Upload 12 files

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 1.8597137928009033,
+    "eval_runtime": 7.0057,
+    "eval_samples": 97,
+    "eval_samples_per_second": 13.846,
+    "eval_steps_per_second": 1.856,
+    "perplexity": 6.421898514793739,
+    "train_loss": 1.7339835345426344,
+    "train_runtime": 586.4467,
+    "train_samples": 374,
+    "train_samples_per_second": 3.826,
+    "train_steps_per_second": 3.826
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_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,
+  "gradient_checkpointing": false,
+  "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,
+  "resid_pdrop": 0.1,
+  "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": "4.10.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 1.8597137928009033,
+    "eval_runtime": 7.0057,
+    "eval_samples": 97,
+    "eval_samples_per_second": 13.846,
+    "eval_steps_per_second": 1.856,
+    "perplexity": 6.421898514793739
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:533f55eac0c18343614d39ca6d6e8bc10d335b0a773046621c55755583d365ed
+size 510407951

special_tokens_map.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 1.7339835345426344,
+    "train_runtime": 586.4467,
+    "train_samples": 374,
+    "train_samples_per_second": 3.826,
+    "train_steps_per_second": 3.826
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "global_step": 2244,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.34,
+      "learning_rate": 3.885918003565063e-05,
+      "loss": 2.1414,
+      "step": 500
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.7718360071301247e-05,
+      "loss": 1.7805,
+      "step": 1000
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 1.6577540106951873e-05,
+      "loss": 1.6037,
+      "step": 1500
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 5.436720142602496e-06,
+      "loss": 1.5264,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "step": 2244,
+      "total_flos": 1172678639616000.0,
+      "train_loss": 1.7339835345426344,
+      "train_runtime": 586.4467,
+      "train_samples_per_second": 3.826,
+      "train_steps_per_second": 3.826
+    }
+  ],
+  "max_steps": 2244,
+  "num_train_epochs": 6,
+  "total_flos": 1172678639616000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206b329a620ff938357239330399f38a7f0b528a4ad8a4c3fce9ea2d565cf508
+size 2607