diff --git a/checkpoint-0/config.json b/checkpoint-0/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-0/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-0/pytorch_model.bin b/checkpoint-0/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..fa893f2ccbb9d7e06b71d530a16fca95fa6d3731 --- /dev/null +++ b/checkpoint-0/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d9938f9842ab67a4ffdb8192f0ef1a92afea4592e39c9cede29e616f6bb617f +size 552615017 diff --git a/checkpoint-0/special_tokens_map.json b/checkpoint-0/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-0/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-0/tokenizer_config.json b/checkpoint-0/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-0/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-0/training_args.bin b/checkpoint-0/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-0/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-100/config.json b/checkpoint-100/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-100/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..d84140743aa11aa010ece96162a2e636a57d1a33 --- /dev/null +++ b/checkpoint-100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95b0831d31438738fbe580bac666622ed94429f60377340f211ce731fb41d811 +size 1080040817 diff --git a/checkpoint-100/pytorch_model.bin b/checkpoint-100/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..8acc9cafe0fc475448b582786a33e7e758b1aad8 --- /dev/null +++ b/checkpoint-100/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c295b0b5608077d93439f9d63bfa6356eeb9a295dd3b0f7e6661446de5a1b8c1 +size 552615017 diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..792539610e28cfa8f05c937f93354042f2d68045 --- /dev/null +++ b/checkpoint-100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d38398143180e2c7b4595e45e727dd4b9db3fc072bc738ddff7e23b9076743 +size 14567 diff --git a/checkpoint-100/scaler.pt b/checkpoint-100/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..45cc4a33e17645cb0ed4a911b11c77cb2e7ce7f3 --- /dev/null +++ b/checkpoint-100/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13a3423b2fe42f204bc8fe2c666ff379f9fd753a0f13613064a5e71e86b519e8 +size 559 diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..595eec9094e91b3eb24c2de88c461df2c22026ab --- /dev/null +++ b/checkpoint-100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e9b9d31d11c624d89b0c04ad496adf4b5addd3e703848d2583972c703e8da6 +size 623 diff --git a/checkpoint-100/special_tokens_map.json b/checkpoint-100/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-100/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-100/tokenizer_config.json b/checkpoint-100/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-100/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..1a459e5fedabba82cdf8582622845aee863df3ce --- /dev/null +++ b/checkpoint-100/trainer_state.json @@ -0,0 +1,34 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0183333333333335, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 2.7248578265088e+16, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-1000/config.json b/checkpoint-1000/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-1000/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..7fc169199c439821427ef450bbc61d31ccf22342 --- /dev/null +++ b/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ebd8522964f26e55df2f10364d223745289424439cc94085bdb82979f944b41 +size 1080041009 diff --git a/checkpoint-1000/pytorch_model.bin b/checkpoint-1000/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..178db9ab52282169761dba072eeb05c6ccae2545 --- /dev/null +++ b/checkpoint-1000/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:247855c31423bd5c7a45dbf6bd016cdb4a638825dbfffc6cf8fafc1b2332c581 +size 552615017 diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..721c9e9d42c50e3fac9b5315620cc7a004cbddec --- /dev/null +++ b/checkpoint-1000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccde6059ea50589bf1b44294c33973f3c892a3984e386a78745b7e95c795cfc +size 14567 diff --git a/checkpoint-1000/scaler.pt b/checkpoint-1000/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..b04695d3a30e4bab2b78883d9c849c25c37ef7d7 --- /dev/null +++ b/checkpoint-1000/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f810fc7b695697c440d8985f6042b4ba23a9e1027604c265718b518ca29f1b2b +size 559 diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..2a616899591a36b66ac0bd1ceeb324087c181a2a --- /dev/null +++ b/checkpoint-1000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0691206f4bd9ca409d6e7104087a4e0eb05df8f8f555a400f6ecc532edba52d8 +size 623 diff --git a/checkpoint-1000/special_tokens_map.json b/checkpoint-1000/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-1000/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-1000/tokenizer_config.json b/checkpoint-1000/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-1000/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..f73f191fb2c9b16ef872b5a8c7f1f7c9332c87a5 --- /dev/null +++ b/checkpoint-1000/trainer_state.json @@ -0,0 +1,158 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 38.01, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.5554, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.3707, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.1995, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 7.0101, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.7643, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.5143, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 6.2988, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 6.0872, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.8851, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.7103, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.4879, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 5.4167, + "step": 700 + }, + { + "epoch": 28.02, + "learning_rate": 0.00025, + "loss": 5.289, + "step": 750 + }, + { + "epoch": 30.02, + "learning_rate": 0.00022222222222222218, + "loss": 5.1692, + "step": 800 + }, + { + "epoch": 32.02, + "learning_rate": 0.00019444444444444443, + "loss": 5.0667, + "step": 850 + }, + { + "epoch": 34.01, + "learning_rate": 0.00016666666666666666, + "loss": 4.974, + "step": 900 + }, + { + "epoch": 36.01, + "learning_rate": 0.0001388888888888889, + "loss": 4.8927, + "step": 950 + }, + { + "epoch": 38.01, + "learning_rate": 0.00011111111111111109, + "loss": 4.8232, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_loss": 6.224096298217773, + "eval_runtime": 1.093, + "eval_samples_per_second": 78.684, + "eval_steps_per_second": 5.49, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 6.224096298217773, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 504.7666777328044, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 1.093, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 78.684, + "step": 1000 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 2.73798513819648e+17, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-1100/config.json b/checkpoint-1100/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-1100/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-1100/optimizer.pt b/checkpoint-1100/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..d2facb3164d05889c655703a493bfff14f3c5f2d --- /dev/null +++ b/checkpoint-1100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04ea1e7285a3d96ad8857603387d722fcead89015ad3f5b6651127929b23cc7 +size 1080041009 diff --git a/checkpoint-1100/pytorch_model.bin b/checkpoint-1100/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..abb8f8c056fe90b0d9ee7ceb1d096f7c6315c27f --- /dev/null +++ b/checkpoint-1100/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ca8f39022cf81ff35f8652d2c1e4ef22c0d2a21bd981e6d7435f13d5d4137dd +size 552615017 diff --git a/checkpoint-1100/rng_state.pth b/checkpoint-1100/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..70de8d26a2f6072a1c7d8c6577baa461f1217a8e --- /dev/null +++ b/checkpoint-1100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:168dbcc62126ec9f97e2483b9b89af15cedf2a44d8188827c66505215429e35d +size 14567 diff --git a/checkpoint-1100/scaler.pt b/checkpoint-1100/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..37bf049fbd5fd721203bf0238edc8ff67dbd8f94 --- /dev/null +++ b/checkpoint-1100/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fb16c30b686aa43e110b0d33f9d46bf3127b7124542ca8dc34831233d4675a0 +size 559 diff --git a/checkpoint-1100/scheduler.pt b/checkpoint-1100/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..c158169ec0bb09620952d544fd4b4edea0cc9cf4 --- /dev/null +++ b/checkpoint-1100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f1b7713e4bb40428f29080b7d08d4a52f779ac863737861e4724292b2cf6c59 +size 623 diff --git a/checkpoint-1100/special_tokens_map.json b/checkpoint-1100/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-1100/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-1100/tokenizer_config.json b/checkpoint-1100/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-1100/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-1100/trainer_state.json b/checkpoint-1100/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..4074e7314ecf207e49da0b72c8faca56faec94b9 --- /dev/null +++ b/checkpoint-1100/trainer_state.json @@ -0,0 +1,170 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 42.00666666666667, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.5554, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.3707, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.1995, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 7.0101, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.7643, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.5143, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 6.2988, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 6.0872, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.8851, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.7103, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.4879, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 5.4167, + "step": 700 + }, + { + "epoch": 28.02, + "learning_rate": 0.00025, + "loss": 5.289, + "step": 750 + }, + { + "epoch": 30.02, + "learning_rate": 0.00022222222222222218, + "loss": 5.1692, + "step": 800 + }, + { + "epoch": 32.02, + "learning_rate": 0.00019444444444444443, + "loss": 5.0667, + "step": 850 + }, + { + "epoch": 34.01, + "learning_rate": 0.00016666666666666666, + "loss": 4.974, + "step": 900 + }, + { + "epoch": 36.01, + "learning_rate": 0.0001388888888888889, + "loss": 4.8927, + "step": 950 + }, + { + "epoch": 38.01, + "learning_rate": 0.00011111111111111109, + "loss": 4.8232, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_loss": 6.224096298217773, + "eval_runtime": 1.093, + "eval_samples_per_second": 78.684, + "eval_steps_per_second": 5.49, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 6.224096298217773, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 504.7666777328044, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 1.093, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 78.684, + "step": 1000 + }, + { + "epoch": 40.01, + "learning_rate": 8.333333333333333e-05, + "loss": 4.764, + "step": 1050 + }, + { + "epoch": 42.01, + "learning_rate": 5.5555555555555545e-05, + "loss": 4.7157, + "step": 1100 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 3.01211183480832e+17, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1100/training_args.bin b/checkpoint-1100/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-1100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-1200/config.json b/checkpoint-1200/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-1200/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-1200/optimizer.pt b/checkpoint-1200/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..49625a3e746b821d1adf032f8b9ca6c014d724c3 --- /dev/null +++ b/checkpoint-1200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9640e33417d9757387b0afef1981f30feb565588adb154bb8a6ab9cf67c287d +size 1080041009 diff --git a/checkpoint-1200/pytorch_model.bin b/checkpoint-1200/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..f79983d5dbb88118e61a116ba5e599353b7c5690 --- /dev/null +++ b/checkpoint-1200/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872925222354b943fb237b58df7a40e18c7f6948b9f6f4f842f04322113fef07 +size 552615017 diff --git a/checkpoint-1200/rng_state.pth b/checkpoint-1200/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..9c6678e6ad97a3516ebc9334e5170945ad37eeda --- /dev/null +++ b/checkpoint-1200/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d6ca2370cb2b45eeeb60c22b23142120cf7ccfd8972f95f3b77ee44b9a42876 +size 14567 diff --git a/checkpoint-1200/scaler.pt b/checkpoint-1200/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..8953dddccbefc4703c09dcda27d83c15add2bade --- /dev/null +++ b/checkpoint-1200/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19c7277eaca0850ae3e9b6790b3d002d820169cce0671185e672c28c8ae8e056 +size 559 diff --git a/checkpoint-1200/scheduler.pt b/checkpoint-1200/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..310d39c17fc616a9c83286ed00f0f4cefba9f5df --- /dev/null +++ b/checkpoint-1200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:935a8fb09a6e9698d9894853b05e181b3f56098deaaecddde08e55f06bf000c4 +size 623 diff --git a/checkpoint-1200/special_tokens_map.json b/checkpoint-1200/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-1200/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-1200/tokenizer_config.json b/checkpoint-1200/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-1200/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-1200/trainer_state.json b/checkpoint-1200/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..bcc0812562038286c38744e5d23c50a7f0dbfeac --- /dev/null +++ b/checkpoint-1200/trainer_state.json @@ -0,0 +1,182 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 46.00333333333333, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.5554, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.3707, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.1995, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 7.0101, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.7643, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.5143, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 6.2988, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 6.0872, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.8851, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.7103, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.4879, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 5.4167, + "step": 700 + }, + { + "epoch": 28.02, + "learning_rate": 0.00025, + "loss": 5.289, + "step": 750 + }, + { + "epoch": 30.02, + "learning_rate": 0.00022222222222222218, + "loss": 5.1692, + "step": 800 + }, + { + "epoch": 32.02, + "learning_rate": 0.00019444444444444443, + "loss": 5.0667, + "step": 850 + }, + { + "epoch": 34.01, + "learning_rate": 0.00016666666666666666, + "loss": 4.974, + "step": 900 + }, + { + "epoch": 36.01, + "learning_rate": 0.0001388888888888889, + "loss": 4.8927, + "step": 950 + }, + { + "epoch": 38.01, + "learning_rate": 0.00011111111111111109, + "loss": 4.8232, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_loss": 6.224096298217773, + "eval_runtime": 1.093, + "eval_samples_per_second": 78.684, + "eval_steps_per_second": 5.49, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 6.224096298217773, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 504.7666777328044, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 1.093, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 78.684, + "step": 1000 + }, + { + "epoch": 40.01, + "learning_rate": 8.333333333333333e-05, + "loss": 4.764, + "step": 1050 + }, + { + "epoch": 42.01, + "learning_rate": 5.5555555555555545e-05, + "loss": 4.7157, + "step": 1100 + }, + { + "epoch": 44.01, + "learning_rate": 2.7777777777777772e-05, + "loss": 4.6788, + "step": 1150 + }, + { + "epoch": 46.0, + "learning_rate": 0.0, + "loss": 4.6542, + "step": 1200 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 3.28623853142016e+17, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1200/training_args.bin b/checkpoint-1200/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-1200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-200/config.json b/checkpoint-200/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-200/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..5827ddcc6ba0ecce90fda8c0f197b3c1b56e5cb5 --- /dev/null +++ b/checkpoint-200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46c38d293e19e8ea507f115c746c6b98dbbc03ede3e54880188b4e0307ef02b7 +size 1080040817 diff --git a/checkpoint-200/pytorch_model.bin b/checkpoint-200/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..1bcfc4744d9a3f6210b42db65e4ba6dae930aa84 --- /dev/null +++ b/checkpoint-200/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d6e589131f0fcf474c69bcf7b853cf037859cd3c1cb4308a25b14e3200264f +size 552615017 diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..48444ba84e55957bf984acc3ff13415d196708e1 --- /dev/null +++ b/checkpoint-200/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ffd0e797e91de51a2142a6db329c7d60f8dbdcd8fe416ade5d73eac8dc1936 +size 14567 diff --git a/checkpoint-200/scaler.pt b/checkpoint-200/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..365b52ebf376498237a843f6d7332e5a49b14902 --- /dev/null +++ b/checkpoint-200/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb6982c29cd162f49aeb531674acf574eccd46a8f556bec596040d7c3b95200a +size 559 diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..36cb8da739c80a63971a62f06f781c40ac0fceb2 --- /dev/null +++ b/checkpoint-200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a992625ada6d884e508ff9392d16738b4a4163147f8fcbf9f46be82ecae9888 +size 623 diff --git a/checkpoint-200/special_tokens_map.json b/checkpoint-200/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-200/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-200/tokenizer_config.json b/checkpoint-200/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-200/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..0d0016ac7462db741d44971277c9aad9feec61c1 --- /dev/null +++ b/checkpoint-200/trainer_state.json @@ -0,0 +1,46 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 7.015, + "global_step": 200, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.5554, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.3707, + "step": 200 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 5.4661247926272e+16, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-300/config.json b/checkpoint-300/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-300/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..8f6cd00301cb9d1b31568a2d79aba3f61acb7515 --- /dev/null +++ b/checkpoint-300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51f79234cc666c06ca6a709cf0b0759eaae7292b1700ea40b977af68db0b6e7b +size 1080041009 diff --git a/checkpoint-300/pytorch_model.bin b/checkpoint-300/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..3cb6b95fe62bf40dd0e609b37943385838251f82 --- /dev/null +++ b/checkpoint-300/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:149af0b8bd0ed5f2a8223291aee58efe3d1cd9f0de5388d1f29469e87dcb0493 +size 552615017 diff --git a/checkpoint-300/rng_state.pth b/checkpoint-300/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..276aa8199a7c2ca5e79426447c0b72bdc24392a1 --- /dev/null +++ b/checkpoint-300/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9923c4e70690bd1fab7970a7d074aa0adf9792fc78401dd8af4aacf45296c273 +size 14567 diff --git a/checkpoint-300/scaler.pt b/checkpoint-300/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..01066cf4761ea9d2f7962f5181762f7b08690b79 --- /dev/null +++ b/checkpoint-300/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0967b9f865f16344c55f5ccc3cf7d6e8e97ca61dda304e931ca6bad130f48dd1 +size 559 diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..681987f21e79cd4685aac32a5e6b74341e25d936 --- /dev/null +++ b/checkpoint-300/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1db899b266916f792a0898ceb27a87eaf76647f10c29cc0c13ce22f12a12efd +size 623 diff --git a/checkpoint-300/special_tokens_map.json b/checkpoint-300/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-300/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-300/tokenizer_config.json b/checkpoint-300/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-300/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..32f621e079735c793a7b074df06528fe81a460fe --- /dev/null +++ b/checkpoint-300/trainer_state.json @@ -0,0 +1,58 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 11.011666666666667, + "global_step": 300, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.5554, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.3707, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.1995, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 7.0101, + "step": 300 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 8.2073917587456e+16, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-400/config.json b/checkpoint-400/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-400/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..d8a47d3bb61a6089a2aba0fab44ab3679de41dd2 --- /dev/null +++ b/checkpoint-400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66fff67da45bd3d9275472ce2c22109c91478742985377e28fbb7cd782b34a49 +size 1080041009 diff --git a/checkpoint-400/pytorch_model.bin b/checkpoint-400/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..ddda01819096f37749a2d24fbfc1665db469d4c2 --- /dev/null +++ b/checkpoint-400/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bef905b8bb93c8190043937a07c69eb3c61f5abfe997186e566a485476fa2aa2 +size 552615017 diff --git a/checkpoint-400/rng_state.pth b/checkpoint-400/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..00a144a2c9178e2ff407cec9718bd6c51c65461a --- /dev/null +++ b/checkpoint-400/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8de4688647a8ec26fcd1c8a20e7ca569b47505c873934fef3fbc5c4a39c5ac3b +size 14567 diff --git a/checkpoint-400/scaler.pt b/checkpoint-400/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..9c7aef4199e98d81152810b661dbaffc01963383 --- /dev/null +++ b/checkpoint-400/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476e510c8ea7edbd2b51d1e76a4e037820a5639381c0d8b5d32dafa492795a1e +size 559 diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..967673cfc91836d239beb5a7ede06992232ba309 --- /dev/null +++ b/checkpoint-400/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db087d678047b5c346bbb8511936612c1fdf223c6fd70321e97369bc31ed76a8 +size 623 diff --git a/checkpoint-400/special_tokens_map.json b/checkpoint-400/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-400/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-400/tokenizer_config.json b/checkpoint-400/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-400/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..1bd62ae059b272788ddbe16ff14924deffb091ca --- /dev/null +++ b/checkpoint-400/trainer_state.json @@ -0,0 +1,70 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 15.008333333333333, + "global_step": 400, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.5554, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.3707, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.1995, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 7.0101, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.7643, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.5143, + "step": 400 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 1.0948658724864e+17, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-400/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-500/config.json b/checkpoint-500/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-500/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..dd91e2a49f663d004212b0bfaf3dc7c6d498f159 --- /dev/null +++ b/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53e35add7793aa239e6f9ee7d9e500eceacda8a0c8c310997286d26e7752786c +size 1080041009 diff --git a/checkpoint-500/pytorch_model.bin b/checkpoint-500/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..f48ad1017734d9f313038092a3a14eaddca83deb --- /dev/null +++ b/checkpoint-500/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1189242cb6c19e21a585cda0fdc5c579f922b61621e67066699f0dc4ab5511cc +size 552615017 diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..d681395a3f243642912e32b45f1e21f45b3e55da --- /dev/null +++ b/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9062f7c3c3a5cbf83ef7e7d153df9c308cd515d0a4a4e69d8f45c9e29d10b07f +size 14567 diff --git a/checkpoint-500/scaler.pt b/checkpoint-500/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..e8b96c9c2837f2c95b1d07d4fc3f245f9ad1ef62 --- /dev/null +++ b/checkpoint-500/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fa4c7be44c959599b8b43bb9bc3371e9e4e5bbc5758b3ab5afcccfda3e72e67 +size 559 diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..77b958181a5b47b022b96b38a6207f274a1b6604 --- /dev/null +++ b/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:026fae4a90d56c24de94b10dfa7a75b6ba4e43bd5c1a3fdb2d77356b81cd6f8a +size 623 diff --git a/checkpoint-500/special_tokens_map.json b/checkpoint-500/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-500/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-500/tokenizer_config.json b/checkpoint-500/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-500/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..c807be3e1b061dd4ad8444c5c7063e950ac36685 --- /dev/null +++ b/checkpoint-500/trainer_state.json @@ -0,0 +1,82 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 19.005, + "global_step": 500, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.5554, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.3707, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.1995, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 7.0101, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.7643, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.5143, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 6.2988, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 6.0872, + "step": 500 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 1.36899256909824e+17, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-600/config.json b/checkpoint-600/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-600/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..84b64e655f0f5e54872bbdf35dd7fafefbfe6aa5 --- /dev/null +++ b/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f7d311651d710f647b531f751bd198ca48bd360c7d69d73442142374037845 +size 1080041009 diff --git a/checkpoint-600/pytorch_model.bin b/checkpoint-600/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..2c5cc851a8785b5093ee0b57ac4e09615ad2990f --- /dev/null +++ b/checkpoint-600/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd8eafa5c7c4118daf4579a8fe7d06fc03089f894658a32048742666d7655d7c +size 552615017 diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..af1cc2b4e9294f33d25ca012333e9f117e18aa08 --- /dev/null +++ b/checkpoint-600/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:115d00853994772811c21dbb0e72d72e42af6f61e37e2ad340dc31a1ec2d5d53 +size 14567 diff --git a/checkpoint-600/scaler.pt b/checkpoint-600/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..f95b3e36da01561ec333a83ee8419ad225633e06 --- /dev/null +++ b/checkpoint-600/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e8415b86bbce347c0df306b84a695add049c2a3b2d0b6f4dda3bf036d341150 +size 559 diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..62e5359badd619e7dad2c51d98fa8043d9948f0b --- /dev/null +++ b/checkpoint-600/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700940432b1c2117248896e2ce5a58d93c051d92ea97707f74d76bf1ef24deee +size 623 diff --git a/checkpoint-600/special_tokens_map.json b/checkpoint-600/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-600/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-600/tokenizer_config.json b/checkpoint-600/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-600/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..c983a019e8bd55d0042f51def9a634cfb95a83ed --- /dev/null +++ b/checkpoint-600/trainer_state.json @@ -0,0 +1,94 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 23.001666666666665, + "global_step": 600, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.5554, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.3707, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.1995, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 7.0101, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.7643, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.5143, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 6.2988, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 6.0872, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.8851, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.7103, + "step": 600 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 1.64311926571008e+17, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-700/config.json b/checkpoint-700/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-700/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..a33d58b83153ab9c752bcaafa493f16fba06e1fd --- /dev/null +++ b/checkpoint-700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74045cde5a0a8bbb650cd406105de0d9e72a60748607bb135acb0d6dfbf09042 +size 1080041009 diff --git a/checkpoint-700/pytorch_model.bin b/checkpoint-700/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..f5f2e7aa43a727805cdd46e5958dc0e989665960 --- /dev/null +++ b/checkpoint-700/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:358e7bb3f4bdc576f750c4944597ddc4029c99fbe0b4af01a2b5d22299028ba3 +size 552615017 diff --git a/checkpoint-700/rng_state.pth b/checkpoint-700/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..6f0970499015dd38006959b715c602abe32dc3ab --- /dev/null +++ b/checkpoint-700/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6918f19262c53c7d0f2fdd9a02fe00086f70667222950c20bd6bb238f87abc34 +size 14567 diff --git a/checkpoint-700/scaler.pt b/checkpoint-700/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..12f2b8ec834e54a2bd7cfdd0e07b0c6e125b6490 --- /dev/null +++ b/checkpoint-700/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb213daf5cce18a5f92167ca14da9df084d907f2b9796efc4666630f312b58c +size 559 diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..42408b6253265af34ae78746144fbba9316e0d7e --- /dev/null +++ b/checkpoint-700/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2d4910fd408e002ebeff50d62bfb043dcae5ef658777d0c3ee4a3bbb515ec15 +size 623 diff --git a/checkpoint-700/special_tokens_map.json b/checkpoint-700/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-700/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-700/tokenizer_config.json b/checkpoint-700/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-700/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..c2ec8ec0ddb4beac7c7670955c2a29fbbc590d66 --- /dev/null +++ b/checkpoint-700/trainer_state.json @@ -0,0 +1,106 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 26.02, + "global_step": 700, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.5554, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.3707, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.1995, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 7.0101, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.7643, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.5143, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 6.2988, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 6.0872, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.8851, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.7103, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.4879, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 5.4167, + "step": 700 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 1.91560504836096e+17, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-700/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-800/config.json b/checkpoint-800/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-800/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..299fd369668f63c25bfe556705b6229901a64616 --- /dev/null +++ b/checkpoint-800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57ae17150c3cff507a06bdfabd5b0a5829cf4da2c3d45540321f04d9c7ade988 +size 1080041009 diff --git a/checkpoint-800/pytorch_model.bin b/checkpoint-800/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..d48d5b51e1639207aed27ae0e033058032aff638 --- /dev/null +++ b/checkpoint-800/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffd556f8f33145a7e7e62ac97bc34dabb311d3aa5d8348c373e864f08070d8dd +size 552615017 diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..c2758244a5ade3759d3b2dfcbc8e21dd25bafde0 --- /dev/null +++ b/checkpoint-800/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944bdfd64ba1f1e9f3d9310ecbbba214899524b699c163a8f5d1f3d8f1cd16af +size 14567 diff --git a/checkpoint-800/scaler.pt b/checkpoint-800/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..b3c73372264156b02df8dada2192ee3c96dd5fc4 --- /dev/null +++ b/checkpoint-800/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c2074cdcefbaa0a39f736d6b0f7bf018c350d49e85648bc8accc4f756ad816e +size 559 diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..75713dbce3771306ca00343ecc497c4f19a01d03 --- /dev/null +++ b/checkpoint-800/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b27fb255c84833fb6ab5d93679cb236a569de9a1c4f805f72a2f60a2bc7c7499 +size 623 diff --git a/checkpoint-800/special_tokens_map.json b/checkpoint-800/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-800/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-800/tokenizer_config.json b/checkpoint-800/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-800/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..de0fc3b90f831647a7c9d92ed08d5bbea3a537b9 --- /dev/null +++ b/checkpoint-800/trainer_state.json @@ -0,0 +1,118 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 30.016666666666666, + "global_step": 800, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.5554, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.3707, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.1995, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 7.0101, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.7643, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.5143, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 6.2988, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 6.0872, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.8851, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.7103, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.4879, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 5.4167, + "step": 700 + }, + { + "epoch": 28.02, + "learning_rate": 0.00025, + "loss": 5.289, + "step": 750 + }, + { + "epoch": 30.02, + "learning_rate": 0.00022222222222222218, + "loss": 5.1692, + "step": 800 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 2.1897317449728e+17, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-800/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/checkpoint-900/config.json b/checkpoint-900/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/checkpoint-900/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/checkpoint-900/optimizer.pt b/checkpoint-900/optimizer.pt new file mode 100755 index 0000000000000000000000000000000000000000..8f16984e5ba59f84c35bd7adc446163f32f912d0 --- /dev/null +++ b/checkpoint-900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3520da4d17d43a9c8b3837737c015363dbbd619b58496a3b27c380ba6ad23b23 +size 1080041009 diff --git a/checkpoint-900/pytorch_model.bin b/checkpoint-900/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..97cba88667a304afd62334c021432a3984653fc9 --- /dev/null +++ b/checkpoint-900/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db97a377282be9bdfff91f9d10032739f4242a21360c746adc44159e5f1521b +size 552615017 diff --git a/checkpoint-900/rng_state.pth b/checkpoint-900/rng_state.pth new file mode 100755 index 0000000000000000000000000000000000000000..fdc2f8cc47596029b59ee75e3d86e493f95dc0e6 --- /dev/null +++ b/checkpoint-900/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d7d9cde46cff9cbfd4591e9e2fb648cc84f0448dfdb3661a90f719f6084bcd0 +size 14567 diff --git a/checkpoint-900/scaler.pt b/checkpoint-900/scaler.pt new file mode 100755 index 0000000000000000000000000000000000000000..be54cb13c777bc6feccb478ff218e7e21fad482a --- /dev/null +++ b/checkpoint-900/scaler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8695f57df923e22b943b0b0f2b9cc7007008e80b53ccee275b3a35963fe67e9 +size 559 diff --git a/checkpoint-900/scheduler.pt b/checkpoint-900/scheduler.pt new file mode 100755 index 0000000000000000000000000000000000000000..539d7c83ea252818dc9cbffac08cf340bb05a454 --- /dev/null +++ b/checkpoint-900/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2cb09e5db72772a15094286e93cbb61d745d9b63863703cf53da0bcb9827821 +size 623 diff --git a/checkpoint-900/special_tokens_map.json b/checkpoint-900/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/checkpoint-900/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/checkpoint-900/tokenizer_config.json b/checkpoint-900/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/checkpoint-900/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/checkpoint-900/trainer_state.json b/checkpoint-900/trainer_state.json new file mode 100755 index 0000000000000000000000000000000000000000..089b85c9f5f6eac8e8c90c526dc5afcca82d9e37 --- /dev/null +++ b/checkpoint-900/trainer_state.json @@ -0,0 +1,130 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 34.013333333333335, + "global_step": 900, + "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": 11.1254, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9373, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7501, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.5554, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.3707, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.1995, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 7.0101, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.7643, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.5143, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 6.2988, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 6.0872, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.8851, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.7103, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.4879, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 5.4167, + "step": 700 + }, + { + "epoch": 28.02, + "learning_rate": 0.00025, + "loss": 5.289, + "step": 750 + }, + { + "epoch": 30.02, + "learning_rate": 0.00022222222222222218, + "loss": 5.1692, + "step": 800 + }, + { + "epoch": 32.02, + "learning_rate": 0.00019444444444444443, + "loss": 5.0667, + "step": 850 + }, + { + "epoch": 34.01, + "learning_rate": 0.00016666666666666666, + "loss": 4.974, + "step": 900 + } + ], + "max_steps": 1200, + "num_train_epochs": 9223372036854775807, + "total_flos": 2.46385844158464e+17, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-900/training_args.bin b/checkpoint-900/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/checkpoint-900/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183 diff --git a/config.json b/config.json new file mode 100755 index 0000000000000000000000000000000000000000..010a39070324d45f3a6fa1fe9997539307c8f44b --- /dev/null +++ b/config.json @@ -0,0 +1,38 @@ +{ + "activation_function": "gelu_new", + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 0, + "embd_pdrop": 0.1, + "eos_token_id": 0, + "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": 64000 +} diff --git a/metrics.json b/metrics.json new file mode 100755 index 0000000000000000000000000000000000000000..bbcebd3594c765ff77900a8051aaf806322dfdc8 --- /dev/null +++ b/metrics.json @@ -0,0 +1,2507 @@ +{"num_parameters": 134994432, "trainable_parameters": 134994432, "step": 0} +{"train_info/time_between_train_steps": 5.4535791873931885, "step": 0} +{"info/global_step": 1, "train_info/time_within_train_step": 19.41210389137268, "step": 1} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 20933.7958984375, "train_info/memory_reserved": 24596.0, "train_info/memory_max_reserved": 24596.0, "_timestamp": 1737042754, "_runtime": 54}, "step": 1} +{"logs": {"train/loss": 11.1254, "train/learning_rate": 4.9999999999999996e-06, "train/epoch": 0.0, "_timestamp": 1737042754, "_runtime": 54}, "step": 1} +{"train_info/time_between_train_steps": 0.03403925895690918, "step": 1} +{"info/global_step": 2, "train_info/time_within_train_step": 13.310196876525879, "step": 2} +{"train_info/time_between_train_steps": 0.005971431732177734, "step": 2} +{"info/global_step": 3, "train_info/time_within_train_step": 13.242412328720093, "step": 3} +{"train_info/time_between_train_steps": 0.005936384201049805, "step": 3} +{"info/global_step": 4, "train_info/time_within_train_step": 13.393738269805908, "step": 4} +{"train_info/time_between_train_steps": 0.006124734878540039, "step": 4} +{"info/global_step": 5, "train_info/time_within_train_step": 13.283753871917725, "step": 5} +{"train_info/time_between_train_steps": 0.0059244632720947266, "step": 5} +{"info/global_step": 6, "train_info/time_within_train_step": 13.477338552474976, "step": 6} +{"train_info/time_between_train_steps": 0.006094694137573242, "step": 6} +{"info/global_step": 7, "train_info/time_within_train_step": 13.372934818267822, "step": 7} +{"train_info/time_between_train_steps": 0.005744457244873047, "step": 7} +{"info/global_step": 8, "train_info/time_within_train_step": 13.271119594573975, "step": 8} +{"train_info/time_between_train_steps": 0.005739450454711914, "step": 8} +{"info/global_step": 9, "train_info/time_within_train_step": 13.242470741271973, "step": 9} +{"train_info/time_between_train_steps": 0.005811929702758789, "step": 9} +{"info/global_step": 10, "train_info/time_within_train_step": 13.24958062171936, "step": 10} +{"train_info/time_between_train_steps": 0.005561113357543945, "step": 10} +{"info/global_step": 11, "train_info/time_within_train_step": 13.24008822441101, "step": 11} +{"train_info/time_between_train_steps": 0.005634307861328125, "step": 11} +{"info/global_step": 12, "train_info/time_within_train_step": 13.250287055969238, "step": 12} +{"train_info/time_between_train_steps": 0.005714893341064453, "step": 12} +{"info/global_step": 13, "train_info/time_within_train_step": 13.29531741142273, "step": 13} +{"train_info/time_between_train_steps": 0.005644321441650391, "step": 13} +{"info/global_step": 14, "train_info/time_within_train_step": 13.24581241607666, "step": 14} +{"train_info/time_between_train_steps": 0.005715847015380859, "step": 14} +{"info/global_step": 15, "train_info/time_within_train_step": 13.2181236743927, "step": 15} +{"train_info/time_between_train_steps": 0.0057756900787353516, "step": 15} +{"info/global_step": 16, "train_info/time_within_train_step": 13.39607572555542, "step": 16} +{"train_info/time_between_train_steps": 0.00592041015625, "step": 16} +{"info/global_step": 17, "train_info/time_within_train_step": 13.23344087600708, "step": 17} +{"train_info/time_between_train_steps": 0.0047686100006103516, "step": 17} +{"info/global_step": 18, "train_info/time_within_train_step": 13.164736032485962, "step": 18} +{"train_info/time_between_train_steps": 0.0059206485748291016, "step": 18} +{"info/global_step": 19, "train_info/time_within_train_step": 13.164814949035645, "step": 19} +{"train_info/time_between_train_steps": 0.00577998161315918, "step": 19} +{"info/global_step": 20, "train_info/time_within_train_step": 13.155732154846191, "step": 20} +{"train_info/time_between_train_steps": 0.005175113677978516, "step": 20} +{"info/global_step": 21, "train_info/time_within_train_step": 13.18655014038086, "step": 21} +{"train_info/time_between_train_steps": 0.005454063415527344, "step": 21} +{"info/global_step": 22, "train_info/time_within_train_step": 13.18589162826538, "step": 22} +{"train_info/time_between_train_steps": 0.0051119327545166016, "step": 22} +{"info/global_step": 23, "train_info/time_within_train_step": 13.176607370376587, "step": 23} +{"train_info/time_between_train_steps": 0.005583524703979492, "step": 23} +{"info/global_step": 24, "train_info/time_within_train_step": 13.162652492523193, "step": 24} +{"train_info/time_between_train_steps": 0.005690097808837891, "step": 24} +{"info/global_step": 25, "train_info/time_within_train_step": 13.190025329589844, "step": 25} +{"train_info/time_between_train_steps": 0.005975246429443359, "step": 25} +{"info/global_step": 26, "train_info/time_within_train_step": 13.228508234024048, "step": 26} +{"train_info/time_between_train_steps": 0.006487131118774414, "step": 26} +{"train_info/time_between_train_steps": 10.625017642974854, "step": 26} +{"info/global_step": 27, "train_info/time_within_train_step": 13.144358158111572, "step": 27} +{"train_info/time_between_train_steps": 0.005156040191650391, "step": 27} +{"info/global_step": 28, "train_info/time_within_train_step": 13.308714628219604, "step": 28} +{"train_info/time_between_train_steps": 0.004658937454223633, "step": 28} +{"info/global_step": 29, "train_info/time_within_train_step": 13.236867189407349, "step": 29} +{"train_info/time_between_train_steps": 0.005779743194580078, "step": 29} +{"info/global_step": 30, "train_info/time_within_train_step": 13.298593997955322, "step": 30} +{"train_info/time_between_train_steps": 0.00548863410949707, "step": 30} +{"info/global_step": 31, "train_info/time_within_train_step": 13.314964771270752, "step": 31} +{"train_info/time_between_train_steps": 0.005868196487426758, "step": 31} +{"info/global_step": 32, "train_info/time_within_train_step": 13.321768283843994, "step": 32} +{"train_info/time_between_train_steps": 0.005798816680908203, "step": 32} +{"info/global_step": 33, "train_info/time_within_train_step": 13.220804452896118, "step": 33} +{"train_info/time_between_train_steps": 0.005552053451538086, "step": 33} +{"info/global_step": 34, "train_info/time_within_train_step": 13.219722032546997, "step": 34} +{"train_info/time_between_train_steps": 0.0053975582122802734, "step": 34} +{"info/global_step": 35, "train_info/time_within_train_step": 13.204567670822144, "step": 35} +{"train_info/time_between_train_steps": 0.005379199981689453, "step": 35} +{"info/global_step": 36, "train_info/time_within_train_step": 13.200857400894165, "step": 36} +{"train_info/time_between_train_steps": 0.005481719970703125, "step": 36} +{"info/global_step": 37, "train_info/time_within_train_step": 13.219065189361572, "step": 37} +{"train_info/time_between_train_steps": 0.00534820556640625, "step": 37} +{"info/global_step": 38, "train_info/time_within_train_step": 13.219971179962158, "step": 38} +{"train_info/time_between_train_steps": 0.005759239196777344, "step": 38} +{"info/global_step": 39, "train_info/time_within_train_step": 13.24278450012207, "step": 39} +{"train_info/time_between_train_steps": 0.005958080291748047, "step": 39} +{"info/global_step": 40, "train_info/time_within_train_step": 13.244534492492676, "step": 40} +{"train_info/time_between_train_steps": 0.005457639694213867, "step": 40} +{"info/global_step": 41, "train_info/time_within_train_step": 13.22006106376648, "step": 41} +{"train_info/time_between_train_steps": 0.005915641784667969, "step": 41} +{"info/global_step": 42, "train_info/time_within_train_step": 13.220372676849365, "step": 42} +{"train_info/time_between_train_steps": 0.005404472351074219, "step": 42} +{"info/global_step": 43, "train_info/time_within_train_step": 13.239909410476685, "step": 43} +{"train_info/time_between_train_steps": 0.005715370178222656, "step": 43} +{"info/global_step": 44, "train_info/time_within_train_step": 13.306650876998901, "step": 44} +{"train_info/time_between_train_steps": 0.005650520324707031, "step": 44} +{"info/global_step": 45, "train_info/time_within_train_step": 13.38676929473877, "step": 45} +{"train_info/time_between_train_steps": 0.0056285858154296875, "step": 45} +{"info/global_step": 46, "train_info/time_within_train_step": 13.359261512756348, "step": 46} +{"train_info/time_between_train_steps": 0.005619525909423828, "step": 46} +{"info/global_step": 47, "train_info/time_within_train_step": 13.660894870758057, "step": 47} +{"train_info/time_between_train_steps": 0.0055391788482666016, "step": 47} +{"info/global_step": 48, "train_info/time_within_train_step": 13.208506107330322, "step": 48} +{"train_info/time_between_train_steps": 0.005347013473510742, "step": 48} +{"info/global_step": 49, "train_info/time_within_train_step": 13.27770209312439, "step": 49} +{"train_info/time_between_train_steps": 0.006010532379150391, "step": 49} +{"info/global_step": 50, "train_info/time_within_train_step": 13.414702653884888, "step": 50} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737043416, "_runtime": 716}, "step": 50} +{"logs": {"train/loss": 8.9373, "train/learning_rate": 0.00025, "train/epoch": 1.02, "_timestamp": 1737043416, "_runtime": 716}, "step": 50} +{"train_info/time_between_train_steps": 0.3233036994934082, "step": 50} +{"info/global_step": 51, "train_info/time_within_train_step": 13.822027683258057, "step": 51} +{"train_info/time_between_train_steps": 0.006083965301513672, "step": 51} +{"info/global_step": 52, "train_info/time_within_train_step": 13.31462025642395, "step": 52} +{"train_info/time_between_train_steps": 0.009040594100952148, "step": 52} +{"train_info/time_between_train_steps": 10.914963245391846, "step": 52} +{"info/global_step": 53, "train_info/time_within_train_step": 13.151320934295654, "step": 53} +{"train_info/time_between_train_steps": 0.005881071090698242, "step": 53} +{"info/global_step": 54, "train_info/time_within_train_step": 13.305388450622559, "step": 54} +{"train_info/time_between_train_steps": 0.00571131706237793, "step": 54} +{"info/global_step": 55, "train_info/time_within_train_step": 13.180503845214844, "step": 55} +{"train_info/time_between_train_steps": 0.0057489871978759766, "step": 55} +{"info/global_step": 56, "train_info/time_within_train_step": 13.315492153167725, "step": 56} +{"train_info/time_between_train_steps": 0.005399227142333984, "step": 56} +{"info/global_step": 57, "train_info/time_within_train_step": 13.18904423713684, "step": 57} +{"train_info/time_between_train_steps": 0.005415916442871094, "step": 57} +{"info/global_step": 58, "train_info/time_within_train_step": 13.25245189666748, "step": 58} +{"train_info/time_between_train_steps": 0.005353212356567383, "step": 58} +{"info/global_step": 59, "train_info/time_within_train_step": 13.192890882492065, "step": 59} +{"train_info/time_between_train_steps": 0.005494594573974609, "step": 59} +{"info/global_step": 60, "train_info/time_within_train_step": 13.201428651809692, "step": 60} +{"train_info/time_between_train_steps": 0.0050313472747802734, "step": 60} +{"info/global_step": 61, "train_info/time_within_train_step": 13.149874925613403, "step": 61} +{"train_info/time_between_train_steps": 0.005030393600463867, "step": 61} +{"info/global_step": 62, "train_info/time_within_train_step": 13.251850128173828, "step": 62} +{"train_info/time_between_train_steps": 0.005478620529174805, "step": 62} +{"info/global_step": 63, "train_info/time_within_train_step": 13.149345874786377, "step": 63} +{"train_info/time_between_train_steps": 0.004816293716430664, "step": 63} +{"info/global_step": 64, "train_info/time_within_train_step": 13.178620338439941, "step": 64} +{"train_info/time_between_train_steps": 0.005716085433959961, "step": 64} +{"info/global_step": 65, "train_info/time_within_train_step": 13.169520139694214, "step": 65} +{"train_info/time_between_train_steps": 0.005689859390258789, "step": 65} +{"info/global_step": 66, "train_info/time_within_train_step": 13.176181077957153, "step": 66} +{"train_info/time_between_train_steps": 0.00568699836730957, "step": 66} +{"info/global_step": 67, "train_info/time_within_train_step": 13.16291093826294, "step": 67} +{"train_info/time_between_train_steps": 0.005168914794921875, "step": 67} +{"info/global_step": 68, "train_info/time_within_train_step": 13.164479494094849, "step": 68} +{"train_info/time_between_train_steps": 0.005454540252685547, "step": 68} +{"info/global_step": 69, "train_info/time_within_train_step": 13.193722248077393, "step": 69} +{"train_info/time_between_train_steps": 0.005567073822021484, "step": 69} +{"info/global_step": 70, "train_info/time_within_train_step": 13.159748792648315, "step": 70} +{"train_info/time_between_train_steps": 0.005545377731323242, "step": 70} +{"info/global_step": 71, "train_info/time_within_train_step": 13.155874490737915, "step": 71} +{"train_info/time_between_train_steps": 0.005261898040771484, "step": 71} +{"info/global_step": 72, "train_info/time_within_train_step": 13.160300016403198, "step": 72} +{"train_info/time_between_train_steps": 0.0051195621490478516, "step": 72} +{"info/global_step": 73, "train_info/time_within_train_step": 13.20437240600586, "step": 73} +{"train_info/time_between_train_steps": 0.00574040412902832, "step": 73} +{"info/global_step": 74, "train_info/time_within_train_step": 13.183499336242676, "step": 74} +{"train_info/time_between_train_steps": 0.00535273551940918, "step": 74} +{"info/global_step": 75, "train_info/time_within_train_step": 13.181864976882935, "step": 75} +{"train_info/time_between_train_steps": 0.00567317008972168, "step": 75} +{"info/global_step": 76, "train_info/time_within_train_step": 13.179375886917114, "step": 76} +{"train_info/time_between_train_steps": 0.005279064178466797, "step": 76} +{"info/global_step": 77, "train_info/time_within_train_step": 13.279209613800049, "step": 77} +{"train_info/time_between_train_steps": 0.005228996276855469, "step": 77} +{"info/global_step": 78, "train_info/time_within_train_step": 13.218862056732178, "step": 78} +{"train_info/time_between_train_steps": 0.006999015808105469, "step": 78} +{"train_info/time_between_train_steps": 10.8113112449646, "step": 78} +{"info/global_step": 79, "train_info/time_within_train_step": 13.128291368484497, "step": 79} +{"train_info/time_between_train_steps": 0.00482630729675293, "step": 79} +{"info/global_step": 80, "train_info/time_within_train_step": 13.278856992721558, "step": 80} +{"train_info/time_between_train_steps": 0.004958391189575195, "step": 80} +{"info/global_step": 81, "train_info/time_within_train_step": 13.15917706489563, "step": 81} +{"train_info/time_between_train_steps": 0.0048427581787109375, "step": 81} +{"info/global_step": 82, "train_info/time_within_train_step": 13.255605459213257, "step": 82} +{"train_info/time_between_train_steps": 0.005327939987182617, "step": 82} +{"info/global_step": 83, "train_info/time_within_train_step": 13.14238691329956, "step": 83} +{"train_info/time_between_train_steps": 0.0056362152099609375, "step": 83} +{"info/global_step": 84, "train_info/time_within_train_step": 13.237958192825317, "step": 84} +{"train_info/time_between_train_steps": 0.005804300308227539, "step": 84} +{"info/global_step": 85, "train_info/time_within_train_step": 13.163093328475952, "step": 85} +{"train_info/time_between_train_steps": 0.006276607513427734, "step": 85} +{"info/global_step": 86, "train_info/time_within_train_step": 13.155407428741455, "step": 86} +{"train_info/time_between_train_steps": 0.005453348159790039, "step": 86} +{"info/global_step": 87, "train_info/time_within_train_step": 13.12904667854309, "step": 87} +{"train_info/time_between_train_steps": 0.0054509639739990234, "step": 87} +{"info/global_step": 88, "train_info/time_within_train_step": 13.135400533676147, "step": 88} +{"train_info/time_between_train_steps": 0.0051686763763427734, "step": 88} +{"info/global_step": 89, "train_info/time_within_train_step": 13.149075508117676, "step": 89} +{"train_info/time_between_train_steps": 0.005596637725830078, "step": 89} +{"info/global_step": 90, "train_info/time_within_train_step": 13.145171880722046, "step": 90} +{"train_info/time_between_train_steps": 0.0052297115325927734, "step": 90} +{"info/global_step": 91, "train_info/time_within_train_step": 13.166054010391235, "step": 91} +{"train_info/time_between_train_steps": 0.004929304122924805, "step": 91} +{"info/global_step": 92, "train_info/time_within_train_step": 13.238338947296143, "step": 92} +{"train_info/time_between_train_steps": 0.0053637027740478516, "step": 92} +{"info/global_step": 93, "train_info/time_within_train_step": 13.142606019973755, "step": 93} +{"train_info/time_between_train_steps": 0.005768537521362305, "step": 93} +{"info/global_step": 94, "train_info/time_within_train_step": 13.112319231033325, "step": 94} +{"train_info/time_between_train_steps": 0.0045108795166015625, "step": 94} +{"info/global_step": 95, "train_info/time_within_train_step": 13.127200841903687, "step": 95} +{"train_info/time_between_train_steps": 0.004609584808349609, "step": 95} +{"info/global_step": 96, "train_info/time_within_train_step": 13.15071153640747, "step": 96} +{"train_info/time_between_train_steps": 0.005339622497558594, "step": 96} +{"info/global_step": 97, "train_info/time_within_train_step": 13.116189002990723, "step": 97} +{"train_info/time_between_train_steps": 0.004724979400634766, "step": 97} +{"info/global_step": 98, "train_info/time_within_train_step": 13.12274956703186, "step": 98} +{"train_info/time_between_train_steps": 0.005046367645263672, "step": 98} +{"info/global_step": 99, "train_info/time_within_train_step": 13.125561714172363, "step": 99} +{"train_info/time_between_train_steps": 0.0047359466552734375, "step": 99} +{"info/global_step": 100, "train_info/time_within_train_step": 13.970131874084473, "step": 100} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737044101, "_runtime": 1401}, "step": 100} +{"logs": {"train/loss": 7.7501, "train/learning_rate": 0.0005, "train/epoch": 3.02, "_timestamp": 1737044101, "_runtime": 1401}, "step": 100} +{"train_info/time_between_train_steps": 106.08041572570801, "step": 100} +{"info/global_step": 101, "train_info/time_within_train_step": 13.053698062896729, "step": 101} +{"train_info/time_between_train_steps": 0.004776716232299805, "step": 101} +{"info/global_step": 102, "train_info/time_within_train_step": 13.070367813110352, "step": 102} +{"train_info/time_between_train_steps": 0.005761623382568359, "step": 102} +{"info/global_step": 103, "train_info/time_within_train_step": 13.072675228118896, "step": 103} +{"train_info/time_between_train_steps": 0.005767107009887695, "step": 103} +{"info/global_step": 104, "train_info/time_within_train_step": 13.10114574432373, "step": 104} +{"train_info/time_between_train_steps": 0.006520509719848633, "step": 104} +{"train_info/time_between_train_steps": 10.417776584625244, "step": 104} +{"info/global_step": 105, "train_info/time_within_train_step": 13.078856229782104, "step": 105} +{"train_info/time_between_train_steps": 0.004678487777709961, "step": 105} +{"info/global_step": 106, "train_info/time_within_train_step": 13.192702770233154, "step": 106} +{"train_info/time_between_train_steps": 0.00567936897277832, "step": 106} +{"info/global_step": 107, "train_info/time_within_train_step": 13.191052675247192, "step": 107} +{"train_info/time_between_train_steps": 0.00510406494140625, "step": 107} +{"info/global_step": 108, "train_info/time_within_train_step": 13.222720861434937, "step": 108} +{"train_info/time_between_train_steps": 0.0052754878997802734, "step": 108} +{"info/global_step": 109, "train_info/time_within_train_step": 13.133912563323975, "step": 109} +{"train_info/time_between_train_steps": 0.004526376724243164, "step": 109} +{"info/global_step": 110, "train_info/time_within_train_step": 13.241387128829956, "step": 110} +{"train_info/time_between_train_steps": 0.005639553070068359, "step": 110} +{"info/global_step": 111, "train_info/time_within_train_step": 13.1383216381073, "step": 111} +{"train_info/time_between_train_steps": 0.0047152042388916016, "step": 111} +{"info/global_step": 112, "train_info/time_within_train_step": 13.147491216659546, "step": 112} +{"train_info/time_between_train_steps": 0.004927873611450195, "step": 112} +{"info/global_step": 113, "train_info/time_within_train_step": 13.150473356246948, "step": 113} +{"train_info/time_between_train_steps": 0.005528450012207031, "step": 113} +{"info/global_step": 114, "train_info/time_within_train_step": 13.210435152053833, "step": 114} +{"train_info/time_between_train_steps": 0.004624843597412109, "step": 114} +{"info/global_step": 115, "train_info/time_within_train_step": 13.150916814804077, "step": 115} +{"train_info/time_between_train_steps": 0.005506277084350586, "step": 115} +{"info/global_step": 116, "train_info/time_within_train_step": 13.158223152160645, "step": 116} +{"train_info/time_between_train_steps": 0.0051386356353759766, "step": 116} +{"info/global_step": 117, "train_info/time_within_train_step": 13.143196105957031, "step": 117} +{"train_info/time_between_train_steps": 0.005300045013427734, "step": 117} +{"info/global_step": 118, "train_info/time_within_train_step": 13.209844589233398, "step": 118} +{"train_info/time_between_train_steps": 0.004799365997314453, "step": 118} +{"info/global_step": 119, "train_info/time_within_train_step": 13.142775774002075, "step": 119} +{"train_info/time_between_train_steps": 0.005205392837524414, "step": 119} +{"info/global_step": 120, "train_info/time_within_train_step": 13.138302564620972, "step": 120} +{"train_info/time_between_train_steps": 0.00517582893371582, "step": 120} +{"info/global_step": 121, "train_info/time_within_train_step": 13.14360785484314, "step": 121} +{"train_info/time_between_train_steps": 0.005515098571777344, "step": 121} +{"info/global_step": 122, "train_info/time_within_train_step": 13.153029441833496, "step": 122} +{"train_info/time_between_train_steps": 0.0057408809661865234, "step": 122} +{"info/global_step": 123, "train_info/time_within_train_step": 13.264589786529541, "step": 123} +{"train_info/time_between_train_steps": 0.0050432682037353516, "step": 123} +{"info/global_step": 124, "train_info/time_within_train_step": 13.146171569824219, "step": 124} +{"train_info/time_between_train_steps": 0.005510807037353516, "step": 124} +{"info/global_step": 125, "train_info/time_within_train_step": 13.1348135471344, "step": 125} +{"train_info/time_between_train_steps": 0.005553722381591797, "step": 125} +{"info/global_step": 126, "train_info/time_within_train_step": 13.143357753753662, "step": 126} +{"train_info/time_between_train_steps": 0.005113363265991211, "step": 126} +{"info/global_step": 127, "train_info/time_within_train_step": 13.152823209762573, "step": 127} +{"train_info/time_between_train_steps": 0.0052945613861083984, "step": 127} +{"info/global_step": 128, "train_info/time_within_train_step": 13.171822547912598, "step": 128} +{"train_info/time_between_train_steps": 0.0059320926666259766, "step": 128} +{"info/global_step": 129, "train_info/time_within_train_step": 13.150821447372437, "step": 129} +{"train_info/time_between_train_steps": 0.005275249481201172, "step": 129} +{"info/global_step": 130, "train_info/time_within_train_step": 13.179596185684204, "step": 130} +{"train_info/time_between_train_steps": 0.006565093994140625, "step": 130} +{"train_info/time_between_train_steps": 10.527751684188843, "step": 130} +{"info/global_step": 131, "train_info/time_within_train_step": 13.130107879638672, "step": 131} +{"train_info/time_between_train_steps": 0.005017757415771484, "step": 131} +{"info/global_step": 132, "train_info/time_within_train_step": 13.245707511901855, "step": 132} +{"train_info/time_between_train_steps": 0.0052645206451416016, "step": 132} +{"info/global_step": 133, "train_info/time_within_train_step": 13.156974077224731, "step": 133} +{"train_info/time_between_train_steps": 0.0054666996002197266, "step": 133} +{"info/global_step": 134, "train_info/time_within_train_step": 13.236759662628174, "step": 134} +{"train_info/time_between_train_steps": 0.0048062801361083984, "step": 134} +{"info/global_step": 135, "train_info/time_within_train_step": 13.144018650054932, "step": 135} +{"train_info/time_between_train_steps": 0.005358219146728516, "step": 135} +{"info/global_step": 136, "train_info/time_within_train_step": 13.272417068481445, "step": 136} +{"train_info/time_between_train_steps": 0.0052983760833740234, "step": 136} +{"info/global_step": 137, "train_info/time_within_train_step": 13.160524606704712, "step": 137} +{"train_info/time_between_train_steps": 0.004587888717651367, "step": 137} +{"info/global_step": 138, "train_info/time_within_train_step": 13.220677614212036, "step": 138} +{"train_info/time_between_train_steps": 0.005226612091064453, "step": 138} +{"info/global_step": 139, "train_info/time_within_train_step": 13.119510173797607, "step": 139} +{"train_info/time_between_train_steps": 0.0050542354583740234, "step": 139} +{"info/global_step": 140, "train_info/time_within_train_step": 13.150648355484009, "step": 140} +{"train_info/time_between_train_steps": 0.005369424819946289, "step": 140} +{"info/global_step": 141, "train_info/time_within_train_step": 13.160821676254272, "step": 141} +{"train_info/time_between_train_steps": 0.0055027008056640625, "step": 141} +{"info/global_step": 142, "train_info/time_within_train_step": 13.138500213623047, "step": 142} +{"train_info/time_between_train_steps": 0.0054738521575927734, "step": 142} +{"info/global_step": 143, "train_info/time_within_train_step": 13.134425401687622, "step": 143} +{"train_info/time_between_train_steps": 0.005367279052734375, "step": 143} +{"info/global_step": 144, "train_info/time_within_train_step": 13.129117250442505, "step": 144} +{"train_info/time_between_train_steps": 0.004932403564453125, "step": 144} +{"info/global_step": 145, "train_info/time_within_train_step": 13.978641271591187, "step": 145} +{"train_info/time_between_train_steps": 0.0053102970123291016, "step": 145} +{"info/global_step": 146, "train_info/time_within_train_step": 13.134652614593506, "step": 146} +{"train_info/time_between_train_steps": 0.005064249038696289, "step": 146} +{"info/global_step": 147, "train_info/time_within_train_step": 13.130070447921753, "step": 147} +{"train_info/time_between_train_steps": 0.004438638687133789, "step": 147} +{"info/global_step": 148, "train_info/time_within_train_step": 13.132777452468872, "step": 148} +{"train_info/time_between_train_steps": 0.004592180252075195, "step": 148} +{"info/global_step": 149, "train_info/time_within_train_step": 13.137349128723145, "step": 149} +{"train_info/time_between_train_steps": 