Training in progress, step 500

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "aubmindlab/aragpt2-base",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "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,
+  "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,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 5,
+      "repetition_penalty": 3.0,
+      "top_p": 0.95
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 64000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789006e0feeadfe21241a5aa18a6a7fb868c4c138e11edfa164c9725c3488296
+size 539992704

runs/Oct21_04-51-06_6cc911818caa/events.out.tfevents.1729486278.6cc911818caa.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d55294ad1a7dc933a2def20567c3b870c4a4510a0779688d9f136d2417443e2
+size 5313

runs/Oct21_04-55-50_6cc911818caa/events.out.tfevents.1729486553.6cc911818caa.30.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38dac8d645753a1d26c0eb5e0b120e8bc0fbc48ba7be5c933a738b9db90f8117
+size 4184

runs/Oct21_04-56-36_6cc911818caa/events.out.tfevents.1729486601.6cc911818caa.30.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab8df4f1157a6cd7ae14216267985164627d5e5d60e6e5c973007480dbc2ecb
+size 5524

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 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "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:c2019a7b60bb823b876d73ba135591db89ce29011d619ee572023be9f5ddb466
+size 5176