commit files to HF hub

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 1013907456,
+    "init_mem_cpu_peaked_delta": 153968640,
+    "init_mem_gpu_alloc_delta": 511148032,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 184762368,
+    "train_mem_cpu_peaked_delta": 463081472,
+    "train_mem_gpu_alloc_delta": 1500642816,
+    "train_mem_gpu_peaked_delta": 7988768768,
+    "train_runtime": 760.1324,
+    "train_samples": 1453,
+    "train_samples_per_second": 2.869
+}

checkpoint-1000/config.json

@@ -0,0 +1,36 @@
+{
+  "_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,
+  "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
+    }
+  },
+  "transformers_version": "4.5.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce25b245e78a1ad1ece29de8607a72df0a974ecf5ae420528395ec4020d3d699
+size 995611287

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3c88702af61c00ad4d4c504a62ebce13c9acbc91b653414d81e666f2ed99666
+size 510408315

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424c1ea0fbf31ea8aab2aa5fc6b7aa0588f26270bde42a4c84f6c479df43ac35
+size 559

checkpoint-1000/special_tokens_map.json

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

checkpoint-1000/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"}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,28 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.375515818431912,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.853736817973407e-05,
+      "loss": 3.1317,
+      "step": 500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2.7074736359468134e-05,
+      "loss": 2.8754,
+      "step": 1000
+    }
+  ],
+  "max_steps": 2181,
+  "num_train_epochs": 3,
+  "total_flos": 1528351802523648.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f33abff4fb70cec388fc6432fae8a00c87f1ed1cee32c138fdaf1b2bc37665
+size 2351

checkpoint-1500/config.json

@@ -0,0 +1,36 @@
+{
+  "_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,
+  "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
+    }
+  },
+  "transformers_version": "4.5.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515be2e029e5b67450760aa466ef2fc757c00b1fae3975cb50ccd706bda4dc8b
+size 995611287

checkpoint-1500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf45e0165327c41ab9aa1d3f9158bea39dc8ed02692ba63087898ab6d11659d2
+size 510408315

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ced28b2f2640ca79c1dfd3e2043b92dcf461cd5754dfc4a788a857555af423
+size 559

checkpoint-1500/special_tokens_map.json

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

checkpoint-1500/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"}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.063273727647868,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.853736817973407e-05,
+      "loss": 3.1317,
+      "step": 500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2.7074736359468134e-05,
+      "loss": 2.8754,
+      "step": 1000
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.56121045392022e-05,
+      "loss": 2.7749,
+      "step": 1500
+    }
+  ],
+  "max_steps": 2181,
+  "num_train_epochs": 3,
+  "total_flos": 2292145424695296.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f33abff4fb70cec388fc6432fae8a00c87f1ed1cee32c138fdaf1b2bc37665
+size 2351

checkpoint-2000/config.json

@@ -0,0 +1,36 @@
+{
+  "_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,
+  "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
+    }
+  },
+  "transformers_version": "4.5.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb81f346b9687b4cec2c55fbf796c24372b89ce6c878edb8de9d1e5992fe80ff
+size 995611287

checkpoint-2000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b39d4eb863d9f7472bdd9a6f5536d36ddb576fc03235c88e837425cc894a74d
+size 510408315

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744d9451ef662d8d4c63313ea8658575d994832c4eee5da4182e3f5eb2807835
+size 559

checkpoint-2000/special_tokens_map.json

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

checkpoint-2000/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"}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.751031636863824,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.853736817973407e-05,
+      "loss": 3.1317,
+      "step": 500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2.7074736359468134e-05,
+      "loss": 2.8754,
+      "step": 1000
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.56121045392022e-05,
+      "loss": 2.7749,
+      "step": 1500
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.149472718936268e-06,
+      "loss": 2.6897,
+      "step": 2000
+    }
+  ],
+  "max_steps": 2181,
+  "num_train_epochs": 3,
+  "total_flos": 3056703605047296.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f33abff4fb70cec388fc6432fae8a00c87f1ed1cee32c138fdaf1b2bc37665
+size 2351

checkpoint-500/config.json

@@ -0,0 +1,36 @@
+{
+  "_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,
+  "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
+    }
+  },
+  "transformers_version": "4.5.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eae7f5229a3fac5a868c53501084c38a899457e57a3578c3e49c11e518796c0
+size 995611287

checkpoint-500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056455c41661f68666d01c56dcaabb36089a70bbeb6e3b1fedb45a40b7ed9a27
+size 510408315

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b60e1b6045b4b67dfc4baeb67b1279882c28f943ee655b87a17db3e37f2d52d
+size 559

checkpoint-500/special_tokens_map.json

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

checkpoint-500/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"}

checkpoint-500/trainer_state.json

@@ -0,0 +1,22 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.687757909215956,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.853736817973407e-05,
+      "loss": 3.1317,
+      "step": 500
+    }
+  ],
+  "max_steps": 2181,
+  "num_train_epochs": 3,
+  "total_flos": 764558180352000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f33abff4fb70cec388fc6432fae8a00c87f1ed1cee32c138fdaf1b2bc37665
+size 2351

config.json

@@ -0,0 +1,36 @@
+{
+  "_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,
+  "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
+    }
+  },
+  "transformers_version": "4.5.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3a172fc80ba8ea839189962cc329b194a76b5ba74b97ffc7ff094ebfe8272a
+size 510408315

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"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 1013907456,
+    "init_mem_cpu_peaked_delta": 153968640,
+    "init_mem_gpu_alloc_delta": 511148032,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 184762368,
+    "train_mem_cpu_peaked_delta": 463081472,
+    "train_mem_gpu_alloc_delta": 1500642816,
+    "train_mem_gpu_peaked_delta": 7988768768,
+    "train_runtime": 760.1324,
+    "train_samples": 1453,
+    "train_samples_per_second": 2.869
+}

trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 2181,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.853736817973407e-05,
+      "loss": 3.1317,
+      "step": 500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2.7074736359468134e-05,
+      "loss": 2.8754,
+      "step": 1000
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.56121045392022e-05,
+      "loss": 2.7749,
+      "step": 1500
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.149472718936268e-06,
+      "loss": 2.6897,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "step": 2181,
+      "total_flos": 3332709108154368.0,
+      "train_runtime": 760.1324,
+      "train_samples_per_second": 2.869
+    }
+  ],
+  "max_steps": 2181,
+  "num_train_epochs": 3,
+  "total_flos": 3332709108154368.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f33abff4fb70cec388fc6432fae8a00c87f1ed1cee32c138fdaf1b2bc37665
+size 2351