Adding model checkpoints and config files

checkpoint-0/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "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,
+  "reorder_and_upcast_attn": true,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.2,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 1024
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": false,
+  "vocab_size": 40000
+}

checkpoint-0/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9622ade3c0035b7db303909b741eb04294a44eed0e355c6a3c7084d578f6ff91
+size 478887017

checkpoint-0/special_tokens_map.json

@@ -0,0 +1 @@
+{}

checkpoint-0/tokenizer_config.json

@@ -0,0 +1 @@
+{"tokenizer_class": "PassthroughTokenizer"}

checkpoint-0/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec32810d4409696d65bce9761313a0cffdb55152ef1e6f8c42d0c5245db5910b
+size 3183

checkpoint-100/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "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,
+  "reorder_and_upcast_attn": true,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.2,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 1024
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": false,
+  "vocab_size": 40000
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:763e95a19326453151c078ac82156151575f2a8212748c29cf1655c75749b7c6
+size 932584817

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6847eaddc5573263b0ca412922b8f9e9ea08dda8660931959627765bcdfcaf3
+size 478887017

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386c17eb6576e40b2821d3ee8cd710f2fcbec7d487c772bcb0ac357cf64e107d
+size 14567

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a3423b2fe42f204bc8fe2c666ff379f9fd753a0f13613064a5e71e86b519e8
+size 559

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e9b9d31d11c624d89b0c04ad496adf4b5addd3e703848d2583972c703e8da6
+size 623

checkpoint-100/special_tokens_map.json

@@ -0,0 +1 @@
+{}

checkpoint-100/tokenizer_config.json

@@ -0,0 +1 @@
+{"tokenizer_class": "PassthroughTokenizer"}

checkpoint-100/trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.013333333333333,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 10.6943,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.0309,
+      "step": 50
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0005,
+      "loss": 6.3992,
+      "step": 100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.7002441170944e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec32810d4409696d65bce9761313a0cffdb55152ef1e6f8c42d0c5245db5910b
+size 3183

checkpoint-1000/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "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,
+  "reorder_and_upcast_attn": true,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.2,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 1024
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": false,
+  "vocab_size": 40000
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac8246c3abbb2705ff06369375347e13fbfd58343183722d2d84e16285a6ffe
+size 932585009

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf44e090bfd7b39cd967739bdb38fb8e2a2e624a4cbbc8b7436b5425f0fb7dfc
+size 478887017

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf4adb1bde900fc1851d8a4d67a08bb5dca38277271ee4c42adb5dfccbf8e6a
+size 14567

checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f810fc7b695697c440d8985f6042b4ba23a9e1027604c265718b518ca29f1b2b
+size 559

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0691206f4bd9ca409d6e7104087a4e0eb05df8f8f555a400f6ecc532edba52d8
+size 623

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1 @@
+{}

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1 @@
+{"tokenizer_class": "PassthroughTokenizer"}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,158 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 35.016666666666666,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 10.6943,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.0309,
+      "step": 50
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0005,
+      "loss": 6.3992,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.8993,
+      "step": 150
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 5.5735,
+      "step": 200
+    },
+    {
+      "epoch": 8.02,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 5.3482,
+      "step": 250
+    },
+    {
+      "epoch": 10.02,
+      "learning_rate": 0.0005,
+      "loss": 5.2461,
+      "step": 300
+    },
+    {
+      "epoch": 12.01,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 5.1084,
+      "step": 350
+    },
+    {
+      "epoch": 14.01,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.9262,
+      "step": 400
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.6872,
+      "step": 450
+    },
+    {
+      "epoch": 17.02,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.4739,
+      "step": 500
+    },
+    {
+      "epoch": 19.02,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.3509,
+      "step": 550
+    },
+    {
+      "epoch": 21.01,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 4.2242,
+      "step": 600
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 4.1122,
+      "step": 650
+    },
+    {
+      "epoch": 24.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.9942,
+      "step": 700
+    },
+    {
+      "epoch": 26.02,
+      "learning_rate": 0.00025,
+      "loss": 3.9348,
+      "step": 750
+    },
+    {
+      "epoch": 28.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.8595,
+      "step": 800
+    },
+    {
+      "epoch": 30.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.7895,
+      "step": 850
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.7275,
+      "step": 900
+    },
+    {
+      "epoch": 33.02,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.6509,
+      "step": 950
+    },
+    {
+      "epoch": 35.02,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.6252,
+      "step": 1000
+    },
+    {
+      "epoch": 35.02,
+      "eval_loss": 4.426984786987305,
+      "eval_runtime": 1.6605,
+      "eval_samples_per_second": 54.804,
+      "eval_steps_per_second": 3.613,
+      "step": 1000
+    },
+    {
+      "epoch": 35.02,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_loss": 4.426984786987305,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_ppl": 83.67872695828713,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_runtime": 1.6605,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 54.804,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.7043464019968e+17,
+  "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:ec32810d4409696d65bce9761313a0cffdb55152ef1e6f8c42d0c5245db5910b
+size 3183

