Upload 7 files

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "openai-community/gpt2-medium",
+  "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": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "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": "4.44.2",
+  "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": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77960448ec3cb16a984b83912a8c21e602e68fbac80792e91ce715308e194b35
+size 1431912264

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44f79ff739cc5aa0ef599b98b5913e4acc17f62aee68fdf0baa7408ff7fd5567
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c876e240607339da7ccc68813410e25a08f9f67fd0ed4b052a348a0a3af8ea
+size 1064

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 10050,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19900497512437812,
+      "grad_norm": 0.26937374472618103,
+      "learning_rate": 4.738219895287958e-05,
+      "loss": 2.1306,
+      "step": 1000
+    },
+    {
+      "epoch": 0.39800995024875624,
+      "grad_norm": 0.1997993439435959,
+      "learning_rate": 4.2146596858638745e-05,
+      "loss": 0.3628,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.2434607893228531,
+      "learning_rate": 3.691099476439791e-05,
+      "loss": 0.354,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7960199004975125,
+      "grad_norm": 0.1875876635313034,
+      "learning_rate": 3.167539267015707e-05,
+      "loss": 0.3529,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9950248756218906,
+      "grad_norm": 0.2847432792186737,
+      "learning_rate": 2.643979057591623e-05,
+      "loss": 0.3518,
+      "step": 5000
+    },
+    {
+      "epoch": 1.1940298507462686,
+      "grad_norm": 0.21426910161972046,
+      "learning_rate": 2.1204188481675396e-05,
+      "loss": 0.3414,
+      "step": 6000
+    },
+    {
+      "epoch": 1.3930348258706466,
+      "grad_norm": 0.24933403730392456,
+      "learning_rate": 1.5968586387434557e-05,
+      "loss": 0.3444,
+      "step": 7000
+    },
+    {
+      "epoch": 1.5920398009950247,
+      "grad_norm": 0.2430945485830307,
+      "learning_rate": 1.0732984293193717e-05,
+      "loss": 0.3504,
+      "step": 8000
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 0.2998332381248474,
+      "learning_rate": 5.49738219895288e-06,
+      "loss": 0.3344,
+      "step": 9000
+    },
+    {
+      "epoch": 1.9900497512437811,
+      "grad_norm": 0.15377995371818542,
+      "learning_rate": 2.617801047120419e-07,
+      "loss": 0.3431,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10050,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.88611238559744e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:376a9519dca2ce1aa5625bb880da870ac3ac4512cff65bc1268b082837ce1961
+size 5176