0.005503416061401367, "step": 149} +{"info/global_step": 150, "train_info/time_within_train_step": 13.16748833656311, "step": 150} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737044889, "_runtime": 2189}, "step": 150} +{"logs": {"train/loss": 7.5554, "train/learning_rate": 0.0005833333333333333, "train/epoch": 5.02, "_timestamp": 1737044889, "_runtime": 2189}, "step": 150} +{"train_info/time_between_train_steps": 0.03410172462463379, "step": 150} +{"info/global_step": 151, "train_info/time_within_train_step": 13.137807130813599, "step": 151} +{"train_info/time_between_train_steps": 0.005026817321777344, "step": 151} +{"info/global_step": 152, "train_info/time_within_train_step": 13.144388437271118, "step": 152} +{"train_info/time_between_train_steps": 0.005255460739135742, "step": 152} +{"info/global_step": 153, "train_info/time_within_train_step": 13.15921401977539, "step": 153} +{"train_info/time_between_train_steps": 0.0055963993072509766, "step": 153} +{"info/global_step": 154, "train_info/time_within_train_step": 13.243871927261353, "step": 154} +{"train_info/time_between_train_steps": 0.005547046661376953, "step": 154} +{"info/global_step": 155, "train_info/time_within_train_step": 13.160653829574585, "step": 155} +{"train_info/time_between_train_steps": 0.005807161331176758, "step": 155} +{"info/global_step": 156, "train_info/time_within_train_step": 13.171351194381714, "step": 156} +{"train_info/time_between_train_steps": 0.006638288497924805, "step": 156} +{"train_info/time_between_train_steps": 10.687065839767456, "step": 156} +{"info/global_step": 157, "train_info/time_within_train_step": 13.148336410522461, "step": 157} +{"train_info/time_between_train_steps": 0.004746437072753906, "step": 157} +{"info/global_step": 158, "train_info/time_within_train_step": 13.252790212631226, "step": 158} +{"train_info/time_between_train_steps": 0.004847288131713867, "step": 158} +{"info/global_step": 159, "train_info/time_within_train_step": 13.161377191543579, "step": 159} +{"train_info/time_between_train_steps": 0.004966259002685547, "step": 159} +{"info/global_step": 160, "train_info/time_within_train_step": 13.2335524559021, "step": 160} +{"train_info/time_between_train_steps": 0.005404233932495117, "step": 160} +{"info/global_step": 161, "train_info/time_within_train_step": 13.155864000320435, "step": 161} +{"train_info/time_between_train_steps": 0.005206584930419922, "step": 161} +{"info/global_step": 162, "train_info/time_within_train_step": 13.21136999130249, "step": 162} +{"train_info/time_between_train_steps": 0.004538297653198242, "step": 162} +{"info/global_step": 163, "train_info/time_within_train_step": 13.157902002334595, "step": 163} +{"train_info/time_between_train_steps": 0.0051038265228271484, "step": 163} +{"info/global_step": 164, "train_info/time_within_train_step": 13.160720348358154, "step": 164} +{"train_info/time_between_train_steps": 0.005418300628662109, "step": 164} +{"info/global_step": 165, "train_info/time_within_train_step": 13.139524698257446, "step": 165} +{"train_info/time_between_train_steps": 0.004893302917480469, "step": 165} +{"info/global_step": 166, "train_info/time_within_train_step": 13.140752077102661, "step": 166} +{"train_info/time_between_train_steps": 0.004510402679443359, "step": 166} +{"info/global_step": 167, "train_info/time_within_train_step": 13.149878978729248, "step": 167} +{"train_info/time_between_train_steps": 0.0052030086517333984, "step": 167} +{"info/global_step": 168, "train_info/time_within_train_step": 13.150586605072021, "step": 168} +{"train_info/time_between_train_steps": 0.005118370056152344, "step": 168} +{"info/global_step": 169, "train_info/time_within_train_step": 13.242500305175781, "step": 169} +{"train_info/time_between_train_steps": 0.005398988723754883, "step": 169} +{"info/global_step": 170, "train_info/time_within_train_step": 13.149663209915161, "step": 170} +{"train_info/time_between_train_steps": 0.00480341911315918, "step": 170} +{"info/global_step": 171, "train_info/time_within_train_step": 13.15907907485962, "step": 171} +{"train_info/time_between_train_steps": 0.004668474197387695, "step": 171} +{"info/global_step": 172, "train_info/time_within_train_step": 13.143714189529419, "step": 172} +{"train_info/time_between_train_steps": 0.004711627960205078, "step": 172} +{"info/global_step": 173, "train_info/time_within_train_step": 13.143195152282715, "step": 173} +{"train_info/time_between_train_steps": 0.00538182258605957, "step": 173} +{"info/global_step": 174, "train_info/time_within_train_step": 13.149892091751099, "step": 174} +{"train_info/time_between_train_steps": 0.005299091339111328, "step": 174} +{"info/global_step": 175, "train_info/time_within_train_step": 13.172989845275879, "step": 175} +{"train_info/time_between_train_steps": 0.005542278289794922, "step": 175} +{"info/global_step": 176, "train_info/time_within_train_step": 13.157660007476807, "step": 176} +{"train_info/time_between_train_steps": 0.0048542022705078125, "step": 176} +{"info/global_step": 177, "train_info/time_within_train_step": 13.150105953216553, "step": 177} +{"train_info/time_between_train_steps": 0.004398345947265625, "step": 177} +{"info/global_step": 178, "train_info/time_within_train_step": 13.14542841911316, "step": 178} +{"train_info/time_between_train_steps": 0.005562305450439453, "step": 178} +{"info/global_step": 179, "train_info/time_within_train_step": 13.158605098724365, "step": 179} +{"train_info/time_between_train_steps": 0.004889965057373047, "step": 179} +{"info/global_step": 180, "train_info/time_within_train_step": 13.167277812957764, "step": 180} +{"train_info/time_between_train_steps": 0.005501747131347656, "step": 180} +{"info/global_step": 181, "train_info/time_within_train_step": 13.180287599563599, "step": 181} +{"train_info/time_between_train_steps": 0.00571894645690918, "step": 181} +{"info/global_step": 182, "train_info/time_within_train_step": 13.185755014419556, "step": 182} +{"train_info/time_between_train_steps": 0.007185935974121094, "step": 182} +{"train_info/time_between_train_steps": 10.4781494140625, "step": 182} +{"info/global_step": 183, "train_info/time_within_train_step": 13.13330626487732, "step": 183} +{"train_info/time_between_train_steps": 0.00509190559387207, "step": 183} +{"info/global_step": 184, "train_info/time_within_train_step": 13.327796936035156, "step": 184} +{"train_info/time_between_train_steps": 0.004564523696899414, "step": 184} +{"info/global_step": 185, "train_info/time_within_train_step": 13.148524045944214, "step": 185} +{"train_info/time_between_train_steps": 0.004586696624755859, "step": 185} +{"info/global_step": 186, "train_info/time_within_train_step": 13.269145250320435, "step": 186} +{"train_info/time_between_train_steps": 0.0057032108306884766, "step": 186} +{"info/global_step": 187, "train_info/time_within_train_step": 13.164761066436768, "step": 187} +{"train_info/time_between_train_steps": 0.00502467155456543, "step": 187} +{"info/global_step": 188, "train_info/time_within_train_step": 13.246380805969238, "step": 188} +{"train_info/time_between_train_steps": 0.00493931770324707, "step": 188} +{"info/global_step": 189, "train_info/time_within_train_step": 13.199136972427368, "step": 189} +{"train_info/time_between_train_steps": 0.004914760589599609, "step": 189} +{"info/global_step": 190, "train_info/time_within_train_step": 13.176084756851196, "step": 190} +{"train_info/time_between_train_steps": 0.004600048065185547, "step": 190} +{"info/global_step": 191, "train_info/time_within_train_step": 13.173737049102783, "step": 191} +{"train_info/time_between_train_steps": 0.005501985549926758, "step": 191} +{"info/global_step": 192, "train_info/time_within_train_step": 13.175480604171753, "step": 192} +{"train_info/time_between_train_steps": 0.004936933517456055, "step": 192} +{"info/global_step": 193, "train_info/time_within_train_step": 13.164453506469727, "step": 193} +{"train_info/time_between_train_steps": 0.004920482635498047, "step": 193} +{"info/global_step": 194, "train_info/time_within_train_step": 13.182109355926514, "step": 194} +{"train_info/time_between_train_steps": 0.005327939987182617, "step": 194} +{"info/global_step": 195, "train_info/time_within_train_step": 13.170765399932861, "step": 195} +{"train_info/time_between_train_steps": 0.00470733642578125, "step": 195} +{"info/global_step": 196, "train_info/time_within_train_step": 13.173516035079956, "step": 196} +{"train_info/time_between_train_steps": 0.0052373409271240234, "step": 196} +{"info/global_step": 197, "train_info/time_within_train_step": 13.731809377670288, "step": 197} +{"train_info/time_between_train_steps": 0.005174875259399414, "step": 197} +{"info/global_step": 198, "train_info/time_within_train_step": 14.444057703018188, "step": 198} +{"train_info/time_between_train_steps": 0.004777431488037109, "step": 198} +{"info/global_step": 199, "train_info/time_within_train_step": 13.552964687347412, "step": 199} +{"train_info/time_between_train_steps": 0.004743099212646484, "step": 199} +{"info/global_step": 200, "train_info/time_within_train_step": 13.142582178115845, "step": 200} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737045575, "_runtime": 2875}, "step": 200} +{"logs": {"train/loss": 7.3707, "train/learning_rate": 0.0005555555555555556, "train/epoch": 7.01, "_timestamp": 1737045575, "_runtime": 2875}, "step": 200} +{"train_info/time_between_train_steps": 127.59843325614929, "step": 200} +{"info/global_step": 201, "train_info/time_within_train_step": 13.098040342330933, "step": 201} +{"train_info/time_between_train_steps": 0.0049974918365478516, "step": 201} +{"info/global_step": 202, "train_info/time_within_train_step": 13.10106873512268, "step": 202} +{"train_info/time_between_train_steps": 0.005295991897583008, "step": 202} +{"info/global_step": 203, "train_info/time_within_train_step": 13.09785509109497, "step": 203} +{"train_info/time_between_train_steps": 0.0048482418060302734, "step": 203} +{"info/global_step": 204, "train_info/time_within_train_step": 13.099602222442627, "step": 204} +{"train_info/time_between_train_steps": 0.00494694709777832, "step": 204} +{"info/global_step": 205, "train_info/time_within_train_step": 13.089128255844116, "step": 205} +{"train_info/time_between_train_steps": 0.004715681076049805, "step": 205} +{"info/global_step": 206, "train_info/time_within_train_step": 13.122116565704346, "step": 206} +{"train_info/time_between_train_steps": 0.005043983459472656, "step": 206} +{"info/global_step": 207, "train_info/time_within_train_step": 13.130628824234009, "step": 207} +{"train_info/time_between_train_steps": 0.00575709342956543, "step": 207} +{"info/global_step": 208, "train_info/time_within_train_step": 13.159044027328491, "step": 208} +{"train_info/time_between_train_steps": 0.0058553218841552734, "step": 208} +{"train_info/time_between_train_steps": 10.508044958114624, "step": 208} +{"info/global_step": 209, "train_info/time_within_train_step": 13.095623016357422, "step": 209} +{"train_info/time_between_train_steps": 0.005488872528076172, "step": 209} +{"info/global_step": 210, "train_info/time_within_train_step": 13.211602687835693, "step": 210} +{"train_info/time_between_train_steps": 0.005154609680175781, "step": 210} +{"info/global_step": 211, "train_info/time_within_train_step": 13.121558427810669, "step": 211} +{"train_info/time_between_train_steps": 0.005002498626708984, "step": 211} +{"info/global_step": 212, "train_info/time_within_train_step": 13.207428216934204, "step": 212} +{"train_info/time_between_train_steps": 0.0049817562103271484, "step": 212} +{"info/global_step": 213, "train_info/time_within_train_step": 13.127369165420532, "step": 213} +{"train_info/time_between_train_steps": 0.005035400390625, "step": 213} +{"info/global_step": 214, "train_info/time_within_train_step": 13.303440570831299, "step": 214} +{"train_info/time_between_train_steps": 0.0054779052734375, "step": 214} +{"info/global_step": 215, "train_info/time_within_train_step": 13.151482105255127, "step": 215} +{"train_info/time_between_train_steps": 0.005669116973876953, "step": 215} +{"info/global_step": 216, "train_info/time_within_train_step": 13.156200408935547, "step": 216} +{"train_info/time_between_train_steps": 0.005377531051635742, "step": 216} +{"info/global_step": 217, "train_info/time_within_train_step": 13.132978200912476, "step": 217} +{"train_info/time_between_train_steps": 0.0054302215576171875, "step": 217} +{"info/global_step": 218, "train_info/time_within_train_step": 13.144919633865356, "step": 218} +{"train_info/time_between_train_steps": 0.004785060882568359, "step": 218} +{"info/global_step": 219, "train_info/time_within_train_step": 13.154337882995605, "step": 219} +{"train_info/time_between_train_steps": 0.0052509307861328125, "step": 219} +{"info/global_step": 220, "train_info/time_within_train_step": 13.138511419296265, "step": 220} +{"train_info/time_between_train_steps": 0.005385160446166992, "step": 220} +{"info/global_step": 221, "train_info/time_within_train_step": 13.140175104141235, "step": 221} +{"train_info/time_between_train_steps": 0.005479097366333008, "step": 221} +{"info/global_step": 222, "train_info/time_within_train_step": 13.129884004592896, "step": 222} +{"train_info/time_between_train_steps": 0.0043621063232421875, "step": 222} +{"info/global_step": 223, "train_info/time_within_train_step": 13.141127586364746, "step": 223} +{"train_info/time_between_train_steps": 0.005034685134887695, "step": 223} +{"info/global_step": 224, "train_info/time_within_train_step": 13.128291368484497, "step": 224} +{"train_info/time_between_train_steps": 0.0054628849029541016, "step": 224} +{"info/global_step": 225, "train_info/time_within_train_step": 13.141265630722046, "step": 225} +{"train_info/time_between_train_steps": 0.004823207855224609, "step": 225} +{"info/global_step": 226, "train_info/time_within_train_step": 13.14009690284729, "step": 226} +{"train_info/time_between_train_steps": 0.004952192306518555, "step": 226} +{"info/global_step": 227, "train_info/time_within_train_step": 13.165108442306519, "step": 227} +{"train_info/time_between_train_steps": 0.005760908126831055, "step": 227} +{"info/global_step": 228, "train_info/time_within_train_step": 13.143255949020386, "step": 228} +{"train_info/time_between_train_steps": 0.004827976226806641, "step": 228} +{"info/global_step": 229, "train_info/time_within_train_step": 13.14697527885437, "step": 229} +{"train_info/time_between_train_steps": 0.004318952560424805, "step": 229} +{"info/global_step": 230, "train_info/time_within_train_step": 13.23759388923645, "step": 230} +{"train_info/time_between_train_steps": 0.005020856857299805, "step": 230} +{"info/global_step": 231, "train_info/time_within_train_step": 13.149013042449951, "step": 231} +{"train_info/time_between_train_steps": 0.0055694580078125, "step": 231} +{"info/global_step": 232, "train_info/time_within_train_step": 13.150447130203247, "step": 232} +{"train_info/time_between_train_steps": 0.005208253860473633, "step": 232} +{"info/global_step": 233, "train_info/time_within_train_step": 13.153683423995972, "step": 233} +{"train_info/time_between_train_steps": 0.005784034729003906, "step": 233} +{"info/global_step": 234, "train_info/time_within_train_step": 13.160710096359253, "step": 234} +{"train_info/time_between_train_steps": 0.0057795047760009766, "step": 234} +{"train_info/time_between_train_steps": 10.71243667602539, "step": 234} +{"info/global_step": 235, "train_info/time_within_train_step": 13.135595083236694, "step": 235} +{"train_info/time_between_train_steps": 0.0055980682373046875, "step": 235} +{"info/global_step": 236, "train_info/time_within_train_step": 13.241471290588379, "step": 236} +{"train_info/time_between_train_steps": 0.005292654037475586, "step": 236} +{"info/global_step": 237, "train_info/time_within_train_step": 13.1466064453125, "step": 237} +{"train_info/time_between_train_steps": 0.005619049072265625, "step": 237} +{"info/global_step": 238, "train_info/time_within_train_step": 13.236050844192505, "step": 238} +{"train_info/time_between_train_steps": 0.005363941192626953, "step": 238} +{"info/global_step": 239, "train_info/time_within_train_step": 13.135868787765503, "step": 239} +{"train_info/time_between_train_steps": 0.005362987518310547, "step": 239} +{"info/global_step": 240, "train_info/time_within_train_step": 13.273885726928711, "step": 240} +{"train_info/time_between_train_steps": 0.005405902862548828, "step": 240} +{"info/global_step": 241, "train_info/time_within_train_step": 13.160743713378906, "step": 241} +{"train_info/time_between_train_steps": 0.005781650543212891, "step": 241} +{"info/global_step": 242, "train_info/time_within_train_step": 13.16359829902649, "step": 242} +{"train_info/time_between_train_steps": 0.0053865909576416016, "step": 242} +{"info/global_step": 243, "train_info/time_within_train_step": 13.152009010314941, "step": 243} +{"train_info/time_between_train_steps": 0.005134105682373047, "step": 243} +{"info/global_step": 244, "train_info/time_within_train_step": 13.14705753326416, "step": 244} +{"train_info/time_between_train_steps": 0.005170583724975586, "step": 244} +{"info/global_step": 245, "train_info/time_within_train_step": 13.241686344146729, "step": 245} +{"train_info/time_between_train_steps": 0.005151510238647461, "step": 245} +{"info/global_step": 246, "train_info/time_within_train_step": 13.177162408828735, "step": 246} +{"train_info/time_between_train_steps": 0.004960060119628906, "step": 246} +{"info/global_step": 247, "train_info/time_within_train_step": 13.152596473693848, "step": 247} +{"train_info/time_between_train_steps": 0.0048999786376953125, "step": 247} +{"info/global_step": 248, "train_info/time_within_train_step": 13.147886991500854, "step": 248} +{"train_info/time_between_train_steps": 0.005768537521362305, "step": 248} +{"info/global_step": 249, "train_info/time_within_train_step": 13.138670444488525, "step": 249} +{"train_info/time_between_train_steps": 0.005401611328125, "step": 249} +{"info/global_step": 250, "train_info/time_within_train_step": 13.145252227783203, "step": 250} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737046384, "_runtime": 3684}, "step": 250} +{"logs": {"train/loss": 7.1995, "train/learning_rate": 0.0005277777777777777, "train/epoch": 9.01, "_timestamp": 1737046384, "_runtime": 3684}, "step": 250} +{"train_info/time_between_train_steps": 0.05730009078979492, "step": 250} +{"info/global_step": 251, "train_info/time_within_train_step": 13.147182941436768, "step": 251} +{"train_info/time_between_train_steps": 0.005374431610107422, "step": 251} +{"info/global_step": 252, "train_info/time_within_train_step": 13.156690835952759, "step": 252} +{"train_info/time_between_train_steps": 0.005021810531616211, "step": 252} +{"info/global_step": 253, "train_info/time_within_train_step": 13.159743070602417, "step": 253} +{"train_info/time_between_train_steps": 0.005561113357543945, "step": 253} +{"info/global_step": 254, "train_info/time_within_train_step": 13.141443490982056, "step": 254} +{"train_info/time_between_train_steps": 0.0050525665283203125, "step": 254} +{"info/global_step": 255, "train_info/time_within_train_step": 13.157981157302856, "step": 255} +{"train_info/time_between_train_steps": 0.005022525787353516, "step": 255} +{"info/global_step": 256, "train_info/time_within_train_step": 13.144202470779419, "step": 256} +{"train_info/time_between_train_steps": 0.005360126495361328, "step": 256} +{"info/global_step": 257, "train_info/time_within_train_step": 13.169939279556274, "step": 257} +{"train_info/time_between_train_steps": 0.0054531097412109375, "step": 257} +{"info/global_step": 258, "train_info/time_within_train_step": 13.160223722457886, "step": 258} +{"train_info/time_between_train_steps": 0.005582571029663086, "step": 258} +{"info/global_step": 259, "train_info/time_within_train_step": 13.177849054336548, "step": 259} +{"train_info/time_between_train_steps": 0.006043434143066406, "step": 259} +{"info/global_step": 260, "train_info/time_within_train_step": 13.264009952545166, "step": 260} +{"train_info/time_between_train_steps": 0.00634765625, "step": 260} +{"train_info/time_between_train_steps": 10.462361335754395, "step": 260} +{"info/global_step": 261, "train_info/time_within_train_step": 13.12927532196045, "step": 261} +{"train_info/time_between_train_steps": 0.005263328552246094, "step": 261} +{"info/global_step": 262, "train_info/time_within_train_step": 13.232313632965088, "step": 262} +{"train_info/time_between_train_steps": 0.005014181137084961, "step": 262} +{"info/global_step": 263, "train_info/time_within_train_step": 13.137266874313354, "step": 263} +{"train_info/time_between_train_steps": 0.005194425582885742, "step": 263} +{"info/global_step": 264, "train_info/time_within_train_step": 13.252653121948242, "step": 264} +{"train_info/time_between_train_steps": 0.005362272262573242, "step": 264} +{"info/global_step": 265, "train_info/time_within_train_step": 13.143710136413574, "step": 265} +{"train_info/time_between_train_steps": 0.005582571029663086, "step": 265} +{"info/global_step": 266, "train_info/time_within_train_step": 13.214916467666626, "step": 266} +{"train_info/time_between_train_steps": 0.006330251693725586, "step": 266} +{"info/global_step": 267, "train_info/time_within_train_step": 13.17039155960083, "step": 267} +{"train_info/time_between_train_steps": 0.005662202835083008, "step": 267} +{"info/global_step": 268, "train_info/time_within_train_step": 13.1529061794281, "step": 268} +{"train_info/time_between_train_steps": 0.005441904067993164, "step": 268} +{"info/global_step": 269, "train_info/time_within_train_step": 13.133459329605103, "step": 269} +{"train_info/time_between_train_steps": 0.005271196365356445, "step": 269} +{"info/global_step": 270, "train_info/time_within_train_step": 13.141175270080566, "step": 270} +{"train_info/time_between_train_steps": 0.005730628967285156, "step": 270} +{"info/global_step": 271, "train_info/time_within_train_step": 13.160172700881958, "step": 271} +{"train_info/time_between_train_steps": 0.005190610885620117, "step": 271} +{"info/global_step": 272, "train_info/time_within_train_step": 13.143724203109741, "step": 272} +{"train_info/time_between_train_steps": 0.0053293704986572266, "step": 272} +{"info/global_step": 273, "train_info/time_within_train_step": 13.158929109573364, "step": 273} +{"train_info/time_between_train_steps": 0.005375862121582031, "step": 273} +{"info/global_step": 274, "train_info/time_within_train_step": 13.149166822433472, "step": 274} +{"train_info/time_between_train_steps": 0.005471706390380859, "step": 274} +{"info/global_step": 275, "train_info/time_within_train_step": 13.228844404220581, "step": 275} +{"train_info/time_between_train_steps": 0.005532264709472656, "step": 275} +{"info/global_step": 276, "train_info/time_within_train_step": 13.139062643051147, "step": 276} +{"train_info/time_between_train_steps": 0.005452871322631836, "step": 276} +{"info/global_step": 277, "train_info/time_within_train_step": 13.137736320495605, "step": 277} +{"train_info/time_between_train_steps": 0.005283355712890625, "step": 277} +{"info/global_step": 278, "train_info/time_within_train_step": 13.148170948028564, "step": 278} +{"train_info/time_between_train_steps": 0.00540471076965332, "step": 278} +{"info/global_step": 279, "train_info/time_within_train_step": 13.152893304824829, "step": 279} +{"train_info/time_between_train_steps": 0.00579524040222168, "step": 279} +{"info/global_step": 280, "train_info/time_within_train_step": 13.152781248092651, "step": 280} +{"train_info/time_between_train_steps": 0.0057718753814697266, "step": 280} +{"info/global_step": 281, "train_info/time_within_train_step": 13.16136384010315, "step": 281} +{"train_info/time_between_train_steps": 0.005819559097290039, "step": 281} +{"info/global_step": 282, "train_info/time_within_train_step": 13.159112930297852, "step": 282} +{"train_info/time_between_train_steps": 0.005544185638427734, "step": 282} +{"info/global_step": 283, "train_info/time_within_train_step": 13.144165992736816, "step": 283} +{"train_info/time_between_train_steps": 0.0052165985107421875, "step": 283} +{"info/global_step": 284, "train_info/time_within_train_step": 13.156139850616455, "step": 284} +{"train_info/time_between_train_steps": 0.005297422409057617, "step": 284} +{"info/global_step": 285, "train_info/time_within_train_step": 13.155330657958984, "step": 285} +{"train_info/time_between_train_steps": 0.005274772644042969, "step": 285} +{"info/global_step": 286, "train_info/time_within_train_step": 13.1834135055542, "step": 286} +{"train_info/time_between_train_steps": 0.006499767303466797, "step": 286} +{"train_info/time_between_train_steps": 10.588277578353882, "step": 286} +{"info/global_step": 287, "train_info/time_within_train_step": 13.132827043533325, "step": 287} +{"train_info/time_between_train_steps": 0.005046844482421875, "step": 287} +{"info/global_step": 288, "train_info/time_within_train_step": 13.208151578903198, "step": 288} +{"train_info/time_between_train_steps": 0.005453824996948242, "step": 288} +{"info/global_step": 289, "train_info/time_within_train_step": 13.132028818130493, "step": 289} +{"train_info/time_between_train_steps": 0.005337715148925781, "step": 289} +{"info/global_step": 290, "train_info/time_within_train_step": 13.30484390258789, "step": 290} +{"train_info/time_between_train_steps": 0.0054209232330322266, "step": 290} +{"info/global_step": 291, "train_info/time_within_train_step": 13.136637449264526, "step": 291} +{"train_info/time_between_train_steps": 0.00538945198059082, "step": 291} +{"info/global_step": 292, "train_info/time_within_train_step": 13.233179807662964, "step": 292} +{"train_info/time_between_train_steps": 0.005153656005859375, "step": 292} +{"info/global_step": 293, "train_info/time_within_train_step": 13.156912326812744, "step": 293} +{"train_info/time_between_train_steps": 0.004937887191772461, "step": 293} +{"info/global_step": 294, "train_info/time_within_train_step": 13.160658597946167, "step": 294} +{"train_info/time_between_train_steps": 0.005010128021240234, "step": 294} +{"info/global_step": 295, "train_info/time_within_train_step": 13.129380464553833, "step": 295} +{"train_info/time_between_train_steps": 0.005170106887817383, "step": 295} +{"info/global_step": 296, "train_info/time_within_train_step": 13.127889394760132, "step": 296} +{"train_info/time_between_train_steps": 0.0053043365478515625, "step": 296} +{"info/global_step": 297, "train_info/time_within_train_step": 13.139974355697632, "step": 297} +{"train_info/time_between_train_steps": 0.005559444427490234, "step": 297} +{"info/global_step": 298, "train_info/time_within_train_step": 13.146471977233887, "step": 298} +{"train_info/time_between_train_steps": 0.00562596321105957, "step": 298} +{"info/global_step": 299, "train_info/time_within_train_step": 13.136924028396606, "step": 299} +{"train_info/time_between_train_steps": 0.0052032470703125, "step": 299} +{"info/global_step": 300, "train_info/time_within_train_step": 13.141156673431396, "step": 300} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737047066, "_runtime": 4366}, "step": 300} +{"logs": {"train/loss": 7.0101, "train/learning_rate": 0.0005, "train/epoch": 11.01, "_timestamp": 1737047066, "_runtime": 4366}, "step": 300} +{"train_info/time_between_train_steps": 87.82307457923889, "step": 300} +{"info/global_step": 301, "train_info/time_within_train_step": 13.12482476234436, "step": 301} +{"train_info/time_between_train_steps": 0.004999876022338867, "step": 301} +{"info/global_step": 302, "train_info/time_within_train_step": 13.060575008392334, "step": 302} +{"train_info/time_between_train_steps": 0.005352973937988281, "step": 302} +{"info/global_step": 303, "train_info/time_within_train_step": 13.07834529876709, "step": 303} +{"train_info/time_between_train_steps": 0.00558161735534668, "step": 303} +{"info/global_step": 304, "train_info/time_within_train_step": 13.092987298965454, "step": 304} +{"train_info/time_between_train_steps": 0.005318403244018555, "step": 304} +{"info/global_step": 305, "train_info/time_within_train_step": 13.113940477371216, "step": 305} +{"train_info/time_between_train_steps": 0.005355358123779297, "step": 305} +{"info/global_step": 306, "train_info/time_within_train_step": 13.20494794845581, "step": 306} +{"train_info/time_between_train_steps": 0.005032062530517578, "step": 306} +{"info/global_step": 307, "train_info/time_within_train_step": 13.1302649974823, "step": 307} +{"train_info/time_between_train_steps": 0.005597352981567383, "step": 307} +{"info/global_step": 308, "train_info/time_within_train_step": 13.138895750045776, "step": 308} +{"train_info/time_between_train_steps": 0.0056667327880859375, "step": 308} +{"info/global_step": 309, "train_info/time_within_train_step": 13.162137031555176, "step": 309} +{"train_info/time_between_train_steps": 0.005255460739135742, "step": 309} +{"info/global_step": 310, "train_info/time_within_train_step": 13.161312103271484, "step": 310} +{"train_info/time_between_train_steps": 0.005545854568481445, "step": 310} +{"info/global_step": 311, "train_info/time_within_train_step": 13.151823282241821, "step": 311} +{"train_info/time_between_train_steps": 0.0063495635986328125, "step": 311} +{"info/global_step": 312, "train_info/time_within_train_step": 13.166690349578857, "step": 312} +{"train_info/time_between_train_steps": 0.005690813064575195, "step": 312} +{"train_info/time_between_train_steps": 10.589568138122559, "step": 312} +{"info/global_step": 313, "train_info/time_within_train_step": 13.132603645324707, "step": 313} +{"train_info/time_between_train_steps": 0.005347490310668945, "step": 313} +{"info/global_step": 314, "train_info/time_within_train_step": 13.216631889343262, "step": 314} +{"train_info/time_between_train_steps": 0.005261898040771484, "step": 314} +{"info/global_step": 315, "train_info/time_within_train_step": 13.191703081130981, "step": 315} +{"train_info/time_between_train_steps": 0.0055005550384521484, "step": 315} +{"info/global_step": 316, "train_info/time_within_train_step": 13.240283250808716, "step": 316} +{"train_info/time_between_train_steps": 0.0051767826080322266, "step": 316} +{"info/global_step": 317, "train_info/time_within_train_step": 13.14381718635559, "step": 317} +{"train_info/time_between_train_steps": 0.0052793025970458984, "step": 317} +{"info/global_step": 318, "train_info/time_within_train_step": 13.191456317901611, "step": 318} +{"train_info/time_between_train_steps": 0.004677295684814453, "step": 318} +{"info/global_step": 319, "train_info/time_within_train_step": 13.13670802116394, "step": 319} +{"train_info/time_between_train_steps": 0.005194664001464844, "step": 319} +{"info/global_step": 320, "train_info/time_within_train_step": 13.137206792831421, "step": 320} +{"train_info/time_between_train_steps": 0.004846334457397461, "step": 320} +{"info/global_step": 321, "train_info/time_within_train_step": 13.225013732910156, "step": 321} +{"train_info/time_between_train_steps": 0.0048999786376953125, "step": 321} +{"info/global_step": 322, "train_info/time_within_train_step": 13.180575609207153, "step": 322} +{"train_info/time_between_train_steps": 0.005295515060424805, "step": 322} +{"info/global_step": 323, "train_info/time_within_train_step": 13.1538565158844, "step": 323} +{"train_info/time_between_train_steps": 0.005424976348876953, "step": 323} +{"info/global_step": 324, "train_info/time_within_train_step": 13.142998933792114, "step": 324} +{"train_info/time_between_train_steps": 0.005109071731567383, "step": 324} +{"info/global_step": 325, "train_info/time_within_train_step": 13.134130716323853, "step": 325} +{"train_info/time_between_train_steps": 0.0052013397216796875, "step": 325} +{"info/global_step": 326, "train_info/time_within_train_step": 13.131737470626831, "step": 326} +{"train_info/time_between_train_steps": 0.005060434341430664, "step": 326} +{"info/global_step": 327, "train_info/time_within_train_step": 13.140645503997803, "step": 327} +{"train_info/time_between_train_steps": 0.0056302547454833984, "step": 327} +{"info/global_step": 328, "train_info/time_within_train_step": 13.137006998062134, "step": 328} +{"train_info/time_between_train_steps": 0.004464387893676758, "step": 328} +{"info/global_step": 329, "train_info/time_within_train_step": 13.148486375808716, "step": 329} +{"train_info/time_between_train_steps": 0.005566835403442383, "step": 329} +{"info/global_step": 330, "train_info/time_within_train_step": 13.158847093582153, "step": 330} +{"train_info/time_between_train_steps": 0.005483388900756836, "step": 330} +{"info/global_step": 331, "train_info/time_within_train_step": 13.160878419876099, "step": 331} +{"train_info/time_between_train_steps": 0.005778074264526367, "step": 331} +{"info/global_step": 332, "train_info/time_within_train_step": 13.136240482330322, "step": 332} +{"train_info/time_between_train_steps": 0.004712820053100586, "step": 332} +{"info/global_step": 333, "train_info/time_within_train_step": 13.160590410232544, "step": 333} +{"train_info/time_between_train_steps": 0.004769325256347656, "step": 333} +{"info/global_step": 334, "train_info/time_within_train_step": 13.157323837280273, "step": 334} +{"train_info/time_between_train_steps": 0.005633115768432617, "step": 334} +{"info/global_step": 