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": 64000
+}

checkpoint-0/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d9938f9842ab67a4ffdb8192f0ef1a92afea4592e39c9cede29e616f6bb617f
+size 552615017

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:ce5ee64ec673c5915c725d59ab09d5567c896e983bbaa61ee563d03df6350d2f
+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": 64000
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4547f92d7100e31e3deb39b44f6f22305a0894d90aab2a883a4d15394b930012
+size 1080040817

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6606650d0527e0a3ac6af190f2cf114bc9c9df37604f2f0ea2c56bf7b88d8711
+size 552615017

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58496e945c16a650ef4a460d1ac1592df28955ae14889c83910e110247a11e11
+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": 3.0083333333333333,
+  "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": 11.1049,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.1845,
+      "step": 50
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0005,
+      "loss": 5.9529,
+      "step": 100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.7041634975744e+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:ce5ee64ec673c5915c725d59ab09d5567c896e983bbaa61ee563d03df6350d2f
+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": 64000
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57f7023ea2fc223853366c846fc06cfd4e9af3565ac1f92228e07364e5b12b7
+size 1080041009

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feaf65ae0b5bc37c29dd98d0ce7aa049d828220e3602831b83266de5f7856fb8
+size 552615017

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394d180f63a23adf48a4ef738fe5b39b3b50aa94348457023737b14f18b9c037
+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": 33.00833333333333,
+  "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": 11.1049,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.1845,
+      "step": 50
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0005,
+      "loss": 5.9529,
+      "step": 100
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.1965,
+      "step": 150
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.8925,
+      "step": 200
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 4.7182,
+      "step": 250
+    },
+    {
+      "epoch": 9.03,
+      "learning_rate": 0.0005,
+      "loss": 4.561,
+      "step": 300
+    },
+    {
+      "epoch": 11.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.4282,
+      "step": 350
+    },
+    {
+      "epoch": 13.01,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.2476,
+      "step": 400
+    },
+    {
+      "epoch": 14.03,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.0259,
+      "step": 450
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.8942,
+      "step": 500
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.7583,
+      "step": 550
+    },
+    {
+      "epoch": 19.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.6224,
+      "step": 600
+    },
+    {
+      "epoch": 21.02,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.55,
+      "step": 650
+    },
+    {
+      "epoch": 23.01,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.4646,
+      "step": 700
+    },
+    {
+      "epoch": 24.02,
+      "learning_rate": 0.00025,
+      "loss": 3.3628,
+      "step": 750
+    },
+    {
+      "epoch": 26.02,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.3208,
+      "step": 800
+    },
+    {
+      "epoch": 28.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.2586,
+      "step": 850
+    },
+    {
+      "epoch": 29.02,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.179,
+      "step": 900
+    },
+    {
+      "epoch": 31.02,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.1549,
+      "step": 950
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.109,
+      "step": 1000
+    },
+    {
+      "epoch": 33.01,
+      "eval_loss": 3.771193027496338,
+      "eval_runtime": 2.3153,
+      "eval_samples_per_second": 51.828,
+      "eval_steps_per_second": 3.455,
+      "step": 1000
+    },
+    {
+      "epoch": 33.01,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_loss": 3.771193027496338,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_ppl": 43.43184933001428,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_runtime": 2.3153,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 51.828,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.70701680656384e+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:ce5ee64ec673c5915c725d59ab09d5567c896e983bbaa61ee563d03df6350d2f
+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": 64000
+}

checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d50cb83c99564e1e5d3175eea21dacb67ba376d216c36c391dd2180aa4f075
+size 1080041009

checkpoint-1100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:467d06af9b109ba6e6d6491715b596472f2392acad5ef29a5dd5227f028ea538
+size 552615017

