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": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": 21128
+}

checkpoint-0/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4cb7ddeb977797468ae0b2e8a977bb66b33b53cf9ce0a85051cfaa03f3f32eb
+size 420912233

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:c1b35750be97d879197cd55984e3e07f6504747c6e5cdcc00a60dc8b2336ab3f
+size 3183

checkpoint-100/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": 21128
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ec9c716646a936e17664b6ac897e8ef1c5e346e4604248879910abe36c9d9d
+size 816635249

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5c0334ea74d21e0c345920408cfa289848610a5fbcc9d166f1a1d3d02b73a7
+size 420912233

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf2b9119c5ee54f7d5de06e880d4157349bc34f034dd2f1f90bb759f212bdc47
+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": 2.0233333333333334,
+  "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": 10.1057,
+      "step": 1
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00025,
+      "loss": 6.9186,
+      "step": 50
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0005,
+      "loss": 5.0259,
+      "step": 100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.7043725312e+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:c1b35750be97d879197cd55984e3e07f6504747c6e5cdcc00a60dc8b2336ab3f
+size 3183

checkpoint-1000/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": 21128
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc7546fecf1ccf0d1c40d7d1b86eeaebaa6e63bca5a30e2ce2c6fe9822dbe29
+size 816635441

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac5314f8463f130b2ec7fecdcf5b17c9f2f0e77d7cff436be736695089a48115
+size 420912233

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073bb4d4e2cdffa2f0d4373aa6e4d7efc3b064cb8395beb8f55fbc1a2d560b58
+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": 27.023333333333333,
+  "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": 10.1057,
+      "step": 1
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00025,
+      "loss": 6.9186,
+      "step": 50
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0005,
+      "loss": 5.0259,
+      "step": 100
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 4.4066,
+      "step": 150
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.0717,
+      "step": 200
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 3.9529,
+      "step": 250
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005,
+      "loss": 3.8418,
+      "step": 300
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 3.638,
+      "step": 350
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 3.5046,
+      "step": 400
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 3.3451,
+      "step": 450
+    },
+    {
+      "epoch": 13.03,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.2467,
+      "step": 500
+    },
+    {
+      "epoch": 15.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.1935,
+      "step": 550
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.0847,
+      "step": 600
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.0537,
+      "step": 650
+    },
+    {
+      "epoch": 19.01,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 2.9658,
+      "step": 700
+    },
+    {
+      "epoch": 20.02,
+      "learning_rate": 0.00025,
+      "loss": 2.914,
+      "step": 750
+    },
+    {
+      "epoch": 22.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 2.8995,
+      "step": 800
+    },
+    {
+      "epoch": 23.02,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 2.8259,
+      "step": 850
+    },
+    {
+      "epoch": 24.03,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 2.7888,
+      "step": 900
+    },
+    {
+      "epoch": 26.01,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 2.7837,
+      "step": 950
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 2.7195,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_loss": 3.4416074752807617,
+      "eval_runtime": 6.4098,
+      "eval_samples_per_second": 20.593,
+      "eval_steps_per_second": 1.404,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 3.4416074752807617,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 31.2371307474338,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 6.4098,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 20.593,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.714432274432e+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:c1b35750be97d879197cd55984e3e07f6504747c6e5cdcc00a60dc8b2336ab3f
+size 3183

checkpoint-1100/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": 21128
+}

checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81f003f07937484c4fd75cced6fba8d3c8c9a244f89ceea845a06c546b52914
+size 816635441

checkpoint-1100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a3279b646b1c08d5bb370d4d4001bef421e25d0546ba330525d19f67e3da31
+size 420912233

