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 sha256:088c8fcefdd47abc129ae367f065620e70e4951c63a9577d9d478c7d35200f59
+size 200488216

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e191200a25bf69ad996abf543a4d51d943303b5f89cf8df185795a394897a602
+size 400994762

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c26b721a47560839f4ea6a742640c6feae80733b0bd86d3d74f597a25b73f53
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6986a33bfdcb6dbd0621ee09062f262a64a1665cc1fd9a047c8bad68dc5f6e7
+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 +1,282 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 15625,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.5894356966018677,
+      "eval_runtime": 0.3606,
+      "eval_samples_per_second": 554.597,
+      "eval_steps_per_second": 69.325,
+      "step": 6250
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 2.763144016265869,
+      "learning_rate": 2.9199999999999998e-05,
+      "loss": 1.6354,
+      "step": 6500
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.51094913482666,
+      "learning_rate": 2.7600000000000003e-05,
+      "loss": 1.608,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.746187686920166,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.5902,
+      "step": 7500
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 2.614292621612549,
+      "learning_rate": 2.44e-05,
+      "loss": 1.5796,
+      "step": 8000
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 2.1394238471984863,
+      "learning_rate": 2.2800000000000002e-05,
+      "loss": 1.568,
+      "step": 8500
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.9124952554702759,
+      "learning_rate": 2.12e-05,
+      "loss": 1.5566,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.509089708328247,
+      "eval_runtime": 0.3633,
+      "eval_samples_per_second": 550.468,
+      "eval_steps_per_second": 68.808,
+      "step": 9375
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 2.2496132850646973,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 1.5474,
+      "step": 9500
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 2.7561938762664795,
+      "learning_rate": 1.8e-05,
+      "loss": 1.5342,
+      "step": 10000
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 2.425009250640869,
+      "learning_rate": 1.6400000000000002e-05,
+      "loss": 1.5275,
+      "step": 10500
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 2.3009116649627686,
+      "learning_rate": 1.48e-05,
+      "loss": 1.5229,
+      "step": 11000
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 1.9781867265701294,
+      "learning_rate": 1.32e-05,
+      "loss": 1.5173,
+      "step": 11500
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 2.1366450786590576,
+      "learning_rate": 1.16e-05,
+      "loss": 1.5139,
+      "step": 12000
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.4061367511749268,
+      "learning_rate": 1e-05,
+      "loss": 1.5129,
+      "step": 12500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4799761772155762,
+      "eval_runtime": 0.3596,
+      "eval_samples_per_second": 556.199,
+      "eval_steps_per_second": 69.525,
+      "step": 12500
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 2.6364712715148926,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 1.5005,
+      "step": 13000
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 2.217536211013794,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 1.4976,
+      "step": 13500
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 2.4257490634918213,
+      "learning_rate": 5.2e-06,
+      "loss": 1.4963,
+      "step": 14000
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 2.2251973152160645,
+      "learning_rate": 3.6e-06,
+      "loss": 1.4925,
+      "step": 14500
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 2.1918082237243652,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4919,
+      "step": 15000
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 2.1191954612731934,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.4899,
+      "step": 15500
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4121727120000000.0,
+  "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