335, "train_info/time_within_train_step": 13.388092517852783, "step": 335} +{"train_info/time_between_train_steps": 0.0047414302825927734, "step": 335} +{"info/global_step": 336, "train_info/time_within_train_step": 13.329254627227783, "step": 336} +{"train_info/time_between_train_steps": 0.00494694709777832, "step": 336} +{"info/global_step": 337, "train_info/time_within_train_step": 13.400241374969482, "step": 337} +{"train_info/time_between_train_steps": 0.0053331851959228516, "step": 337} +{"info/global_step": 338, "train_info/time_within_train_step": 13.180921792984009, "step": 338} +{"train_info/time_between_train_steps": 0.005915403366088867, "step": 338} +{"train_info/time_between_train_steps": 10.45800495147705, "step": 338} +{"info/global_step": 339, "train_info/time_within_train_step": 13.139612197875977, "step": 339} +{"train_info/time_between_train_steps": 0.004880428314208984, "step": 339} +{"info/global_step": 340, "train_info/time_within_train_step": 13.2431800365448, "step": 340} +{"train_info/time_between_train_steps": 0.004698991775512695, "step": 340} +{"info/global_step": 341, "train_info/time_within_train_step": 13.133566617965698, "step": 341} +{"train_info/time_between_train_steps": 0.005122184753417969, "step": 341} +{"info/global_step": 342, "train_info/time_within_train_step": 13.230170249938965, "step": 342} +{"train_info/time_between_train_steps": 0.005197048187255859, "step": 342} +{"info/global_step": 343, "train_info/time_within_train_step": 13.132453918457031, "step": 343} +{"train_info/time_between_train_steps": 0.005728960037231445, "step": 343} +{"info/global_step": 344, "train_info/time_within_train_step": 13.223841905593872, "step": 344} +{"train_info/time_between_train_steps": 0.0057642459869384766, "step": 344} +{"info/global_step": 345, "train_info/time_within_train_step": 13.157945394515991, "step": 345} +{"train_info/time_between_train_steps": 0.005812883377075195, "step": 345} +{"info/global_step": 346, "train_info/time_within_train_step": 13.162490129470825, "step": 346} +{"train_info/time_between_train_steps": 0.005713701248168945, "step": 346} +{"info/global_step": 347, "train_info/time_within_train_step": 13.150875568389893, "step": 347} +{"train_info/time_between_train_steps": 0.005066871643066406, "step": 347} +{"info/global_step": 348, "train_info/time_within_train_step": 13.153858423233032, "step": 348} +{"train_info/time_between_train_steps": 0.005521535873413086, "step": 348} +{"info/global_step": 349, "train_info/time_within_train_step": 13.140729665756226, "step": 349} +{"train_info/time_between_train_steps": 0.005475282669067383, "step": 349} +{"info/global_step": 350, "train_info/time_within_train_step": 13.153545379638672, "step": 350} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737047835, "_runtime": 5135}, "step": 350} +{"logs": {"train/loss": 6.7643, "train/learning_rate": 0.00047222222222222224, "train/epoch": 13.01, "_timestamp": 1737047835, "_runtime": 5135}, "step": 350} +{"train_info/time_between_train_steps": 0.034095048904418945, "step": 350} +{"info/global_step": 351, "train_info/time_within_train_step": 13.15204405784607, "step": 351} +{"train_info/time_between_train_steps": 0.004500150680541992, "step": 351} +{"info/global_step": 352, "train_info/time_within_train_step": 13.237589359283447, "step": 352} +{"train_info/time_between_train_steps": 0.005079746246337891, "step": 352} +{"info/global_step": 353, "train_info/time_within_train_step": 13.157244205474854, "step": 353} +{"train_info/time_between_train_steps": 0.00560307502746582, "step": 353} +{"info/global_step": 354, "train_info/time_within_train_step": 13.164137840270996, "step": 354} +{"train_info/time_between_train_steps": 0.00568389892578125, "step": 354} +{"info/global_step": 355, "train_info/time_within_train_step": 13.172420978546143, "step": 355} +{"train_info/time_between_train_steps": 0.005502223968505859, "step": 355} +{"info/global_step": 356, "train_info/time_within_train_step": 13.149338960647583, "step": 356} +{"train_info/time_between_train_steps": 0.0052032470703125, "step": 356} +{"info/global_step": 357, "train_info/time_within_train_step": 13.147924900054932, "step": 357} +{"train_info/time_between_train_steps": 0.005618572235107422, "step": 357} +{"info/global_step": 358, "train_info/time_within_train_step": 13.188486814498901, "step": 358} +{"train_info/time_between_train_steps": 0.005463838577270508, "step": 358} +{"info/global_step": 359, "train_info/time_within_train_step": 13.148617267608643, "step": 359} +{"train_info/time_between_train_steps": 0.005085945129394531, "step": 359} +{"info/global_step": 360, "train_info/time_within_train_step": 13.163352012634277, "step": 360} +{"train_info/time_between_train_steps": 0.0047130584716796875, "step": 360} +{"info/global_step": 361, "train_info/time_within_train_step": 13.165786266326904, "step": 361} +{"train_info/time_between_train_steps": 0.005883693695068359, "step": 361} +{"info/global_step": 362, "train_info/time_within_train_step": 13.176889419555664, "step": 362} +{"train_info/time_between_train_steps": 0.005960226058959961, "step": 362} +{"info/global_step": 363, "train_info/time_within_train_step": 13.19010305404663, "step": 363} +{"train_info/time_between_train_steps": 0.005741119384765625, "step": 363} +{"info/global_step": 364, "train_info/time_within_train_step": 13.174140691757202, "step": 364} +{"train_info/time_between_train_steps": 0.006745338439941406, "step": 364} +{"train_info/time_between_train_steps": 10.553680896759033, "step": 364} +{"info/global_step": 365, "train_info/time_within_train_step": 13.141868114471436, "step": 365} +{"train_info/time_between_train_steps": 0.005547285079956055, "step": 365} +{"info/global_step": 366, "train_info/time_within_train_step": 13.255563497543335, "step": 366} +{"train_info/time_between_train_steps": 0.005614042282104492, "step": 366} +{"info/global_step": 367, "train_info/time_within_train_step": 13.252876043319702, "step": 367} +{"train_info/time_between_train_steps": 0.005640983581542969, "step": 367} +{"info/global_step": 368, "train_info/time_within_train_step": 13.275405645370483, "step": 368} +{"train_info/time_between_train_steps": 0.00550532341003418, "step": 368} +{"info/global_step": 369, "train_info/time_within_train_step": 13.15587854385376, "step": 369} +{"train_info/time_between_train_steps": 0.005823850631713867, "step": 369} +{"info/global_step": 370, "train_info/time_within_train_step": 13.231029510498047, "step": 370} +{"train_info/time_between_train_steps": 0.00552058219909668, "step": 370} +{"info/global_step": 371, "train_info/time_within_train_step": 13.146700143814087, "step": 371} +{"train_info/time_between_train_steps": 0.004990577697753906, "step": 371} +{"info/global_step": 372, "train_info/time_within_train_step": 13.149737358093262, "step": 372} +{"train_info/time_between_train_steps": 0.004920005798339844, "step": 372} +{"info/global_step": 373, "train_info/time_within_train_step": 13.131833791732788, "step": 373} +{"train_info/time_between_train_steps": 0.005265474319458008, "step": 373} +{"info/global_step": 374, "train_info/time_within_train_step": 13.129788160324097, "step": 374} +{"train_info/time_between_train_steps": 0.004765510559082031, "step": 374} +{"info/global_step": 375, "train_info/time_within_train_step": 13.159634351730347, "step": 375} +{"train_info/time_between_train_steps": 0.005429744720458984, "step": 375} +{"info/global_step": 376, "train_info/time_within_train_step": 13.143515348434448, "step": 376} +{"train_info/time_between_train_steps": 0.004970550537109375, "step": 376} +{"info/global_step": 377, "train_info/time_within_train_step": 13.152321815490723, "step": 377} +{"train_info/time_between_train_steps": 0.004331111907958984, "step": 377} +{"info/global_step": 378, "train_info/time_within_train_step": 13.140723943710327, "step": 378} +{"train_info/time_between_train_steps": 0.004538059234619141, "step": 378} +{"info/global_step": 379, "train_info/time_within_train_step": 13.146851301193237, "step": 379} +{"train_info/time_between_train_steps": 0.0051422119140625, "step": 379} +{"info/global_step": 380, "train_info/time_within_train_step": 13.138108730316162, "step": 380} +{"train_info/time_between_train_steps": 0.00506901741027832, "step": 380} +{"info/global_step": 381, "train_info/time_within_train_step": 13.134528160095215, "step": 381} +{"train_info/time_between_train_steps": 0.005415201187133789, "step": 381} +{"info/global_step": 382, "train_info/time_within_train_step": 13.22348165512085, "step": 382} +{"train_info/time_between_train_steps": 0.005198478698730469, "step": 382} +{"info/global_step": 383, "train_info/time_within_train_step": 13.13679814338684, "step": 383} +{"train_info/time_between_train_steps": 0.0052030086517333984, "step": 383} +{"info/global_step": 384, "train_info/time_within_train_step": 13.146345853805542, "step": 384} +{"train_info/time_between_train_steps": 0.0050983428955078125, "step": 384} +{"info/global_step": 385, "train_info/time_within_train_step": 13.143035888671875, "step": 385} +{"train_info/time_between_train_steps": 0.005083322525024414, "step": 385} +{"info/global_step": 386, "train_info/time_within_train_step": 13.139216661453247, "step": 386} +{"train_info/time_between_train_steps": 0.0049114227294921875, "step": 386} +{"info/global_step": 387, "train_info/time_within_train_step": 13.143736600875854, "step": 387} +{"train_info/time_between_train_steps": 0.0048596858978271484, "step": 387} +{"info/global_step": 388, "train_info/time_within_train_step": 13.152121782302856, "step": 388} +{"train_info/time_between_train_steps": 0.004683256149291992, "step": 388} +{"info/global_step": 389, "train_info/time_within_train_step": 13.380467176437378, "step": 389} +{"train_info/time_between_train_steps": 0.005159139633178711, "step": 389} +{"info/global_step": 390, "train_info/time_within_train_step": 13.177008628845215, "step": 390} +{"train_info/time_between_train_steps": 0.005103349685668945, "step": 390} +{"train_info/time_between_train_steps": 10.634500980377197, "step": 390} +{"info/global_step": 391, "train_info/time_within_train_step": 13.11020541191101, "step": 391} +{"train_info/time_between_train_steps": 0.0052411556243896484, "step": 391} +{"info/global_step": 392, "train_info/time_within_train_step": 13.221742868423462, "step": 392} +{"train_info/time_between_train_steps": 0.005017757415771484, "step": 392} +{"info/global_step": 393, "train_info/time_within_train_step": 13.177190065383911, "step": 393} +{"train_info/time_between_train_steps": 0.004326343536376953, "step": 393} +{"info/global_step": 394, "train_info/time_within_train_step": 13.240257740020752, "step": 394} +{"train_info/time_between_train_steps": 0.005076169967651367, "step": 394} +{"info/global_step": 395, "train_info/time_within_train_step": 13.146656513214111, "step": 395} +{"train_info/time_between_train_steps": 0.0051784515380859375, "step": 395} +{"info/global_step": 396, "train_info/time_within_train_step": 13.215723991394043, "step": 396} +{"train_info/time_between_train_steps": 0.0046844482421875, "step": 396} +{"info/global_step": 397, "train_info/time_within_train_step": 13.238762617111206, "step": 397} +{"train_info/time_between_train_steps": 0.0056264400482177734, "step": 397} +{"info/global_step": 398, "train_info/time_within_train_step": 13.181663990020752, "step": 398} +{"train_info/time_between_train_steps": 0.0044934749603271484, "step": 398} +{"info/global_step": 399, "train_info/time_within_train_step": 13.129464864730835, "step": 399} +{"train_info/time_between_train_steps": 0.004905223846435547, "step": 399} +{"info/global_step": 400, "train_info/time_within_train_step": 13.129154682159424, "step": 400} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737048518, "_runtime": 5818}, "step": 400} +{"logs": {"train/loss": 6.5143, "train/learning_rate": 0.00044444444444444436, "train/epoch": 15.01, "_timestamp": 1737048518, "_runtime": 5818}, "step": 400} +{"train_info/time_between_train_steps": 158.44379353523254, "step": 400} +{"info/global_step": 401, "train_info/time_within_train_step": 13.028373003005981, "step": 401} +{"train_info/time_between_train_steps": 0.004864692687988281, "step": 401} +{"info/global_step": 402, "train_info/time_within_train_step": 13.04751181602478, "step": 402} +{"train_info/time_between_train_steps": 0.004359245300292969, "step": 402} +{"info/global_step": 403, "train_info/time_within_train_step": 13.071047067642212, "step": 403} +{"train_info/time_between_train_steps": 0.005438566207885742, "step": 403} +{"info/global_step": 404, "train_info/time_within_train_step": 13.081970453262329, "step": 404} +{"train_info/time_between_train_steps": 0.005644798278808594, "step": 404} +{"info/global_step": 405, "train_info/time_within_train_step": 13.101216554641724, "step": 405} +{"train_info/time_between_train_steps": 0.004565238952636719, "step": 405} +{"info/global_step": 406, "train_info/time_within_train_step": 13.09685206413269, "step": 406} +{"train_info/time_between_train_steps": 0.0053517818450927734, "step": 406} +{"info/global_step": 407, "train_info/time_within_train_step": 13.108677387237549, "step": 407} +{"train_info/time_between_train_steps": 0.005150794982910156, "step": 407} +{"info/global_step": 408, "train_info/time_within_train_step": 13.119786739349365, "step": 408} +{"train_info/time_between_train_steps": 0.0042781829833984375, "step": 408} +{"info/global_step": 409, "train_info/time_within_train_step": 13.11577033996582, "step": 409} +{"train_info/time_between_train_steps": 0.005171537399291992, "step": 409} +{"info/global_step": 410, "train_info/time_within_train_step": 13.128525733947754, "step": 410} +{"train_info/time_between_train_steps": 0.004877805709838867, "step": 410} +{"info/global_step": 411, "train_info/time_within_train_step": 13.140875339508057, "step": 411} +{"train_info/time_between_train_steps": 0.00575566291809082, "step": 411} +{"info/global_step": 412, "train_info/time_within_train_step": 13.14485239982605, "step": 412} +{"train_info/time_between_train_steps": 0.004674673080444336, "step": 412} +{"info/global_step": 413, "train_info/time_within_train_step": 13.223682165145874, "step": 413} +{"train_info/time_between_train_steps": 0.005619525909423828, "step": 413} +{"info/global_step": 414, "train_info/time_within_train_step": 13.146251440048218, "step": 414} +{"train_info/time_between_train_steps": 0.00498652458190918, "step": 414} +{"info/global_step": 415, "train_info/time_within_train_step": 13.173091650009155, "step": 415} +{"train_info/time_between_train_steps": 0.005700111389160156, "step": 415} +{"info/global_step": 416, "train_info/time_within_train_step": 13.183507680892944, "step": 416} +{"train_info/time_between_train_steps": 0.005829334259033203, "step": 416} +{"train_info/time_between_train_steps": 10.533447742462158, "step": 416} +{"info/global_step": 417, "train_info/time_within_train_step": 13.153259992599487, "step": 417} +{"train_info/time_between_train_steps": 0.004658937454223633, "step": 417} +{"info/global_step": 418, "train_info/time_within_train_step": 13.223934412002563, "step": 418} +{"train_info/time_between_train_steps": 0.00536799430847168, "step": 418} +{"info/global_step": 419, "train_info/time_within_train_step": 13.141163349151611, "step": 419} +{"train_info/time_between_train_steps": 0.005299806594848633, "step": 419} +{"info/global_step": 420, "train_info/time_within_train_step": 13.263400554656982, "step": 420} +{"train_info/time_between_train_steps": 0.0050051212310791016, "step": 420} +{"info/global_step": 421, "train_info/time_within_train_step": 13.16071891784668, "step": 421} +{"train_info/time_between_train_steps": 0.00528264045715332, "step": 421} +{"info/global_step": 422, "train_info/time_within_train_step": 13.227565288543701, "step": 422} +{"train_info/time_between_train_steps": 0.00562739372253418, "step": 422} +{"info/global_step": 423, "train_info/time_within_train_step": 13.160566091537476, "step": 423} +{"train_info/time_between_train_steps": 0.004963874816894531, "step": 423} +{"info/global_step": 424, "train_info/time_within_train_step": 13.147746324539185, "step": 424} +{"train_info/time_between_train_steps": 0.004641294479370117, "step": 424} +{"info/global_step": 425, "train_info/time_within_train_step": 13.14651370048523, "step": 425} +{"train_info/time_between_train_steps": 0.0050811767578125, "step": 425} +{"info/global_step": 426, "train_info/time_within_train_step": 13.15995454788208, "step": 426} +{"train_info/time_between_train_steps": 0.00467228889465332, "step": 426} +{"info/global_step": 427, "train_info/time_within_train_step": 13.216192245483398, "step": 427} +{"train_info/time_between_train_steps": 0.005209922790527344, "step": 427} +{"info/global_step": 428, "train_info/time_within_train_step": 13.22744870185852, "step": 428} +{"train_info/time_between_train_steps": 0.004843235015869141, "step": 428} +{"info/global_step": 429, "train_info/time_within_train_step": 13.155495643615723, "step": 429} +{"train_info/time_between_train_steps": 0.004858255386352539, "step": 429} +{"info/global_step": 430, "train_info/time_within_train_step": 13.177109003067017, "step": 430} +{"train_info/time_between_train_steps": 0.005363941192626953, "step": 430} +{"info/global_step": 431, "train_info/time_within_train_step": 13.190231561660767, "step": 431} +{"train_info/time_between_train_steps": 0.005266666412353516, "step": 431} +{"info/global_step": 432, "train_info/time_within_train_step": 13.175321578979492, "step": 432} +{"train_info/time_between_train_steps": 0.004828453063964844, "step": 432} +{"info/global_step": 433, "train_info/time_within_train_step": 13.158584833145142, "step": 433} +{"train_info/time_between_train_steps": 0.005431175231933594, "step": 433} +{"info/global_step": 434, "train_info/time_within_train_step": 13.162984609603882, "step": 434} +{"train_info/time_between_train_steps": 0.005547046661376953, "step": 434} +{"info/global_step": 435, "train_info/time_within_train_step": 13.169513940811157, "step": 435} +{"train_info/time_between_train_steps": 0.004521369934082031, "step": 435} +{"info/global_step": 436, "train_info/time_within_train_step": 13.16205358505249, "step": 436} +{"train_info/time_between_train_steps": 0.0044782161712646484, "step": 436} +{"info/global_step": 437, "train_info/time_within_train_step": 13.158400774002075, "step": 437} +{"train_info/time_between_train_steps": 0.005209445953369141, "step": 437} +{"info/global_step": 438, "train_info/time_within_train_step": 13.161128759384155, "step": 438} +{"train_info/time_between_train_steps": 0.00569605827331543, "step": 438} +{"info/global_step": 439, "train_info/time_within_train_step": 13.179784774780273, "step": 439} +{"train_info/time_between_train_steps": 0.006020784378051758, "step": 439} +{"info/global_step": 440, "train_info/time_within_train_step": 13.177318811416626, "step": 440} +{"train_info/time_between_train_steps": 0.005411624908447266, "step": 440} +{"info/global_step": 441, "train_info/time_within_train_step": 13.17177939414978, "step": 441} +{"train_info/time_between_train_steps": 0.005769014358520508, "step": 441} +{"info/global_step": 442, "train_info/time_within_train_step": 13.199005842208862, "step": 442} +{"train_info/time_between_train_steps": 0.006211996078491211, "step": 442} +{"train_info/time_between_train_steps": 10.568457841873169, "step": 442} +{"info/global_step": 443, "train_info/time_within_train_step": 13.255701065063477, "step": 443} +{"train_info/time_between_train_steps": 0.005398273468017578, "step": 443} +{"info/global_step": 444, "train_info/time_within_train_step": 13.23123288154602, "step": 444} +{"train_info/time_between_train_steps": 0.005145072937011719, "step": 444} +{"info/global_step": 445, "train_info/time_within_train_step": 13.141732215881348, "step": 445} +{"train_info/time_between_train_steps": 0.005373954772949219, "step": 445} +{"info/global_step": 446, "train_info/time_within_train_step": 13.278223276138306, "step": 446} +{"train_info/time_between_train_steps": 0.005124092102050781, "step": 446} +{"info/global_step": 447, "train_info/time_within_train_step": 13.172541618347168, "step": 447} +{"train_info/time_between_train_steps": 0.005368709564208984, "step": 447} +{"info/global_step": 448, "train_info/time_within_train_step": 13.251002073287964, "step": 448} +{"train_info/time_between_train_steps": 0.005753040313720703, "step": 448} +{"info/global_step": 449, "train_info/time_within_train_step": 13.167092561721802, "step": 449} +{"train_info/time_between_train_steps": 0.005326747894287109, "step": 449} +{"info/global_step": 450, "train_info/time_within_train_step": 13.153067827224731, "step": 450} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737049357, "_runtime": 6657}, "step": 450} +{"logs": {"train/loss": 6.2988, "train/learning_rate": 0.00041666666666666664, "train/epoch": 17.01, "_timestamp": 1737049357, "_runtime": 6657}, "step": 450} +{"train_info/time_between_train_steps": 0.060033559799194336, "step": 450} +{"info/global_step": 451, "train_info/time_within_train_step": 13.143661975860596, "step": 451} +{"train_info/time_between_train_steps": 0.005014657974243164, "step": 451} +{"info/global_step": 452, "train_info/time_within_train_step": 13.179842948913574, "step": 452} +{"train_info/time_between_train_steps": 0.005606651306152344, "step": 452} +{"info/global_step": 453, "train_info/time_within_train_step": 13.171229124069214, "step": 453} +{"train_info/time_between_train_steps": 0.004892110824584961, "step": 453} +{"info/global_step": 454, "train_info/time_within_train_step": 13.148154258728027, "step": 454} +{"train_info/time_between_train_steps": 0.0048370361328125, "step": 454} +{"info/global_step": 455, "train_info/time_within_train_step": 13.141892194747925, "step": 455} +{"train_info/time_between_train_steps": 0.004644155502319336, "step": 455} +{"info/global_step": 456, "train_info/time_within_train_step": 13.153473138809204, "step": 456} +{"train_info/time_between_train_steps": 0.005321025848388672, "step": 456} +{"info/global_step": 457, "train_info/time_within_train_step": 13.177098989486694, "step": 457} +{"train_info/time_between_train_steps": 0.005201578140258789, "step": 457} +{"info/global_step": 458, "train_info/time_within_train_step": 13.166281461715698, "step": 458} +{"train_info/time_between_train_steps": 0.005576610565185547, "step": 458} +{"info/global_step": 459, "train_info/time_within_train_step": 13.229225397109985, "step": 459} +{"train_info/time_between_train_steps": 0.005149364471435547, "step": 459} +{"info/global_step": 460, "train_info/time_within_train_step": 13.151775121688843, "step": 460} +{"train_info/time_between_train_steps": 0.005503177642822266, "step": 460} +{"info/global_step": 461, "train_info/time_within_train_step": 13.146617889404297, "step": 461} +{"train_info/time_between_train_steps": 0.0054378509521484375, "step": 461} +{"info/global_step": 462, "train_info/time_within_train_step": 13.174449443817139, "step": 462} +{"train_info/time_between_train_steps": 0.005353689193725586, "step": 462} +{"info/global_step": 463, "train_info/time_within_train_step": 13.162302017211914, "step": 463} +{"train_info/time_between_train_steps": 0.005429267883300781, "step": 463} +{"info/global_step": 464, "train_info/time_within_train_step": 13.14271354675293, "step": 464} +{"train_info/time_between_train_steps": 0.005277395248413086, "step": 464} +{"info/global_step": 465, "train_info/time_within_train_step": 13.150964498519897, "step": 465} +{"train_info/time_between_train_steps": 0.005789041519165039, "step": 465} +{"info/global_step": 466, "train_info/time_within_train_step": 13.170047760009766, "step": 466} +{"train_info/time_between_train_steps": 0.005128145217895508, "step": 466} +{"info/global_step": 467, "train_info/time_within_train_step": 13.163861274719238, "step": 467} +{"train_info/time_between_train_steps": 0.00541377067565918, "step": 467} +{"info/global_step": 468, "train_info/time_within_train_step": 13.18132996559143, "step": 468} +{"train_info/time_between_train_steps": 0.0067141056060791016, "step": 468} +{"train_info/time_between_train_steps": 10.687260389328003, "step": 468} +{"info/global_step": 469, "train_info/time_within_train_step": 13.129275798797607, "step": 469} +{"train_info/time_between_train_steps": 0.005291938781738281, "step": 469} +{"info/global_step": 470, "train_info/time_within_train_step": 13.212058067321777, "step": 470} +{"train_info/time_between_train_steps": 0.005488395690917969, "step": 470} +{"info/global_step": 471, "train_info/time_within_train_step": 13.14845085144043, "step": 471} +{"train_info/time_between_train_steps": 0.005455493927001953, "step": 471} +{"info/global_step": 472, "train_info/time_within_train_step": 13.24535608291626, "step": 472} +{"train_info/time_between_train_steps": 0.005235433578491211, "step": 472} +{"info/global_step": 473, "train_info/time_within_train_step": 13.152563095092773, "step": 473} +{"train_info/time_between_train_steps": 0.004766225814819336, "step": 473} +{"info/global_step": 474, "train_info/time_within_train_step": 13.32717776298523, "step": 474} +{"train_info/time_between_train_steps": 0.0053403377532958984, "step": 474} +{"info/global_step": 475, "train_info/time_within_train_step": 13.158115863800049, "step": 475} +{"train_info/time_between_train_steps": 0.00575709342956543, "step": 475} +{"info/global_step": 476, "train_info/time_within_train_step": 13.151586771011353, "step": 476} +{"train_info/time_between_train_steps": 0.005548000335693359, "step": 476} +{"info/global_step": 477, "train_info/time_within_train_step": 13.155014514923096, "step": 477} +{"train_info/time_between_train_steps": 0.0052564144134521484, "step": 477} +{"info/global_step": 478, "train_info/time_within_train_step": 14.289186716079712, "step": 478} +{"train_info/time_between_train_steps": 0.005213737487792969, "step": 478} +{"info/global_step": 479, "train_info/time_within_train_step": 13.388388633728027, "step": 479} +{"train_info/time_between_train_steps": 0.005400896072387695, "step": 479} +{"info/global_step": 480, "train_info/time_within_train_step": 13.36742377281189, "step": 480} +{"train_info/time_between_train_steps": 0.00509953498840332, "step": 480} +{"info/global_step": 481, "train_info/time_within_train_step": 13.164369821548462, "step": 481} +{"train_info/time_between_train_steps": 0.004721879959106445, "step": 481} +{"info/global_step": 482, "train_info/time_within_train_step": 13.171973466873169, "step": 482} +{"train_info/time_between_train_steps": 0.005250692367553711, "step": 482} +{"info/global_step": 483, "train_info/time_within_train_step": 13.181526184082031, "step": 483} +{"train_info/time_between_train_steps": 0.0054874420166015625, "step": 483} +{"info/global_step": 484, "train_info/time_within_train_step": 13.191877841949463, "step": 484} +{"train_info/time_between_train_steps": 0.005352973937988281, "step": 484} +{"info/global_step": 485, "train_info/time_within_train_step": 13.180753707885742, "step": 485} +{"train_info/time_between_train_steps": 0.005574464797973633, "step": 485} +{"info/global_step": 486, "train_info/time_within_train_step": 13.172295808792114, "step": 486} +{"train_info/time_between_train_steps": 0.004935264587402344, "step": 486} +{"info/global_step": 487, "train_info/time_within_train_step": 13.189427137374878, "step": 487} +{"train_info/time_between_train_steps": 0.0051991939544677734, "step": 487} +{"info/global_step": 488, "train_info/time_within_train_step": 13.179785013198853, "step": 488} +{"train_info/time_between_train_steps": 0.007586240768432617, "step": 488} +{"info/global_step": 489, "train_info/time_within_train_step": 13.247365951538086, "step": 489} +{"train_info/time_between_train_steps": 0.004962444305419922, "step": 489} +{"info/global_step": 490, "train_info/time_within_train_step": 13.167542219161987, "step": 490} +{"train_info/time_between_train_steps": 0.00954747200012207, "step": 490} +{"info/global_step": 491, "train_info/time_within_train_step": 13.184480905532837, "step": 491} +{"train_info/time_between_train_steps": 0.009261846542358398, "step": 491} +{"info/global_step": 492, "train_info/time_within_train_step": 13.196009874343872, "step": 492} +{"train_info/time_between_train_steps": 0.00811457633972168, "step": 492} +{"info/global_step": 493, "train_info/time_within_train_step": 13.208119630813599, "step": 493} +{"train_info/time_between_train_steps": 0.008200645446777344, "step": 493} +{"info/global_step": 494, "train_info/time_within_train_step": 13.202356100082397, "step": 494} +{"train_info/time_between_train_steps": 0.010138750076293945, "step": 494} +{"train_info/time_between_train_steps": 10.482252359390259, "step": 494} +{"info/global_step": 495, "train_info/time_within_train_step": 13.18244981765747, "step": 495} +{"train_info/time_between_train_steps": 0.004557371139526367, "step": 495} +{"info/global_step": 496, "train_info/time_within_train_step": 13.258861541748047, "step": 496} +{"train_info/time_between_train_steps": 0.0049037933349609375, "step": 496} +{"info/global_step": 497, "train_info/time_within_train_step": 13.15784740447998, "step": 497} +{"train_info/time_between_train_steps": 0.004629373550415039, "step": 497} +{"info/global_step": 498, "train_info/time_within_train_step": 13.445284605026245, "step": 498} +{"train_info/time_between_train_steps": 0.005177974700927734, "step": 498} +{"info/global_step": 499, "train_info/time_within_train_step": 13.182300806045532, "step": 499} +{"train_info/time_between_train_steps": 0.005495548248291016, "step": 499} +{"info/global_step": 500, "train_info/time_within_train_step": 13.58137559890747, "step": 500} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737050043, "_runtime": 7343}, "step": 500} +{"logs": {"train/loss": 6.0872, "train/learning_rate": 0.00038888888888888887, "train/epoch": 19.0, "_timestamp": 1737050043, "_runtime": 7343}, "step": 500} +{"train_info/time_between_train_steps": 49.75981163978577, "step": 500} +{"info/global_step": 501, "train_info/time_within_train_step": 13.492936611175537, "step": 501} +{"train_info/time_between_train_steps": 0.005629539489746094, "step": 501} +{"info/global_step": 502, "train_info/time_within_train_step": 13.097649574279785, "step": 502} +{"train_info/time_between_train_steps": 0.0049991607666015625, "step": 502} +{"info/global_step": 503, "train_info/time_within_train_step": 13.108084917068481, "step": 503} +{"train_info/time_between_train_steps": 0.005513191223144531, "step": 503} +{"info/global_step": 504, "train_info/time_within_train_step": 13.207884550094604, "step": 504} +{"train_info/time_between_train_steps": 0.005457878112792969, "step": 504} +{"info/global_step": 505, "train_info/time_within_train_step": 13.14906644821167, "step": 505} +{"train_info/time_between_train_steps": 0.005468130111694336, "step": 505} +{"info/global_step": 506, "train_info/time_within_train_step": 13.15066385269165, "step": 506} +{"train_info/time_between_train_steps": 0.0054492950439453125, "step": 506} +{"info/global_step": 507, "train_info/time_within_train_step": 13.132938385009766, "step": 507} +{"train_info/time_between_train_steps": 0.005261659622192383, "step": 507} +{"info/global_step": 508, "train_info/time_within_train_step": 13.122555494308472, "step": 508} +{"train_info/time_between_train_steps": 0.005295991897583008, "step": 508} +{"info/global_step": 509, "train_info/time_within_train_step": 13.15595269203186, "step": 509} +{"train_info/time_between_train_steps": 0.005239963531494141, "step": 509} +{"info/global_step": 510, "train_info/time_within_train_step": 13.175070524215698, "step": 510} +{"train_info/time_between_train_steps": 0.005423545837402344, "step": 510} +{"info/global_step": 511, "train_info/time_within_train_step": 13.154147624969482, "step": 511} +{"train_info/time_between_train_steps": 0.0050013065338134766, "step": 511} +{"info/global_step": 512, "train_info/time_within_train_step": 13.155023336410522, "step": 512} +{"train_info/time_between_train_steps": 0.005511760711669922, "step": 512} +{"info/global_step": 513, "train_info/time_within_train_step": 13.155903339385986, "step": 513} +{"train_info/time_between_train_steps": 0.004673004150390625, "step": 513} +{"info/global_step": 514, "train_info/time_within_train_step": 13.198946237564087, "step": 514} +{"train_info/time_between_train_steps": 0.00542140007019043, "step": 514} +{"info/global_step": 515, "train_info/time_within_train_step": 13.190898180007935, "step": 515} +{"train_info/time_between_train_steps": 0.004963874816894531, "step": 515} +{"info/global_step": 516, "train_info/time_within_train_step": 13.156097412109375, "step": 516} +{"train_info/time_between_train_steps": 0.005410671234130859, "step": 516} +{"info/global_step": 517, "train_info/time_within_train_step": 13.159156560897827, "step": 517} +{"train_info/time_between_train_steps": 0.0054280757904052734, "step": 517} +{"info/global_step": 518, "train_info/time_within_train_step": 13.173563241958618, "step": 518} +{"train_info/time_between_train_steps": 0.007931947708129883, "step": 518} +{"info/global_step": 519, "train_info/time_within_train_step": 13.234477758407593, "step": 519} +{"train_info/time_between_train_steps": 0.005731344223022461, "step": 519} +{"info/global_step": 520, "train_info/time_within_train_step": 