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c7d341a5b762c20e215d6aed5ce9bd5b1a68f4a7b69498b4e1dae71559aa493
+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": 30.016666666666666,
+  "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": 10.1057,
+      "step": 1
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00025,
+      "loss": 6.9186,
+      "step": 50
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0005,
+      "loss": 5.0259,
+      "step": 100
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 4.4066,
+      "step": 150
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.0717,
+      "step": 200
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 3.9529,
+      "step": 250
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005,
+      "loss": 3.8418,
+      "step": 300
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 3.638,
+      "step": 350
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 3.5046,
+      "step": 400
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 3.3451,
+      "step": 450
+    },
+    {
+      "epoch": 13.03,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.2467,
+      "step": 500
+    },
+    {
+      "epoch": 15.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.1935,
+      "step": 550
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.0847,
+      "step": 600
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.0537,
+      "step": 650
+    },
+    {
+      "epoch": 19.01,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 2.9658,
+      "step": 700
+    },
+    {
+      "epoch": 20.02,
+      "learning_rate": 0.00025,
+      "loss": 2.914,
+      "step": 750
+    },
+    {
+      "epoch": 22.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 2.8995,
+      "step": 800
+    },
+    {
+      "epoch": 23.02,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 2.8259,
+      "step": 850
+    },
+    {
+      "epoch": 24.03,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 2.7888,
+      "step": 900
+    },
+    {
+      "epoch": 26.01,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 2.7837,
+      "step": 950
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 2.7195,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_loss": 3.4416074752807617,
+      "eval_runtime": 6.4098,
+      "eval_samples_per_second": 20.593,
+      "eval_steps_per_second": 1.404,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 3.4416074752807617,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 31.2371307474338,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 6.4098,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 20.593,
+      "step": 1000
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 2.7186,
+      "step": 1050
+    },
+    {
+      "epoch": 30.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 2.6634,
+      "step": 1100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.986306633728e+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:c1b35750be97d879197cd55984e3e07f6504747c6e5cdcc00a60dc8b2336ab3f
+size 3183

checkpoint-1200/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": 21128
+}

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:265f7bd427ee51103d82ed2fb0ec5351c167ab4052ea8f186c688346f172492a
+size 816635441

checkpoint-1200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fec5a3b6a479aa9359b1a1bd83bd33ff311990014fd6d42f5dafb272dd223d5
+size 420912233

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4370a90bd99585f0d7c30a5291ac27b6d766574cccf1ec17689cbd0f2533b864
+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": 33.01,
+  "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": 10.1057,
+      "step": 1
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00025,
+      "loss": 6.9186,
+      "step": 50
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0005,
+      "loss": 5.0259,
+      "step": 100
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 4.4066,
+      "step": 150
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.0717,
+      "step": 200
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 3.9529,
+      "step": 250
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005,
+      "loss": 3.8418,
+      "step": 300
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 3.638,
+      "step": 350
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 3.5046,
+      "step": 400
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 3.3451,
+      "step": 450
+    },
+    {
+      "epoch": 13.03,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.2467,
+      "step": 500
+    },
+    {
+      "epoch": 15.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.1935,
+      "step": 550
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.0847,
+      "step": 600
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.0537,
+      "step": 650
+    },
+    {
+      "epoch": 19.01,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 2.9658,
+      "step": 700
+    },
+    {
+      "epoch": 20.02,
+      "learning_rate": 0.00025,
+      "loss": 2.914,
+      "step": 750
+    },
+    {
+      "epoch": 22.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 2.8995,
+      "step": 800
+    },
+    {
+      "epoch": 23.02,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 2.8259,
+      "step": 850
+    },
+    {
+      "epoch": 24.03,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 2.7888,
+      "step": 900
+    },
+    {
+      "epoch": 26.01,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 2.7837,
+      "step": 950
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 2.7195,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_loss": 3.4416074752807617,
+      "eval_runtime": 6.4098,
+      "eval_samples_per_second": 20.593,
+      "eval_steps_per_second": 1.404,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 3.4416074752807617,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 31.2371307474338,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 6.4098,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 20.593,
+      "step": 1000
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 2.7186,
+      "step": 1050
+    },
+    {
+      "epoch": 30.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 2.6634,
+      "step": 1100
+    },
+    {
+      "epoch": 31.03,
+      "learning_rate": 2.7777777777777772e-05,
+      "loss": 2.6397,
+      "step": 1150
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.0,
+      "loss": 2.6492,
+      "step": 1200
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 3.258180993024e+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:c1b35750be97d879197cd55984e3e07f6504747c6e5cdcc00a60dc8b2336ab3f
+size 3183

checkpoint-200/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": 21128
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75f41b025baaffbb6e7ab85128bf744ab29a952a42e03b0d9bc1e6261374a33
+size 816635249

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7447d4f7711d8f3bf5bfde0461090910459224ea38e1f6fcbddf825777b76297
+size 420912233

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39f44e4b5be7446f136f301364ee8d940bbcc5f80d28b465050f2a5f6747422
+size 14567