Config files

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "/kaggle/input/ghazal-models1/results/checkpoint-6500",
+  "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": 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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.30.2"
+}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea437f76ed73066b02778f43976551be7fc01dd6494eb365c8d8d86cbb2f9d0c
+size 627

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.702182284980744,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.598844672657253e-05,
+      "loss": 2.1906,
+      "step": 500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.197689345314506e-05,
+      "loss": 2.1043,
+      "step": 1000
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 3.796534017971759e-05,
+      "loss": 2.0649,
+      "step": 1500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 3.395378690629012e-05,
+      "loss": 2.0252,
+      "step": 2000
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 2.9942233632862648e-05,
+      "loss": 2.0077,
+      "step": 2500
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 2.5930680359435173e-05,
+      "loss": 1.9865,
+      "step": 3000
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 2.1919127086007704e-05,
+      "loss": 1.9667,
+      "step": 3500
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 1.7907573812580232e-05,
+      "loss": 1.9602,
+      "step": 4000
+    },
+    {
+      "epoch": 5.78,
+      "learning_rate": 1.389602053915276e-05,
+      "loss": 1.9431,
+      "step": 4500
+    },
+    {
+      "epoch": 6.42,
+      "learning_rate": 9.884467265725289e-06,
+      "loss": 1.9363,
+      "step": 5000
+    },
+    {
+      "epoch": 7.06,
+      "learning_rate": 5.8729139922978185e-06,
+      "loss": 1.9312,
+      "step": 5500
+    },
+    {
+      "epoch": 7.7,
+      "learning_rate": 1.8613607188703468e-06,
+      "loss": 1.9242,
+      "step": 6000
+    }
+  ],
+  "max_steps": 6232,
+  "num_train_epochs": 8,
+  "total_flos": 1.2529214226432e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abe64331589a40fdd6b65aadb2c8245486475c2b9582f2516c9a2e983fc905d
+size 3963