first commit

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 499.67,
+    "eval_loss": 5.67578125,
+    "eval_runtime": 0.0865,
+    "eval_samples": 9,
+    "eval_samples_per_second": 104.106,
+    "eval_steps_per_second": 23.135,
+    "perplexity": 291.71615278815983,
+    "train_loss": 0.8276048583984374,
+    "train_runtime": 639.1734,
+    "train_samples": 23,
+    "train_samples_per_second": 17.992,
+    "train_steps_per_second": 0.782
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "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": "float16",
+  "transformers_version": "4.13.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 499.67,
+    "eval_loss": 5.67578125,
+    "eval_runtime": 0.0865,
+    "eval_samples": 9,
+    "eval_samples_per_second": 104.106,
+    "eval_steps_per_second": 23.135,
+    "perplexity": 291.71615278815983
+}

global_step749/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe2250f060bf84e6a8f2cd505f0fd203c0897cf01fe1aef48646a0ba9ae857e
+size 170135099

global_step749/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e4a8974e5b53b7c0da528b158799e1067d6335a703e64b5b5984255806882
+size 982958359

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c7af5912efddf9ae72108390b7309f5d4ad68284e8a323ec5afc556aa87595
+size 170133371

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": "distilgpt2", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 499.67,
+    "train_loss": 0.8276048583984374,
+    "train_runtime": 639.1734,
+    "train_samples": 23,
+    "train_samples_per_second": 17.992,
+    "train_steps_per_second": 0.782
+}

trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 499.6666666666667,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 199.67,
+      "eval_loss": 4.546875,
+      "eval_runtime": 0.0857,
+      "eval_samples_per_second": 105.046,
+      "eval_steps_per_second": 23.344,
+      "step": 200
+    },
+    {
+      "epoch": 399.67,
+      "eval_loss": 5.43359375,
+      "eval_runtime": 0.0856,
+      "eval_samples_per_second": 105.16,
+      "eval_steps_per_second": 23.369,
+      "step": 400
+    },
+    {
+      "epoch": 499.67,
+      "learning_rate": 5e-05,
+      "loss": 0.8276,
+      "step": 500
+    },
+    {
+      "epoch": 499.67,
+      "step": 500,
+      "total_flos": 3003083546165248.0,
+      "train_loss": 0.8276048583984374,
+      "train_runtime": 639.1734,
+      "train_samples_per_second": 17.992,
+      "train_steps_per_second": 0.782
+    }
+  ],
+  "max_steps": 500,
+  "num_train_epochs": 500,
+  "total_flos": 3003083546165248.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d20f7e55570ae3c982208f96205c5ae8fcc5abf26d55c695a4a61956d3109dad
+size 3887