Upload 13 files

dewd/checkpoint-1101/config.json

@@ -0,0 +1,38 @@
+{
+  "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": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

dewd/checkpoint-1101/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.51.3"
+}

dewd/checkpoint-1101/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f4bb10d5ea25e776b99bb7452e8a0127a61e02dd431d89403472b188a0e138f
+size 3096165928

dewd/checkpoint-1101/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a593c88c9b552098f1ebdfb320342fe91e2d6ee92cd4b614e64cc1221d335e
+size 1897646694

dewd/checkpoint-1101/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b3ad05688fc7a448a1148993cae0014349a0663375c1ce4d7461980db48b24
+size 14244

dewd/checkpoint-1101/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec528f16dc443253446fbf60ee5652ef3e5e5bfcbee302e982a2657ca342826
+size 1064

dewd/checkpoint-1101/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

dewd/checkpoint-1101/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "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": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

dewd/checkpoint-1101/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1101,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22706630336058128,
+      "grad_norm": 1.8386303186416626,
+      "learning_rate": 3.869209809264305e-05,
+      "loss": 1.3775,
+      "step": 250
+    },
+    {
+      "epoch": 0.45413260672116257,
+      "grad_norm": 1.83552885055542,
+      "learning_rate": 2.7338782924613986e-05,
+      "loss": 1.3109,
+      "step": 500
+    },
+    {
+      "epoch": 0.6811989100817438,
+      "grad_norm": 1.9307498931884766,
+      "learning_rate": 1.5985467756584924e-05,
+      "loss": 1.2712,
+      "step": 750
+    },
+    {
+      "epoch": 0.9082652134423251,
+      "grad_norm": 2.483839511871338,
+      "learning_rate": 4.6321525885558584e-06,
+      "loss": 1.2495,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 1101,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2395969014988800.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

dewd/checkpoint-1101/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6277986a0b803290bce05d19e7cae50d410970994873a18fd5c94019f592b3
+size 5240