Upload 13 files

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": 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": "4.44.2",
+  "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": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df35b4624f89c737fa475488f503857f306b6ae8b9b3555d68d10923da703e67
+size 497774208

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6878ab7931572c848278dcbbfc7dd7f2f967407ea215a964fe16a743206fcae4
+size 995642298

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286f3de29f4982a52d6acb94cdfd5b43f659d50c352c9d93e6ce2086385c7b0e
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2ee69f09faec1344a4358c979ab57b812a125bcb74ea043a04e57883b0f77d
+size 1064

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|>"
+}

trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05790622665655238,
+  "eval_steps": 500,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002895311332827619,
+      "grad_norm": 1.7338896989822388,
+      "learning_rate": 4.985523443335862e-05,
+      "loss": 3.1507,
+      "step": 500
+    },
+    {
+      "epoch": 0.005790622665655238,
+      "grad_norm": 1.2579742670059204,
+      "learning_rate": 4.9710468866717244e-05,
+      "loss": 2.6357,
+      "step": 1000
+    },
+    {
+      "epoch": 0.008685933998482857,
+      "grad_norm": 0.9996505975723267,
+      "learning_rate": 4.956570330007586e-05,
+      "loss": 2.4288,
+      "step": 1500
+    },
+    {
+      "epoch": 0.011581245331310476,
+      "grad_norm": 0.9657206535339355,
+      "learning_rate": 4.942093773343448e-05,
+      "loss": 2.2119,
+      "step": 2000
+    },
+    {
+      "epoch": 0.014476556664138095,
+      "grad_norm": 1.044640064239502,
+      "learning_rate": 4.92761721667931e-05,
+      "loss": 2.1225,
+      "step": 2500
+    },
+    {
+      "epoch": 0.017371867996965714,
+      "grad_norm": 0.8428456783294678,
+      "learning_rate": 4.913140660015172e-05,
+      "loss": 2.0409,
+      "step": 3000
+    },
+    {
+      "epoch": 0.02026717932979333,
+      "grad_norm": 1.2827749252319336,
+      "learning_rate": 4.898664103351033e-05,
+      "loss": 1.9031,
+      "step": 3500
+    },
+    {
+      "epoch": 0.023162490662620952,
+      "grad_norm": 0.9291247129440308,
+      "learning_rate": 4.884187546686895e-05,
+      "loss": 1.8438,
+      "step": 4000
+    },
+    {
+      "epoch": 0.02605780199544857,
+      "grad_norm": 0.7757951617240906,
+      "learning_rate": 4.8697109900227575e-05,
+      "loss": 1.7833,
+      "step": 4500
+    },
+    {
+      "epoch": 0.02895311332827619,
+      "grad_norm": 1.520269751548767,
+      "learning_rate": 4.855234433358619e-05,
+      "loss": 1.6942,
+      "step": 5000
+    },
+    {
+      "epoch": 0.03184842466110381,
+      "grad_norm": 1.2558553218841553,
+      "learning_rate": 4.840757876694481e-05,
+      "loss": 1.6669,
+      "step": 5500
+    },
+    {
+      "epoch": 0.03474373599393143,
+      "grad_norm": 1.3526251316070557,
+      "learning_rate": 4.826281320030343e-05,
+      "loss": 1.6115,
+      "step": 6000
+    },
+    {
+      "epoch": 0.037639047326759045,
+      "grad_norm": 2.5751099586486816,
+      "learning_rate": 4.811804763366205e-05,
+      "loss": 1.5629,
+      "step": 6500
+    },
+    {
+      "epoch": 0.04053435865958666,
+      "grad_norm": 1.3569105863571167,
+      "learning_rate": 4.797328206702067e-05,
+      "loss": 1.5258,
+      "step": 7000
+    },
+    {
+      "epoch": 0.04342966999241429,
+      "grad_norm": 1.7734428644180298,
+      "learning_rate": 4.782851650037929e-05,
+      "loss": 1.475,
+      "step": 7500
+    },
+    {
+      "epoch": 0.046324981325241904,
+      "grad_norm": 0.7975415587425232,
+      "learning_rate": 4.7683750933737905e-05,
+      "loss": 1.437,
+      "step": 8000
+    },
+    {
+      "epoch": 0.04922029265806952,
+      "grad_norm": 0.8590123057365417,
+      "learning_rate": 4.753898536709653e-05,
+      "loss": 1.4263,
+      "step": 8500
+    },
+    {
+      "epoch": 0.05211560399089714,
+      "grad_norm": 1.1225152015686035,
+      "learning_rate": 4.739421980045515e-05,
+      "loss": 1.3528,
+      "step": 9000
+    },
+    {
+      "epoch": 0.05501091532372476,
+      "grad_norm": 1.1342971324920654,
+      "learning_rate": 4.7249454233813765e-05,
+      "loss": 1.3576,
+      "step": 9500
+    },
+    {
+      "epoch": 0.05790622665655238,
+      "grad_norm": 0.9445364475250244,
+      "learning_rate": 4.710468866717238e-05,
+      "loss": 1.3283,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 172693,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.180672512e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc4dcbbcc559ab355890f3760b1f8d88cc54784c5d0996be3781ae4ab4eeb93
+size 5112