Upload 11 files

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 3.0843306716728804,
+    "train_runtime": 651.911,
+    "train_samples": 27380,
+    "train_samples_per_second": 251.998,
+    "train_steps_per_second": 7.878
+}

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": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e753d852d896dbc6c19ff6d27feab2c01d80ed9c22d2322713bd2164a0cea8bc
+size 510398013

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 3.0843306716728804,
+    "train_runtime": 651.911,
+    "train_samples": 27380,
+    "train_samples_per_second": 251.998,
+    "train_steps_per_second": 7.878
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "global_step": 5136,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.6678348909657322e-05,
+      "loss": 3.4613,
+      "step": 855
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.379996064919674,
+      "eval_loss": 3.267564535140991,
+      "eval_runtime": 5.6641,
+      "eval_samples_per_second": 612.45,
+      "eval_steps_per_second": 19.244,
+      "step": 856
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.3348909657320874e-05,
+      "loss": 3.1795,
+      "step": 1710
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3921627842066009,
+      "eval_loss": 3.1766529083251953,
+      "eval_runtime": 5.4681,
+      "eval_samples_per_second": 634.404,
+      "eval_steps_per_second": 19.934,
+      "step": 1712
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.0023364485981309e-05,
+      "loss": 3.0578,
+      "step": 2565
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.3995662260291837,
+      "eval_loss": 3.1288623809814453,
+      "eval_runtime": 5.5494,
+      "eval_samples_per_second": 625.117,
+      "eval_steps_per_second": 19.642,
+      "step": 2568
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.6939252336448605e-06,
+      "loss": 2.9786,
+      "step": 3420
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.40441186563988524,
+      "eval_loss": 3.0984020233154297,
+      "eval_runtime": 5.4908,
+      "eval_samples_per_second": 631.781,
+      "eval_steps_per_second": 19.851,
+      "step": 3424
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 3.3683800623052966e-06,
+      "loss": 2.9286,
+      "step": 4275
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.4070245759493381,
+      "eval_loss": 3.081953525543213,
+      "eval_runtime": 5.5218,
+      "eval_samples_per_second": 628.241,
+      "eval_steps_per_second": 19.74,
+      "step": 4280
+    },
+    {
+      "epoch": 5.99,
+      "learning_rate": 3.8940809968847356e-08,
+      "loss": 2.9012,
+      "step": 5130
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4076605947462102,
+      "eval_loss": 3.077474355697632,
+      "eval_runtime": 5.5146,
+      "eval_samples_per_second": 629.057,
+      "eval_steps_per_second": 19.766,
+      "step": 5136
+    },
+    {
+      "epoch": 6.0,
+      "step": 5136,
+      "total_flos": 5365631877120000.0,
+      "train_loss": 3.0843306716728804,
+      "train_runtime": 651.911,
+      "train_samples_per_second": 251.998,
+      "train_steps_per_second": 7.878
+    }
+  ],
+  "max_steps": 5136,
+  "num_train_epochs": 6,
+  "total_flos": 5365631877120000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edfecb2298056c8e4e446ac8e56499c3b73f57517dffa27892661fbdcdc6503a
+size 3387