Upload 8 files

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": "4.29.2",
+  "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": "4.29.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c1ca7fac0464eb649e9608130b214f4924b06da3f5bf5d8a545478ddc167b7
+size 995601029

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:486fc6f5c387628b002432ccf85ecd0fa23d29302747a6c59e42c0abf08d393f
+size 510395581

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bf7ba22c31a9d84100c4a515af11e961ad5b2b3975e26af4f998de60906fa34
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baac70be454cb0d2865de99c41c0d7ef8d106d02d6971c9f2839ad84fe2ddf7c
+size 627

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 25.380710659898476,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.27,
+      "learning_rate": 4.7884940778341796e-05,
+      "loss": 0.8566,
+      "step": 500
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 4.576988155668359e-05,
+      "loss": 0.722,
+      "step": 1000
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 4.365482233502538e-05,
+      "loss": 0.6826,
+      "step": 1500
+    },
+    {
+      "epoch": 5.08,
+      "learning_rate": 4.153976311336718e-05,
+      "loss": 0.5997,
+      "step": 2000
+    },
+    {
+      "epoch": 6.35,
+      "learning_rate": 3.942470389170897e-05,
+      "loss": 0.5507,
+      "step": 2500
+    },
+    {
+      "epoch": 7.61,
+      "learning_rate": 3.7309644670050766e-05,
+      "loss": 0.4943,
+      "step": 3000
+    },
+    {
+      "epoch": 8.88,
+      "learning_rate": 3.519458544839256e-05,
+      "loss": 0.4431,
+      "step": 3500
+    },
+    {
+      "epoch": 10.15,
+      "learning_rate": 3.307952622673435e-05,
+      "loss": 0.3848,
+      "step": 4000
+    },
+    {
+      "epoch": 11.42,
+      "learning_rate": 3.096446700507614e-05,
+      "loss": 0.3571,
+      "step": 4500
+    },
+    {
+      "epoch": 12.69,
+      "learning_rate": 2.8849407783417938e-05,
+      "loss": 0.3179,
+      "step": 5000
+    },
+    {
+      "epoch": 13.96,
+      "learning_rate": 2.6734348561759732e-05,
+      "loss": 0.2933,
+      "step": 5500
+    },
+    {
+      "epoch": 15.23,
+      "learning_rate": 2.4619289340101523e-05,
+      "loss": 0.2575,
+      "step": 6000
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 2.2504230118443317e-05,
+      "loss": 0.2348,
+      "step": 6500
+    },
+    {
+      "epoch": 17.77,
+      "learning_rate": 2.038917089678511e-05,
+      "loss": 0.2036,
+      "step": 7000
+    },
+    {
+      "epoch": 19.04,
+      "learning_rate": 1.8274111675126904e-05,
+      "loss": 0.1889,
+      "step": 7500
+    },
+    {
+      "epoch": 20.3,
+      "learning_rate": 1.6159052453468698e-05,
+      "loss": 0.1695,
+      "step": 8000
+    },
+    {
+      "epoch": 21.57,
+      "learning_rate": 1.404399323181049e-05,
+      "loss": 0.1583,
+      "step": 8500
+    },
+    {
+      "epoch": 22.84,
+      "learning_rate": 1.1928934010152284e-05,
+      "loss": 0.1535,
+      "step": 9000
+    },
+    {
+      "epoch": 24.11,
+      "learning_rate": 9.813874788494078e-06,
+      "loss": 0.1327,
+      "step": 9500
+    },
+    {
+      "epoch": 25.38,
+      "learning_rate": 7.698815566835872e-06,
+      "loss": 0.1252,
+      "step": 10000
+    }
+  ],
+  "max_steps": 11820,
+  "num_train_epochs": 30,
+  "total_flos": 1791279360000000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2802f5bf6470e7b577037aeeefc040dcc15a42998a1241879f14fb09658aabfe
+size 3899