Adding model checkpoints and config files

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

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": 50257
+}

checkpoint-0/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4794ea0b9a495e87fc34e316efe1b585527d6e3d15e4d093362ab24ee74ab3f
+size 510396521

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 sha256:67f7e9168f5c2f1ec1e35bd35f5d780b58186d6d6f08bd8f48bb03603de745d9
+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": 50257
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b7a9f5203e15a77188ea883e9b736765ce687c6f6c7eebbc56e446dbfd557bf
+size 995603825

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb29d41ae7c2ed7b96667db285c2a37c308ab5b8f00bfd2839f0d7cf80717ae
+size 510396521

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a3018099490baed59d6d1f88e0c8b0f17d0c64d2711c0d15944f420a4719c3
+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": 4.003333333333333,
+  "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": 10.8568,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00025,
+      "loss": 8.4903,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0005,
+      "loss": 7.2157,
+      "step": 100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.6825285173248e+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 sha256:67f7e9168f5c2f1ec1e35bd35f5d780b58186d6d6f08bd8f48bb03603de745d9
+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": 50257
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18c9e570516b504b44a27abf8037ed70470b917513886a1fe228187e703b5d4
+size 995604017

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e409e431d1f3beafa0e2d8dc9384b097a982c714964dd1b769632e6dac3235f9
+size 510396521

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af637066e973ba5fc0226605a7e2357deafb22317384328045c909e3d5ceaabd
+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": 41.013333333333335,
+  "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": 10.8568,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00025,
+      "loss": 8.4903,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0005,
+      "loss": 7.2157,
+      "step": 100
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 6.6121,
+      "step": 150
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 6.0811,
+      "step": 200
+    },
+    {
+      "epoch": 10.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 5.6744,
+      "step": 250
+    },
+    {
+      "epoch": 12.01,
+      "learning_rate": 0.0005,
+      "loss": 5.4147,
+      "step": 300
+    },
+    {
+      "epoch": 14.01,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 5.246,
+      "step": 350
+    },
+    {
+      "epoch": 16.01,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 5.1141,
+      "step": 400
+    },
+    {
+      "epoch": 18.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.9877,
+      "step": 450
+    },
+    {
+      "epoch": 20.02,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.8652,
+      "step": 500
+    },
+    {
+      "epoch": 22.02,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.7263,
+      "step": 550
+    },
+    {
+      "epoch": 24.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 4.5808,
+      "step": 600
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 4.4631,
+      "step": 650
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 4.3476,
+      "step": 700
+    },
+    {
+      "epoch": 31.0,
+      "learning_rate": 0.00025,
+      "loss": 4.2499,
+      "step": 750
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 4.1602,
+      "step": 800
+    },
+    {
+      "epoch": 35.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 4.0822,
+      "step": 850
+    },
+    {
+      "epoch": 37.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 4.0101,
+      "step": 900
+    },
+    {
+      "epoch": 39.01,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.9461,
+      "step": 950
+    },
+    {
+      "epoch": 41.01,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.8885,
+      "step": 1000
+    },
+    {
+      "epoch": 41.01,
+      "eval_loss": 5.021076202392578,
+      "eval_runtime": 1.8249,
+      "eval_samples_per_second": 50.963,
+      "eval_steps_per_second": 3.288,
+      "step": 1000
+    },
+    {
+      "epoch": 41.01,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_loss": 5.021076202392578,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_ppl": 151.57434071608614,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_runtime": 1.8249,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 50.963,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.68270097006592e+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 sha256:67f7e9168f5c2f1ec1e35bd35f5d780b58186d6d6f08bd8f48bb03603de745d9
+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": 50257
+}

checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0c23b41e25df3269ac5d9bb3e5e7c63093ce7feab46516aacb9ac0497045eb
+size 995604017

checkpoint-1100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4ce441fe9157791d118a0ec6ce0d3f80d3ed61a3a3a289d8426ac6fac171a7
+size 510396521

