Training in progress, step 500

config.json

@@ -0,0 +1,39 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 128,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 0,
+  "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": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 50000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    0
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.57.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b92803334c888df91c260879d942ef96f6015e24df010625605318e4a48a33
+size 496984704

runs/Oct23_20-36-10_43fd9daf6d9e/events.out.tfevents.1761251840.43fd9daf6d9e.294.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc22d104b98e25a9f7e37dd071576b06ab705d55bed20e1de1a108fb4b2b3fb
+size 10438

runs/Oct23_20-38-57_43fd9daf6d9e/events.out.tfevents.1761251940.43fd9daf6d9e.294.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a041c35accb08d181eecf0856d03689cb89bdc5f11e70fc080492313adea6f
+size 5263

runs/Oct23_20-48-54_43fd9daf6d9e/events.out.tfevents.1761252538.43fd9daf6d9e.7219.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33bea2aee10ecf6a350c9d280033aea4cceb185f8ad9d32c459a5eaea97f6fb
+size 5263

runs/Oct23_20-49-23_43fd9daf6d9e/events.out.tfevents.1761252566.43fd9daf6d9e.7219.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bbe8c989c7fd3d3c91937868f140ac94240223d61f814e833896f725a5bcaa
+size 5263

runs/Oct23_20-51-08_43fd9daf6d9e/events.out.tfevents.1761252671.43fd9daf6d9e.7219.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32704e00c83d999543a5e5e059428d36fd8f66c3866234decf056fbc5ebfa391
+size 5259

runs/Oct23_20-51-37_43fd9daf6d9e/events.out.tfevents.1761252704.43fd9daf6d9e.7219.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112884f61fa2037289cf879274ab96acd462af961e039d27d64675fe91d46ced
+size 5741

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "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:aa20dc633cdcab2d6e5d708d31fb75f36d12bad249d010b6e52dc37e899e73ec
+size 5841