Initial upload

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 1.0566342449062363,
+    "train_runtime": 22320.8822,
+    "train_samples": 72734,
+    "train_samples_per_second": 16.293,
+    "train_steps_per_second": 2.037
+}

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-125M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      6
+    ]
+  ],
+  "bos_token_id": 50256,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 12,
+  "num_layers": 12,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2964a03ca6932ff5928846083b5d4e835721e0c8bc033d7d10f67c93cb14752e
+size 551185105

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-125M", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 1.0566342449062363,
+    "train_runtime": 22320.8822,
+    "train_samples": 72734,
+    "train_samples_per_second": 16.293,
+    "train_steps_per_second": 2.037
+}

trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 45460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.600087989441267e-05,
+      "loss": 1.1857,
+      "step": 9092
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1187185049057007,
+      "eval_runtime": 193.7266,
+      "eval_samples_per_second": 41.522,
+      "eval_steps_per_second": 10.381,
+      "step": 9092
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2003079630444347e-05,
+      "loss": 1.0728,
+      "step": 18184
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0675935745239258,
+      "eval_runtime": 193.8852,
+      "eval_samples_per_second": 41.488,
+      "eval_steps_per_second": 10.372,
+      "step": 18184
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.003519577650682e-06,
+      "loss": 1.0286,
+      "step": 27276
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.045861005783081,
+      "eval_runtime": 193.844,
+      "eval_samples_per_second": 41.497,
+      "eval_steps_per_second": 10.374,
+      "step": 27276
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.004839419269689e-06,
+      "loss": 1.0046,
+      "step": 36368
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.0346417427062988,
+      "eval_runtime": 191.4491,
+      "eval_samples_per_second": 42.016,
+      "eval_steps_per_second": 10.504,
+      "step": 36368
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 7.039155301363837e-09,
+      "loss": 0.9914,
+      "step": 45460
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.0310282707214355,
+      "eval_runtime": 191.6107,
+      "eval_samples_per_second": 41.981,
+      "eval_steps_per_second": 10.495,
+      "step": 45460
+    },
+    {
+      "epoch": 5.0,
+      "step": 45460,
+      "total_flos": 1.8998637018218496e+17,
+      "train_loss": 1.0566342449062363,
+      "train_runtime": 22320.8822,
+      "train_samples_per_second": 16.293,
+      "train_steps_per_second": 2.037
+    }
+  ],
+  "max_steps": 45460,
+  "num_train_epochs": 5,
+  "total_flos": 1.8998637018218496e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d80c1413c7fff6fc1e4cc48729d38f35919891f98c066d8a6fb3ad964c8380
+size 3759