Training in progress, step 125

config.json

@@ -0,0 +1,41 @@
+{
+ "_name_or_path": "gpt2-medium",
+ "activation_function": "gelu_new",
+ "architectures": [
+ "GPT2LMHeadModel"
+ ],
+ "attn_pdrop": 0.1,
+ "bos_token_id": 50256,
+ "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": 1024,
+ "n_head": 16,
+ "n_inner": null,
+ "n_layer": 24,
+ "n_positions": 1024,
+ "n_special": 0,
+ "predict_special_tokens": true,
+ "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": "4.44.2",
+ "use_cache": true,
+ "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5753a8f8e5aae38780ba1b8feaef835a33e2bf036cb6011bd4d7c8dd52b1904
+size 1419322880

runs/Sep05_16-42-05_154f73f5ff3a/events.out.tfevents.1725554597.154f73f5ff3a.2528.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c89afcf554f3d7836a95f6389a16ab5832532bb20596590eefa038b22209b22
+size 5709

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 +1,20 @@
+{
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "50256": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|endoftext|>",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|endoftext|>",
+ "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 sha256:354a55a2ff558b24f9f78eb143100d06be0a82046d7a09dde8fe4fb68cf03faf
+size 5176