checkpoint-1100/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "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,
+  "reorder_and_upcast_attn": true,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.2,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 1024
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": false,
+  "vocab_size": 40000
+}

checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e012da7f649b852c88a87f14719b8c372e53478b6fc3b96eacd48c19c4866d5
+size 932585009

checkpoint-1100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2555c69e7959c8584ac1e360bc6eeec56a25ec2f367b27f9cafabd673c6879bd
+size 478887017

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8fa6bd9a7e10e7ff22301a3696a92e40fd74711bb89bcaf9b67e304f602564
+size 14567

checkpoint-1100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb16c30b686aa43e110b0d33f9d46bf3127b7124542ca8dc34831233d4675a0
+size 559

checkpoint-1100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1b7713e4bb40428f29080b7d08d4a52f779ac863737861e4724292b2cf6c59
+size 623

checkpoint-1100/special_tokens_map.json

@@ -0,0 +1 @@
+{}

checkpoint-1100/tokenizer_config.json

@@ -0,0 +1 @@
+{"tokenizer_class": "PassthroughTokenizer"}

checkpoint-1100/trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 39.00666666666667,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 10.6943,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.0309,
+      "step": 50
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0005,
+      "loss": 6.3992,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.8993,
+      "step": 150
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 5.5735,
+      "step": 200
+    },
+    {
+      "epoch": 8.02,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 5.3482,
+      "step": 250
+    },
+    {
+      "epoch": 10.02,
+      "learning_rate": 0.0005,
+      "loss": 5.2461,
+      "step": 300
+    },
+    {
+      "epoch": 12.01,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 5.1084,
+      "step": 350
+    },
+    {
+      "epoch": 14.01,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.9262,
+      "step": 400
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.6872,
+      "step": 450
+    },
+    {
+      "epoch": 17.02,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.4739,
+      "step": 500
+    },
+    {
+      "epoch": 19.02,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.3509,
+      "step": 550
+    },
+    {
+      "epoch": 21.01,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 4.2242,
+      "step": 600
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 4.1122,
+      "step": 650
+    },
+    {
+      "epoch": 24.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.9942,
+      "step": 700
+    },
+    {
+      "epoch": 26.02,
+      "learning_rate": 0.00025,
+      "loss": 3.9348,
+      "step": 750
+    },
+    {
+      "epoch": 28.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.8595,
+      "step": 800
+    },
+    {
+      "epoch": 30.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.7895,
+      "step": 850
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.7275,
+      "step": 900
+    },
+    {
+      "epoch": 33.02,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.6509,
+      "step": 950
+    },
+    {
+      "epoch": 35.02,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.6252,
+      "step": 1000
+    },
+    {
+      "epoch": 35.02,
+      "eval_loss": 4.426984786987305,
+      "eval_runtime": 1.6605,
+      "eval_samples_per_second": 54.804,
+      "eval_steps_per_second": 3.613,
+      "step": 1000
+    },
+    {
+      "epoch": 35.02,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_loss": 4.426984786987305,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_ppl": 83.67872695828713,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_runtime": 1.6605,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 54.804,
+      "step": 1000
+    },
+    {
+      "epoch": 37.01,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.5819,
+      "step": 1050
+    },
+    {
+      "epoch": 39.01,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.5432,
+      "step": 1100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.97519127068672e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec32810d4409696d65bce9761313a0cffdb55152ef1e6f8c42d0c5245db5910b
+size 3183

checkpoint-1200/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "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,
+  "reorder_and_upcast_attn": true,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.2,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 1024
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": false,
+  "vocab_size": 40000
+}

