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": "4.38.2",
+  "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:c888c10456369529f0782ddff007e9730f63ceefffb57c20b08b3898ca9d117a
+size 497774208

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b82aef63dd81a31957b75b23a43abdf2d2f1ee3b7466a413f916c036506222
+size 995642298

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c5befeb7a8ede1a63f570b2a9ca46ee90311fd0aee8739e268282bfa64b45d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09fc2bd9358da628a3e465c6a7759a95b495fd186af7df11a948e186a372391
+size 1064

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": 832.680419921875,
+  "best_model_checkpoint": "./finetuned_qa11\\checkpoint-61",
+  "epoch": 0.9908629441624366,
+  "eval_steps": 500,
+  "global_step": 61,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.81,
+      "grad_norm": 7.192448616027832,
+      "learning_rate": 2.4221311475409835e-06,
+      "loss": 3.5889,
+      "step": 50
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 2.146763801574707,
+      "eval_perplexity": 832.680419921875,
+      "eval_runtime": 349.8385,
+      "eval_samples_per_second": 1.103,
+      "eval_steps_per_second": 0.071,
+      "step": 61
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 244,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1028902699008000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:623d4c49986c6792bfabeec9f72f5d176df1f1880e204db2a8234e1adcd71d8d
+size 4856