Upload folder using huggingface_hub

checkpoint-5000/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": "4.34.1",
+  "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": "4.34.1"
+}

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052ec99bd62754d269275fa644c295f6c3cc898afb7533de906afe19687971be
+size 995642298

checkpoint-5000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb9886c27b3b19d20b3573db7ad2a18c91a703c9c082817b087b95b11bab88d2
+size 497807706

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:803f31f631259c039a6a9847e117a0cbcd4d02e241a970233042c1c44bc581c2
+size 14244

checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ae61e837be3ada9de530496f3f4fe1da31f4699408459fe2a0b05c3e210f0d
+size 1064

checkpoint-5000/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 5e-05,
+      "loss": 4.7743,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 4.246,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 4.0284,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 3.8618,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 3.7563,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 3.7115,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 3.6593,
+      "step": 3500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 3.5533,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 3.5842,
+      "step": 4500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 3.5502,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5000,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2612920320000000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b47a42702c70ac229d4d3fdcba72a731a68a72817c2f0c2780e51219b0c838a
+size 4472