checking in the initial version files

Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/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": "4.3.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32b4bd756116544a3796f0262a49e2e52c359fce21f6f78df9729e68b3d47856
+size 995611287

Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7823b696f0e4c4df4fdae6c1a5ef0a9121fcd9dee4d4bc84a6f7186fb0fd0043
+size 510408315

Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:889349d3cbf5b5010c0ba7ca85c6a7d913eaedb8ba23c23ddcddc68d1d0ed5bd
+size 623

Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/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}}

Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "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, "model_max_length": 1024, "name_or_path": "gpt2"}

Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 1.9876124858856201,
+  "best_model_checkpoint": "Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130",
+  "epoch": 2.0,
+  "global_step": 5130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 5e-05,
+      "loss": 2.1955,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.4600431965442765e-05,
+      "loss": 1.8704,
+      "step": 1000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.920086393088553e-05,
+      "loss": 1.7624,
+      "step": 1500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.38012958963283e-05,
+      "loss": 1.7039,
+      "step": 2000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.840172786177106e-05,
+      "loss": 1.6626,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.0070595741271973,
+      "eval_runtime": 102.1824,
+      "eval_samples_per_second": 386.446,
+      "step": 2565
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.3002159827213822e-05,
+      "loss": 1.6134,
+      "step": 3000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.7602591792656588e-05,
+      "loss": 1.5933,
+      "step": 3500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.2203023758099353e-05,
+      "loss": 1.5742,
+      "step": 4000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 6.803455723542117e-06,
+      "loss": 1.5735,
+      "step": 4500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.4038876889848812e-06,
+      "loss": 1.5623,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.9876124858856201,
+      "eval_runtime": 102.2828,
+      "eval_samples_per_second": 386.067,
+      "step": 5130
+    }
+  ],
+  "max_steps": 5130,
+  "num_train_epochs": 2,
+  "total_flos": 31377467721646080,
+  "trial_name": null,
+  "trial_params": null
+}

Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2f8fdc136c0bb46924b24f040a6637be9e4fc5e59e4d88776a32348fdfbc02
+size 2159

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "Checkpoints_1_6_M/gpt2-python-language-model/checkpoint-5130",
+  "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": 500
+    }
+  },
+  "transformers_version": "4.3.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:967afc9178c6e73626cf1546465c3956939ccfe109696be51c5af53b0f82de15
+size 510408315

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 @@
+{"errors": "replace", "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, "model_max_length": 1024, "name_or_path": "gpt2"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2f8fdc136c0bb46924b24f040a6637be9e4fc5e59e4d88776a32348fdfbc02
+size 2159