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": 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": 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 sha256:9131ae0630f22b78604e09cef0c8dff88cf8609406b033dc165bbc050b6e1da2
+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": 50257
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65cc974bf237bc4862473ddce017e3404673c57386cec7b2a2d6e873dcb3a93
+size 995603825

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac8eb634b6294563efa3695830adc9cbef4faeb48f8df74ebdbbb4a5e562804
+size 510396521

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a64a197a7edf9a57e22c83e4a5734db266884b0986318b21348437ee23ba0d5
+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": 3.015833333333333,
+  "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": 11.0218,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 7.9982,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 5.8003,
+      "step": 100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.7521367146496e+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 sha256:9131ae0630f22b78604e09cef0c8dff88cf8609406b033dc165bbc050b6e1da2
+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": 50257
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e4e07613c8ac44dc3af95312b585a4daee3e55d655364c9dd2a065a9700c53
+size 995604017

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:837c8447ca30c606924c1ecf01f27fbb454363cacf7eef54c3782b034ca3e795
+size 510396521

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd76cd7940b6b0e5c7ab4b6336bb8b9f14f6188754dd45cd75f0c98a7b5c4f7
+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": 37.00083333333333,
+  "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": 11.0218,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 7.9982,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 5.8003,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.17,
+      "step": 150
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.9158,
+      "step": 200
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 4.7809,
+      "step": 250
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0005,
+      "loss": 4.6208,
+      "step": 300
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.3481,
+      "step": 350
+    },
+    {
+      "epoch": 14.02,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.2378,
+      "step": 400
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.0729,
+      "step": 450
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.941,
+      "step": 500
+    },
+    {
+      "epoch": 20.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.826,
+      "step": 550
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.7276,
+      "step": 600
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.6415,
+      "step": 650
+    },
+    {
+      "epoch": 25.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.4952,
+      "step": 700
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00025,
+      "loss": 3.4946,
+      "step": 750
+    },
+    {
+      "epoch": 29.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.4295,
+      "step": 800
+    },
+    {
+      "epoch": 31.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.3698,
+      "step": 850
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.3143,
+      "step": 900
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.2639,
+      "step": 950
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.2163,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 4.151810169219971,
+      "eval_runtime": 4.074,
+      "eval_samples_per_second": 49.828,
+      "eval_steps_per_second": 3.191,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 4.151810169219971,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 63.548930563193956,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 4.074,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 49.828,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.76998818627584e+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 sha256:9131ae0630f22b78604e09cef0c8dff88cf8609406b033dc165bbc050b6e1da2
+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": 50257
+}

checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ba8cbb1ffab22e189d5b327faa5e5799e4ad6c953255bf21a6ad6690584707
+size 995604017

checkpoint-1100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2213975aac7827e883852b1894da7ff46c13649b0cb3510e687e05e6e44683f9
+size 510396521

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e353cf611e1b76337f7001522c0bcdd4788189f63cefafdbff751e5826f33e
+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": 40.016666666666666,
+  "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": 11.0218,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 7.9982,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 5.8003,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.17,
+      "step": 150
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.9158,
+      "step": 200
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 4.7809,
+      "step": 250
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0005,
+      "loss": 4.6208,
+      "step": 300
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.3481,
+      "step": 350
+    },
+    {
+      "epoch": 14.02,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.2378,
+      "step": 400
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.0729,
+      "step": 450
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.941,
+      "step": 500
+    },
+    {
+      "epoch": 20.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.826,
+      "step": 550
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.7276,
+      "step": 600
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.6415,
+      "step": 650
+    },
+    {
+      "epoch": 25.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.4952,
+      "step": 700
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00025,
+      "loss": 3.4946,
+      "step": 750
+    },
+    {
+      "epoch": 29.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.4295,
+      "step": 800
+    },
+    {
+      "epoch": 31.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.3698,
+      "step": 850
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.3143,
+      "step": 900
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.2639,
+      "step": 950
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.2163,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 4.151810169219971,
+      "eval_runtime": 4.074,
+      "eval_samples_per_second": 49.828,
+      "eval_steps_per_second": 3.191,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 4.151810169219971,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 63.548930563193956,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 4.074,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 49.828,
+      "step": 1000
+    },
+    {
+      "epoch": 38.02,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.1173,
+      "step": 1050
+    },
+    {
+      "epoch": 40.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.142,
+      "step": 1100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 3.0452018577408e+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 sha256:9131ae0630f22b78604e09cef0c8dff88cf8609406b033dc165bbc050b6e1da2
+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": 50257
+}

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ac9a0d65845dfbbb8f8de320048d07c8a5fb00a775559df577a94122c31944
+size 995604017

checkpoint-1200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d1c2d7de9d86848620ec52ff13e53708da6000aa61b632e09724ee3a03a716
+size 510396521

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd43dac14229a387880bebbbe71e1a3e7065e469b52ed4055a8800fb99db168
+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": 44.01,
+  "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": 11.0218,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 7.9982,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 5.8003,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.17,
+      "step": 150
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.9158,
+      "step": 200
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 4.7809,
+      "step": 250
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0005,
+      "loss": 4.6208,
+      "step": 300
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.3481,
+      "step": 350
+    },
+    {
+      "epoch": 14.02,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.2378,
+      "step": 400
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.0729,
+      "step": 450
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.941,
+      "step": 500
+    },
+    {
+      "epoch": 20.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.826,
+      "step": 550
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.7276,
+      "step": 600
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.6415,
+      "step": 650
+    },
+    {
+      "epoch": 25.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.4952,
+      "step": 700
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00025,
+      "loss": 3.4946,
+      "step": 750
+    },
+    {
+      "epoch": 29.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.4295,
+      "step": 800
+    },
+    {
+      "epoch": 31.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.3698,
+      "step": 850
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.3143,
+      "step": 900
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.2639,
+      "step": 950
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.2163,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 4.151810169219971,
+      "eval_runtime": 4.074,
+      "eval_samples_per_second": 49.828,
+      "eval_steps_per_second": 3.191,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 4.151810169219971,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 63.548930563193956,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 4.074,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 49.828,
+      "step": 1000
+    },
+    {
+      "epoch": 38.02,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.1173,
+      "step": 1050
+    },
+    {
+      "epoch": 40.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.142,
+      "step": 1100
+    },
+    {
+      "epoch": 42.01,
+      "learning_rate": 2.7777777777777772e-05,
+      "loss": 3.1114,
+      "step": 1150
+    },
+    {
+      "epoch": 44.01,
+      "learning_rate": 0.0,
+      "loss": 3.0867,
+      "step": 1200
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 3.32296573943808e+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 sha256:9131ae0630f22b78604e09cef0c8dff88cf8609406b033dc165bbc050b6e1da2
+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": 50257
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28bfe6f6521538ad0413b5082cfab69823fcc146df3f851d8ad7d5ee4f30488a
+size 995603825

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c8b6b6f84c1e7e1832ad3793b2ac1eabaaa1a1ab52c200ab485eb9374da2f0c
+size 510396521

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda9c9259b80afbf9ea4107a8ff05e32f82acd24ef88f164fe3bc210879ec50a
+size 14567

checkpoint-200/scaler.pt

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