Upload 14 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 45453
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "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_embd": 128,
+  "n_head": 4,
+  "n_inner": null,
+  "n_layer": 4,
+  "n_positions": 128,
+  "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": "4.55.2",
+  "use_cache": true,
+  "vocab_size": 45454
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca168e522a23f021baa09b14cf9176341458548f7f5f6e8b056dd3ce2493689
+size 26516400

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29067d542cd0a634e5ae8f55ad1fb25d7a6cd55f835fdedb5f518f754e864426
+size 53065355

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58361e3a4864ff9dd9092fd17f5849be31a9c8cde2b2a083af8facf89b0b71d
+size 14455

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc93abff9ade3709958a8d84ec836000a871561eaa9e7b637dd95cb204b441a0
+size 1465

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "45453": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.0,
+  "eval_steps": 500,
+  "global_step": 5460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.7493112947658402,
+      "grad_norm": 0.7576850652694702,
+      "learning_rate": 0.0001834011090573013,
+      "loss": 7.6099,
+      "step": 500
+    },
+    {
+      "epoch": 5.4958677685950414,
+      "grad_norm": 0.9583437442779541,
+      "learning_rate": 0.000164916820702403,
+      "loss": 6.3788,
+      "step": 1000
+    },
+    {
+      "epoch": 8.242424242424242,
+      "grad_norm": 0.9470735788345337,
+      "learning_rate": 0.00014643253234750462,
+      "loss": 6.0154,
+      "step": 1500
+    },
+    {
+      "epoch": 10.991735537190083,
+      "grad_norm": 1.1763713359832764,
+      "learning_rate": 0.0001279482439926063,
+      "loss": 5.7785,
+      "step": 2000
+    },
+    {
+      "epoch": 13.738292011019285,
+      "grad_norm": 1.2199171781539917,
+      "learning_rate": 0.00010946395563770794,
+      "loss": 5.598,
+      "step": 2500
+    },
+    {
+      "epoch": 16.484848484848484,
+      "grad_norm": 1.387698769569397,
+      "learning_rate": 9.097966728280961e-05,
+      "loss": 5.4652,
+      "step": 3000
+    },
+    {
+      "epoch": 19.231404958677686,
+      "grad_norm": 1.1531177759170532,
+      "learning_rate": 7.249537892791128e-05,
+      "loss": 5.3563,
+      "step": 3500
+    },
+    {
+      "epoch": 21.980716253443525,
+      "grad_norm": 1.260562777519226,
+      "learning_rate": 5.4011090573012945e-05,
+      "loss": 5.2734,
+      "step": 4000
+    },
+    {
+      "epoch": 24.727272727272727,
+      "grad_norm": 1.3761156797409058,
+      "learning_rate": 3.55268022181146e-05,
+      "loss": 5.2048,
+      "step": 4500
+    },
+    {
+      "epoch": 27.47382920110193,
+      "grad_norm": 1.3121483325958252,
+      "learning_rate": 1.7042513863216268e-05,
+      "loss": 5.1634,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 212251634565120.0,
+  "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:e7300b283b1cd8a54a41c1e8ea3a4a8af36c7a24c5aa3b79bcbfc4e7e92afcdc
+size 5649