Training in progress, step 500

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<pad>": 50258,
+  "<|startoftext|>": 50257,
+  "<|summarize|>": 50259
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50257,
+  "dtype": "float32",
+  "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": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "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
+    }
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50260
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50257,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92be64b1ef888804108e9c0328645bf582fab74022c7fb979be82d2f587ece47
+size 497783424

runs/Dec23_06-34-28_3cfe822c60b1/events.out.tfevents.1766471672.3cfe822c60b1.55.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47a903688bf692107409018fcfd2fd528b87576ec5aed1c9521f7ca125085c3
+size 5479

runs/Dec23_06-34-28_3cfe822c60b1/events.out.tfevents.1766494438.3cfe822c60b1.55.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e053c4576ad43b6e404c9a9f598ec27f7d634074ccc9fb45372733a6d569e2b2
+size 5454

runs/Dec23_13-04-49_3cfe822c60b1/events.out.tfevents.1766495095.3cfe822c60b1.55.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c431a2812ea39459dbdbf12be93455133ae7205d03fad0df3266679a0fbc9503
+size 5454

runs/Dec23_13-14-14_3cfe822c60b1/events.out.tfevents.1766495658.3cfe822c60b1.55.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35abb23b8a1ebebc81e6e0c00435ee3612bbba98fe3d0d4cd4193af405787198
+size 5454

runs/Dec23_13-15-13_3cfe822c60b1/events.out.tfevents.1766495720.3cfe822c60b1.55.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305c923acddb56c2e1e5a63c778593f6ec9ac32b9bef9d283597b4a3f9de5b11
+size 5479

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|summarize|>"
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50259": {
+      "content": "<|summarize|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|summarize|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee93c85938849fcfd24c229fd19c8bd5fc2e38561a741c0fa11e042dde3d4388
+size 5841