13.290724515914917, "step": 520} +{"train_info/time_between_train_steps": 0.006723642349243164, "step": 520} +{"train_info/time_between_train_steps": 10.48966121673584, "step": 520} +{"info/global_step": 521, "train_info/time_within_train_step": 13.161790609359741, "step": 521} +{"train_info/time_between_train_steps": 0.00543975830078125, "step": 521} +{"info/global_step": 522, "train_info/time_within_train_step": 13.27576756477356, "step": 522} +{"train_info/time_between_train_steps": 0.005128145217895508, "step": 522} +{"info/global_step": 523, "train_info/time_within_train_step": 13.161595106124878, "step": 523} +{"train_info/time_between_train_steps": 0.005034446716308594, "step": 523} +{"info/global_step": 524, "train_info/time_within_train_step": 13.298680543899536, "step": 524} +{"train_info/time_between_train_steps": 0.005557060241699219, "step": 524} +{"info/global_step": 525, "train_info/time_within_train_step": 13.160043001174927, "step": 525} +{"train_info/time_between_train_steps": 0.0051043033599853516, "step": 525} +{"info/global_step": 526, "train_info/time_within_train_step": 13.47208309173584, "step": 526} +{"train_info/time_between_train_steps": 0.005533456802368164, "step": 526} +{"info/global_step": 527, "train_info/time_within_train_step": 13.730180978775024, "step": 527} +{"train_info/time_between_train_steps": 0.0048635005950927734, "step": 527} +{"info/global_step": 528, "train_info/time_within_train_step": 13.247702836990356, "step": 528} +{"train_info/time_between_train_steps": 0.005614042282104492, "step": 528} +{"info/global_step": 529, "train_info/time_within_train_step": 13.166488885879517, "step": 529} +{"train_info/time_between_train_steps": 0.00551915168762207, "step": 529} +{"info/global_step": 530, "train_info/time_within_train_step": 13.163092851638794, "step": 530} +{"train_info/time_between_train_steps": 0.004907846450805664, "step": 530} +{"info/global_step": 531, "train_info/time_within_train_step": 13.153510570526123, "step": 531} +{"train_info/time_between_train_steps": 0.004786491394042969, "step": 531} +{"info/global_step": 532, "train_info/time_within_train_step": 13.167988777160645, "step": 532} +{"train_info/time_between_train_steps": 0.005303144454956055, "step": 532} +{"info/global_step": 533, "train_info/time_within_train_step": 13.177228689193726, "step": 533} +{"train_info/time_between_train_steps": 0.005084514617919922, "step": 533} +{"info/global_step": 534, "train_info/time_within_train_step": 13.169659852981567, "step": 534} +{"train_info/time_between_train_steps": 0.0057163238525390625, "step": 534} +{"info/global_step": 535, "train_info/time_within_train_step": 13.251246452331543, "step": 535} +{"train_info/time_between_train_steps": 0.005512714385986328, "step": 535} +{"info/global_step": 536, "train_info/time_within_train_step": 13.19650650024414, "step": 536} +{"train_info/time_between_train_steps": 0.005248308181762695, "step": 536} +{"info/global_step": 537, "train_info/time_within_train_step": 13.177477598190308, "step": 537} +{"train_info/time_between_train_steps": 0.005284309387207031, "step": 537} +{"info/global_step": 538, "train_info/time_within_train_step": 13.157864093780518, "step": 538} +{"train_info/time_between_train_steps": 0.005584239959716797, "step": 538} +{"info/global_step": 539, "train_info/time_within_train_step": 13.189089059829712, "step": 539} +{"train_info/time_between_train_steps": 0.005572080612182617, "step": 539} +{"info/global_step": 540, "train_info/time_within_train_step": 13.176896333694458, "step": 540} +{"train_info/time_between_train_steps": 0.004812717437744141, "step": 540} +{"info/global_step": 541, "train_info/time_within_train_step": 13.17787766456604, "step": 541} +{"train_info/time_between_train_steps": 0.004807949066162109, "step": 541} +{"info/global_step": 542, "train_info/time_within_train_step": 13.177517652511597, "step": 542} +{"train_info/time_between_train_steps": 0.005934476852416992, "step": 542} +{"info/global_step": 543, "train_info/time_within_train_step": 13.181588411331177, "step": 543} +{"train_info/time_between_train_steps": 0.0056819915771484375, "step": 543} +{"info/global_step": 544, "train_info/time_within_train_step": 13.219518899917603, "step": 544} +{"train_info/time_between_train_steps": 0.00593113899230957, "step": 544} +{"info/global_step": 545, "train_info/time_within_train_step": 13.193526268005371, "step": 545} +{"train_info/time_between_train_steps": 0.006052494049072266, "step": 545} +{"info/global_step": 546, "train_info/time_within_train_step": 13.209814310073853, "step": 546} +{"train_info/time_between_train_steps": 0.0066869258880615234, "step": 546} +{"train_info/time_between_train_steps": 10.631006956100464, "step": 546} +{"info/global_step": 547, "train_info/time_within_train_step": 13.16486406326294, "step": 547} +{"train_info/time_between_train_steps": 0.005309581756591797, "step": 547} +{"info/global_step": 548, "train_info/time_within_train_step": 13.24838638305664, "step": 548} +{"train_info/time_between_train_steps": 0.005346775054931641, "step": 548} +{"info/global_step": 549, "train_info/time_within_train_step": 13.152796268463135, "step": 549} +{"train_info/time_between_train_steps": 0.005345344543457031, "step": 549} +{"info/global_step": 550, "train_info/time_within_train_step": 13.354852676391602, "step": 550} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737050778, "_runtime": 8078}, "step": 550} +{"logs": {"train/loss": 5.8851, "train/learning_rate": 0.0003611111111111111, "train/epoch": 21.0, "_timestamp": 1737050778, "_runtime": 8078}, "step": 550} +{"train_info/time_between_train_steps": 0.05283164978027344, "step": 550} +{"info/global_step": 551, "train_info/time_within_train_step": 13.170129537582397, "step": 551} +{"train_info/time_between_train_steps": 0.0050470829010009766, "step": 551} +{"info/global_step": 552, "train_info/time_within_train_step": 13.225307703018188, "step": 552} +{"train_info/time_between_train_steps": 0.005196094512939453, "step": 552} +{"info/global_step": 553, "train_info/time_within_train_step": 13.190243005752563, "step": 553} +{"train_info/time_between_train_steps": 0.005647897720336914, "step": 553} +{"info/global_step": 554, "train_info/time_within_train_step": 13.200756311416626, "step": 554} +{"train_info/time_between_train_steps": 0.004831790924072266, "step": 554} +{"info/global_step": 555, "train_info/time_within_train_step": 13.178327560424805, "step": 555} +{"train_info/time_between_train_steps": 0.0053904056549072266, "step": 555} +{"info/global_step": 556, "train_info/time_within_train_step": 13.176541090011597, "step": 556} +{"train_info/time_between_train_steps": 0.005406856536865234, "step": 556} +{"info/global_step": 557, "train_info/time_within_train_step": 13.171412944793701, "step": 557} +{"train_info/time_between_train_steps": 0.0054624080657958984, "step": 557} +{"info/global_step": 558, "train_info/time_within_train_step": 13.180216550827026, "step": 558} +{"train_info/time_between_train_steps": 0.00535893440246582, "step": 558} +{"info/global_step": 559, "train_info/time_within_train_step": 13.169126033782959, "step": 559} +{"train_info/time_between_train_steps": 0.005289316177368164, "step": 559} +{"info/global_step": 560, "train_info/time_within_train_step": 13.161798477172852, "step": 560} +{"train_info/time_between_train_steps": 0.004411458969116211, "step": 560} +{"info/global_step": 561, "train_info/time_within_train_step": 13.163430213928223, "step": 561} +{"train_info/time_between_train_steps": 0.00532841682434082, "step": 561} +{"info/global_step": 562, "train_info/time_within_train_step": 13.188849925994873, "step": 562} +{"train_info/time_between_train_steps": 0.005474567413330078, "step": 562} +{"info/global_step": 563, "train_info/time_within_train_step": 13.16209602355957, "step": 563} +{"train_info/time_between_train_steps": 0.005597591400146484, "step": 563} +{"info/global_step": 564, "train_info/time_within_train_step": 13.161327838897705, "step": 564} +{"train_info/time_between_train_steps": 0.005401134490966797, "step": 564} +{"info/global_step": 565, "train_info/time_within_train_step": 13.26825499534607, "step": 565} +{"train_info/time_between_train_steps": 0.005046844482421875, "step": 565} +{"info/global_step": 566, "train_info/time_within_train_step": 13.180810928344727, "step": 566} +{"train_info/time_between_train_steps": 0.0053517818450927734, "step": 566} +{"info/global_step": 567, "train_info/time_within_train_step": 13.19362187385559, "step": 567} +{"train_info/time_between_train_steps": 0.005179405212402344, "step": 567} +{"info/global_step": 568, "train_info/time_within_train_step": 13.204235076904297, "step": 568} +{"train_info/time_between_train_steps": 0.0054895877838134766, "step": 568} +{"info/global_step": 569, "train_info/time_within_train_step": 13.179399728775024, "step": 569} +{"train_info/time_between_train_steps": 0.005605936050415039, "step": 569} +{"info/global_step": 570, "train_info/time_within_train_step": 13.179284811019897, "step": 570} +{"train_info/time_between_train_steps": 0.005403041839599609, "step": 570} +{"info/global_step": 571, "train_info/time_within_train_step": 13.195216178894043, "step": 571} +{"train_info/time_between_train_steps": 0.006516218185424805, "step": 571} +{"info/global_step": 572, "train_info/time_within_train_step": 13.21661376953125, "step": 572} +{"train_info/time_between_train_steps": 0.006551504135131836, "step": 572} +{"train_info/time_between_train_steps": 10.743035078048706, "step": 572} +{"info/global_step": 573, "train_info/time_within_train_step": 13.141010999679565, "step": 573} +{"train_info/time_between_train_steps": 0.004923343658447266, "step": 573} +{"info/global_step": 574, "train_info/time_within_train_step": 13.239370584487915, "step": 574} +{"train_info/time_between_train_steps": 0.005239009857177734, "step": 574} +{"info/global_step": 575, "train_info/time_within_train_step": 13.190409421920776, "step": 575} +{"train_info/time_between_train_steps": 0.005539655685424805, "step": 575} +{"info/global_step": 576, "train_info/time_within_train_step": 13.243494749069214, "step": 576} +{"train_info/time_between_train_steps": 0.0051081180572509766, "step": 576} +{"info/global_step": 577, "train_info/time_within_train_step": 13.15767765045166, "step": 577} +{"train_info/time_between_train_steps": 0.0049381256103515625, "step": 577} +{"info/global_step": 578, "train_info/time_within_train_step": 13.24255633354187, "step": 578} +{"train_info/time_between_train_steps": 0.0055387020111083984, "step": 578} +{"info/global_step": 579, "train_info/time_within_train_step": 13.153284311294556, "step": 579} +{"train_info/time_between_train_steps": 0.004548311233520508, "step": 579} +{"info/global_step": 580, "train_info/time_within_train_step": 13.255801677703857, "step": 580} +{"train_info/time_between_train_steps": 0.005281686782836914, "step": 580} +{"info/global_step": 581, "train_info/time_within_train_step": 13.16877794265747, "step": 581} +{"train_info/time_between_train_steps": 0.004798173904418945, "step": 581} +{"info/global_step": 582, "train_info/time_within_train_step": 13.167258024215698, "step": 582} +{"train_info/time_between_train_steps": 0.004964590072631836, "step": 582} +{"info/global_step": 583, "train_info/time_within_train_step": 13.172164916992188, "step": 583} +{"train_info/time_between_train_steps": 0.0050852298736572266, "step": 583} +{"info/global_step": 584, "train_info/time_within_train_step": 13.180160760879517, "step": 584} +{"train_info/time_between_train_steps": 0.005170345306396484, "step": 584} +{"info/global_step": 585, "train_info/time_within_train_step": 13.15996766090393, "step": 585} +{"train_info/time_between_train_steps": 0.00516963005065918, "step": 585} +{"info/global_step": 586, "train_info/time_within_train_step": 13.170907020568848, "step": 586} +{"train_info/time_between_train_steps": 0.005199909210205078, "step": 586} +{"info/global_step": 587, "train_info/time_within_train_step": 13.170702457427979, "step": 587} +{"train_info/time_between_train_steps": 0.0055921077728271484, "step": 587} +{"info/global_step": 588, "train_info/time_within_train_step": 13.173717498779297, "step": 588} +{"train_info/time_between_train_steps": 0.005079984664916992, "step": 588} +{"info/global_step": 589, "train_info/time_within_train_step": 13.16407060623169, "step": 589} +{"train_info/time_between_train_steps": 0.005295276641845703, "step": 589} +{"info/global_step": 590, "train_info/time_within_train_step": 13.174593687057495, "step": 590} +{"train_info/time_between_train_steps": 0.004910707473754883, "step": 590} +{"info/global_step": 591, "train_info/time_within_train_step": 13.166644811630249, "step": 591} +{"train_info/time_between_train_steps": 0.005075216293334961, "step": 591} +{"info/global_step": 592, "train_info/time_within_train_step": 13.175219058990479, "step": 592} +{"train_info/time_between_train_steps": 0.005871772766113281, "step": 592} +{"info/global_step": 593, "train_info/time_within_train_step": 13.185558557510376, "step": 593} +{"train_info/time_between_train_steps": 0.005649566650390625, "step": 593} +{"info/global_step": 594, "train_info/time_within_train_step": 13.170727491378784, "step": 594} +{"train_info/time_between_train_steps": 0.0052602291107177734, "step": 594} +{"info/global_step": 595, "train_info/time_within_train_step": 13.170151710510254, "step": 595} +{"train_info/time_between_train_steps": 0.0054302215576171875, "step": 595} +{"info/global_step": 596, "train_info/time_within_train_step": 13.256454706192017, "step": 596} +{"train_info/time_between_train_steps": 0.00583338737487793, "step": 596} +{"info/global_step": 597, "train_info/time_within_train_step": 13.17465877532959, "step": 597} +{"train_info/time_between_train_steps": 0.00548863410949707, "step": 597} +{"info/global_step": 598, "train_info/time_within_train_step": 13.209933280944824, "step": 598} +{"train_info/time_between_train_steps": 0.006634712219238281, "step": 598} +{"train_info/time_between_train_steps": 11.628950119018555, "step": 598} +{"info/global_step": 599, "train_info/time_within_train_step": 13.195846557617188, "step": 599} +{"train_info/time_between_train_steps": 0.004912376403808594, "step": 599} +{"info/global_step": 600, "train_info/time_within_train_step": 13.264164447784424, "step": 600} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737051462, "_runtime": 8762}, "step": 600} +{"logs": {"train/loss": 5.7103, "train/learning_rate": 0.0003333333333333333, "train/epoch": 23.0, "_timestamp": 1737051462, "_runtime": 8762}, "step": 600} +{"train_info/time_between_train_steps": 17.085770845413208, "step": 600} +{"info/global_step": 601, "train_info/time_within_train_step": 13.1085946559906, "step": 601} +{"train_info/time_between_train_steps": 0.006119966506958008, "step": 601} +{"info/global_step": 602, "train_info/time_within_train_step": 13.22075629234314, "step": 602} +{"train_info/time_between_train_steps": 0.005515098571777344, "step": 602} +{"info/global_step": 603, "train_info/time_within_train_step": 13.123002290725708, "step": 603} +{"train_info/time_between_train_steps": 0.004610538482666016, "step": 603} +{"info/global_step": 604, "train_info/time_within_train_step": 13.728559494018555, "step": 604} +{"train_info/time_between_train_steps": 0.0049686431884765625, "step": 604} +{"info/global_step": 605, "train_info/time_within_train_step": 13.9741370677948, "step": 605} +{"train_info/time_between_train_steps": 0.004735708236694336, "step": 605} +{"info/global_step": 606, "train_info/time_within_train_step": 13.281490802764893, "step": 606} +{"train_info/time_between_train_steps": 0.004880189895629883, "step": 606} +{"info/global_step": 607, "train_info/time_within_train_step": 13.126940965652466, "step": 607} +{"train_info/time_between_train_steps": 0.004863739013671875, "step": 607} +{"info/global_step": 608, "train_info/time_within_train_step": 13.13039755821228, "step": 608} +{"train_info/time_between_train_steps": 0.0050313472747802734, "step": 608} +{"info/global_step": 609, "train_info/time_within_train_step": 13.1629798412323, "step": 609} +{"train_info/time_between_train_steps": 0.005218505859375, "step": 609} +{"info/global_step": 610, "train_info/time_within_train_step": 13.150203227996826, "step": 610} +{"train_info/time_between_train_steps": 0.005198240280151367, "step": 610} +{"info/global_step": 611, "train_info/time_within_train_step": 13.245985746383667, "step": 611} +{"train_info/time_between_train_steps": 0.005343437194824219, "step": 611} +{"info/global_step": 612, "train_info/time_within_train_step": 13.157521963119507, "step": 612} +{"train_info/time_between_train_steps": 0.005342245101928711, "step": 612} +{"info/global_step": 613, "train_info/time_within_train_step": 13.152660846710205, "step": 613} +{"train_info/time_between_train_steps": 0.0050427913665771484, "step": 613} +{"info/global_step": 614, "train_info/time_within_train_step": 13.16163969039917, "step": 614} +{"train_info/time_between_train_steps": 0.005525827407836914, "step": 614} +{"info/global_step": 615, "train_info/time_within_train_step": 13.169620513916016, "step": 615} +{"train_info/time_between_train_steps": 0.005524635314941406, "step": 615} +{"info/global_step": 616, "train_info/time_within_train_step": 13.172721147537231, "step": 616} +{"train_info/time_between_train_steps": 0.005350828170776367, "step": 616} +{"info/global_step": 617, "train_info/time_within_train_step": 13.174564838409424, "step": 617} +{"train_info/time_between_train_steps": 0.0056610107421875, "step": 617} +{"info/global_step": 618, "train_info/time_within_train_step": 13.174737930297852, "step": 618} +{"train_info/time_between_train_steps": 0.005238056182861328, "step": 618} +{"info/global_step": 619, "train_info/time_within_train_step": 13.19188141822815, "step": 619} +{"train_info/time_between_train_steps": 0.005233049392700195, "step": 619} +{"info/global_step": 620, "train_info/time_within_train_step": 13.169717788696289, "step": 620} +{"train_info/time_between_train_steps": 0.0059642791748046875, "step": 620} +{"info/global_step": 621, "train_info/time_within_train_step": 13.163357257843018, "step": 621} +{"train_info/time_between_train_steps": 0.005464315414428711, "step": 621} +{"info/global_step": 622, "train_info/time_within_train_step": 13.188621759414673, "step": 622} +{"train_info/time_between_train_steps": 0.004925966262817383, "step": 622} +{"info/global_step": 623, "train_info/time_within_train_step": 13.24378490447998, "step": 623} +{"train_info/time_between_train_steps": 0.006209135055541992, "step": 623} +{"info/global_step": 624, "train_info/time_within_train_step": 13.210256814956665, "step": 624} +{"train_info/time_between_train_steps": 0.00641179084777832, "step": 624} +{"train_info/time_between_train_steps": 10.59144115447998, "step": 624} +{"info/global_step": 625, "train_info/time_within_train_step": 13.152135133743286, "step": 625} +{"train_info/time_between_train_steps": 0.00564265251159668, "step": 625} +{"info/global_step": 626, "train_info/time_within_train_step": 13.341295003890991, "step": 626} +{"train_info/time_between_train_steps": 0.005108833312988281, "step": 626} +{"info/global_step": 627, "train_info/time_within_train_step": 13.281057596206665, "step": 627} +{"train_info/time_between_train_steps": 0.004883527755737305, "step": 627} +{"info/global_step": 628, "train_info/time_within_train_step": 13.265774726867676, "step": 628} +{"train_info/time_between_train_steps": 0.0046443939208984375, "step": 628} +{"info/global_step": 629, "train_info/time_within_train_step": 13.15680742263794, "step": 629} +{"train_info/time_between_train_steps": 0.005042552947998047, "step": 629} +{"info/global_step": 630, "train_info/time_within_train_step": 13.251508712768555, "step": 630} +{"train_info/time_between_train_steps": 0.005680084228515625, "step": 630} +{"info/global_step": 631, "train_info/time_within_train_step": 13.180830240249634, "step": 631} +{"train_info/time_between_train_steps": 0.005019187927246094, "step": 631} +{"info/global_step": 632, "train_info/time_within_train_step": 13.144858121871948, "step": 632} +{"train_info/time_between_train_steps": 0.0053060054779052734, "step": 632} +{"info/global_step": 633, "train_info/time_within_train_step": 13.140306234359741, "step": 633} +{"train_info/time_between_train_steps": 0.005255222320556641, "step": 633} +{"info/global_step": 634, "train_info/time_within_train_step": 13.132642030715942, "step": 634} +{"train_info/time_between_train_steps": 0.005666017532348633, "step": 634} +{"info/global_step": 635, "train_info/time_within_train_step": 13.14229416847229, "step": 635} +{"train_info/time_between_train_steps": 0.005310773849487305, "step": 635} +{"info/global_step": 636, "train_info/time_within_train_step": 13.16404414176941, "step": 636} +{"train_info/time_between_train_steps": 0.005549192428588867, "step": 636} +{"info/global_step": 637, "train_info/time_within_train_step": 13.149210214614868, "step": 637} +{"train_info/time_between_train_steps": 0.004935503005981445, "step": 637} +{"info/global_step": 638, "train_info/time_within_train_step": 13.13482666015625, "step": 638} +{"train_info/time_between_train_steps": 0.005378007888793945, "step": 638} +{"info/global_step": 639, "train_info/time_within_train_step": 13.15166687965393, "step": 639} +{"train_info/time_between_train_steps": 0.005108356475830078, "step": 639} +{"info/global_step": 640, "train_info/time_within_train_step": 13.147981643676758, "step": 640} +{"train_info/time_between_train_steps": 0.0054416656494140625, "step": 640} +{"info/global_step": 641, "train_info/time_within_train_step": 13.159327745437622, "step": 641} +{"train_info/time_between_train_steps": 0.005213260650634766, "step": 641} +{"info/global_step": 642, "train_info/time_within_train_step": 13.222649335861206, "step": 642} +{"train_info/time_between_train_steps": 0.0049915313720703125, "step": 642} +{"info/global_step": 643, "train_info/time_within_train_step": 13.146457433700562, "step": 643} +{"train_info/time_between_train_steps": 0.00550079345703125, "step": 643} +{"info/global_step": 644, "train_info/time_within_train_step": 13.167520523071289, "step": 644} +{"train_info/time_between_train_steps": 0.005868434906005859, "step": 644} +{"info/global_step": 645, "train_info/time_within_train_step": 13.148894309997559, "step": 645} +{"train_info/time_between_train_steps": 0.00533747673034668, "step": 645} +{"info/global_step": 646, "train_info/time_within_train_step": 13.161538362503052, "step": 646} +{"train_info/time_between_train_steps": 0.005857944488525391, "step": 646} +{"info/global_step": 647, "train_info/time_within_train_step": 13.157063722610474, "step": 647} +{"train_info/time_between_train_steps": 0.005439281463623047, "step": 647} +{"info/global_step": 648, "train_info/time_within_train_step": 13.151614904403687, "step": 648} +{"train_info/time_between_train_steps": 0.0053594112396240234, "step": 648} +{"info/global_step": 649, "train_info/time_within_train_step": 13.171105861663818, "step": 649} +{"train_info/time_between_train_steps": 0.005234479904174805, "step": 649} +{"info/global_step": 650, "train_info/time_within_train_step": 13.185908555984497, "step": 650} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737052155, "_runtime": 9455}, "step": 650} +{"logs": {"train/loss": 5.4879, "train/learning_rate": 0.00030555555555555555, "train/epoch": 24.02, "_timestamp": 1737052155, "_runtime": 9455}, "step": 650} +{"train_info/time_between_train_steps": 0.040967702865600586, "step": 650} +{"train_info/time_between_train_steps": 10.69295334815979, "step": 650} +{"info/global_step": 651, "train_info/time_within_train_step": 13.122320413589478, "step": 651} +{"train_info/time_between_train_steps": 0.005033016204833984, "step": 651} +{"info/global_step": 652, "train_info/time_within_train_step": 13.23039984703064, "step": 652} +{"train_info/time_between_train_steps": 0.005541086196899414, "step": 652} +{"info/global_step": 653, "train_info/time_within_train_step": 13.15305757522583, "step": 653} +{"train_info/time_between_train_steps": 0.005347013473510742, "step": 653} +{"info/global_step": 654, "train_info/time_within_train_step": 13.261266231536865, "step": 654} +{"train_info/time_between_train_steps": 0.0051534175872802734, "step": 654} +{"info/global_step": 655, "train_info/time_within_train_step": 13.150328397750854, "step": 655} +{"train_info/time_between_train_steps": 0.0056040287017822266, "step": 655} +{"info/global_step": 656, "train_info/time_within_train_step": 13.229875087738037, "step": 656} +{"train_info/time_between_train_steps": 0.004777193069458008, "step": 656} +{"info/global_step": 657, "train_info/time_within_train_step": 13.227392435073853, "step": 657} +{"train_info/time_between_train_steps": 0.005400896072387695, "step": 657} +{"info/global_step": 658, "train_info/time_within_train_step": 13.160017728805542, "step": 658} +{"train_info/time_between_train_steps": 0.005196094512939453, "step": 658} +{"info/global_step": 659, "train_info/time_within_train_step": 13.142138004302979, "step": 659} +{"train_info/time_between_train_steps": 0.004756450653076172, "step": 659} +{"info/global_step": 660, "train_info/time_within_train_step": 13.14125657081604, "step": 660} +{"train_info/time_between_train_steps": 0.00505828857421875, "step": 660} +{"info/global_step": 661, "train_info/time_within_train_step": 13.144708156585693, "step": 661} +{"train_info/time_between_train_steps": 0.005692243576049805, "step": 661} +{"info/global_step": 662, "train_info/time_within_train_step": 13.153093576431274, "step": 662} +{"train_info/time_between_train_steps": 0.005150556564331055, "step": 662} +{"info/global_step": 663, "train_info/time_within_train_step": 13.150268793106079, "step": 663} +{"train_info/time_between_train_steps": 0.004701137542724609, "step": 663} +{"info/global_step": 664, "train_info/time_within_train_step": 13.144120454788208, "step": 664} +{"train_info/time_between_train_steps": 0.005550861358642578, "step": 664} +{"info/global_step": 665, "train_info/time_within_train_step": 13.14119577407837, "step": 665} +{"train_info/time_between_train_steps": 0.0050051212310791016, "step": 665} +{"info/global_step": 666, "train_info/time_within_train_step": 13.162955284118652, "step": 666} +{"train_info/time_between_train_steps": 0.005223512649536133, "step": 666} +{"info/global_step": 667, "train_info/time_within_train_step": 13.165148973464966, "step": 667} +{"train_info/time_between_train_steps": 0.005484819412231445, "step": 667} +{"info/global_step": 668, "train_info/time_within_train_step": 13.152826309204102, "step": 668} +{"train_info/time_between_train_steps": 0.005194664001464844, "step": 668} +{"info/global_step": 669, "train_info/time_within_train_step": 13.144013404846191, "step": 669} +{"train_info/time_between_train_steps": 0.005582332611083984, "step": 669} +{"info/global_step": 670, "train_info/time_within_train_step": 13.15664553642273, "step": 670} +{"train_info/time_between_train_steps": 0.005597114562988281, "step": 670} +{"info/global_step": 671, "train_info/time_within_train_step": 13.158592939376831, "step": 671} +{"train_info/time_between_train_steps": 0.005173683166503906, "step": 671} +{"info/global_step": 672, "train_info/time_within_train_step": 13.237786054611206, "step": 672} +{"train_info/time_between_train_steps": 0.005440235137939453, "step": 672} +{"info/global_step": 673, "train_info/time_within_train_step": 13.159809589385986, "step": 673} +{"train_info/time_between_train_steps": 0.005285024642944336, "step": 673} +{"info/global_step": 674, "train_info/time_within_train_step": 13.154329061508179, "step": 674} +{"train_info/time_between_train_steps": 0.005530834197998047, "step": 674} +{"info/global_step": 675, "train_info/time_within_train_step": 13.15680480003357, "step": 675} +{"train_info/time_between_train_steps": 0.005463123321533203, "step": 675} +{"info/global_step": 676, "train_info/time_within_train_step": 13.17735767364502, "step": 676} +{"train_info/time_between_train_steps": 0.006453752517700195, "step": 676} +{"train_info/time_between_train_steps": 12.513005018234253, "step": 676} +{"info/global_step": 677, "train_info/time_within_train_step": 13.150383710861206, "step": 677} +{"train_info/time_between_train_steps": 0.00548863410949707, "step": 677} +{"info/global_step": 678, "train_info/time_within_train_step": 13.204968929290771, "step": 678} +{"train_info/time_between_train_steps": 0.005334138870239258, "step": 678} +{"info/global_step": 679, "train_info/time_within_train_step": 13.132947206497192, "step": 679} +{"train_info/time_between_train_steps": 0.005270957946777344, "step": 679} +{"info/global_step": 680, "train_info/time_within_train_step": 13.233970403671265, "step": 680} +{"train_info/time_between_train_steps": 0.005230426788330078, "step": 680} +{"info/global_step": 681, "train_info/time_within_train_step": 13.143903970718384, "step": 681} +{"train_info/time_between_train_steps": 0.00558781623840332, "step": 681} +{"info/global_step": 682, "train_info/time_within_train_step": 13.202484369277954, "step": 682} +{"train_info/time_between_train_steps": 0.00472259521484375, "step": 682} +{"info/global_step": 683, "train_info/time_within_train_step": 13.15568494796753, "step": 683} +{"train_info/time_between_train_steps": 0.005724668502807617, "step": 683} +{"info/global_step": 684, "train_info/time_within_train_step": 13.187571048736572, "step": 684} +{"train_info/time_between_train_steps": 0.005585908889770508, "step": 684} +{"info/global_step": 685, "train_info/time_within_train_step": 13.15169644355774, "step": 685} +{"train_info/time_between_train_steps": 0.0055370330810546875, "step": 685} +{"info/global_step": 686, "train_info/time_within_train_step": 13.13529896736145, "step": 686} +{"train_info/time_between_train_steps": 0.005381345748901367, "step": 686} +{"info/global_step": 687, "train_info/time_within_train_step": 13.230672359466553, "step": 687} +{"train_info/time_between_train_steps": 0.005221843719482422, "step": 687} +{"info/global_step": 688, "train_info/time_within_train_step": 13.141880989074707, "step": 688} +{"train_info/time_between_train_steps": 0.004877328872680664, "step": 688} +{"info/global_step": 689, "train_info/time_within_train_step": 13.160399913787842, "step": 689} +{"train_info/time_between_train_steps": 0.005350351333618164, "step": 689} +{"info/global_step": 690, "train_info/time_within_train_step": 13.147004127502441, "step": 690} +{"train_info/time_between_train_steps": 0.005299806594848633, "step": 690} +{"info/global_step": 691, "train_info/time_within_train_step": 13.139352798461914, "step": 691} +{"train_info/time_between_train_steps": 0.005372524261474609, "step": 691} +{"info/global_step": 692, "train_info/time_within_train_step": 13.151225328445435, "step": 692} +{"train_info/time_between_train_steps": 0.0054895877838134766, "step": 692} +{"info/global_step": 693, "train_info/time_within_train_step": 13.142423868179321, "step": 693} +{"train_info/time_between_train_steps": 0.005553245544433594, "step": 693} +{"info/global_step": 694, "train_info/time_within_train_step": 13.137107849121094, "step": 694} +{"train_info/time_between_train_steps": 0.004970550537109375, "step": 694} +{"info/global_step": 695, "train_info/time_within_train_step": 13.144739866256714, "step": 695} +{"train_info/time_between_train_steps": 0.005587100982666016, "step": 695} +{"info/global_step": 696, "train_info/time_within_train_step": 13.145357131958008, "step": 696} +{"train_info/time_between_train_steps": 0.005342006683349609, "step": 696} +{"info/global_step": 697, "train_info/time_within_train_step": 13.157617568969727, "step": 697} +{"train_info/time_between_train_steps": 0.005005598068237305, "step": 697} +{"info/global_step": 698, "train_info/time_within_train_step": 13.136272430419922, "step": 698} +{"train_info/time_between_train_steps": 0.005407810211181641, "step": 698} +{"info/global_step": 699, "train_info/time_within_train_step": 13.364650964736938, "step": 699} +{"train_info/time_between_train_steps": 0.005879402160644531, "step": 699} +{"info/global_step": 700, "train_info/time_within_train_step": 13.15635633468628, "step": 700} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737052838, "_runtime": 10138}, "step": 700} +{"logs": {"train/loss": 5.4167, "train/learning_rate": 0.0002777777777777778, "train/epoch": 26.02, "_timestamp": 1737052838, "_runtime": 10138}, "step": 700} +{"train_info/time_between_train_steps": 17.218106508255005, "step": 700} +{"info/global_step": 701, "train_info/time_within_train_step": 13.135749578475952, "step": 701} +{"train_info/time_between_train_steps": 0.00566411018371582, "step": 701} +{"info/global_step": 702, "train_info/time_within_train_step": 13.15044355392456, "step": 702} +{"train_info/time_between_train_steps": 0.006289243698120117, "step": 702} +{"train_info/time_between_train_steps": 10.564927339553833, "step": 702} +{"info/global_step": 703, "train_info/time_within_train_step": 13.093574285507202, "step": 703} +{"train_info/time_between_train_steps": 0.005181312561035156, "step": 703} +{"info/global_step": 704, "train_info/time_within_train_step": 13.245555639266968, "step": 704} +{"train_info/time_between_train_steps": 0.005608797073364258, "step": 704} +{"info/global_step": 705, "train_info/time_within_train_step": 