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": 50258
+}

checkpoint-0/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28fc75d2dcd1513adf448c40546844d043bcc20c27c91e66794e777abd46a657
+size 510399593

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:a4e776cdc9224e2cfce3f2fbeadf5a233abede786c6e7415418f42a0943b801f
+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": 50258
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08951eebdc1d259a1f6b9348ad382cc96920fcb10e0f3002c26ca8d446298c0b
+size 995609969

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31174999157698948e1dcb9c83d8ffabf1d071c581243f34611d56e4bbf87953
+size 510399593

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe71c909637a5ae9ee1851d9c38e23f6ccee60e223424eea519ad833402807c
+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": 10.9381,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.1535,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 6.3027,
+      "step": 100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.7231332990976e+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:a4e776cdc9224e2cfce3f2fbeadf5a233abede786c6e7415418f42a0943b801f
+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": 50258
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea9e4403d5924a53dd5f06758a75db54dabb99f42110351983affadfccdfd47
+size 995610161

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7533d6bec340473054fa35abdebc872322614ab505e437285cf93aea6c8f5fe8
+size 510399593

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d13732deb3ee495f2d77b9195f56d29c6d5d40a3b15b46e768dde20754366b3
+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": 10.9381,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.1535,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 6.3027,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.5764,
+      "step": 150
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 5.1661,
+      "step": 200
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 4.9617,
+      "step": 250
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0005,
+      "loss": 4.8355,
+      "step": 300
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.6745,
+      "step": 350
+    },
+    {
+      "epoch": 14.02,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.5938,
+      "step": 400
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.4347,
+      "step": 450
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.2584,
+      "step": 500
+    },
+    {
+      "epoch": 20.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.1031,
+      "step": 550
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.9753,
+      "step": 600
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.8633,
+      "step": 650
+    },
+    {
+      "epoch": 25.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.725,
+      "step": 700
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00025,
+      "loss": 3.6879,
+      "step": 750
+    },
+    {
+      "epoch": 29.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.614,
+      "step": 800
+    },
+    {
+      "epoch": 31.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.5484,
+      "step": 850
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.4879,
+      "step": 900
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.4323,
+      "step": 950
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.3835,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 4.287466526031494,
+      "eval_runtime": 2.0602,
+      "eval_samples_per_second": 49.509,
+      "eval_steps_per_second": 3.398,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 4.287466526031494,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 72.78184382077507,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 2.0602,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 49.509,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.73421730709504e+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:a4e776cdc9224e2cfce3f2fbeadf5a233abede786c6e7415418f42a0943b801f
+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": 50258
+}

checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5afe748d60e2bcb1d3205b3e152f121adb1ac0dcdc77f73b336eb3160b0b28bc
+size 995610161

checkpoint-1100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c379e44b4e621b494df392e72f1a345bcb3bd01dd80c0812acf8ce2939fb833d
+size 510399593

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ffb57a9bbe0419706375166a34c9a8df2e514ef94d40bc1541a96da5c4299b2
+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": 10.9381,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.1535,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 6.3027,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.5764,
+      "step": 150
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 5.1661,
+      "step": 200
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 4.9617,
+      "step": 250
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0005,
+      "loss": 4.8355,
+      "step": 300
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.6745,
+      "step": 350
+    },
+    {
+      "epoch": 14.02,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.5938,
+      "step": 400
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.4347,
+      "step": 450
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.2584,
+      "step": 500
+    },
+    {
+      "epoch": 20.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.1031,
+      "step": 550
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.9753,
+      "step": 600
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.8633,
+      "step": 650
+    },
+    {
+      "epoch": 25.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.725,
+      "step": 700
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00025,
+      "loss": 3.6879,
+      "step": 750
+    },
+    {
+      "epoch": 29.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.614,
+      "step": 800
+    },
+    {
+      "epoch": 31.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.5484,
+      "step": 850
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.4879,
+      "step": 900
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.4323,
+      "step": 950
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.3835,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 4.287466526031494,
+      "eval_runtime": 2.0602,
+      "eval_samples_per_second": 49.509,
+      "eval_steps_per_second": 3.398,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 4.287466526031494,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 72.78184382077507,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 2.0602,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 49.509,
+      "step": 1000
+    },
+    {
+      "epoch": 38.02,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.3029,
+      "step": 1050
+    },
+    {
+      "epoch": 40.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.3057,
+      "step": 1100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 3.0065306370048e+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:a4e776cdc9224e2cfce3f2fbeadf5a233abede786c6e7415418f42a0943b801f
+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": 50258
+}

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332fa102b4009c0b0e6c27e7bba9065ae3ee5888fcec40a7f804af06b23ba6bd
+size 995610161

checkpoint-1200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a7cb049911eeca440b3274bad253a9050fcf6054987108f42a55d3bbab9569
+size 510399593

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0231c15742993598984f8e9b7c59dc8c92bc785cb4799a2d49aff865a53c4d1e
+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": 10.9381,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.1535,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 6.3027,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.5764,
+      "step": 150
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 5.1661,
+      "step": 200
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 4.9617,
+      "step": 250
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0005,
+      "loss": 4.8355,
+      "step": 300
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.6745,
+      "step": 350
+    },
+    {
+      "epoch": 14.02,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.5938,
+      "step": 400
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.4347,
+      "step": 450
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.2584,
+      "step": 500
+    },
+    {
+      "epoch": 20.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.1031,
+      "step": 550
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.9753,
+      "step": 600
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.8633,
+      "step": 650
+    },
+    {
+      "epoch": 25.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.725,
+      "step": 700
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00025,
+      "loss": 3.6879,
+      "step": 750
+    },
+    {
+      "epoch": 29.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.614,
+      "step": 800
+    },
+    {
+      "epoch": 31.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.5484,
+      "step": 850
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.4879,
+      "step": 900
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.4323,
+      "step": 950
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.3835,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 4.287466526031494,
+      "eval_runtime": 2.0602,
+      "eval_samples_per_second": 49.509,
+      "eval_steps_per_second": 3.398,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 4.287466526031494,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 72.78184382077507,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 2.0602,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 49.509,
+      "step": 1000
+    },
+    {
+      "epoch": 38.02,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.3029,
+      "step": 1050
+    },
+    {
+      "epoch": 40.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.3057,
+      "step": 1100
+    },
+    {
+      "epoch": 42.01,
+      "learning_rate": 2.7777777777777772e-05,
+      "loss": 3.2755,
+      "step": 1150
+    },
+    {
+      "epoch": 44.01,
+      "learning_rate": 0.0,
+      "loss": 3.2528,
+      "step": 1200
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 3.28042739662848e+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:a4e776cdc9224e2cfce3f2fbeadf5a233abede786c6e7415418f42a0943b801f
+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": 50258
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d1052a3c50ed94a438edd31299791b75021b531f6f5b893b15dc8319893955
+size 995609969

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c28608bdc56ab3cc62d7dde25681534ec187271425e212ba1f4ef8e69725cdf
+size 510399593

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0b1816e309795f766856b15e312b50d31c431b72aa5b1e7063c695815889d2
+size 14567

checkpoint-200/scaler.pt

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