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1067543a44e6cb7fb257900b4bd992ccb8c0f71709b195188200ccc37d2527
+size 932585009

checkpoint-1200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e9845c6e8cb4406a776fe5804fb47caaaa5e59a527d8eab17bb3795feaf75a
+size 478887017

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64399666047b54adbc257e9a03f2eaa518688485b7c7b36c099f69168e6c89d5
+size 14567

checkpoint-1200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c7277eaca0850ae3e9b6790b3d002d820169cce0671185e672c28c8ae8e056
+size 559

checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:935a8fb09a6e9698d9894853b05e181b3f56098deaaecddde08e55f06bf000c4
+size 623

checkpoint-1200/special_tokens_map.json

@@ -0,0 +1 @@
+{}

checkpoint-1200/tokenizer_config.json

@@ -0,0 +1 @@
+{"tokenizer_class": "PassthroughTokenizer"}

checkpoint-1200/trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 42.02,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 10.6943,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.0309,
+      "step": 50
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0005,
+      "loss": 6.3992,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.8993,
+      "step": 150
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 5.5735,
+      "step": 200
+    },
+    {
+      "epoch": 8.02,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 5.3482,
+      "step": 250
+    },
+    {
+      "epoch": 10.02,
+      "learning_rate": 0.0005,
+      "loss": 5.2461,
+      "step": 300
+    },
+    {
+      "epoch": 12.01,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 5.1084,
+      "step": 350
+    },
+    {
+      "epoch": 14.01,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.9262,
+      "step": 400
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.6872,
+      "step": 450
+    },
+    {
+      "epoch": 17.02,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.4739,
+      "step": 500
+    },
+    {
+      "epoch": 19.02,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.3509,
+      "step": 550
+    },
+    {
+      "epoch": 21.01,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 4.2242,
+      "step": 600
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 4.1122,
+      "step": 650
+    },
+    {
+      "epoch": 24.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.9942,
+      "step": 700
+    },
+    {
+      "epoch": 26.02,
+      "learning_rate": 0.00025,
+      "loss": 3.9348,
+      "step": 750
+    },
+    {
+      "epoch": 28.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.8595,
+      "step": 800
+    },
+    {
+      "epoch": 30.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.7895,
+      "step": 850
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.7275,
+      "step": 900
+    },
+    {
+      "epoch": 33.02,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.6509,
+      "step": 950
+    },
+    {
+      "epoch": 35.02,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.6252,
+      "step": 1000
+    },
+    {
+      "epoch": 35.02,
+      "eval_loss": 4.426984786987305,
+      "eval_runtime": 1.6605,
+      "eval_samples_per_second": 54.804,
+      "eval_steps_per_second": 3.613,
+      "step": 1000
+    },
+    {
+      "epoch": 35.02,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_loss": 4.426984786987305,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_ppl": 83.67872695828713,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_runtime": 1.6605,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 54.804,
+      "step": 1000
+    },
+    {
+      "epoch": 37.01,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.5819,
+      "step": 1050
+    },
+    {
+      "epoch": 39.01,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.5432,
+      "step": 1100
+    },
+    {
+      "epoch": 41.0,
+      "learning_rate": 2.7777777777777772e-05,
+      "loss": 3.5122,
+      "step": 1150
+    },
+    {
+      "epoch": 42.02,
+      "learning_rate": 0.0,
+      "loss": 3.468,
+      "step": 1200
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 3.24521568239616e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec32810d4409696d65bce9761313a0cffdb55152ef1e6f8c42d0c5245db5910b
+size 3183

checkpoint-200/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "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,
+  "reorder_and_upcast_attn": true,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.2,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 1024
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": false,
+  "vocab_size": 40000
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f83c2db06da14144500e17e3854adb182cee696235648c742673e1435c2720a
+size 932584817

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c1a640bd97543a5ced10cfd8ad45fa48e1e364241f25eb83581ae9fcdebc5b
+size 478887017

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f9aa0022b0324582900e2271e62a388a6f0e239bed9f60090432880c00e3b3a
+size 14567

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6982c29cd162f49aeb531674acf574eccd46a8f556bec596040d7c3b95200a
+size 559