13.137161016464233, "step": 705} +{"train_info/time_between_train_steps": 0.005605936050415039, "step": 705} +{"info/global_step": 706, "train_info/time_within_train_step": 13.252620220184326, "step": 706} +{"train_info/time_between_train_steps": 0.004820823669433594, "step": 706} +{"info/global_step": 707, "train_info/time_within_train_step": 13.12906527519226, "step": 707} +{"train_info/time_between_train_steps": 0.0048046112060546875, "step": 707} +{"info/global_step": 708, "train_info/time_within_train_step": 13.210459470748901, "step": 708} +{"train_info/time_between_train_steps": 0.004932880401611328, "step": 708} +{"info/global_step": 709, "train_info/time_within_train_step": 13.1928551197052, "step": 709} +{"train_info/time_between_train_steps": 0.005139350891113281, "step": 709} +{"info/global_step": 710, "train_info/time_within_train_step": 13.153364181518555, "step": 710} +{"train_info/time_between_train_steps": 0.00490570068359375, "step": 710} +{"info/global_step": 711, "train_info/time_within_train_step": 13.132633447647095, "step": 711} +{"train_info/time_between_train_steps": 0.005320549011230469, "step": 711} +{"info/global_step": 712, "train_info/time_within_train_step": 13.145675420761108, "step": 712} +{"train_info/time_between_train_steps": 0.005407810211181641, "step": 712} +{"info/global_step": 713, "train_info/time_within_train_step": 13.154654502868652, "step": 713} +{"train_info/time_between_train_steps": 0.005110025405883789, "step": 713} +{"info/global_step": 714, "train_info/time_within_train_step": 13.144728183746338, "step": 714} +{"train_info/time_between_train_steps": 0.004816532135009766, "step": 714} +{"info/global_step": 715, "train_info/time_within_train_step": 13.154500007629395, "step": 715} +{"train_info/time_between_train_steps": 0.0049326419830322266, "step": 715} +{"info/global_step": 716, "train_info/time_within_train_step": 13.142616748809814, "step": 716} +{"train_info/time_between_train_steps": 0.004930734634399414, "step": 716} +{"info/global_step": 717, "train_info/time_within_train_step": 13.159650087356567, "step": 717} +{"train_info/time_between_train_steps": 0.005349636077880859, "step": 717} +{"info/global_step": 718, "train_info/time_within_train_step": 13.235421419143677, "step": 718} +{"train_info/time_between_train_steps": 0.0045337677001953125, "step": 718} +{"info/global_step": 719, "train_info/time_within_train_step": 13.15585708618164, "step": 719} +{"train_info/time_between_train_steps": 0.004725217819213867, "step": 719} +{"info/global_step": 720, "train_info/time_within_train_step": 13.153103828430176, "step": 720} +{"train_info/time_between_train_steps": 0.005153656005859375, "step": 720} +{"info/global_step": 721, "train_info/time_within_train_step": 13.157384634017944, "step": 721} +{"train_info/time_between_train_steps": 0.0055255889892578125, "step": 721} +{"info/global_step": 722, "train_info/time_within_train_step": 13.169909477233887, "step": 722} +{"train_info/time_between_train_steps": 0.005650043487548828, "step": 722} +{"info/global_step": 723, "train_info/time_within_train_step": 13.164233922958374, "step": 723} +{"train_info/time_between_train_steps": 0.005562782287597656, "step": 723} +{"info/global_step": 724, "train_info/time_within_train_step": 13.14995288848877, "step": 724} +{"train_info/time_between_train_steps": 0.004700660705566406, "step": 724} +{"info/global_step": 725, "train_info/time_within_train_step": 13.15811562538147, "step": 725} +{"train_info/time_between_train_steps": 0.005474090576171875, "step": 725} +{"info/global_step": 726, "train_info/time_within_train_step": 13.18116044998169, "step": 726} +{"train_info/time_between_train_steps": 0.005867958068847656, "step": 726} +{"info/global_step": 727, "train_info/time_within_train_step": 13.18698787689209, "step": 727} +{"train_info/time_between_train_steps": 0.005792140960693359, "step": 727} +{"info/global_step": 728, "train_info/time_within_train_step": 13.278469562530518, "step": 728} +{"train_info/time_between_train_steps": 0.00628352165222168, "step": 728} +{"train_info/time_between_train_steps": 10.703658103942871, "step": 728} +{"info/global_step": 729, "train_info/time_within_train_step": 13.135826110839844, "step": 729} +{"train_info/time_between_train_steps": 0.005776882171630859, "step": 729} +{"info/global_step": 730, "train_info/time_within_train_step": 13.245308637619019, "step": 730} +{"train_info/time_between_train_steps": 0.005205631256103516, "step": 730} +{"info/global_step": 731, "train_info/time_within_train_step": 13.148454666137695, "step": 731} +{"train_info/time_between_train_steps": 0.0052683353424072266, "step": 731} +{"info/global_step": 732, "train_info/time_within_train_step": 13.24231505393982, "step": 732} +{"train_info/time_between_train_steps": 0.005548715591430664, "step": 732} +{"info/global_step": 733, "train_info/time_within_train_step": 13.237354516983032, "step": 733} +{"train_info/time_between_train_steps": 0.00563502311706543, "step": 733} +{"info/global_step": 734, "train_info/time_within_train_step": 13.208290338516235, "step": 734} +{"train_info/time_between_train_steps": 0.004886150360107422, "step": 734} +{"info/global_step": 735, "train_info/time_within_train_step": 13.187101125717163, "step": 735} +{"train_info/time_between_train_steps": 0.005434274673461914, "step": 735} +{"info/global_step": 736, "train_info/time_within_train_step": 13.15675163269043, "step": 736} +{"train_info/time_between_train_steps": 0.004746675491333008, "step": 736} +{"info/global_step": 737, "train_info/time_within_train_step": 13.142183065414429, "step": 737} +{"train_info/time_between_train_steps": 0.00545048713684082, "step": 737} +{"info/global_step": 738, "train_info/time_within_train_step": 13.150141477584839, "step": 738} +{"train_info/time_between_train_steps": 0.004882335662841797, "step": 738} +{"info/global_step": 739, "train_info/time_within_train_step": 13.13864254951477, "step": 739} +{"train_info/time_between_train_steps": 0.0050525665283203125, "step": 739} +{"info/global_step": 740, "train_info/time_within_train_step": 13.173353433609009, "step": 740} +{"train_info/time_between_train_steps": 0.005422830581665039, "step": 740} +{"info/global_step": 741, "train_info/time_within_train_step": 13.141571521759033, "step": 741} +{"train_info/time_between_train_steps": 0.005150318145751953, "step": 741} +{"info/global_step": 742, "train_info/time_within_train_step": 13.134467840194702, "step": 742} +{"train_info/time_between_train_steps": 0.004860877990722656, "step": 742} +{"info/global_step": 743, "train_info/time_within_train_step": 13.13451361656189, "step": 743} +{"train_info/time_between_train_steps": 0.005342006683349609, "step": 743} +{"info/global_step": 744, "train_info/time_within_train_step": 13.141876459121704, "step": 744} +{"train_info/time_between_train_steps": 0.005240917205810547, "step": 744} +{"info/global_step": 745, "train_info/time_within_train_step": 13.152143955230713, "step": 745} +{"train_info/time_between_train_steps": 0.00512242317199707, "step": 745} +{"info/global_step": 746, "train_info/time_within_train_step": 13.14357590675354, "step": 746} +{"train_info/time_between_train_steps": 0.00545811653137207, "step": 746} +{"info/global_step": 747, "train_info/time_within_train_step": 13.15627932548523, "step": 747} +{"train_info/time_between_train_steps": 0.005320310592651367, "step": 747} +{"info/global_step": 748, "train_info/time_within_train_step": 13.172746658325195, "step": 748} +{"train_info/time_between_train_steps": 0.005502462387084961, "step": 748} +{"info/global_step": 749, "train_info/time_within_train_step": 13.23543095588684, "step": 749} +{"train_info/time_between_train_steps": 0.005608558654785156, "step": 749} +{"info/global_step": 750, "train_info/time_within_train_step": 13.154231786727905, "step": 750} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737053538, "_runtime": 10838}, "step": 750} +{"logs": {"train/loss": 5.289, "train/learning_rate": 0.00025, "train/epoch": 28.02, "_timestamp": 1737053538, "_runtime": 10838}, "step": 750} +{"train_info/time_between_train_steps": 0.033461570739746094, "step": 750} +{"info/global_step": 751, "train_info/time_within_train_step": 13.14649748802185, "step": 751} +{"train_info/time_between_train_steps": 0.0051844120025634766, "step": 751} +{"info/global_step": 752, "train_info/time_within_train_step": 13.155487060546875, "step": 752} +{"train_info/time_between_train_steps": 0.005605220794677734, "step": 752} +{"info/global_step": 753, "train_info/time_within_train_step": 13.161301136016846, "step": 753} +{"train_info/time_between_train_steps": 0.006047248840332031, "step": 753} +{"info/global_step": 754, "train_info/time_within_train_step": 13.178990602493286, "step": 754} +{"train_info/time_between_train_steps": 0.006569862365722656, "step": 754} +{"train_info/time_between_train_steps": 10.409180164337158, "step": 754} +{"info/global_step": 755, "train_info/time_within_train_step": 13.130927801132202, "step": 755} +{"train_info/time_between_train_steps": 0.005252838134765625, "step": 755} +{"info/global_step": 756, "train_info/time_within_train_step": 13.229758977890015, "step": 756} +{"train_info/time_between_train_steps": 0.0053558349609375, "step": 756} +{"info/global_step": 757, "train_info/time_within_train_step": 13.159567594528198, "step": 757} +{"train_info/time_between_train_steps": 0.005298137664794922, "step": 757} +{"info/global_step": 758, "train_info/time_within_train_step": 13.232310771942139, "step": 758} +{"train_info/time_between_train_steps": 0.005105018615722656, "step": 758} +{"info/global_step": 759, "train_info/time_within_train_step": 13.139047622680664, "step": 759} +{"train_info/time_between_train_steps": 0.005248308181762695, "step": 759} +{"info/global_step": 760, "train_info/time_within_train_step": 13.243223667144775, "step": 760} +{"train_info/time_between_train_steps": 0.0052263736724853516, "step": 760} +{"info/global_step": 761, "train_info/time_within_train_step": 13.151164531707764, "step": 761} +{"train_info/time_between_train_steps": 0.005820274353027344, "step": 761} +{"info/global_step": 762, "train_info/time_within_train_step": 13.1613028049469, "step": 762} +{"train_info/time_between_train_steps": 0.005488157272338867, "step": 762} +{"info/global_step": 763, "train_info/time_within_train_step": 13.149082899093628, "step": 763} +{"train_info/time_between_train_steps": 0.0054187774658203125, "step": 763} +{"info/global_step": 764, "train_info/time_within_train_step": 13.2299485206604, "step": 764} +{"train_info/time_between_train_steps": 0.005383014678955078, "step": 764} +{"info/global_step": 765, "train_info/time_within_train_step": 13.147213697433472, "step": 765} +{"train_info/time_between_train_steps": 0.005540370941162109, "step": 765} +{"info/global_step": 766, "train_info/time_within_train_step": 13.15593147277832, "step": 766} +{"train_info/time_between_train_steps": 0.00566411018371582, "step": 766} +{"info/global_step": 767, "train_info/time_within_train_step": 13.168869733810425, "step": 767} +{"train_info/time_between_train_steps": 0.005778789520263672, "step": 767} +{"info/global_step": 768, "train_info/time_within_train_step": 13.156437635421753, "step": 768} +{"train_info/time_between_train_steps": 0.005460500717163086, "step": 768} +{"info/global_step": 769, "train_info/time_within_train_step": 13.158560276031494, "step": 769} +{"train_info/time_between_train_steps": 0.005352973937988281, "step": 769} +{"info/global_step": 770, "train_info/time_within_train_step": 13.153831958770752, "step": 770} +{"train_info/time_between_train_steps": 0.005651712417602539, "step": 770} +{"info/global_step": 771, "train_info/time_within_train_step": 13.156651973724365, "step": 771} +{"train_info/time_between_train_steps": 0.00533747673034668, "step": 771} +{"info/global_step": 772, "train_info/time_within_train_step": 13.140797138214111, "step": 772} +{"train_info/time_between_train_steps": 0.0050890445709228516, "step": 772} +{"info/global_step": 773, "train_info/time_within_train_step": 13.140096426010132, "step": 773} +{"train_info/time_between_train_steps": 0.005168914794921875, "step": 773} +{"info/global_step": 774, "train_info/time_within_train_step": 13.137721061706543, "step": 774} +{"train_info/time_between_train_steps": 0.004731893539428711, "step": 774} +{"info/global_step": 775, "train_info/time_within_train_step": 13.161619424819946, "step": 775} +{"train_info/time_between_train_steps": 0.00620722770690918, "step": 775} +{"info/global_step": 776, "train_info/time_within_train_step": 13.15425992012024, "step": 776} +{"train_info/time_between_train_steps": 0.005676984786987305, "step": 776} +{"info/global_step": 777, "train_info/time_within_train_step": 13.238095760345459, "step": 777} +{"train_info/time_between_train_steps": 0.0051288604736328125, "step": 777} +{"info/global_step": 778, "train_info/time_within_train_step": 13.146440982818604, "step": 778} +{"train_info/time_between_train_steps": 0.005594015121459961, "step": 778} +{"info/global_step": 779, "train_info/time_within_train_step": 13.248886585235596, "step": 779} +{"train_info/time_between_train_steps": 0.0051844120025634766, "step": 779} +{"info/global_step": 780, "train_info/time_within_train_step": 13.188185691833496, "step": 780} +{"train_info/time_between_train_steps": 0.006198406219482422, "step": 780} +{"train_info/time_between_train_steps": 10.515503406524658, "step": 780} +{"info/global_step": 781, "train_info/time_within_train_step": 13.141663074493408, "step": 781} +{"train_info/time_between_train_steps": 0.005341053009033203, "step": 781} +{"info/global_step": 782, "train_info/time_within_train_step": 13.221802949905396, "step": 782} +{"train_info/time_between_train_steps": 0.0056459903717041016, "step": 782} +{"info/global_step": 783, "train_info/time_within_train_step": 13.116077184677124, "step": 783} +{"train_info/time_between_train_steps": 0.0050508975982666016, "step": 783} +{"info/global_step": 784, "train_info/time_within_train_step": 13.294913291931152, "step": 784} +{"train_info/time_between_train_steps": 0.005640745162963867, "step": 784} +{"info/global_step": 785, "train_info/time_within_train_step": 13.147292613983154, "step": 785} +{"train_info/time_between_train_steps": 0.004869222640991211, "step": 785} +{"info/global_step": 786, "train_info/time_within_train_step": 13.198103904724121, "step": 786} +{"train_info/time_between_train_steps": 0.00522613525390625, "step": 786} +{"info/global_step": 787, "train_info/time_within_train_step": 13.151930093765259, "step": 787} +{"train_info/time_between_train_steps": 0.00576472282409668, "step": 787} +{"info/global_step": 788, "train_info/time_within_train_step": 13.16570496559143, "step": 788} +{"train_info/time_between_train_steps": 0.00569605827331543, "step": 788} +{"info/global_step": 789, "train_info/time_within_train_step": 13.142187118530273, "step": 789} +{"train_info/time_between_train_steps": 0.004944324493408203, "step": 789} +{"info/global_step": 790, "train_info/time_within_train_step": 13.15329122543335, "step": 790} +{"train_info/time_between_train_steps": 0.004862546920776367, "step": 790} +{"info/global_step": 791, "train_info/time_within_train_step": 13.144909381866455, "step": 791} +{"train_info/time_between_train_steps": 0.005305290222167969, "step": 791} +{"info/global_step": 792, "train_info/time_within_train_step": 13.166491508483887, "step": 792} +{"train_info/time_between_train_steps": 0.005378246307373047, "step": 792} +{"info/global_step": 793, "train_info/time_within_train_step": 13.195808410644531, "step": 793} +{"train_info/time_between_train_steps": 0.005394935607910156, "step": 793} +{"info/global_step": 794, "train_info/time_within_train_step": 13.254528522491455, "step": 794} +{"train_info/time_between_train_steps": 0.005902290344238281, "step": 794} +{"info/global_step": 795, "train_info/time_within_train_step": 13.163563251495361, "step": 795} +{"train_info/time_between_train_steps": 0.005456209182739258, "step": 795} +{"info/global_step": 796, "train_info/time_within_train_step": 13.148713111877441, "step": 796} +{"train_info/time_between_train_steps": 0.00442814826965332, "step": 796} +{"info/global_step": 797, "train_info/time_within_train_step": 13.15234637260437, "step": 797} +{"train_info/time_between_train_steps": 0.005461931228637695, "step": 797} +{"info/global_step": 798, "train_info/time_within_train_step": 13.149566173553467, "step": 798} +{"train_info/time_between_train_steps": 0.0056304931640625, "step": 798} +{"info/global_step": 799, "train_info/time_within_train_step": 13.262049913406372, "step": 799} +{"train_info/time_between_train_steps": 0.0051653385162353516, "step": 799} +{"info/global_step": 800, "train_info/time_within_train_step": 13.166760921478271, "step": 800} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737054220, "_runtime": 11520}, "step": 800} +{"logs": {"train/loss": 5.1692, "train/learning_rate": 0.00022222222222222218, "train/epoch": 30.02, "_timestamp": 1737054220, "_runtime": 11520}, "step": 800} +{"train_info/time_between_train_steps": 17.948591232299805, "step": 800} +{"info/global_step": 801, "train_info/time_within_train_step": 13.111987113952637, "step": 801} +{"train_info/time_between_train_steps": 0.0056192874908447266, "step": 801} +{"info/global_step": 802, "train_info/time_within_train_step": 13.126225471496582, "step": 802} +{"train_info/time_between_train_steps": 0.0055463314056396484, "step": 802} +{"info/global_step": 803, "train_info/time_within_train_step": 13.13168478012085, "step": 803} +{"train_info/time_between_train_steps": 0.005266427993774414, "step": 803} +{"info/global_step": 804, "train_info/time_within_train_step": 13.138727903366089, "step": 804} +{"train_info/time_between_train_steps": 0.00580906867980957, "step": 804} +{"info/global_step": 805, "train_info/time_within_train_step": 13.419206142425537, "step": 805} +{"train_info/time_between_train_steps": 0.00556182861328125, "step": 805} +{"info/global_step": 806, "train_info/time_within_train_step": 13.18229341506958, "step": 806} +{"train_info/time_between_train_steps": 0.00669407844543457, "step": 806} +{"train_info/time_between_train_steps": 10.644389629364014, "step": 806} +{"info/global_step": 807, "train_info/time_within_train_step": 13.130859851837158, "step": 807} +{"train_info/time_between_train_steps": 0.004991292953491211, "step": 807} +{"info/global_step": 808, "train_info/time_within_train_step": 13.258140802383423, "step": 808} +{"train_info/time_between_train_steps": 0.004680156707763672, "step": 808} +{"info/global_step": 809, "train_info/time_within_train_step": 13.425403833389282, "step": 809} +{"train_info/time_between_train_steps": 0.0052564144134521484, "step": 809} +{"info/global_step": 810, "train_info/time_within_train_step": 13.23122787475586, "step": 810} +{"train_info/time_between_train_steps": 0.004892110824584961, "step": 810} +{"info/global_step": 811, "train_info/time_within_train_step": 13.153984546661377, "step": 811} +{"train_info/time_between_train_steps": 0.004558563232421875, "step": 811} +{"info/global_step": 812, "train_info/time_within_train_step": 13.212257623672485, "step": 812} +{"train_info/time_between_train_steps": 0.00503087043762207, "step": 812} +{"info/global_step": 813, "train_info/time_within_train_step": 13.177459001541138, "step": 813} +{"train_info/time_between_train_steps": 0.005810737609863281, "step": 813} +{"info/global_step": 814, "train_info/time_within_train_step": 13.189414739608765, "step": 814} +{"train_info/time_between_train_steps": 0.0052471160888671875, "step": 814} +{"info/global_step": 815, "train_info/time_within_train_step": 13.184537887573242, "step": 815} +{"train_info/time_between_train_steps": 0.005487680435180664, "step": 815} +{"info/global_step": 816, "train_info/time_within_train_step": 13.185201644897461, "step": 816} +{"train_info/time_between_train_steps": 0.005174160003662109, "step": 816} +{"info/global_step": 817, "train_info/time_within_train_step": 13.181937456130981, "step": 817} +{"train_info/time_between_train_steps": 0.0050182342529296875, "step": 817} +{"info/global_step": 818, "train_info/time_within_train_step": 13.18984603881836, "step": 818} +{"train_info/time_between_train_steps": 0.005338907241821289, "step": 818} +{"info/global_step": 819, "train_info/time_within_train_step": 13.153783321380615, "step": 819} +{"train_info/time_between_train_steps": 0.005373954772949219, "step": 819} +{"info/global_step": 820, "train_info/time_within_train_step": 13.160249948501587, "step": 820} +{"train_info/time_between_train_steps": 0.005499124526977539, "step": 820} +{"info/global_step": 821, "train_info/time_within_train_step": 13.184773921966553, "step": 821} +{"train_info/time_between_train_steps": 0.005430936813354492, "step": 821} +{"info/global_step": 822, "train_info/time_within_train_step": 13.185620546340942, "step": 822} +{"train_info/time_between_train_steps": 0.005486011505126953, "step": 822} +{"info/global_step": 823, "train_info/time_within_train_step": 13.16890811920166, "step": 823} +{"train_info/time_between_train_steps": 0.005223751068115234, "step": 823} +{"info/global_step": 824, "train_info/time_within_train_step": 13.182410955429077, "step": 824} +{"train_info/time_between_train_steps": 0.005312204360961914, "step": 824} +{"info/global_step": 825, "train_info/time_within_train_step": 13.244897603988647, "step": 825} +{"train_info/time_between_train_steps": 0.005601167678833008, "step": 825} +{"info/global_step": 826, "train_info/time_within_train_step": 13.170170307159424, "step": 826} +{"train_info/time_between_train_steps": 0.005475521087646484, "step": 826} +{"info/global_step": 827, "train_info/time_within_train_step": 13.181177854537964, "step": 827} +{"train_info/time_between_train_steps": 0.005362987518310547, "step": 827} +{"info/global_step": 828, "train_info/time_within_train_step": 13.172871589660645, "step": 828} +{"train_info/time_between_train_steps": 0.005705356597900391, "step": 828} +{"info/global_step": 829, "train_info/time_within_train_step": 13.180216312408447, "step": 829} +{"train_info/time_between_train_steps": 0.006066083908081055, "step": 829} +{"info/global_step": 830, "train_info/time_within_train_step": 13.189790964126587, "step": 830} +{"train_info/time_between_train_steps": 0.005629539489746094, "step": 830} +{"info/global_step": 831, "train_info/time_within_train_step": 13.227689027786255, "step": 831} +{"train_info/time_between_train_steps": 0.006012439727783203, "step": 831} +{"info/global_step": 832, "train_info/time_within_train_step": 13.207450151443481, "step": 832} +{"train_info/time_between_train_steps": 0.006013631820678711, "step": 832} +{"train_info/time_between_train_steps": 10.39729619026184, "step": 832} +{"info/global_step": 833, "train_info/time_within_train_step": 13.150279998779297, "step": 833} +{"train_info/time_between_train_steps": 0.005884647369384766, "step": 833} +{"info/global_step": 834, "train_info/time_within_train_step": 13.325342178344727, "step": 834} +{"train_info/time_between_train_steps": 0.005831003189086914, "step": 834} +{"info/global_step": 835, "train_info/time_within_train_step": 13.175477981567383, "step": 835} +{"train_info/time_between_train_steps": 0.005344390869140625, "step": 835} +{"info/global_step": 836, "train_info/time_within_train_step": 13.257867336273193, "step": 836} +{"train_info/time_between_train_steps": 0.005406618118286133, "step": 836} +{"info/global_step": 837, "train_info/time_within_train_step": 13.175119161605835, "step": 837} +{"train_info/time_between_train_steps": 0.0050585269927978516, "step": 837} +{"info/global_step": 838, "train_info/time_within_train_step": 13.247334957122803, "step": 838} +{"train_info/time_between_train_steps": 0.005785942077636719, "step": 838} +{"info/global_step": 839, "train_info/time_within_train_step": 13.171172618865967, "step": 839} +{"train_info/time_between_train_steps": 0.005127429962158203, "step": 839} +{"info/global_step": 840, "train_info/time_within_train_step": 13.295686483383179, "step": 840} +{"train_info/time_between_train_steps": 0.005268573760986328, "step": 840} +{"info/global_step": 841, "train_info/time_within_train_step": 13.173797369003296, "step": 841} +{"train_info/time_between_train_steps": 0.004981279373168945, "step": 841} +{"info/global_step": 842, "train_info/time_within_train_step": 13.164618492126465, "step": 842} +{"train_info/time_between_train_steps": 0.0051310062408447266, "step": 842} +{"info/global_step": 843, "train_info/time_within_train_step": 13.168022155761719, "step": 843} +{"train_info/time_between_train_steps": 0.005357980728149414, "step": 843} +{"info/global_step": 844, "train_info/time_within_train_step": 13.185361862182617, "step": 844} +{"train_info/time_between_train_steps": 0.005446434020996094, "step": 844} +{"info/global_step": 845, "train_info/time_within_train_step": 13.191130638122559, "step": 845} +{"train_info/time_between_train_steps": 0.00503849983215332, "step": 845} +{"info/global_step": 846, "train_info/time_within_train_step": 13.172265768051147, "step": 846} +{"train_info/time_between_train_steps": 0.00539088249206543, "step": 846} +{"info/global_step": 847, "train_info/time_within_train_step": 13.174234867095947, "step": 847} +{"train_info/time_between_train_steps": 0.005102872848510742, "step": 847} +{"info/global_step": 848, "train_info/time_within_train_step": 13.158806562423706, "step": 848} +{"train_info/time_between_train_steps": 0.005378007888793945, "step": 848} +{"info/global_step": 849, "train_info/time_within_train_step": 13.178940057754517, "step": 849} +{"train_info/time_between_train_steps": 0.005471467971801758, "step": 849} +{"info/global_step": 850, "train_info/time_within_train_step": 13.164758205413818, "step": 850} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737054922, "_runtime": 12222}, "step": 850} +{"logs": {"train/loss": 5.0667, "train/learning_rate": 0.00019444444444444443, "train/epoch": 32.02, "_timestamp": 1737054922, "_runtime": 12222}, "step": 850} +{"train_info/time_between_train_steps": 0.033814430236816406, "step": 850} +{"info/global_step": 851, "train_info/time_within_train_step": 13.170103311538696, "step": 851} +{"train_info/time_between_train_steps": 0.00492405891418457, "step": 851} +{"info/global_step": 852, "train_info/time_within_train_step": 13.172248125076294, "step": 852} +{"train_info/time_between_train_steps": 0.006645917892456055, "step": 852} +{"info/global_step": 853, "train_info/time_within_train_step": 13.173507690429688, "step": 853} +{"train_info/time_between_train_steps": 0.005346775054931641, "step": 853} +{"info/global_step": 854, "train_info/time_within_train_step": 13.144110918045044, "step": 854} +{"train_info/time_between_train_steps": 0.005007505416870117, "step": 854} +{"info/global_step": 855, "train_info/time_within_train_step": 13.237018823623657, "step": 855} +{"train_info/time_between_train_steps": 0.005511760711669922, "step": 855} +{"info/global_step": 856, "train_info/time_within_train_step": 13.148158073425293, "step": 856} +{"train_info/time_between_train_steps": 0.0058100223541259766, "step": 856} +{"info/global_step": 857, "train_info/time_within_train_step": 13.190478324890137, "step": 857} +{"train_info/time_between_train_steps": 0.0058917999267578125, "step": 857} +{"info/global_step": 858, "train_info/time_within_train_step": 13.186256170272827, "step": 858} +{"train_info/time_between_train_steps": 0.0063283443450927734, "step": 858} +{"train_info/time_between_train_steps": 10.550017833709717, "step": 858} +{"info/global_step": 859, "train_info/time_within_train_step": 13.130511999130249, "step": 859} +{"train_info/time_between_train_steps": 0.005600929260253906, "step": 859} +{"info/global_step": 860, "train_info/time_within_train_step": 13.282915830612183, "step": 860} +{"train_info/time_between_train_steps": 0.005181074142456055, "step": 860} +{"info/global_step": 861, "train_info/time_within_train_step": 13.18196177482605, "step": 861} +{"train_info/time_between_train_steps": 0.0048236846923828125, "step": 861} +{"info/global_step": 862, "train_info/time_within_train_step": 13.251065731048584, "step": 862} +{"train_info/time_between_train_steps": 0.004850864410400391, "step": 862} +{"info/global_step": 863, "train_info/time_within_train_step": 13.149627923965454, "step": 863} +{"train_info/time_between_train_steps": 0.005384206771850586, "step": 863} +{"info/global_step": 864, "train_info/time_within_train_step": 13.249711513519287, "step": 864} +{"train_info/time_between_train_steps": 0.0054934024810791016, "step": 864} +{"info/global_step": 865, "train_info/time_within_train_step": 13.175431728363037, "step": 865} +{"train_info/time_between_train_steps": 0.006032466888427734, "step": 865} +{"info/global_step": 866, "train_info/time_within_train_step": 13.184547185897827, "step": 866} +{"train_info/time_between_train_steps": 0.005315303802490234, "step": 866} +{"info/global_step": 867, "train_info/time_within_train_step": 13.180686712265015, "step": 867} +{"train_info/time_between_train_steps": 0.0050427913665771484, "step": 867} +{"info/global_step": 868, "train_info/time_within_train_step": 13.163492918014526, "step": 868} +{"train_info/time_between_train_steps": 0.0051212310791015625, "step": 868} +{"info/global_step": 869, "train_info/time_within_train_step": 13.177081108093262, "step": 869} +{"train_info/time_between_train_steps": 0.005200624465942383, "step": 869} +{"info/global_step": 870, "train_info/time_within_train_step": 13.25130033493042, "step": 870} +{"train_info/time_between_train_steps": 0.005403280258178711, "step": 870} +{"info/global_step": 871, "train_info/time_within_train_step": 13.17026400566101, "step": 871} +{"train_info/time_between_train_steps": 0.0057752132415771484, "step": 871} +{"info/global_step": 872, "train_info/time_within_train_step": 13.159773588180542, "step": 872} +{"train_info/time_between_train_steps": 0.00505518913269043, "step": 872} +{"info/global_step": 873, "train_info/time_within_train_step": 13.166005849838257, "step": 873} +{"train_info/time_between_train_steps": 0.005190610885620117, "step": 873} +{"info/global_step": 874, "train_info/time_within_train_step": 13.196224451065063, "step": 874} +{"train_info/time_between_train_steps": 0.005457401275634766, "step": 874} +{"info/global_step": 875, "train_info/time_within_train_step": 13.18263030052185, "step": 875} +{"train_info/time_between_train_steps": 0.00537419319152832, "step": 875} +{"info/global_step": 876, "train_info/time_within_train_step": 13.173092603683472, "step": 876} +{"train_info/time_between_train_steps": 0.005518198013305664, "step": 876} +{"info/global_step": 877, "train_info/time_within_train_step": 13.191819190979004, "step": 877} +{"train_info/time_between_train_steps": 0.005678653717041016, "step": 877} +{"info/global_step": 878, "train_info/time_within_train_step": 13.1828031539917, "step": 878} +{"train_info/time_between_train_steps": 0.005792140960693359, "step": 878} +{"info/global_step": 879, "train_info/time_within_train_step": 13.182075500488281, "step": 879} +{"train_info/time_between_train_steps": 0.005280256271362305, "step": 879} +{"info/global_step": 880, "train_info/time_within_train_step": 13.193438529968262, "step": 880} +{"train_info/time_between_train_steps": 0.0057506561279296875, "step": 880} +{"info/global_step": 881, "train_info/time_within_train_step": 13.161237716674805, "step": 881} +{"train_info/time_between_train_steps": 0.0048983097076416016, "step": 881} +{"info/global_step": 882, "train_info/time_within_train_step": 13.186245203018188, "step": 882} +{"train_info/time_between_train_steps": 0.005420684814453125, "step": 882} +{"info/global_step": 883, "train_info/time_within_train_step": 13.209301948547363, "step": 883} +{"train_info/time_between_train_steps": 0.005978584289550781, "step": 883} +{"info/global_step": 884, "train_info/time_within_train_step": 13.23449158668518, "step": 884} +{"train_info/time_between_train_steps": 0.00666046142578125, "step": 884} +{"train_info/time_between_train_steps": 10.648364305496216, "step": 884} +{"info/global_step": 885, "train_info/time_within_train_step": 13.225030660629272, "step": 885} +{"train_info/time_between_train_steps": 0.005584001541137695, "step": 885} +{"info/global_step": 886, "train_info/time_within_train_step": 13.268396377563477, "step": 886} +{"train_info/time_between_train_steps": 0.005686759948730469, "step": 886} +{"info/global_step": 887, "train_info/time_within_train_step": 13.212366104125977, "step": 887} +{"train_info/time_between_train_steps": 0.00569915771484375, "step": 887} +{"info/global_step": 888, "train_info/time_within_train_step": 13.300197124481201, "step": 888} +{"train_info/time_between_train_steps": 0.005662679672241211, "step": 888} +{"info/global_step": 889, "train_info/time_within_train_step": 13.179272890090942, "step": 889} +{"train_info/time_between_train_steps": 0.0052411556243896484, "step": 889} +{"info/global_step": 890, "train_info/time_within_train_step": 13.247196674346924, "step": 890} +{"train_info/time_between_train_steps": 0.005403041839599609, "step": 890} +{"info/global_step": 891, "train_info/time_within_train_step": 13.180927276611328, "step": 891} +{"train_info/time_between_train_steps": 0.0055043697357177734, "step": 