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": 50265,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50265,
+  "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": 50304
+}

checkpoint-0/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bf6710370f171ee8d9458cdd95869d242e2df0f5a9a4d008d7fcf6814e88665
+size 510540905

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 sha256:485c9b2d729535bbb8f758f4771309eb0027c65ce008ed7854cba07ae7df8dac
+size 3183

checkpoint-100/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50265,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50265,
+  "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": 50304
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af80915f804bb8d399004d0769b2016e4d5ec316aad90fea99c1928a7c9cea0a
+size 995892593

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e26f49434628bed2d16a5b73d19d86c0628c476fa274c7cd6af6129356c798
+size 510540905

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b060df0f5798b013eca023f0faaea1308e82b83691b58e6cd0ca4ce78e1ae5fc
+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": 11.0133,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.26,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 6.2745,
+      "step": 100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.7535476916224e+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 sha256:485c9b2d729535bbb8f758f4771309eb0027c65ce008ed7854cba07ae7df8dac
+size 3183

checkpoint-1000/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50265,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50265,
+  "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": 50304
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758a763b0e22b2e20b0924fb3306e695f48deee9f391401b8cb38b55b0d473f5
+size 995892785

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cf62178f4ab46aa726f3adafb6af9d924dc0d48220e1ea62d56f4dcbf405fef
+size 510540905

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb115187959259fc96bde36e2eec6991edb3e1d2742cee93eaf4e6b48b1d67f
+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": 11.0133,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.26,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 6.2745,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.6705,
+      "step": 150
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 5.3288,
+      "step": 200
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 5.1396,
+      "step": 250
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0005,
+      "loss": 4.9995,
+      "step": 300
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.7272,
+      "step": 350
+    },
+    {
+      "epoch": 14.02,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.6129,
+      "step": 400
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.4105,
+      "step": 450
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.2453,
+      "step": 500
+    },
+    {
+      "epoch": 20.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.1117,
+      "step": 550
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.9934,
+      "step": 600
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.8898,
+      "step": 650
+    },
+    {
+      "epoch": 25.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.7236,
+      "step": 700
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00025,
+      "loss": 3.7193,
+      "step": 750
+    },
+    {
+      "epoch": 29.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.646,
+      "step": 800
+    },
+    {
+      "epoch": 31.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.58,
+      "step": 850
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.5186,
+      "step": 900
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.4626,
+      "step": 950
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.4116,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 4.330337047576904,
+      "eval_runtime": 2.0072,
+      "eval_samples_per_second": 52.311,
+      "eval_steps_per_second": 3.487,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 4.330337047576904,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 75.96988772111594,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 2.0072,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 52.311,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.77172839120896e+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 sha256:485c9b2d729535bbb8f758f4771309eb0027c65ce008ed7854cba07ae7df8dac
+size 3183

checkpoint-1100/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50265,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50265,
+  "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": 50304
+}

checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cbbbf1631dafdcdba7911e5a24a85364228b36f0802291aae686324471aed1
+size 995892785

checkpoint-1100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f37bd0988711cdc551180a5bdb2928cd776897a596dc2449dbdf9b9fcc1f55
+size 510540905

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ced93d91dfc25f3f24cdbd5d296a722d6c5a9010530936a22627d8c1964893
+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": 11.0133,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.26,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 6.2745,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.6705,
+      "step": 150
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 5.3288,
+      "step": 200
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 5.1396,
+      "step": 250
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0005,
+      "loss": 4.9995,
+      "step": 300
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.7272,
+      "step": 350
+    },
+    {
+      "epoch": 14.02,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.6129,
+      "step": 400
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.4105,
+      "step": 450
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.2453,
+      "step": 500
+    },
+    {
+      "epoch": 20.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.1117,
+      "step": 550
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.9934,
+      "step": 600
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.8898,
+      "step": 650
+    },
+    {
+      "epoch": 25.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.7236,
+      "step": 700
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00025,
+      "loss": 3.7193,
+      "step": 750
+    },
+    {
+      "epoch": 29.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.646,
+      "step": 800
+    },
+    {
+      "epoch": 31.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.58,
+      "step": 850
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.5186,
+      "step": 900
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.4626,
+      "step": 950
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.4116,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 4.330337047576904,
+      "eval_runtime": 2.0072,
+      "eval_samples_per_second": 52.311,
+      "eval_steps_per_second": 3.487,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 4.330337047576904,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 75.96988772111594,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 2.0072,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 52.311,
+      "step": 1000
+    },
+    {
+      "epoch": 38.02,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.3058,
+      "step": 1050
+    },
+    {
+      "epoch": 40.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.3342,
+      "step": 1100
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 3.0470831603712e+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 sha256:485c9b2d729535bbb8f758f4771309eb0027c65ce008ed7854cba07ae7df8dac
+size 3183

