Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "MyGPT2LMHeadModel"
+  ],
+  "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,
+  "low_rank": null,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 720,
+  "n_head": 2,
+  "n_inner": null,
+  "n_layer": 2,
+  "n_positions": 2048,
+  "network_type": null,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
+  "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": "4.48.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d10df6eff23bab20c60a967b8efc087e44b32825747eb802abf8b1f2cbd7f9b
+size 200488216

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602894dd08bf4ccaab05d6570384a1329a57fba49d21634c18128b51755be0ed
+size 400994762

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab02b72e0e043fa512850002bfb3d004f0ab619d37a36bf5185b936739ee04c
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79ec7450112161711e14f0f9bd3c3d6e82f7b9552f6ea72a343ab48190e7468a
+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 +1,21 @@
+{
+  "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|>"
+}

trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.92,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.2959253787994385,
+      "learning_rate": 4.8400000000000004e-05,
+      "loss": 3.4782,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.3196003437042236,
+      "learning_rate": 4.6800000000000006e-05,
+      "loss": 2.0957,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.5477054119110107,
+      "learning_rate": 4.52e-05,
+      "loss": 2.0086,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.4371566772460938,
+      "learning_rate": 4.36e-05,
+      "loss": 1.9488,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.6890789270401,
+      "learning_rate": 4.2e-05,
+      "loss": 1.8929,
+      "step": 2500
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.6345953941345215,
+      "learning_rate": 4.0400000000000006e-05,
+      "loss": 1.8377,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.744602918624878,
+      "eval_runtime": 0.3579,
+      "eval_samples_per_second": 558.824,
+      "eval_steps_per_second": 69.853,
+      "step": 3125
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.8465389013290405,
+      "learning_rate": 3.88e-05,
+      "loss": 1.7824,
+      "step": 3500
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.703276515007019,
+      "learning_rate": 3.72e-05,
+      "loss": 1.7505,
+      "step": 4000
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 2.056072235107422,
+      "learning_rate": 3.56e-05,
+      "loss": 1.726,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.597702980041504,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.7057,
+      "step": 5000
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 2.1297709941864014,
+      "learning_rate": 3.24e-05,
+      "loss": 1.6863,
+      "step": 5500
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.2768709659576416,
+      "learning_rate": 3.08e-05,
+      "loss": 1.6646,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15625,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1582743214080000.0,
+  "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:a33cb7fa946aeabeca6d22308fb866ad08ae1dec00b368e0735fe74e0b43591b
+size 5688