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d1b15565ccc155c2fa9e4a348a58d6bd4223a9cb96b372bebcd49aad18dd2d
+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": 45.016666666666666,
+  "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": 10.8568,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00025,
+      "loss": 8.4903,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0005,
+      "loss": 7.2157,
+      "step": 100
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 6.6121,
+      "step": 150
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 6.0811,
+      "step": 200
+    },
+    {
+      "epoch": 10.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 5.6744,
+      "step": 250
+    },
+    {
+      "epoch": 12.01,
+      "learning_rate": 0.0005,
+      "loss": 5.4147,
+      "step": 300
+    },
+    {
+      "epoch": 14.01,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 5.246,
+      "step": 350
+    },
+    {
+      "epoch": 16.01,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 5.1141,
+      "step": 400
+    },
+    {
+      "epoch": 18.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.9877,
+      "step": 450
+    },
+    {
+      "epoch": 20.02,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.8652,
+      "step": 500
+    },
+    {
+      "epoch": 22.02,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.7263,
+      "step": 550
+    },
+    {
+      "epoch": 24.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 4.5808,
+      "step": 600
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 4.4631,
+      "step": 650
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 4.3476,
+      "step": 700
+    },
+    {
+      "epoch": 31.0,
+      "learning_rate": 0.00025,
+      "loss": 4.2499,
+      "step": 750
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 4.1602,
+      "step": 800
+    },
+    {
+      "epoch": 35.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 4.0822,
+      "step": 850
+    },
+    {
+      "epoch": 37.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 4.0101,
+      "step": 900
+    },
+    {
+      "epoch": 39.01,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.9461,
+      "step": 950
+    },
+    {
+      "epoch": 41.01,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.8885,
+      "step": 1000
+    },
+    {
+      "epoch": 41.01,
+      "eval_loss": 5.021076202392578,
+      "eval_runtime": 1.8249,
+      "eval_samples_per_second": 50.963,
+      "eval_steps_per_second": 3.288,
+      "step": 1000
+    },
+    {
+      "epoch": 41.01,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_loss": 5.021076202392578,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_ppl": 151.57434071608614,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_runtime": 1.8249,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 50.963,
+      "step": 1000
+    },
+    {
+      "epoch": 43.02,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.8378,
+      "step": 1050
+    },
+    {
+      "epoch": 45.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.795,
+      "step": 1100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.9509538217984e+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 sha256:67f7e9168f5c2f1ec1e35bd35f5d780b58186d6d6f08bd8f48bb03603de745d9
+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": 50257
+}

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201b22a881d3789c42efd0e925f4fbcdc18ec4fbfbb5a75b4a74149c94a1664c
+size 995604017

checkpoint-1200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b9f48b694f4ac212bb477a4db493a3f40b3c0f0e909fb907932a38053feda2
+size 510396521

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3bddfc6d4177a0230536d802ec243aca93e907818d4201e49b31c7d35d0b56f
+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": 49.02,
+  "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": 10.8568,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00025,
+      "loss": 8.4903,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0005,
+      "loss": 7.2157,
+      "step": 100
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 6.6121,
+      "step": 150
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 6.0811,
+      "step": 200
+    },
+    {
+      "epoch": 10.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 5.6744,
+      "step": 250
+    },
+    {
+      "epoch": 12.01,
+      "learning_rate": 0.0005,
+      "loss": 5.4147,
+      "step": 300
+    },
+    {
+      "epoch": 14.01,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 5.246,
+      "step": 350
+    },
+    {
+      "epoch": 16.01,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 5.1141,
+      "step": 400
+    },
+    {
+      "epoch": 18.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.9877,
+      "step": 450
+    },
+    {
+      "epoch": 20.02,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.8652,
+      "step": 500
+    },
+    {
+      "epoch": 22.02,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.7263,
+      "step": 550
+    },
+    {
+      "epoch": 24.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 4.5808,
+      "step": 600
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 4.4631,
+      "step": 650
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 4.3476,
+      "step": 700
+    },
+    {
+      "epoch": 31.0,
+      "learning_rate": 0.00025,
+      "loss": 4.2499,
+      "step": 750
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 4.1602,
+      "step": 800
+    },
+    {
+      "epoch": 35.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 4.0822,
+      "step": 850
+    },
+    {
+      "epoch": 37.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 4.0101,
+      "step": 900
+    },
+    {
+      "epoch": 39.01,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.9461,
+      "step": 950
+    },
+    {
+      "epoch": 41.01,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.8885,
+      "step": 1000
+    },
+    {
+      "epoch": 41.01,
+      "eval_loss": 5.021076202392578,
+      "eval_runtime": 1.8249,
+      "eval_samples_per_second": 50.963,
+      "eval_steps_per_second": 3.288,
+      "step": 1000
+    },
+    {
+      "epoch": 41.01,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_loss": 5.021076202392578,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_ppl": 151.57434071608614,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_runtime": 1.8249,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 50.963,
+      "step": 1000
+    },
+    {
+      "epoch": 43.02,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.8378,
+      "step": 1050
+    },
+    {
+      "epoch": 45.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.795,
+      "step": 1100
+    },
+    {
+      "epoch": 47.02,
+      "learning_rate": 2.7777777777777772e-05,
+      "loss": 3.759,
+      "step": 1150
+    },
+    {
+      "epoch": 49.02,
+      "learning_rate": 0.0,
+      "loss": 3.7334,
+      "step": 1200
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 3.21920667353088e+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 sha256:67f7e9168f5c2f1ec1e35bd35f5d780b58186d6d6f08bd8f48bb03603de745d9
+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": 50257
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e651467b29517c40a2e70447746188c6a2e98fd86a3d90559df00c3653f9a2e
+size 995603825

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7df9668b20e0f0a79420d6f9bd6467e70c5d1cdfade2b7beeb6399acacdc7f
+size 510396521

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118cfc04cdc7ea346d7b9d6a5dd3116ee811ae964097668c186b577cff7ae02b
+size 14567