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": 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:f315e249c575e17de3e6961ca2ae12d127be6daa71a9eab261285cd82649d224
+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:a0e0bff3da591a37483fbdb2c6720640af7f0ea4c999c910dba2eb453a70a204
+size 816635249

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3c905b92cc53437524205131a67a775f18714e2013b47cf9d71af80f762b28
+size 420912233

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207530ef64ef63afe414764b2b31c49b25058123a2a475653cc795510e30185b
+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": 10.1072,
+      "step": 1
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00025,
+      "loss": 6.9379,
+      "step": 50
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0005,
+      "loss": 4.9342,
+      "step": 100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.7044770480128e+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:f315e249c575e17de3e6961ca2ae12d127be6daa71a9eab261285cd82649d224
+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 sha256:0cfa38bb1ba6e891e3bc944e9b8e7ee876b6c234b9b49d764ed8e600c7c55c74
+size 816635441

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c98c76b89281c7e76d491f5a38dc852e84312c1c49ca1ceb74e29312692197a4
+size 420912233

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc08780ff5de424785b55796236eefb06ce7099ddacd7d500c5f1576fab3027
+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": 10.1072,
+      "step": 1
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00025,
+      "loss": 6.9379,
+      "step": 50
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0005,
+      "loss": 4.9342,
+      "step": 100
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 4.3732,
+      "step": 150
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.0714,
+      "step": 200
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 3.9498,
+      "step": 250
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005,
+      "loss": 3.8436,
+      "step": 300
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 3.625,
+      "step": 350
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 3.5012,
+      "step": 400
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 3.3399,
+      "step": 450
+    },
+    {
+      "epoch": 13.03,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.2438,
+      "step": 500
+    },
+    {
+      "epoch": 15.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.1962,
+      "step": 550
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.0903,
+      "step": 600
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.0601,
+      "step": 650
+    },
+    {
+      "epoch": 19.01,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 2.9726,
+      "step": 700
+    },
+    {
+      "epoch": 20.02,
+      "learning_rate": 0.00025,
+      "loss": 2.9202,
+      "step": 750
+    },
+    {
+      "epoch": 22.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 2.9065,
+      "step": 800
+    },
+    {
+      "epoch": 23.02,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 2.8338,
+      "step": 850
+    },
+    {
+      "epoch": 24.03,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 2.7941,
+      "step": 900
+    },
+    {
+      "epoch": 26.01,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 2.7915,
+      "step": 950
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 2.7268,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_loss": 3.4587721824645996,
+      "eval_runtime": 2.4277,
+      "eval_samples_per_second": 54.372,
+      "eval_steps_per_second": 3.707,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 3.4587721824645996,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 31.777935045784314,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 2.4277,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 54.372,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.71457337212928e+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:f315e249c575e17de3e6961ca2ae12d127be6daa71a9eab261285cd82649d224
+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:a3052769795b4e67ca9a03ef223df4ce71777479a3489e2b1e4f85d887d302b4
+size 816635441

checkpoint-1100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88e8dcddb6f8dfc4a1c7386c56528608c898c77d1d3872a7b9f82e19bcdb40c
+size 420912233