891} +{"info/global_step": 892, "train_info/time_within_train_step": 13.18980860710144, "step": 892} +{"train_info/time_between_train_steps": 0.005313873291015625, "step": 892} +{"info/global_step": 893, "train_info/time_within_train_step": 13.18825912475586, "step": 893} +{"train_info/time_between_train_steps": 0.005263566970825195, "step": 893} +{"info/global_step": 894, "train_info/time_within_train_step": 13.156934022903442, "step": 894} +{"train_info/time_between_train_steps": 0.0050776004791259766, "step": 894} +{"info/global_step": 895, "train_info/time_within_train_step": 13.177976608276367, "step": 895} +{"train_info/time_between_train_steps": 0.005388498306274414, "step": 895} +{"info/global_step": 896, "train_info/time_within_train_step": 13.170011281967163, "step": 896} +{"train_info/time_between_train_steps": 0.005040168762207031, "step": 896} +{"info/global_step": 897, "train_info/time_within_train_step": 13.179864168167114, "step": 897} +{"train_info/time_between_train_steps": 0.005299806594848633, "step": 897} +{"info/global_step": 898, "train_info/time_within_train_step": 13.186468601226807, "step": 898} +{"train_info/time_between_train_steps": 0.0052490234375, "step": 898} +{"info/global_step": 899, "train_info/time_within_train_step": 13.154967308044434, "step": 899} +{"train_info/time_between_train_steps": 0.005398750305175781, "step": 899} +{"info/global_step": 900, "train_info/time_within_train_step": 13.183003187179565, "step": 900} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737055605, "_runtime": 12905}, "step": 900} +{"logs": {"train/loss": 4.974, "train/learning_rate": 0.00016666666666666666, "train/epoch": 34.01, "_timestamp": 1737055605, "_runtime": 12905}, "step": 900} +{"train_info/time_between_train_steps": 54.40784931182861, "step": 900} +{"info/global_step": 901, "train_info/time_within_train_step": 13.163692712783813, "step": 901} +{"train_info/time_between_train_steps": 0.0052127838134765625, "step": 901} +{"info/global_step": 902, "train_info/time_within_train_step": 14.208363771438599, "step": 902} +{"train_info/time_between_train_steps": 0.005326986312866211, "step": 902} +{"info/global_step": 903, "train_info/time_within_train_step": 13.189409971237183, "step": 903} +{"train_info/time_between_train_steps": 0.0054013729095458984, "step": 903} +{"info/global_step": 904, "train_info/time_within_train_step": 13.121700525283813, "step": 904} +{"train_info/time_between_train_steps": 0.004761934280395508, "step": 904} +{"info/global_step": 905, "train_info/time_within_train_step": 13.125966548919678, "step": 905} +{"train_info/time_between_train_steps": 0.005281925201416016, "step": 905} +{"info/global_step": 906, "train_info/time_within_train_step": 13.58372712135315, "step": 906} +{"train_info/time_between_train_steps": 0.0049741268157958984, "step": 906} +{"info/global_step": 907, "train_info/time_within_train_step": 13.298492431640625, "step": 907} +{"train_info/time_between_train_steps": 0.0050585269927978516, "step": 907} +{"info/global_step": 908, "train_info/time_within_train_step": 13.178668737411499, "step": 908} +{"train_info/time_between_train_steps": 0.005131244659423828, "step": 908} +{"info/global_step": 909, "train_info/time_within_train_step": 13.173994779586792, "step": 909} +{"train_info/time_between_train_steps": 0.005850791931152344, "step": 909} +{"info/global_step": 910, "train_info/time_within_train_step": 13.18959379196167, "step": 910} +{"train_info/time_between_train_steps": 0.006916999816894531, "step": 910} +{"train_info/time_between_train_steps": 10.388779640197754, "step": 910} +{"info/global_step": 911, "train_info/time_within_train_step": 13.13180685043335, "step": 911} +{"train_info/time_between_train_steps": 0.0053424835205078125, "step": 911} +{"info/global_step": 912, "train_info/time_within_train_step": 13.235596895217896, "step": 912} +{"train_info/time_between_train_steps": 0.0052640438079833984, "step": 912} +{"info/global_step": 913, "train_info/time_within_train_step": 13.15436601638794, "step": 913} +{"train_info/time_between_train_steps": 0.005397319793701172, "step": 913} +{"info/global_step": 914, "train_info/time_within_train_step": 13.264317989349365, "step": 914} +{"train_info/time_between_train_steps": 0.005204677581787109, "step": 914} +{"info/global_step": 915, "train_info/time_within_train_step": 13.167200565338135, "step": 915} +{"train_info/time_between_train_steps": 0.00512385368347168, "step": 915} +{"info/global_step": 916, "train_info/time_within_train_step": 13.358310461044312, "step": 916} +{"train_info/time_between_train_steps": 0.0051555633544921875, "step": 916} +{"info/global_step": 917, "train_info/time_within_train_step": 13.162481307983398, "step": 917} +{"train_info/time_between_train_steps": 0.005919218063354492, "step": 917} +{"info/global_step": 918, "train_info/time_within_train_step": 13.172241687774658, "step": 918} +{"train_info/time_between_train_steps": 0.004864692687988281, "step": 918} +{"info/global_step": 919, "train_info/time_within_train_step": 13.172750234603882, "step": 919} +{"train_info/time_between_train_steps": 0.005512237548828125, "step": 919} +{"info/global_step": 920, "train_info/time_within_train_step": 13.180976152420044, "step": 920} +{"train_info/time_between_train_steps": 0.005492448806762695, "step": 920} +{"info/global_step": 921, "train_info/time_within_train_step": 13.191106796264648, "step": 921} +{"train_info/time_between_train_steps": 0.004980564117431641, "step": 921} +{"info/global_step": 922, "train_info/time_within_train_step": 13.164928674697876, "step": 922} +{"train_info/time_between_train_steps": 0.0050432682037353516, "step": 922} +{"info/global_step": 923, "train_info/time_within_train_step": 13.150308609008789, "step": 923} +{"train_info/time_between_train_steps": 0.005554676055908203, "step": 923} +{"info/global_step": 924, "train_info/time_within_train_step": 13.162983894348145, "step": 924} +{"train_info/time_between_train_steps": 0.005485057830810547, "step": 924} +{"info/global_step": 925, "train_info/time_within_train_step": 13.162710428237915, "step": 925} +{"train_info/time_between_train_steps": 0.005457162857055664, "step": 925} +{"info/global_step": 926, "train_info/time_within_train_step": 13.175662517547607, "step": 926} +{"train_info/time_between_train_steps": 0.005179643630981445, "step": 926} +{"info/global_step": 927, "train_info/time_within_train_step": 13.242236375808716, "step": 927} +{"train_info/time_between_train_steps": 0.00558781623840332, "step": 927} +{"info/global_step": 928, "train_info/time_within_train_step": 13.225018739700317, "step": 928} +{"train_info/time_between_train_steps": 0.0047571659088134766, "step": 928} +{"info/global_step": 929, "train_info/time_within_train_step": 13.166862487792969, "step": 929} +{"train_info/time_between_train_steps": 0.005927324295043945, "step": 929} +{"info/global_step": 930, "train_info/time_within_train_step": 13.1643545627594, "step": 930} +{"train_info/time_between_train_steps": 0.005224704742431641, "step": 930} +{"info/global_step": 931, "train_info/time_within_train_step": 13.17909049987793, "step": 931} +{"train_info/time_between_train_steps": 0.005247831344604492, "step": 931} +{"info/global_step": 932, "train_info/time_within_train_step": 13.27111554145813, "step": 932} +{"train_info/time_between_train_steps": 0.0053539276123046875, "step": 932} +{"info/global_step": 933, "train_info/time_within_train_step": 13.200427293777466, "step": 933} +{"train_info/time_between_train_steps": 0.005013465881347656, "step": 933} +{"info/global_step": 934, "train_info/time_within_train_step": 13.19251298904419, "step": 934} +{"train_info/time_between_train_steps": 0.0055387020111083984, "step": 934} +{"info/global_step": 935, "train_info/time_within_train_step": 13.175217628479004, "step": 935} +{"train_info/time_between_train_steps": 0.005521535873413086, "step": 935} +{"info/global_step": 936, "train_info/time_within_train_step": 13.21323013305664, "step": 936} +{"train_info/time_between_train_steps": 0.006734132766723633, "step": 936} +{"train_info/time_between_train_steps": 10.543728828430176, "step": 936} +{"info/global_step": 937, "train_info/time_within_train_step": 13.175780773162842, "step": 937} +{"train_info/time_between_train_steps": 0.0055084228515625, "step": 937} +{"info/global_step": 938, "train_info/time_within_train_step": 13.268184900283813, "step": 938} +{"train_info/time_between_train_steps": 0.005852937698364258, "step": 938} +{"info/global_step": 939, "train_info/time_within_train_step": 13.173907995223999, "step": 939} +{"train_info/time_between_train_steps": 0.005380153656005859, "step": 939} +{"info/global_step": 940, "train_info/time_within_train_step": 13.26323676109314, "step": 940} +{"train_info/time_between_train_steps": 0.0053331851959228516, "step": 940} +{"info/global_step": 941, "train_info/time_within_train_step": 13.172625303268433, "step": 941} +{"train_info/time_between_train_steps": 0.0048639774322509766, "step": 941} +{"info/global_step": 942, "train_info/time_within_train_step": 13.23144268989563, "step": 942} +{"train_info/time_between_train_steps": 0.005544900894165039, "step": 942} +{"info/global_step": 943, "train_info/time_within_train_step": 13.183188915252686, "step": 943} +{"train_info/time_between_train_steps": 0.005684852600097656, "step": 943} +{"info/global_step": 944, "train_info/time_within_train_step": 13.175395965576172, "step": 944} +{"train_info/time_between_train_steps": 0.004923582077026367, "step": 944} +{"info/global_step": 945, "train_info/time_within_train_step": 13.184758424758911, "step": 945} +{"train_info/time_between_train_steps": 0.005269050598144531, "step": 945} +{"info/global_step": 946, "train_info/time_within_train_step": 13.153177499771118, "step": 946} +{"train_info/time_between_train_steps": 0.005377769470214844, "step": 946} +{"info/global_step": 947, "train_info/time_within_train_step": 13.256067514419556, "step": 947} +{"train_info/time_between_train_steps": 0.005098581314086914, "step": 947} +{"info/global_step": 948, "train_info/time_within_train_step": 13.170628070831299, "step": 948} +{"train_info/time_between_train_steps": 0.00539398193359375, "step": 948} +{"info/global_step": 949, "train_info/time_within_train_step": 13.176814317703247, "step": 949} +{"train_info/time_between_train_steps": 0.005452394485473633, "step": 949} +{"info/global_step": 950, "train_info/time_within_train_step": 13.18592619895935, "step": 950} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737056345, "_runtime": 13645}, "step": 950} +{"logs": {"train/loss": 4.8927, "train/learning_rate": 0.0001388888888888889, "train/epoch": 36.01, "_timestamp": 1737056345, "_runtime": 13645}, "step": 950} +{"train_info/time_between_train_steps": 0.0730125904083252, "step": 950} +{"info/global_step": 951, "train_info/time_within_train_step": 13.172723770141602, "step": 951} +{"train_info/time_between_train_steps": 0.005235910415649414, "step": 951} +{"info/global_step": 952, "train_info/time_within_train_step": 13.153952360153198, "step": 952} +{"train_info/time_between_train_steps": 0.005295276641845703, "step": 952} +{"info/global_step": 953, "train_info/time_within_train_step": 13.161052465438843, "step": 953} +{"train_info/time_between_train_steps": 0.00484013557434082, "step": 953} +{"info/global_step": 954, "train_info/time_within_train_step": 13.175802946090698, "step": 954} +{"train_info/time_between_train_steps": 0.005458831787109375, "step": 954} +{"info/global_step": 955, "train_info/time_within_train_step": 13.175347089767456, "step": 955} +{"train_info/time_between_train_steps": 0.005620718002319336, "step": 955} +{"info/global_step": 956, "train_info/time_within_train_step": 13.171059608459473, "step": 956} +{"train_info/time_between_train_steps": 0.005639791488647461, "step": 956} +{"info/global_step": 957, "train_info/time_within_train_step": 13.168802976608276, "step": 957} +{"train_info/time_between_train_steps": 0.005089998245239258, "step": 957} +{"info/global_step": 958, "train_info/time_within_train_step": 13.157405376434326, "step": 958} +{"train_info/time_between_train_steps": 0.0046651363372802734, "step": 958} +{"info/global_step": 959, "train_info/time_within_train_step": 13.172380924224854, "step": 959} +{"train_info/time_between_train_steps": 0.005343914031982422, "step": 959} +{"info/global_step": 960, "train_info/time_within_train_step": 13.185804843902588, "step": 960} +{"train_info/time_between_train_steps": 0.005143642425537109, "step": 960} +{"info/global_step": 961, "train_info/time_within_train_step": 13.174507141113281, "step": 961} +{"train_info/time_between_train_steps": 0.005551576614379883, "step": 961} +{"info/global_step": 962, "train_info/time_within_train_step": 13.272733449935913, "step": 962} +{"train_info/time_between_train_steps": 0.006986379623413086, "step": 962} +{"train_info/time_between_train_steps": 10.601995468139648, "step": 962} +{"info/global_step": 963, "train_info/time_within_train_step": 13.130887508392334, "step": 963} +{"train_info/time_between_train_steps": 0.005393505096435547, "step": 963} +{"info/global_step": 964, "train_info/time_within_train_step": 13.236159801483154, "step": 964} +{"train_info/time_between_train_steps": 0.0055162906646728516, "step": 964} +{"info/global_step": 965, "train_info/time_within_train_step": 13.146737575531006, "step": 965} +{"train_info/time_between_train_steps": 0.0051305294036865234, "step": 965} +{"info/global_step": 966, "train_info/time_within_train_step": 13.248884201049805, "step": 966} +{"train_info/time_between_train_steps": 0.005438804626464844, "step": 966} +{"info/global_step": 967, "train_info/time_within_train_step": 13.15522837638855, "step": 967} +{"train_info/time_between_train_steps": 0.0049648284912109375, "step": 967} +{"info/global_step": 968, "train_info/time_within_train_step": 13.271268844604492, "step": 968} +{"train_info/time_between_train_steps": 0.0055692195892333984, "step": 968} +{"info/global_step": 969, "train_info/time_within_train_step": 13.172784328460693, "step": 969} +{"train_info/time_between_train_steps": 0.00538945198059082, "step": 969} +{"info/global_step": 970, "train_info/time_within_train_step": 13.188387393951416, "step": 970} +{"train_info/time_between_train_steps": 0.005209922790527344, "step": 970} +{"info/global_step": 971, "train_info/time_within_train_step": 13.176089763641357, "step": 971} +{"train_info/time_between_train_steps": 0.005009174346923828, "step": 971} +{"info/global_step": 972, "train_info/time_within_train_step": 13.189733505249023, "step": 972} +{"train_info/time_between_train_steps": 0.004511833190917969, "step": 972} +{"info/global_step": 973, "train_info/time_within_train_step": 13.159041166305542, "step": 973} +{"train_info/time_between_train_steps": 0.0051615238189697266, "step": 973} +{"info/global_step": 974, "train_info/time_within_train_step": 13.174103260040283, "step": 974} +{"train_info/time_between_train_steps": 0.004937648773193359, "step": 974} +{"info/global_step": 975, "train_info/time_within_train_step": 13.178089618682861, "step": 975} +{"train_info/time_between_train_steps": 0.00521397590637207, "step": 975} +{"info/global_step": 976, "train_info/time_within_train_step": 13.184309482574463, "step": 976} +{"train_info/time_between_train_steps": 0.004973888397216797, "step": 976} +{"info/global_step": 977, "train_info/time_within_train_step": 13.270362138748169, "step": 977} +{"train_info/time_between_train_steps": 0.005723714828491211, "step": 977} +{"info/global_step": 978, "train_info/time_within_train_step": 13.176227569580078, "step": 978} +{"train_info/time_between_train_steps": 0.005370140075683594, "step": 978} +{"info/global_step": 979, "train_info/time_within_train_step": 13.166428327560425, "step": 979} +{"train_info/time_between_train_steps": 0.005379199981689453, "step": 979} +{"info/global_step": 980, "train_info/time_within_train_step": 13.19093656539917, "step": 980} +{"train_info/time_between_train_steps": 0.005283355712890625, "step": 980} +{"info/global_step": 981, "train_info/time_within_train_step": 13.182844638824463, "step": 981} +{"train_info/time_between_train_steps": 0.005526304244995117, "step": 981} +{"info/global_step": 982, "train_info/time_within_train_step": 13.194725036621094, "step": 982} +{"train_info/time_between_train_steps": 0.005426883697509766, "step": 982} +{"info/global_step": 983, "train_info/time_within_train_step": 13.168138265609741, "step": 983} +{"train_info/time_between_train_steps": 0.005519390106201172, "step": 983} +{"info/global_step": 984, "train_info/time_within_train_step": 13.163281440734863, "step": 984} +{"train_info/time_between_train_steps": 0.004575014114379883, "step": 984} +{"info/global_step": 985, "train_info/time_within_train_step": 13.210956811904907, "step": 985} +{"train_info/time_between_train_steps": 0.005429506301879883, "step": 985} +{"info/global_step": 986, "train_info/time_within_train_step": 13.208037614822388, "step": 986} +{"train_info/time_between_train_steps": 0.005439281463623047, "step": 986} +{"info/global_step": 987, "train_info/time_within_train_step": 13.184779405593872, "step": 987} +{"train_info/time_between_train_steps": 0.0059185028076171875, "step": 987} +{"info/global_step": 988, "train_info/time_within_train_step": 13.192280769348145, "step": 988} +{"train_info/time_between_train_steps": 0.006399869918823242, "step": 988} +{"train_info/time_between_train_steps": 10.414300203323364, "step": 988} +{"info/global_step": 989, "train_info/time_within_train_step": 13.162468194961548, "step": 989} +{"train_info/time_between_train_steps": 0.005410909652709961, "step": 989} +{"info/global_step": 990, "train_info/time_within_train_step": 13.2565336227417, "step": 990} +{"train_info/time_between_train_steps": 0.005356788635253906, "step": 990} +{"info/global_step": 991, "train_info/time_within_train_step": 13.160038232803345, "step": 991} +{"train_info/time_between_train_steps": 0.0053064823150634766, "step": 991} +{"info/global_step": 992, "train_info/time_within_train_step": 13.379168272018433, "step": 992} +{"train_info/time_between_train_steps": 0.005769014358520508, "step": 992} +{"info/global_step": 993, "train_info/time_within_train_step": 13.188939571380615, "step": 993} +{"train_info/time_between_train_steps": 0.006011486053466797, "step": 993} +{"info/global_step": 994, "train_info/time_within_train_step": 13.299453020095825, "step": 994} +{"train_info/time_between_train_steps": 0.005609750747680664, "step": 994} +{"info/global_step": 995, "train_info/time_within_train_step": 13.184082984924316, "step": 995} +{"train_info/time_between_train_steps": 0.005260467529296875, "step": 995} +{"info/global_step": 996, "train_info/time_within_train_step": 13.19084906578064, "step": 996} +{"train_info/time_between_train_steps": 0.005215167999267578, "step": 996} +{"info/global_step": 997, "train_info/time_within_train_step": 13.173988819122314, "step": 997} +{"train_info/time_between_train_steps": 0.004924774169921875, "step": 997} +{"info/global_step": 998, "train_info/time_within_train_step": 13.185351133346558, "step": 998} +{"train_info/time_between_train_steps": 0.0057222843170166016, "step": 998} +{"info/global_step": 999, "train_info/time_within_train_step": 13.18907880783081, "step": 999} +{"train_info/time_between_train_steps": 0.005118370056152344, "step": 999} +{"info/global_step": 1000, "train_info/time_within_train_step": 13.187747478485107, "step": 1000} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 24598.0, "train_info/memory_max_reserved": 24598.0, "_timestamp": 1737057027, "_runtime": 14327}, "step": 1000} +{"logs": {"train/loss": 4.8232, "train/learning_rate": 0.00011111111111111109, "train/epoch": 38.01, "_timestamp": 1737057027, "_runtime": 14327}, "step": 1000} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 28596.0, "train_info/memory_max_reserved": 28596.0, "_timestamp": 1737057029, "_runtime": 14329}, "step": 1000} +{"logs": {"eval/loss": 6.224096298217773, "eval/runtime": 1.093, "eval/samples_per_second": 78.684, "eval/steps_per_second": 5.49, "train/epoch": 38.01, "_timestamp": 1737057029, "_runtime": 14329}, "step": 1000} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 28596.0, "train_info/memory_max_reserved": 28596.0, "_timestamp": 1737057029, "_runtime": 14329}, "step": 1000} +{"logs": {"eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 6.224096298217773, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 504.7666777328044, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 1.093, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 78.684, "train/epoch": 38.01, "_timestamp": 1737057029, "_runtime": 14329}, "step": 1000} +{"train_info/time_between_train_steps": 17.951379537582397, "step": 1000} +{"info/global_step": 1001, "train_info/time_within_train_step": 13.118332147598267, "step": 1001} +{"train_info/time_between_train_steps": 0.0049724578857421875, "step": 1001} +{"info/global_step": 1002, "train_info/time_within_train_step": 13.151965379714966, "step": 1002} +{"train_info/time_between_train_steps": 0.004480600357055664, "step": 1002} +{"info/global_step": 1003, "train_info/time_within_train_step": 13.153756141662598, "step": 1003} +{"train_info/time_between_train_steps": 0.004815101623535156, "step": 1003} +{"info/global_step": 1004, "train_info/time_within_train_step": 13.13071084022522, "step": 1004} +{"train_info/time_between_train_steps": 0.005419015884399414, "step": 1004} +{"info/global_step": 1005, "train_info/time_within_train_step": 13.176052331924438, "step": 1005} +{"train_info/time_between_train_steps": 0.00557398796081543, "step": 1005} +{"info/global_step": 1006, "train_info/time_within_train_step": 13.161049365997314, "step": 1006} +{"train_info/time_between_train_steps": 0.005566120147705078, "step": 1006} +{"info/global_step": 1007, "train_info/time_within_train_step": 13.152892827987671, "step": 1007} +{"train_info/time_between_train_steps": 0.00549769401550293, "step": 1007} +{"info/global_step": 1008, "train_info/time_within_train_step": 13.282758712768555, "step": 1008} +{"train_info/time_between_train_steps": 0.004564046859741211, "step": 1008} +{"info/global_step": 1009, "train_info/time_within_train_step": 13.144216537475586, "step": 1009} +{"train_info/time_between_train_steps": 0.005824565887451172, "step": 1009} +{"info/global_step": 1010, "train_info/time_within_train_step": 13.166598320007324, "step": 1010} +{"train_info/time_between_train_steps": 0.005846977233886719, "step": 1010} +{"info/global_step": 1011, "train_info/time_within_train_step": 13.182530641555786, "step": 1011} +{"train_info/time_between_train_steps": 0.005930423736572266, "step": 1011} +{"info/global_step": 1012, "train_info/time_within_train_step": 13.18648099899292, "step": 1012} +{"train_info/time_between_train_steps": 0.005656719207763672, "step": 1012} +{"info/global_step": 1013, "train_info/time_within_train_step": 13.18289065361023, "step": 1013} +{"train_info/time_between_train_steps": 0.005882740020751953, "step": 1013} +{"info/global_step": 1014, "train_info/time_within_train_step": 13.195670127868652, "step": 1014} +{"train_info/time_between_train_steps": 0.005591869354248047, "step": 1014} +{"train_info/time_between_train_steps": 10.504663467407227, "step": 1014} +{"info/global_step": 1015, "train_info/time_within_train_step": 13.159752130508423, "step": 1015} +{"train_info/time_between_train_steps": 0.00539708137512207, "step": 1015} +{"info/global_step": 1016, "train_info/time_within_train_step": 13.269752264022827, "step": 1016} +{"train_info/time_between_train_steps": 0.005223989486694336, "step": 1016} +{"info/global_step": 1017, "train_info/time_within_train_step": 13.16347074508667, "step": 1017} +{"train_info/time_between_train_steps": 0.00567936897277832, "step": 1017} +{"info/global_step": 1018, "train_info/time_within_train_step": 13.258201837539673, "step": 1018} +{"train_info/time_between_train_steps": 0.0052890777587890625, "step": 1018} +{"info/global_step": 1019, "train_info/time_within_train_step": 13.198962450027466, "step": 1019} +{"train_info/time_between_train_steps": 0.0056896209716796875, "step": 1019} +{"info/global_step": 1020, "train_info/time_within_train_step": 13.24604320526123, "step": 1020} +{"train_info/time_between_train_steps": 0.004603385925292969, "step": 1020} +{"info/global_step": 1021, "train_info/time_within_train_step": 13.164648294448853, "step": 1021} +{"train_info/time_between_train_steps": 0.005912065505981445, "step": 1021} +{"info/global_step": 1022, "train_info/time_within_train_step": 13.166532754898071, "step": 1022} +{"train_info/time_between_train_steps": 0.005697727203369141, "step": 1022} +{"info/global_step": 1023, "train_info/time_within_train_step": 13.260106563568115, "step": 1023} +{"train_info/time_between_train_steps": 0.0054988861083984375, "step": 1023} +{"info/global_step": 1024, "train_info/time_within_train_step": 13.188216209411621, "step": 1024} +{"train_info/time_between_train_steps": 0.005438566207885742, "step": 1024} +{"info/global_step": 1025, "train_info/time_within_train_step": 13.172646760940552, "step": 1025} +{"train_info/time_between_train_steps": 0.005582094192504883, "step": 1025} +{"info/global_step": 1026, "train_info/time_within_train_step": 13.174288272857666, "step": 1026} +{"train_info/time_between_train_steps": 0.005435466766357422, "step": 1026} +{"info/global_step": 1027, "train_info/time_within_train_step": 13.253735065460205, "step": 1027} +{"train_info/time_between_train_steps": 0.005403280258178711, "step": 1027} +{"info/global_step": 1028, "train_info/time_within_train_step": 13.358360528945923, "step": 1028} +{"train_info/time_between_train_steps": 0.0053136348724365234, "step": 1028} +{"info/global_step": 1029, "train_info/time_within_train_step": 13.178116083145142, "step": 1029} +{"train_info/time_between_train_steps": 0.00538325309753418, "step": 1029} +{"info/global_step": 1030, "train_info/time_within_train_step": 13.16757345199585, "step": 1030} +{"train_info/time_between_train_steps": 0.005493640899658203, "step": 1030} +{"info/global_step": 1031, "train_info/time_within_train_step": 13.180588960647583, "step": 1031} +{"train_info/time_between_train_steps": 0.005019664764404297, "step": 1031} +{"info/global_step": 1032, "train_info/time_within_train_step": 13.176533937454224, "step": 1032} +{"train_info/time_between_train_steps": 0.005474090576171875, "step": 1032} +{"info/global_step": 1033, "train_info/time_within_train_step": 13.217622995376587, "step": 1033} +{"train_info/time_between_train_steps": 0.005115985870361328, "step": 1033} +{"info/global_step": 1034, "train_info/time_within_train_step": 13.172563314437866, "step": 1034} +{"train_info/time_between_train_steps": 0.005103111267089844, "step": 1034} +{"info/global_step": 1035, "train_info/time_within_train_step": 13.172446966171265, "step": 1035} +{"train_info/time_between_train_steps": 0.005616903305053711, "step": 1035} +{"info/global_step": 1036, "train_info/time_within_train_step": 13.1918785572052, "step": 1036} +{"train_info/time_between_train_steps": 0.005738258361816406, "step": 1036} +{"info/global_step": 1037, "train_info/time_within_train_step": 13.186238765716553, "step": 1037} +{"train_info/time_between_train_steps": 0.005223989486694336, "step": 1037} +{"info/global_step": 1038, "train_info/time_within_train_step": 13.181096076965332, "step": 1038} +{"train_info/time_between_train_steps": 0.005515098571777344, "step": 1038} +{"info/global_step": 1039, "train_info/time_within_train_step": 13.278367042541504, "step": 1039} +{"train_info/time_between_train_steps": 0.0057010650634765625, "step": 1039} +{"info/global_step": 1040, "train_info/time_within_train_step": 13.200277090072632, "step": 1040} +{"train_info/time_between_train_steps": 0.006643533706665039, "step": 1040} +{"train_info/time_between_train_steps": 10.649790525436401, "step": 1040} +{"info/global_step": 1041, "train_info/time_within_train_step": 13.163860321044922, "step": 1041} +{"train_info/time_between_train_steps": 0.005407810211181641, "step": 1041} +{"info/global_step": 1042, "train_info/time_within_train_step": 13.243600368499756, "step": 1042} +{"train_info/time_between_train_steps": 0.0053751468658447266, "step": 1042} +{"info/global_step": 1043, "train_info/time_within_train_step": 13.144012928009033, "step": 1043} +{"train_info/time_between_train_steps": 0.005166530609130859, "step": 1043} +{"info/global_step": 1044, "train_info/time_within_train_step": 13.315762758255005, "step": 1044} +{"train_info/time_between_train_steps": 0.005671501159667969, "step": 1044} +{"info/global_step": 1045, "train_info/time_within_train_step": 13.172086477279663, "step": 1045} +{"train_info/time_between_train_steps": 0.005624294281005859, "step": 1045} +{"info/global_step": 1046, "train_info/time_within_train_step": 13.249517917633057, "step": 1046} +{"train_info/time_between_train_steps": 0.005507946014404297, "step": 1046} +{"info/global_step": 1047, "train_info/time_within_train_step": 13.193135499954224, "step": 1047} +{"train_info/time_between_train_steps": 0.005286455154418945, "step": 1047} +{"info/global_step": 1048, "train_info/time_within_train_step": 13.17231559753418, "step": 1048} +{"train_info/time_between_train_steps": 0.0050623416900634766, "step": 1048} +{"info/global_step": 1049, "train_info/time_within_train_step": 13.158819198608398, "step": 1049} +{"train_info/time_between_train_steps": 0.004851579666137695, "step": 1049} +{"info/global_step": 1050, "train_info/time_within_train_step": 13.152888536453247, "step": 1050} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 28596.0, "train_info/memory_max_reserved": 28596.0, "_timestamp": 1737057729, "_runtime": 15029}, "step": 1050} +{"logs": {"train/loss": 4.764, "train/learning_rate": 8.333333333333333e-05, "train/epoch": 40.01, "_timestamp": 1737057729, "_runtime": 15029}, "step": 1050} +{"train_info/time_between_train_steps": 0.05710101127624512, "step": 1050} +{"info/global_step": 1051, "train_info/time_within_train_step": 13.165304183959961, "step": 1051} +{"train_info/time_between_train_steps": 0.00558161735534668, "step": 1051} +{"info/global_step": 1052, "train_info/time_within_train_step": 13.156619310379028, "step": 1052} +{"train_info/time_between_train_steps": 0.005482912063598633, "step": 1052} +{"info/global_step": 1053, "train_info/time_within_train_step": 13.162107229232788, "step": 1053} +{"train_info/time_between_train_steps": 0.005895376205444336, "step": 1053} +{"info/global_step": 1054, "train_info/time_within_train_step": 13.258362770080566, "step": 1054} +{"train_info/time_between_train_steps": 0.0053632259368896484, "step": 1054} +{"info/global_step": 1055, "train_info/time_within_train_step": 13.183296918869019, "step": 1055} +{"train_info/time_between_train_steps": 0.005490541458129883, "step": 1055} +{"info/global_step": 1056, "train_info/time_within_train_step": 13.168810606002808, "step": 1056} +{"train_info/time_between_train_steps": 0.00527191162109375, "step": 1056} +{"info/global_step": 1057, "train_info/time_within_train_step": 13.17206597328186, "step": 1057} +{"train_info/time_between_train_steps": 0.00500178337097168, "step": 1057} +{"info/global_step": 1058, "train_info/time_within_train_step": 13.164136171340942, "step": 1058} +{"train_info/time_between_train_steps": 0.0052869319915771484, "step": 1058} +{"info/global_step": 1059, "train_info/time_within_train_step": 13.181112289428711, "step": 1059} +{"train_info/time_between_train_steps": 0.005167961120605469, "step": 1059} +{"info/global_step": 1060, "train_info/time_within_train_step": 13.180309057235718, "step": 1060} +{"train_info/time_between_train_steps": 0.005184173583984375, "step": 1060} +{"info/global_step": 1061, "train_info/time_within_train_step": 13.16053557395935, "step": 1061} +{"train_info/time_between_train_steps": 0.005040645599365234, "step": 1061} +{"info/global_step": 1062, "train_info/time_within_train_step": 13.156190633773804, "step": 1062} +{"train_info/time_between_train_steps": 0.0049228668212890625, "step": 1062} +{"info/global_step": 1063, "train_info/time_within_train_step": 13.171263217926025, "step": 1063} +{"train_info/time_between_train_steps": 0.005299091339111328, "step": 1063} +{"info/global_step": 1064, "train_info/time_within_train_step": 13.177162647247314, "step": 1064} +{"train_info/time_between_train_steps": 0.004925251007080078, "step": 1064} +{"info/global_step": 1065, "train_info/time_within_train_step": 13.18205451965332, "step": 1065} +{"train_info/time_between_train_steps": 0.0066797733306884766, "step": 1065} +{"info/global_step": 1066, "train_info/time_within_train_step": 13.223137140274048, "step": 1066} +{"train_info/time_between_train_steps": 0.006955862045288086, "step": 1066} +{"train_info/time_between_train_steps": 10.436728239059448, "step": 1066} +{"info/global_step": 1067, "train_info/time_within_train_step": 13.142117977142334, "step": 1067} +{"train_info/time_between_train_steps": 0.005290985107421875, "step": 1067} +{"info/global_step": 1068, "train_info/time_within_train_step": 13.25144362449646, "step": 1068} +{"train_info/time_between_train_steps": 0.0055389404296875, "step": 1068} +{"info/global_step": 1069, "train_info/time_within_train_step": 13.223942041397095, "step": 1069} +{"train_info/time_between_train_steps": 