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93443d06884eb77ceedb13ea088d03d6d30a18ae355271b718160fb29419aa5
+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": 36.016666666666666,
+  "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": 11.1049,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.1845,
+      "step": 50
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0005,
+      "loss": 5.9529,
+      "step": 100
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.1965,
+      "step": 150
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.8925,
+      "step": 200
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 4.7182,
+      "step": 250
+    },
+    {
+      "epoch": 9.03,
+      "learning_rate": 0.0005,
+      "loss": 4.561,
+      "step": 300
+    },
+    {
+      "epoch": 11.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.4282,
+      "step": 350
+    },
+    {
+      "epoch": 13.01,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.2476,
+      "step": 400
+    },
+    {
+      "epoch": 14.03,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.0259,
+      "step": 450
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.8942,
+      "step": 500
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.7583,
+      "step": 550
+    },
+    {
+      "epoch": 19.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.6224,
+      "step": 600
+    },
+    {
+      "epoch": 21.02,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.55,
+      "step": 650
+    },
+    {
+      "epoch": 23.01,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.4646,
+      "step": 700
+    },
+    {
+      "epoch": 24.02,
+      "learning_rate": 0.00025,
+      "loss": 3.3628,
+      "step": 750
+    },
+    {
+      "epoch": 26.02,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.3208,
+      "step": 800
+    },
+    {
+      "epoch": 28.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.2586,
+      "step": 850
+    },
+    {
+      "epoch": 29.02,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.179,
+      "step": 900
+    },
+    {
+      "epoch": 31.02,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.1549,
+      "step": 950
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.109,
+      "step": 1000
+    },
+    {
+      "epoch": 33.01,
+      "eval_loss": 3.771193027496338,
+      "eval_runtime": 2.3153,
+      "eval_samples_per_second": 51.828,
+      "eval_steps_per_second": 3.455,
+      "step": 1000
+    },
+    {
+      "epoch": 33.01,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_loss": 3.771193027496338,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_ppl": 43.43184933001428,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_runtime": 2.3153,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 51.828,
+      "step": 1000
+    },
+    {
+      "epoch": 34.02,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.0475,
+      "step": 1050
+    },
+    {
+      "epoch": 36.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.0353,
+      "step": 1100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.97743315632128e+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:ce5ee64ec673c5915c725d59ab09d5567c896e983bbaa61ee563d03df6350d2f
+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": 64000
+}

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c77ebd7b3e810bc9abfed02f11a55b5c7c56c2f4218b2d712cda53ac3f984ab
+size 1080041009

checkpoint-1200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d481dd90e0112c7b86510b69821042c684cc4f5d27820394af11badd3314e8a
+size 552615017

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9ebfe865a5282871ec45b1fd3fdc036c41e34c0448643d1196546f03780d0e
+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": 39.025,
+  "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": 11.1049,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.1845,
+      "step": 50
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.0005,
+      "loss": 5.9529,
+      "step": 100
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.1965,
+      "step": 150
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.8925,
+      "step": 200
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 4.7182,
+      "step": 250
+    },
+    {
+      "epoch": 9.03,
+      "learning_rate": 0.0005,
+      "loss": 4.561,
+      "step": 300
+    },
+    {
+      "epoch": 11.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.4282,
+      "step": 350
+    },
+    {
+      "epoch": 13.01,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.2476,
+      "step": 400
+    },
+    {
+      "epoch": 14.03,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.0259,
+      "step": 450
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.8942,
+      "step": 500
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.7583,
+      "step": 550
+    },
+    {
+      "epoch": 19.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.6224,
+      "step": 600
+    },
+    {
+      "epoch": 21.02,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.55,
+      "step": 650
+    },
+    {
+      "epoch": 23.01,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.4646,
+      "step": 700
+    },
+    {
+      "epoch": 24.02,
+      "learning_rate": 0.00025,
+      "loss": 3.3628,
+      "step": 750
+    },
+    {
+      "epoch": 26.02,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.3208,
+      "step": 800
+    },
+    {
+      "epoch": 28.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.2586,
+      "step": 850
+    },
+    {
+      "epoch": 29.02,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.179,
+      "step": 900
+    },
+    {
+      "epoch": 31.02,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.1549,
+      "step": 950
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.109,
+      "step": 1000
+    },
+    {
+      "epoch": 33.01,
+      "eval_loss": 3.771193027496338,
+      "eval_runtime": 2.3153,
+      "eval_samples_per_second": 51.828,
+      "eval_steps_per_second": 3.455,
+      "step": 1000
+    },
+    {
+      "epoch": 33.01,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_loss": 3.771193027496338,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_ppl": 43.43184933001428,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_runtime": 2.3153,
+      "eval_/local/xiulyang/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 51.828,
+      "step": 1000
+    },
+    {
+      "epoch": 34.02,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.0475,
+      "step": 1050
+    },
+    {
+      "epoch": 36.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.0353,
+      "step": 1100
+    },
+    {
+      "epoch": 38.01,
+      "learning_rate": 2.7777777777777772e-05,
+      "loss": 3.0056,
+      "step": 1150
+    },
+    {
+      "epoch": 39.02,
+      "learning_rate": 0.0,
+      "loss": 2.9624,
+      "step": 1200
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 3.24784950607872e+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:ce5ee64ec673c5915c725d59ab09d5567c896e983bbaa61ee563d03df6350d2f
+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": 64000
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69570f0d843d941da8491c5d608d1c4f7ed6d0693201944b4b80231337f2fcae
+size 1080040817

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f133ee7219637c8594a9cf12dc29a56c6075c91e046268d9fedf14d8308b1a
+size 552615017

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af37345c427ea9f754fbb6c9c6176b458022161879b0d521e1d1ef82b4fa5d6
+size 14567