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57263e67bf3cdd95a83cf82ef463fe03ed0872e6225b179f010d87e94d17b551
+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": 10.1072,
+      "step": 1
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00025,
+      "loss": 6.9379,
+      "step": 50
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0005,
+      "loss": 4.9342,
+      "step": 100
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 4.3732,
+      "step": 150
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.0714,
+      "step": 200
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 3.9498,
+      "step": 250
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005,
+      "loss": 3.8436,
+      "step": 300
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 3.625,
+      "step": 350
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 3.5012,
+      "step": 400
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 3.3399,
+      "step": 450
+    },
+    {
+      "epoch": 13.03,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.2438,
+      "step": 500
+    },
+    {
+      "epoch": 15.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.1962,
+      "step": 550
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.0903,
+      "step": 600
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.0601,
+      "step": 650
+    },
+    {
+      "epoch": 19.01,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 2.9726,
+      "step": 700
+    },
+    {
+      "epoch": 20.02,
+      "learning_rate": 0.00025,
+      "loss": 2.9202,
+      "step": 750
+    },
+    {
+      "epoch": 22.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 2.9065,
+      "step": 800
+    },
+    {
+      "epoch": 23.02,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 2.8338,
+      "step": 850
+    },
+    {
+      "epoch": 24.03,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 2.7941,
+      "step": 900
+    },
+    {
+      "epoch": 26.01,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 2.7915,
+      "step": 950
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 2.7268,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_loss": 3.4587721824645996,
+      "eval_runtime": 2.4277,
+      "eval_samples_per_second": 54.372,
+      "eval_steps_per_second": 3.707,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 3.4587721824645996,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 31.777935045784314,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 2.4277,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 54.372,
+      "step": 1000
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 2.7262,
+      "step": 1050
+    },
+    {
+      "epoch": 30.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 2.6701,
+      "step": 1100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.9864634089472e+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:f315e249c575e17de3e6961ca2ae12d127be6daa71a9eab261285cd82649d224
+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 sha256:8dfa23e00d412f804a994d257ce794babc8f50934013b77c620bbb117253873f
+size 816635441

checkpoint-1200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb4d6589696541b6a5d42066e70e1f0fd48588b2aa262cd7b5b9f593990c31c7
+size 420912233

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9a793d005134c927444bc883ef1dcd9d1cbc7896b0c3844d99599edebfea67c
+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": 10.1072,
+      "step": 1
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00025,
+      "loss": 6.9379,
+      "step": 50
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.0005,
+      "loss": 4.9342,
+      "step": 100
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 4.3732,
+      "step": 150
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.0714,
+      "step": 200
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 3.9498,
+      "step": 250
+    },
+    {
+      "epoch": 8.01,
+      "learning_rate": 0.0005,
+      "loss": 3.8436,
+      "step": 300
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 3.625,
+      "step": 350
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 3.5012,
+      "step": 400
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 3.3399,
+      "step": 450
+    },
+    {
+      "epoch": 13.03,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 3.2438,
+      "step": 500
+    },
+    {
+      "epoch": 15.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 3.1962,
+      "step": 550
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.0903,
+      "step": 600
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.0601,
+      "step": 650
+    },
+    {
+      "epoch": 19.01,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 2.9726,
+      "step": 700
+    },
+    {
+      "epoch": 20.02,
+      "learning_rate": 0.00025,
+      "loss": 2.9202,
+      "step": 750
+    },
+    {
+      "epoch": 22.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 2.9065,
+      "step": 800
+    },
+    {
+      "epoch": 23.02,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 2.8338,
+      "step": 850
+    },
+    {
+      "epoch": 24.03,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 2.7941,
+      "step": 900
+    },
+    {
+      "epoch": 26.01,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 2.7915,
+      "step": 950
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 2.7268,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_loss": 3.4587721824645996,
+      "eval_runtime": 2.4277,
+      "eval_samples_per_second": 54.372,
+      "eval_steps_per_second": 3.707,
+      "step": 1000
+    },
+    {
+      "epoch": 27.02,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 3.4587721824645996,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 31.777935045784314,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 2.4277,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 54.372,
+      "step": 1000
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 2.7262,
+      "step": 1050
+    },
+    {
+      "epoch": 30.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 2.6701,
+      "step": 1100
+    },
+    {
+      "epoch": 31.03,
+      "learning_rate": 2.7777777777777772e-05,
+      "loss": 2.6452,
+      "step": 1150
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.0,
+      "loss": 2.6559,
+      "step": 1200
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 3.25835344576512e+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:f315e249c575e17de3e6961ca2ae12d127be6daa71a9eab261285cd82649d224
+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:e0d615c60241e4c79b6d1fdaa92f7c7a30b8faf593df18182968c9d04a4e0634
+size 816635249

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f9211ad55bb39b4ee22db2d1f18967347e9d9087b08a0a6ada46c5a862aed3
+size 420912233

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c7ede958dcb6bb605c0331e9f62ef81d5e3ad19dd98e39e321a4b9313a8cf1
+size 14567

checkpoint-200/scaler.pt

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