0.004649639129638672, "step": 1069} +{"info/global_step": 1070, "train_info/time_within_train_step": 13.23838996887207, "step": 1070} +{"train_info/time_between_train_steps": 0.005104780197143555, "step": 1070} +{"info/global_step": 1071, "train_info/time_within_train_step": 13.191587448120117, "step": 1071} +{"train_info/time_between_train_steps": 0.005185127258300781, "step": 1071} +{"info/global_step": 1072, "train_info/time_within_train_step": 13.27291989326477, "step": 1072} +{"train_info/time_between_train_steps": 0.005525827407836914, "step": 1072} +{"info/global_step": 1073, "train_info/time_within_train_step": 13.162170886993408, "step": 1073} +{"train_info/time_between_train_steps": 0.004883766174316406, "step": 1073} +{"info/global_step": 1074, "train_info/time_within_train_step": 13.172575235366821, "step": 1074} +{"train_info/time_between_train_steps": 0.005148649215698242, "step": 1074} +{"info/global_step": 1075, "train_info/time_within_train_step": 13.219160318374634, "step": 1075} +{"train_info/time_between_train_steps": 0.005101442337036133, "step": 1075} +{"info/global_step": 1076, "train_info/time_within_train_step": 13.226964712142944, "step": 1076} +{"train_info/time_between_train_steps": 0.005128145217895508, "step": 1076} +{"info/global_step": 1077, "train_info/time_within_train_step": 13.158967733383179, "step": 1077} +{"train_info/time_between_train_steps": 0.00532078742980957, "step": 1077} +{"info/global_step": 1078, "train_info/time_within_train_step": 13.155529260635376, "step": 1078} +{"train_info/time_between_train_steps": 0.0054779052734375, "step": 1078} +{"info/global_step": 1079, "train_info/time_within_train_step": 13.164444923400879, "step": 1079} +{"train_info/time_between_train_steps": 0.004960060119628906, "step": 1079} +{"info/global_step": 1080, "train_info/time_within_train_step": 13.161465167999268, "step": 1080} +{"train_info/time_between_train_steps": 0.004989147186279297, "step": 1080} +{"info/global_step": 1081, "train_info/time_within_train_step": 13.20128345489502, "step": 1081} +{"train_info/time_between_train_steps": 0.005255222320556641, "step": 1081} +{"info/global_step": 1082, "train_info/time_within_train_step": 13.167839527130127, "step": 1082} +{"train_info/time_between_train_steps": 0.0053789615631103516, "step": 1082} +{"info/global_step": 1083, "train_info/time_within_train_step": 13.170767545700073, "step": 1083} +{"train_info/time_between_train_steps": 0.005163908004760742, "step": 1083} +{"info/global_step": 1084, "train_info/time_within_train_step": 13.25915813446045, "step": 1084} +{"train_info/time_between_train_steps": 0.005658388137817383, "step": 1084} +{"info/global_step": 1085, "train_info/time_within_train_step": 13.17625379562378, "step": 1085} +{"train_info/time_between_train_steps": 0.005186796188354492, "step": 1085} +{"info/global_step": 1086, "train_info/time_within_train_step": 13.17584228515625, "step": 1086} +{"train_info/time_between_train_steps": 0.0052754878997802734, "step": 1086} +{"info/global_step": 1087, "train_info/time_within_train_step": 13.169063568115234, "step": 1087} +{"train_info/time_between_train_steps": 0.004998922348022461, "step": 1087} +{"info/global_step": 1088, "train_info/time_within_train_step": 13.165186882019043, "step": 1088} +{"train_info/time_between_train_steps": 0.005574226379394531, "step": 1088} +{"info/global_step": 1089, "train_info/time_within_train_step": 13.167573690414429, "step": 1089} +{"train_info/time_between_train_steps": 0.005616426467895508, "step": 1089} +{"info/global_step": 1090, "train_info/time_within_train_step": 13.172134637832642, "step": 1090} +{"train_info/time_between_train_steps": 0.005353450775146484, "step": 1090} +{"info/global_step": 1091, "train_info/time_within_train_step": 13.176252603530884, "step": 1091} +{"train_info/time_between_train_steps": 0.005791664123535156, "step": 1091} +{"info/global_step": 1092, "train_info/time_within_train_step": 13.203317403793335, "step": 1092} +{"train_info/time_between_train_steps": 0.006304025650024414, "step": 1092} +{"train_info/time_between_train_steps": 10.502910375595093, "step": 1092} +{"info/global_step": 1093, "train_info/time_within_train_step": 13.151365995407104, "step": 1093} +{"train_info/time_between_train_steps": 0.005204677581787109, "step": 1093} +{"info/global_step": 1094, "train_info/time_within_train_step": 13.259018421173096, "step": 1094} +{"train_info/time_between_train_steps": 0.005645275115966797, "step": 1094} +{"info/global_step": 1095, "train_info/time_within_train_step": 13.17317247390747, "step": 1095} +{"train_info/time_between_train_steps": 0.005410909652709961, "step": 1095} +{"info/global_step": 1096, "train_info/time_within_train_step": 13.263669967651367, "step": 1096} +{"train_info/time_between_train_steps": 0.0057010650634765625, "step": 1096} +{"info/global_step": 1097, "train_info/time_within_train_step": 13.168723821640015, "step": 1097} +{"train_info/time_between_train_steps": 0.005861043930053711, "step": 1097} +{"info/global_step": 1098, "train_info/time_within_train_step": 13.24584698677063, "step": 1098} +{"train_info/time_between_train_steps": 0.005637407302856445, "step": 1098} +{"info/global_step": 1099, "train_info/time_within_train_step": 13.275812149047852, "step": 1099} +{"train_info/time_between_train_steps": 0.0051076412200927734, "step": 1099} +{"info/global_step": 1100, "train_info/time_within_train_step": 13.182929754257202, "step": 1100} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 28596.0, "train_info/memory_max_reserved": 28596.0, "_timestamp": 1737058412, "_runtime": 15712}, "step": 1100} +{"logs": {"train/loss": 4.7157, "train/learning_rate": 5.5555555555555545e-05, "train/epoch": 42.01, "_timestamp": 1737058412, "_runtime": 15712}, "step": 1100} +{"train_info/time_between_train_steps": 22.23865008354187, "step": 1100} +{"info/global_step": 1101, "train_info/time_within_train_step": 13.12781548500061, "step": 1101} +{"train_info/time_between_train_steps": 0.005387306213378906, "step": 1101} +{"info/global_step": 1102, "train_info/time_within_train_step": 13.136518478393555, "step": 1102} +{"train_info/time_between_train_steps": 0.004828691482543945, "step": 1102} +{"info/global_step": 1103, "train_info/time_within_train_step": 13.135165452957153, "step": 1103} +{"train_info/time_between_train_steps": 0.004769325256347656, "step": 1103} +{"info/global_step": 1104, "train_info/time_within_train_step": 13.1336088180542, "step": 1104} +{"train_info/time_between_train_steps": 0.005349397659301758, "step": 1104} +{"info/global_step": 1105, "train_info/time_within_train_step": 13.149808883666992, "step": 1105} +{"train_info/time_between_train_steps": 0.0053653717041015625, "step": 1105} +{"info/global_step": 1106, "train_info/time_within_train_step": 13.165144681930542, "step": 1106} +{"train_info/time_between_train_steps": 0.004867076873779297, "step": 1106} +{"info/global_step": 1107, "train_info/time_within_train_step": 13.159908056259155, "step": 1107} +{"train_info/time_between_train_steps": 0.005307912826538086, "step": 1107} +{"info/global_step": 1108, "train_info/time_within_train_step": 13.13797116279602, "step": 1108} +{"train_info/time_between_train_steps": 0.0051670074462890625, "step": 1108} +{"info/global_step": 1109, "train_info/time_within_train_step": 13.1834237575531, "step": 1109} +{"train_info/time_between_train_steps": 0.004617929458618164, "step": 1109} +{"info/global_step": 1110, "train_info/time_within_train_step": 13.181610584259033, "step": 1110} +{"train_info/time_between_train_steps": 0.005464315414428711, "step": 1110} +{"info/global_step": 1111, "train_info/time_within_train_step": 13.152700901031494, "step": 1111} +{"train_info/time_between_train_steps": 0.0050466060638427734, "step": 1111} +{"info/global_step": 1112, "train_info/time_within_train_step": 13.151675701141357, "step": 1112} +{"train_info/time_between_train_steps": 0.005370378494262695, "step": 1112} +{"info/global_step": 1113, "train_info/time_within_train_step": 13.150107145309448, "step": 1113} +{"train_info/time_between_train_steps": 0.005337953567504883, "step": 1113} +{"info/global_step": 1114, "train_info/time_within_train_step": 13.191432476043701, "step": 1114} +{"train_info/time_between_train_steps": 0.0056917667388916016, "step": 1114} +{"info/global_step": 1115, "train_info/time_within_train_step": 13.258136510848999, "step": 1115} +{"train_info/time_between_train_steps": 0.0055582523345947266, "step": 1115} +{"info/global_step": 1116, "train_info/time_within_train_step": 13.193849086761475, "step": 1116} +{"train_info/time_between_train_steps": 0.005656003952026367, "step": 1116} +{"info/global_step": 1117, "train_info/time_within_train_step": 13.20326042175293, "step": 1117} +{"train_info/time_between_train_steps": 0.006251811981201172, "step": 1117} +{"info/global_step": 1118, "train_info/time_within_train_step": 13.218557119369507, "step": 1118} +{"train_info/time_between_train_steps": 0.006573677062988281, "step": 1118} +{"train_info/time_between_train_steps": 10.623963832855225, "step": 1118} +{"info/global_step": 1119, "train_info/time_within_train_step": 13.160791158676147, "step": 1119} +{"train_info/time_between_train_steps": 0.00590062141418457, "step": 1119} +{"info/global_step": 1120, "train_info/time_within_train_step": 13.262216806411743, "step": 1120} +{"train_info/time_between_train_steps": 0.005576133728027344, "step": 1120} +{"info/global_step": 1121, "train_info/time_within_train_step": 13.15310549736023, "step": 1121} +{"train_info/time_between_train_steps": 0.005502223968505859, "step": 1121} +{"info/global_step": 1122, "train_info/time_within_train_step": 13.262128114700317, "step": 1122} +{"train_info/time_between_train_steps": 0.005768299102783203, "step": 1122} +{"info/global_step": 1123, "train_info/time_within_train_step": 13.18180513381958, "step": 1123} +{"train_info/time_between_train_steps": 0.00572657585144043, "step": 1123} +{"info/global_step": 1124, "train_info/time_within_train_step": 13.221088171005249, "step": 1124} +{"train_info/time_between_train_steps": 0.004981040954589844, "step": 1124} +{"info/global_step": 1125, "train_info/time_within_train_step": 13.168554067611694, "step": 1125} +{"train_info/time_between_train_steps": 0.00472259521484375, "step": 1125} +{"info/global_step": 1126, "train_info/time_within_train_step": 13.181575536727905, "step": 1126} +{"train_info/time_between_train_steps": 0.005143642425537109, "step": 1126} +{"info/global_step": 1127, "train_info/time_within_train_step": 14.920330286026001, "step": 1127} +{"train_info/time_between_train_steps": 0.004867076873779297, "step": 1127} +{"info/global_step": 1128, "train_info/time_within_train_step": 13.191310167312622, "step": 1128} +{"train_info/time_between_train_steps": 0.005075216293334961, "step": 1128} +{"info/global_step": 1129, "train_info/time_within_train_step": 13.160114288330078, "step": 1129} +{"train_info/time_between_train_steps": 0.005264997482299805, "step": 1129} +{"info/global_step": 1130, "train_info/time_within_train_step": 13.241217374801636, "step": 1130} +{"train_info/time_between_train_steps": 0.005668163299560547, "step": 1130} +{"info/global_step": 1131, "train_info/time_within_train_step": 13.183984994888306, "step": 1131} +{"train_info/time_between_train_steps": 0.005221128463745117, "step": 1131} +{"info/global_step": 1132, "train_info/time_within_train_step": 13.183959007263184, "step": 1132} +{"train_info/time_between_train_steps": 0.0049707889556884766, "step": 1132} +{"info/global_step": 1133, "train_info/time_within_train_step": 13.147872924804688, "step": 1133} +{"train_info/time_between_train_steps": 0.005112648010253906, "step": 1133} +{"info/global_step": 1134, "train_info/time_within_train_step": 13.172309398651123, "step": 1134} +{"train_info/time_between_train_steps": 0.00569605827331543, "step": 1134} +{"info/global_step": 1135, "train_info/time_within_train_step": 13.169951438903809, "step": 1135} +{"train_info/time_between_train_steps": 0.005646944046020508, "step": 1135} +{"info/global_step": 1136, "train_info/time_within_train_step": 13.169332265853882, "step": 1136} +{"train_info/time_between_train_steps": 0.005350828170776367, "step": 1136} +{"info/global_step": 1137, "train_info/time_within_train_step": 13.157821655273438, "step": 1137} +{"train_info/time_between_train_steps": 0.005306720733642578, "step": 1137} +{"info/global_step": 1138, "train_info/time_within_train_step": 13.15321946144104, "step": 1138} +{"train_info/time_between_train_steps": 0.005397796630859375, "step": 1138} +{"info/global_step": 1139, "train_info/time_within_train_step": 13.167784214019775, "step": 1139} +{"train_info/time_between_train_steps": 0.005353212356567383, "step": 1139} +{"info/global_step": 1140, "train_info/time_within_train_step": 13.172902822494507, "step": 1140} +{"train_info/time_between_train_steps": 0.0050661563873291016, "step": 1140} +{"info/global_step": 1141, "train_info/time_within_train_step": 13.186085939407349, "step": 1141} +{"train_info/time_between_train_steps": 0.005476713180541992, "step": 1141} +{"info/global_step": 1142, "train_info/time_within_train_step": 13.188807010650635, "step": 1142} +{"train_info/time_between_train_steps": 0.0056247711181640625, "step": 1142} +{"info/global_step": 1143, "train_info/time_within_train_step": 13.1945960521698, "step": 1143} +{"train_info/time_between_train_steps": 0.00572514533996582, "step": 1143} +{"info/global_step": 1144, "train_info/time_within_train_step": 13.215998411178589, "step": 1144} +{"train_info/time_between_train_steps": 0.00619959831237793, "step": 1144} +{"train_info/time_between_train_steps": 10.4587881565094, "step": 1144} +{"info/global_step": 1145, "train_info/time_within_train_step": 13.254960298538208, "step": 1145} +{"train_info/time_between_train_steps": 0.00497889518737793, "step": 1145} +{"info/global_step": 1146, "train_info/time_within_train_step": 13.232897758483887, "step": 1146} +{"train_info/time_between_train_steps": 0.005478858947753906, "step": 1146} +{"info/global_step": 1147, "train_info/time_within_train_step": 13.156521558761597, "step": 1147} +{"train_info/time_between_train_steps": 0.0055694580078125, "step": 1147} +{"info/global_step": 1148, "train_info/time_within_train_step": 13.255180358886719, "step": 1148} +{"train_info/time_between_train_steps": 0.005278110504150391, "step": 1148} +{"info/global_step": 1149, "train_info/time_within_train_step": 13.19677209854126, "step": 1149} +{"train_info/time_between_train_steps": 0.005650997161865234, "step": 1149} +{"info/global_step": 1150, "train_info/time_within_train_step": 13.280482530593872, "step": 1150} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 28596.0, "train_info/memory_max_reserved": 28596.0, "_timestamp": 1737059120, "_runtime": 16420}, "step": 1150} +{"logs": {"train/loss": 4.6788, "train/learning_rate": 2.7777777777777772e-05, "train/epoch": 44.01, "_timestamp": 1737059120, "_runtime": 16420}, "step": 1150} +{"train_info/time_between_train_steps": 0.05544614791870117, "step": 1150} +{"info/global_step": 1151, "train_info/time_within_train_step": 13.245250701904297, "step": 1151} +{"train_info/time_between_train_steps": 0.005319356918334961, "step": 1151} +{"info/global_step": 1152, "train_info/time_within_train_step": 13.178585529327393, "step": 1152} +{"train_info/time_between_train_steps": 0.0053060054779052734, "step": 1152} +{"info/global_step": 1153, "train_info/time_within_train_step": 13.176356077194214, "step": 1153} +{"train_info/time_between_train_steps": 0.004746913909912109, "step": 1153} +{"info/global_step": 1154, "train_info/time_within_train_step": 13.143862247467041, "step": 1154} +{"train_info/time_between_train_steps": 0.005495786666870117, "step": 1154} +{"info/global_step": 1155, "train_info/time_within_train_step": 13.169166326522827, "step": 1155} +{"train_info/time_between_train_steps": 0.005370378494262695, "step": 1155} +{"info/global_step": 1156, "train_info/time_within_train_step": 13.154510498046875, "step": 1156} +{"train_info/time_between_train_steps": 0.004908561706542969, "step": 1156} +{"info/global_step": 1157, "train_info/time_within_train_step": 13.160627841949463, "step": 1157} +{"train_info/time_between_train_steps": 0.005313873291015625, "step": 1157} +{"info/global_step": 1158, "train_info/time_within_train_step": 13.192785501480103, "step": 1158} +{"train_info/time_between_train_steps": 0.004882097244262695, "step": 1158} +{"info/global_step": 1159, "train_info/time_within_train_step": 13.182610511779785, "step": 1159} +{"train_info/time_between_train_steps": 0.005176544189453125, "step": 1159} +{"info/global_step": 1160, "train_info/time_within_train_step": 13.256461381912231, "step": 1160} +{"train_info/time_between_train_steps": 0.005268096923828125, "step": 1160} +{"info/global_step": 1161, "train_info/time_within_train_step": 13.167935371398926, "step": 1161} +{"train_info/time_between_train_steps": 0.005253791809082031, "step": 1161} +{"info/global_step": 1162, "train_info/time_within_train_step": 13.165607929229736, "step": 1162} +{"train_info/time_between_train_steps": 0.00457000732421875, "step": 1162} +{"info/global_step": 1163, "train_info/time_within_train_step": 13.160254716873169, "step": 1163} +{"train_info/time_between_train_steps": 0.004994869232177734, "step": 1163} +{"info/global_step": 1164, "train_info/time_within_train_step": 13.166126489639282, "step": 1164} +{"train_info/time_between_train_steps": 0.005349636077880859, "step": 1164} +{"info/global_step": 1165, "train_info/time_within_train_step": 13.17414903640747, "step": 1165} +{"train_info/time_between_train_steps": 0.005336284637451172, "step": 1165} +{"info/global_step": 1166, "train_info/time_within_train_step": 13.15776252746582, "step": 1166} +{"train_info/time_between_train_steps": 0.005561351776123047, "step": 1166} +{"info/global_step": 1167, "train_info/time_within_train_step": 13.159575939178467, "step": 1167} +{"train_info/time_between_train_steps": 0.005456209182739258, "step": 1167} +{"info/global_step": 1168, "train_info/time_within_train_step": 13.187524318695068, "step": 1168} +{"train_info/time_between_train_steps": 0.005064249038696289, "step": 1168} +{"info/global_step": 1169, "train_info/time_within_train_step": 13.183602571487427, "step": 1169} +{"train_info/time_between_train_steps": 0.005659580230712891, "step": 1169} +{"info/global_step": 1170, "train_info/time_within_train_step": 13.199754476547241, "step": 1170} +{"train_info/time_between_train_steps": 0.006644248962402344, "step": 1170} +{"train_info/time_between_train_steps": 10.532816648483276, "step": 1170} +{"info/global_step": 1171, "train_info/time_within_train_step": 13.15942907333374, "step": 1171} +{"train_info/time_between_train_steps": 0.005055904388427734, "step": 1171} +{"info/global_step": 1172, "train_info/time_within_train_step": 13.222920894622803, "step": 1172} +{"train_info/time_between_train_steps": 0.005592823028564453, "step": 1172} +{"info/global_step": 1173, "train_info/time_within_train_step": 13.201298475265503, "step": 1173} +{"train_info/time_between_train_steps": 0.005442619323730469, "step": 1173} +{"info/global_step": 1174, "train_info/time_within_train_step": 13.282618522644043, "step": 1174} +{"train_info/time_between_train_steps": 0.005174160003662109, "step": 1174} +{"info/global_step": 1175, "train_info/time_within_train_step": 13.537559509277344, "step": 1175} +{"train_info/time_between_train_steps": 0.004940032958984375, "step": 1175} +{"info/global_step": 1176, "train_info/time_within_train_step": 13.294444561004639, "step": 1176} +{"train_info/time_between_train_steps": 0.005580902099609375, "step": 1176} +{"info/global_step": 1177, "train_info/time_within_train_step": 13.169045686721802, "step": 1177} +{"train_info/time_between_train_steps": 0.004952192306518555, "step": 1177} +{"info/global_step": 1178, "train_info/time_within_train_step": 13.168412208557129, "step": 1178} +{"train_info/time_between_train_steps": 0.0055806636810302734, "step": 1178} +{"info/global_step": 1179, "train_info/time_within_train_step": 13.160698652267456, "step": 1179} +{"train_info/time_between_train_steps": 0.005052328109741211, "step": 1179} +{"info/global_step": 1180, "train_info/time_within_train_step": 13.135128021240234, "step": 1180} +{"train_info/time_between_train_steps": 0.005086421966552734, "step": 1180} +{"info/global_step": 1181, "train_info/time_within_train_step": 13.144951105117798, "step": 1181} +{"train_info/time_between_train_steps": 0.005326986312866211, "step": 1181} +{"info/global_step": 1182, "train_info/time_within_train_step": 13.1396963596344, "step": 1182} +{"train_info/time_between_train_steps": 0.005303144454956055, "step": 1182} +{"info/global_step": 1183, "train_info/time_within_train_step": 13.14033555984497, "step": 1183} +{"train_info/time_between_train_steps": 0.005217075347900391, "step": 1183} +{"info/global_step": 1184, "train_info/time_within_train_step": 13.169379472732544, "step": 1184} +{"train_info/time_between_train_steps": 0.0052220821380615234, "step": 1184} +{"info/global_step": 1185, "train_info/time_within_train_step": 13.176678657531738, "step": 1185} +{"train_info/time_between_train_steps": 0.005536794662475586, "step": 1185} +{"info/global_step": 1186, "train_info/time_within_train_step": 13.134204864501953, "step": 1186} +{"train_info/time_between_train_steps": 0.004781961441040039, "step": 1186} +{"info/global_step": 1187, "train_info/time_within_train_step": 13.139978647232056, "step": 1187} +{"train_info/time_between_train_steps": 0.005513429641723633, "step": 1187} +{"info/global_step": 1188, "train_info/time_within_train_step": 13.143131732940674, "step": 1188} +{"train_info/time_between_train_steps": 0.005499362945556641, "step": 1188} +{"info/global_step": 1189, "train_info/time_within_train_step": 13.146424531936646, "step": 1189} +{"train_info/time_between_train_steps": 0.0054035186767578125, "step": 1189} +{"info/global_step": 1190, "train_info/time_within_train_step": 13.147189140319824, "step": 1190} +{"train_info/time_between_train_steps": 0.005013465881347656, "step": 1190} +{"info/global_step": 1191, "train_info/time_within_train_step": 13.224781513214111, "step": 1191} +{"train_info/time_between_train_steps": 0.00554347038269043, "step": 1191} +{"info/global_step": 1192, "train_info/time_within_train_step": 13.152807712554932, "step": 1192} +{"train_info/time_between_train_steps": 0.00470280647277832, "step": 1192} +{"info/global_step": 1193, "train_info/time_within_train_step": 13.148037195205688, "step": 1193} +{"train_info/time_between_train_steps": 0.005625247955322266, "step": 1193} +{"info/global_step": 1194, "train_info/time_within_train_step": 13.14683485031128, "step": 1194} +{"train_info/time_between_train_steps": 0.005478858947753906, "step": 1194} +{"info/global_step": 1195, "train_info/time_within_train_step": 13.163804292678833, "step": 1195} +{"train_info/time_between_train_steps": 0.005693197250366211, "step": 1195} +{"info/global_step": 1196, "train_info/time_within_train_step": 13.167945623397827, "step": 1196} +{"train_info/time_between_train_steps": 0.00601959228515625, "step": 1196} +{"train_info/time_between_train_steps": 10.564131259918213, "step": 1196} +{"info/global_step": 1197, "train_info/time_within_train_step": 13.106530904769897, "step": 1197} +{"train_info/time_between_train_steps": 0.004687309265136719, "step": 1197} +{"info/global_step": 1198, "train_info/time_within_train_step": 13.253942012786865, "step": 1198} +{"train_info/time_between_train_steps": 0.005373716354370117, "step": 1198} +{"info/global_step": 1199, "train_info/time_within_train_step": 13.119935989379883, "step": 1199} +{"train_info/time_between_train_steps": 0.005712032318115234, "step": 1199} +{"info/global_step": 1200, "train_info/time_within_train_step": 13.224280595779419, "step": 1200} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 28596.0, "train_info/memory_max_reserved": 28596.0, "_timestamp": 1737059802, "_runtime": 17102}, "step": 1200} +{"logs": {"train/loss": 4.6542, "train/learning_rate": 0.0, "train/epoch": 46.0, "_timestamp": 1737059802, "_runtime": 17102}, "step": 1200} +{"train_info": {"train_info/memory_allocated": 2080.609375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 28596.0, "train_info/memory_max_reserved": 28596.0, "_timestamp": 1737059833, "_runtime": 17133}, "step": 1200} +{"logs": {"train/train_runtime": 17134.2637, "train/train_samples_per_second": 35.858, "train/train_steps_per_second": 0.07, "train/total_flos": 3.28623853142016e+17, "train/train_loss": 5.960792771180471, "train/epoch": 46.0, "_timestamp": 1737059833, "_runtime": 17133}, "step": 1200} +{"train_info": {"train_info/memory_allocated": 2080.6083984375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 28596.0, "train_info/memory_max_reserved": 28596.0, "_timestamp": 1737059839, "_runtime": 17139}, "step": 1200} +{"logs": {"eval/loss": 6.2187323570251465, "eval/runtime": 0.9009, "eval/samples_per_second": 95.455, "eval/steps_per_second": 6.66, "train/epoch": 46.0, "_timestamp": 1737059839, "_runtime": 17139}, "step": 1200} +{"train_info": {"train_info/memory_allocated": 2080.6083984375, "train_info/memory_max_allocated": 21963.6201171875, "train_info/memory_reserved": 28596.0, "train_info/memory_max_reserved": 28596.0, "_timestamp": 1737059839, "_runtime": 17139}, "step": 1200} +{"logs": {"eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 6.2187323570251465, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 502.0663875307338, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 0.9009, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 95.455, "train/epoch": 46.0, "_timestamp": 1737059839, "_runtime": 17139}, "step": 1200} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..f79983d5dbb88118e61a116ba5e599353b7c5690 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872925222354b943fb237b58df7a40e18c7f6948b9f6f4f842f04322113fef07 +size 552615017 diff --git a/shuffle_local5_ar_AR_randinit_seed53.log b/shuffle_local5_ar_AR_randinit_seed53.log new file mode 100755 index 0000000000000000000000000000000000000000..5fa5e6c82b7b2d877852f1063cc733fda3c4a27a --- /dev/null +++ b/shuffle_local5_ar_AR_randinit_seed53.log @@ -0,0 +1,121 @@ +|=>> 01/16 [16:49:45] - mistral - INFO :: Starting Run: shuffle_local5_ar_AR_randinit_seed53... +|=>> 01/16 [16:49:46] - mistral - INFO :: Setting Random Seed to 53! +|=>> 01/16 [16:49:46] - mistral - INFO :: Building Tokenize and Initializing `gpt2-small` via AutoModel/AutoConfig... +|=>> 01/16 [16:49:46] - mistral - INFO :: Using Configs For Model From: /scratch/ykyao/projects/multilingual-LM/mistral/conf/models/gpt2-small-AR.json ... +|=>> 01/16 [16:49:46] - mistral.models.auto - INFO :: Building Hugging Face GPT2Config from provided configs: {'activation_function': 'gelu_new', 'architectures': ['GPT2LMHeadModel'], 'attn_pdrop': 0.1, 'bos_token_id': 0, 'embd_pdrop': 0.1, 'eos_token_id': 0, 'initializer_range': 0.02, 'layer_norm_epsilon': 1e-05, 'model_type': 'gpt2', 'n_ctx': 1024, 'n_embd': 768, 'n_head': 12, 'n_inner': None, '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': None, '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': '4.35.2', 'use_cache': False, 'vocab_size': 64000} ... +|=>> 01/16 [16:49:46] - mistral.models.auto - INFO :: Fetching Hugging Face [Fast] AutoTokenizer for Model: `gpt2`... +|=>> 01/16 [16:49:46] - mistral.models.auto - INFO :: Using a Pretokenized Dataset +|=>> 01/16 [16:49:46] - mistral.models.auto - INFO :: Initializing Custom GPT-2 Model from Configuration: `gpt2`... +|=>> 01/16 [16:49:49] - mistral - INFO :: Setting Training Arguments from Quinfig... +|=>> 01/16 [16:49:49] - mistral.args.training - INFO :: Setting Gradient Accumulation Steps = `64` [BSZ: 512 World Size: 1 Device BSZ: 8] +|=>> 01/16 [16:49:50] - mistral - INFO :: Downloading and Preprocessing Dataset `/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py`... +|=>> 01/16 [16:49:51] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Generating examples from = /scratch/ykyao/projects//multilingual-LM/data/multilingual/multilingual_data_perturbed/shuffle_local5_ar/train +|=>> 01/16 [16:49:54] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Total sentences: 1020103 +|=>> 01/16 [16:49:54] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Loading pre-tokenized data +|=>> 01/16 [16:49:58] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Concatenating tokenized data using EOS token +|=>> 01/16 [16:49:58] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Chunking tokens into sublists of 1024 +|=>> 01/16 [16:49:59] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Writing dataset as space-separated sequences of tokens +|=>> 01/16 [16:50:10] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Generating examples from = /scratch/ykyao/projects//multilingual-LM/data/multilingual/multilingual_data_perturbed/shuffle_local5_ar/dev +|=>> 01/16 [16:50:10] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Total sentences: 5082 +|=>> 01/16 [16:50:10] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Loading pre-tokenized data +|=>> 01/16 [16:50:10] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Concatenating tokenized data using EOS token +|=>> 01/16 [16:50:10] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Chunking tokens into sublists of 1024 +|=>> 01/16 [16:50:10] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Writing dataset as space-separated sequences of tokens +|=>> 01/16 [16:50:10] - mistral.corpora.auto - INFO :: Building Tokenized Indexed Dataset for {dataset_id}/{dataset_name}... +|=>> 01/16 [16:50:10] - mistral.corpora.auto - INFO :: Building Indexed Dataset for train +|=>> 01/16 [16:50:36] - mistral.corpora.auto - INFO :: Building Indexed Dataset for validation +|=>> 01/16 [16:50:37] - mistral - INFO :: Initializing Model Trainer... +|=>> 01/16 [16:50:37] - mistral - INFO :: Training Arguments: TrainingArguments( +_n_gpu=1, +adafactor=False, +adam_beta1=0.9, +adam_beta2=0.999, +adam_epsilon=1e-08, +bf16=False, +bf16_full_eval=False, +data_seed=53, +dataloader_drop_last=False, +dataloader_num_workers=0, +dataloader_pin_memory=True, +ddp_bucket_cap_mb=None, +ddp_find_unused_parameters=None, +debug=[], +deepspeed=None, +disable_tqdm=False, +do_eval=True, +do_predict=False, +do_train=True, +eval_accumulation_steps=None, +eval_delay=0, +eval_steps=1000, +evaluation_strategy=IntervalStrategy.STEPS, +fp16=True, +fp16_backend=auto, +fp16_full_eval=False, +fp16_opt_level=O1, +gradient_accumulation_steps=64, +gradient_checkpointing=False, +greater_is_better=None, +group_by_length=False, +half_precision_backend=auto, +hub_model_id=None, +hub_strategy=HubStrategy.EVERY_SAVE, +hub_token=, +ignore_data_skip=False, +label_names=None, +label_smoothing_factor=0.0, +learning_rate=0.0006, +length_column_name=length, +load_best_model_at_end=False, +local_rank=-1, +log_level=-1, +log_level_replica=-1, +log_on_each_node=True, +logging_dir=logs, +logging_first_step=True, +logging_nan_inf_filter=True, +logging_steps=50, +logging_strategy=IntervalStrategy.STEPS, +lr_scheduler_type=SchedulerType.LINEAR, +max_grad_norm=1.0, +max_steps=1200, +metric_for_best_model=None, +mp_parameters=, +no_cuda=False, +num_train_epochs=3.0, +optim=OptimizerNames.ADAMW_HF, +output_dir=//scratch/ykyao/projects/multilingual_models/shuffle_local5_ar_AR_randinit/babylm_shuffle_local5_ar_AR_randinit_seed53/runs/shuffle_local5_ar_AR_randinit_seed53, +overwrite_output_dir=False, +past_index=-1, +per_device_eval_batch_size=16, +per_device_train_batch_size=8, +prediction_loss_only=True, +push_to_hub=False, +push_to_hub_model_id=None, +push_to_hub_organization=None, +push_to_hub_token=, +remove_unused_columns=True, +report_to=[], +resume_from_checkpoint=None, +run_name=shuffle_local5_ar_AR_randinit_seed53, +save_on_each_node=False, +save_steps=1000, +save_strategy=IntervalStrategy.STEPS, +save_total_limit=None, +seed=53, +sharded_ddp=[], +skip_memory_metrics=True, +tf32=None, +tpu_metrics_debug=False, +tpu_num_cores=None, +use_legacy_prediction_loop=False, +warmup_ratio=0.0, +warmup_steps=120, +weight_decay=0.1, +xpu_backend=None, +) +|=>> 01/16 [16:50:47] - mistral.core.callbacks - INFO :: Setting W&B Project: ykyao +|=>> 01/16 [16:51:38] - mistral - INFO :: Training... +|=>> 01/16 [16:51:38] - mistral.core.callbacks - INFO :: Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true" +|=>> 01/16 [21:37:19] - mistral - INFO :: ...and that's all folks! +|=>> 01/16 [21:37:19] - mistral - INFO :: Running final evaluation... diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100755 index 0000000000000000000000000000000000000000..9e26dfeeb6e641a33dae4961196235bdb965b21b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1 @@ +{} \ No newline at end of file diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100755 index 0000000000000000000000000000000000000000..00d0bb84ef853fda188d996b93c143bd905b3674 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1 @@ +{"tokenizer_class": "PassthroughTokenizer"} \ No newline at end of file diff --git a/training_args.bin b/training_args.bin new file mode 100755 index 0000000000000000000000000000000000000000..ed0df62a4ad32162085f3274cb2a1a2df787e9c8 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d79e71e7ebfe0ba7cddd2411de1a7a9f9c5324fb83fad0b27f11cc2ecf78f4d +size 3183