.out.tfevents.1725249697.057cf5e5754d.40651.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44f9d518d8c38335838e54ab98b4f46c461dae19578251213719b1a37ad93023
+size 7167

runs/Sep02_04-13-13_057cf5e5754d/events.out.tfevents.1725250416.057cf5e5754d.46154.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48047cc008118a1b72ce000c6bd0b2e34daa6bbbffeddabe9ebb84590caa0d94
+size 6527

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 1024,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f301691bb3017f30fb5540cfddb9f5854e32f3e46d23f02c154dcd5715f8f36b
+size 5432