Upload experiments/ with huggingface_hub

experiments/2023-02-22-5f8754af240241f4c78ba924918b0bfb26f26a17b0e1799c8a046eb3f6dd6e94/configs.json

@@ -0,0 +1,26 @@
+{
+    "output_dir": "./results",
+    "evaluation_strategy": "no",
+    "do_eval": false,
+    "eval_steps": 0,
+    "log_level": "info",
+    "logging_first_step": true,
+    "logging_steps": 5,
+    "logging_dir": "./logs",
+    "save_steps": 150,
+    "save_total_limit": 1,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 6,
+    "optim": "adamw_torch",
+    "gradient_accumulation_steps": 4,
+    "dataloader_drop_last": true,
+    "warmup_steps": 1000,
+    "weight_decay": 0.1,
+    "learning_rate": 0.0001,
+    "deepspeed": "deepspeed.json",
+    "local_rank": 0,
+    "total_gpus": 8,
+    "v_cpus": 64,
+    "total_memory_in_gb": 257604.9765625,
+    "dataset_limit": 0
+}

experiments/2023-02-22-5f8754af240241f4c78ba924918b0bfb26f26a17b0e1799c8a046eb3f6dd6e94/deepspeed.json

@@ -0,0 +1,48 @@
+{
+    "optimizer": {
+        "type": "AdamW",
+        "params": {
+            "lr": 1e-4,
+            "betas": [ 0.9, 0.999 ],
+            "eps": 1e-8,
+            "weight_decay": 0.1
+        }
+    },
+
+    "scheduler": {
+        "type": "WarmupLR",
+        "params": {
+            "warmup_min_lr": 1e-9,
+            "warmup_max_lr": 1e-4,
+            "warmup_num_steps": 1000
+        }
+    },
+
+    "zero_optimization": {
+        "stage": 2,
+        "offload_optimizer": {
+            "device": "cpu",
+            "pin_memory": true
+        },
+        "allgather_partitions": true,
+        "allgather_bucket_size": 5e8,
+        "overlap_comm": true,
+        "reduce_scatter": true,
+        "reduce_bucket_size": 5e8,
+        "contiguous_gradients": true
+    },
+
+    "tensorboard": {
+        "enabled": true,
+        "output_path": "logs/",
+        "job_name": "train_neo"
+    },
+
+    "zero_allow_untested_optimizer": true,
+    "gradient_accumulation_steps": "auto",
+    "gradient_clipping": "auto",
+    "steps_per_print": 2000,
+    "train_batch_size": "auto",
+    "train_micro_batch_size_per_gpu": "auto",
+    "wall_clock_breakdown": false
+}

experiments/2023-02-22-5f8754af240241f4c78ba924918b0bfb26f26a17b0e1799c8a046eb3f6dd6e94/final_checkpoint/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": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

experiments/2023-02-22-5f8754af240241f4c78ba924918b0bfb26f26a17b0e1799c8a046eb3f6dd6e94/final_checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6589651dd8c9588a8faa97daec7814ffcfe998ba2e481eabdcb3e75405761d5d
+size 551154684

experiments/2023-02-22-5f8754af240241f4c78ba924918b0bfb26f26a17b0e1799c8a046eb3f6dd6e94/final_checkpoint/tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

experiments/2023-02-22-5f8754af240241f4c78ba924918b0bfb26f26a17b0e1799c8a046eb3f6dd6e94/final_checkpoint/tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 2048,
+  "name_or_path": "EleutherAI/gpt-neo-125M",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

experiments/2023-02-22-5f8754af240241f4c78ba924918b0bfb26f26a17b0e1799c8a046eb3f6dd6e94/trainer_final_checkpoint/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": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

experiments/2023-02-22-5f8754af240241f4c78ba924918b0bfb26f26a17b0e1799c8a046eb3f6dd6e94/trainer_final_checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6589651dd8c9588a8faa97daec7814ffcfe998ba2e481eabdcb3e75405761d5d
+size 551154684

experiments/2023-02-22-5f8754af240241f4c78ba924918b0bfb26f26a17b0e1799c8a046eb3f6dd6e94/trainer_final_checkpoint/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

experiments/2023-02-22-5f8754af240241f4c78ba924918b0bfb26f26a17b0e1799c8a046eb3f6dd6e94/trainer_final_checkpoint/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 2048,
+  "name_or_path": "EleutherAI/gpt-neo-125M",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

experiments/2023-02-22-5f8754af240241f4c78ba924918b0bfb26f26a17b0e1799c8a046eb3f6dd6e94/trainer_final_checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69255842ed78e689b179c20bae1499576b967ef499d84d9ec162b162d779e910
+size 4475