checkpoint-1200/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50265,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50265,
+  "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": 50304
+}

checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0c9d11601068a097212e66ad796e9addc40ce40b96db203be00918a32abb82
+size 995892785

checkpoint-1200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:980025cd9a2e665af8f0ada0a56235534ff66d167d904d5c65bbd1c23c6e86ef
+size 510540905

checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2002650954344fe856d34fb3916d9e7ccc4d1422cb62944d912a4f05655f6fd4
+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": 11.0133,
+      "step": 1
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00025,
+      "loss": 8.26,
+      "step": 50
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0005,
+      "loss": 6.2745,
+      "step": 100
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 5.6705,
+      "step": 150
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 5.3288,
+      "step": 200
+    },
+    {
+      "epoch": 9.01,
+      "learning_rate": 0.0005277777777777777,
+      "loss": 5.1396,
+      "step": 250
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.0005,
+      "loss": 4.9995,
+      "step": 300
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 0.00047222222222222224,
+      "loss": 4.7272,
+      "step": 350
+    },
+    {
+      "epoch": 14.02,
+      "learning_rate": 0.00044444444444444436,
+      "loss": 4.6129,
+      "step": 400
+    },
+    {
+      "epoch": 16.02,
+      "learning_rate": 0.00041666666666666664,
+      "loss": 4.4105,
+      "step": 450
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.00038888888888888887,
+      "loss": 4.2453,
+      "step": 500
+    },
+    {
+      "epoch": 20.01,
+      "learning_rate": 0.0003611111111111111,
+      "loss": 4.1117,
+      "step": 550
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 3.9934,
+      "step": 600
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.00030555555555555555,
+      "loss": 3.8898,
+      "step": 650
+    },
+    {
+      "epoch": 25.02,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 3.7236,
+      "step": 700
+    },
+    {
+      "epoch": 27.02,
+      "learning_rate": 0.00025,
+      "loss": 3.7193,
+      "step": 750
+    },
+    {
+      "epoch": 29.01,
+      "learning_rate": 0.00022222222222222218,
+      "loss": 3.646,
+      "step": 800
+    },
+    {
+      "epoch": 31.01,
+      "learning_rate": 0.00019444444444444443,
+      "loss": 3.58,
+      "step": 850
+    },
+    {
+      "epoch": 33.01,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 3.5186,
+      "step": 900
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 3.4626,
+      "step": 950
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 0.00011111111111111109,
+      "loss": 3.4116,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 4.330337047576904,
+      "eval_runtime": 2.0072,
+      "eval_samples_per_second": 52.311,
+      "eval_steps_per_second": 3.487,
+      "step": 1000
+    },
+    {
+      "epoch": 37.0,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_loss": 4.330337047576904,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_ppl": 75.96988772111594,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_runtime": 2.0072,
+      "eval_/scratch/xiulyang/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 52.311,
+      "step": 1000
+    },
+    {
+      "epoch": 38.02,
+      "learning_rate": 8.333333333333333e-05,
+      "loss": 3.3058,
+      "step": 1050
+    },
+    {
+      "epoch": 40.02,
+      "learning_rate": 5.5555555555555545e-05,
+      "loss": 3.3342,
+      "step": 1100
+    },
+    {
+      "epoch": 42.01,
+      "learning_rate": 2.7777777777777772e-05,
+      "loss": 3.3016,
+      "step": 1150
+    },
+    {
+      "epoch": 44.01,
+      "learning_rate": 0.0,
+      "loss": 3.2766,
+      "step": 1200
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 3.32503517233152e+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 sha256:485c9b2d729535bbb8f758f4771309eb0027c65ce008ed7854cba07ae7df8dac
+size 3183

checkpoint-200/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50265,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50265,
+  "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": 50304
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a730a5e9799fbbd08eb37092029a845a13250ede6e4058aa0a09605cf54bca7
+size 995892593

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd7facbecc448fe54043e0a03cc906f397a571f0b76383087baa49aca5ee61e
+size 510540905

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90555679dbbb2ebbf44868059eeb5115df285d7937edfdf1319859c23b9af38c
+size 14567

checkpoint-200/scaler.pt

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