Upload 16 files

checkpoint-5000/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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-5000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.38.2"
+}

checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75438337ed3a7cf4c8e6cdc235f67d945712cf25150aa1e136c687c65f780f02
+size 497774208

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7df1acc5509082e7afc36b460563913a9f9e3cea5eda920af848fb32905c9b
+size 995642298

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509fe940a511f75762bca17b4a4a99dab812e1a5803c99761c06d39dda58bf92
+size 14244

checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa8964f4f22ffbf7db17a5c588649cf1f44668823239d5ed2c968072b34a617
+size 1064

checkpoint-5000/trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.935834155972359,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.49,
+      "grad_norm": 5.452001094818115,
+      "learning_rate": 4.5064165844027646e-05,
+      "loss": 2.1074,
+      "step": 500
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 4.521205425262451,
+      "learning_rate": 4.012833168805528e-05,
+      "loss": 1.9379,
+      "step": 1000
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 3.5499987602233887,
+      "learning_rate": 3.519249753208293e-05,
+      "loss": 1.8363,
+      "step": 1500
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 4.4638752937316895,
+      "learning_rate": 3.0256663376110567e-05,
+      "loss": 1.7792,
+      "step": 2000
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 3.7737858295440674,
+      "learning_rate": 2.5320829220138204e-05,
+      "loss": 1.7277,
+      "step": 2500
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 3.5306851863861084,
+      "learning_rate": 2.0384995064165844e-05,
+      "loss": 1.6955,
+      "step": 3000
+    },
+    {
+      "epoch": 3.46,
+      "grad_norm": 3.306370258331299,
+      "learning_rate": 1.5449160908193485e-05,
+      "loss": 1.6628,
+      "step": 3500
+    },
+    {
+      "epoch": 3.95,
+      "grad_norm": 3.6223793029785156,
+      "learning_rate": 1.0513326752221125e-05,
+      "loss": 1.6524,
+      "step": 4000
+    },
+    {
+      "epoch": 4.44,
+      "grad_norm": 3.021146059036255,
+      "learning_rate": 5.577492596248766e-06,
+      "loss": 1.6291,
+      "step": 4500
+    },
+    {
+      "epoch": 4.94,
+      "grad_norm": 3.5867886543273926,
+      "learning_rate": 6.416584402764068e-07,
+      "loss": 1.6234,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5065,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2612659027968000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed5c5d69fe2dc846211cfa0cdd8108ca2e75355db60d0dfcdc0ae8e1c6b34480
+size 4856

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": "4.38.2",
+  "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": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f29273f7ccb32f7f5182d4a68660316a0d171d40c79c04f2c3d7c69744806f9
+size 497774208

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 +1,22 @@
+{
+  "add_bos_token": false,
+  "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|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed5c5d69fe2dc846211cfa0cdd8108ca2e75355db60d0dfcdc0ae8e1c6b34480
+size 4856