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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-0/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..b039fb55059b7b8c9468845371f9d53852e9c2a6 --- /dev/null +++ b/checkpoint-100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5505a4b19d5c4f5b800c85c3aa6c0b5c93f652dc4732dd2bb88f873e3403344 +size 1080040817 diff --git a/checkpoint-100/pytorch_model.bin b/checkpoint-100/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..80eeb83622a26b03ef406df8c220b88e064dffee --- /dev/null +++ b/checkpoint-100/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:279667bf69f0c5df4983c29c50b5b62572aea0a838920ba7f4d2ca8dc533654d +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..cf0f631785d358eafd8deff505b8f228e2456357 --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..ed0f330dacd4c765ff7665c2645758481b0b9361 --- /dev/null +++ b/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75462a3eceb21aa8bc3cbd67614b4c11194fae50d867e0aa26aab43d6c3ab472 +size 1080041009 diff --git a/checkpoint-1000/pytorch_model.bin b/checkpoint-1000/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..14db2afe8dd2b1ac2a9c19d715523343b5a66d60 --- /dev/null +++ b/checkpoint-1000/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e3bc3c0de8e0d3ca819edcbce175ba12a1e1b5e0ad00d72266e94eb6004b96 +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..b3ba2dbbe380a8873be23af62e2a7a78bded49d0 --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.4789, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.2293, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.0315, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 6.7959, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.4806, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.1992, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 5.9306, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 5.6857, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.4707, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.2778, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.0381, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 4.9558, + "step": 700 + }, + { + "epoch": 28.02, + "learning_rate": 0.00025, + "loss": 4.8301, + "step": 750 + }, + { + "epoch": 30.02, + "learning_rate": 0.00022222222222222218, + "loss": 4.7194, + "step": 800 + }, + { + "epoch": 32.02, + "learning_rate": 0.00019444444444444443, + "loss": 4.623, + "step": 850 + }, + { + "epoch": 34.01, + "learning_rate": 0.00016666666666666666, + "loss": 4.5411, + "step": 900 + }, + { + "epoch": 36.01, + "learning_rate": 0.0001388888888888889, + "loss": 4.4663, + "step": 950 + }, + { + "epoch": 38.01, + "learning_rate": 0.00011111111111111109, + "loss": 4.4012, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_loss": 5.870090961456299, + "eval_runtime": 1.066, + "eval_samples_per_second": 80.673, + "eval_steps_per_second": 5.628, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 5.870090961456299, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 354.281204736473, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 1.066, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 80.673, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..8d6762ed632c6f0ddb7056e8c688c636dbd352cb --- /dev/null +++ b/checkpoint-1100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:534dc7124cc3da50d806058b8fb5ebcdfb0befc4eff4503d2c48b13c7fb2b303 +size 1080041009 diff --git a/checkpoint-1100/pytorch_model.bin b/checkpoint-1100/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..c0578f9b3bcd8445a514aa999765456c9ed9a4d4 --- /dev/null +++ b/checkpoint-1100/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9967c71d56f7ca2f2e0b2746678a211cdbcb5b98aa6f336959b46543325cda1c +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..3a6c7de204add46008eed7648a8b5f6d045d0a77 --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.4789, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.2293, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.0315, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 6.7959, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.4806, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.1992, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 5.9306, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 5.6857, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.4707, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.2778, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.0381, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 4.9558, + "step": 700 + }, + { + "epoch": 28.02, + "learning_rate": 0.00025, + "loss": 4.8301, + "step": 750 + }, + { + "epoch": 30.02, + "learning_rate": 0.00022222222222222218, + "loss": 4.7194, + "step": 800 + }, + { + "epoch": 32.02, + "learning_rate": 0.00019444444444444443, + "loss": 4.623, + "step": 850 + }, + { + "epoch": 34.01, + "learning_rate": 0.00016666666666666666, + "loss": 4.5411, + "step": 900 + }, + { + "epoch": 36.01, + "learning_rate": 0.0001388888888888889, + "loss": 4.4663, + "step": 950 + }, + { + "epoch": 38.01, + "learning_rate": 0.00011111111111111109, + "loss": 4.4012, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_loss": 5.870090961456299, + "eval_runtime": 1.066, + "eval_samples_per_second": 80.673, + "eval_steps_per_second": 5.628, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 5.870090961456299, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 354.281204736473, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 1.066, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 80.673, + "step": 1000 + }, + { + "epoch": 40.01, + "learning_rate": 8.333333333333333e-05, + "loss": 4.3477, + "step": 1050 + }, + { + "epoch": 42.01, + "learning_rate": 5.5555555555555545e-05, + "loss": 4.3023, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-1100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..05b946d18ff87088004954f2ce8dbf64fe67f840 --- /dev/null +++ b/checkpoint-1200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ea8723d37c3c02ce4931e325be9e4b45de66132e9173e7a57b8611fa6bfb24 +size 1080041009 diff --git a/checkpoint-1200/pytorch_model.bin b/checkpoint-1200/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..17c024ca0e094247bb38d452d459d97910925044 --- /dev/null +++ b/checkpoint-1200/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce201bd9ca56e628228455cacae4efbd1418527b3c8281dcc8bebcb391013333 +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..a8ae44af838a19eef50e6c11944b932bdf513daf --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.4789, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.2293, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.0315, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 6.7959, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.4806, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.1992, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 5.9306, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 5.6857, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.4707, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.2778, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.0381, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 4.9558, + "step": 700 + }, + { + "epoch": 28.02, + "learning_rate": 0.00025, + "loss": 4.8301, + "step": 750 + }, + { + "epoch": 30.02, + "learning_rate": 0.00022222222222222218, + "loss": 4.7194, + "step": 800 + }, + { + "epoch": 32.02, + "learning_rate": 0.00019444444444444443, + "loss": 4.623, + "step": 850 + }, + { + "epoch": 34.01, + "learning_rate": 0.00016666666666666666, + "loss": 4.5411, + "step": 900 + }, + { + "epoch": 36.01, + "learning_rate": 0.0001388888888888889, + "loss": 4.4663, + "step": 950 + }, + { + "epoch": 38.01, + "learning_rate": 0.00011111111111111109, + "loss": 4.4012, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_loss": 5.870090961456299, + "eval_runtime": 1.066, + "eval_samples_per_second": 80.673, + "eval_steps_per_second": 5.628, + "step": 1000 + }, + { + "epoch": 38.01, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 5.870090961456299, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 354.281204736473, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 1.066, + "eval_/scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 80.673, + "step": 1000 + }, + { + "epoch": 40.01, + "learning_rate": 8.333333333333333e-05, + "loss": 4.3477, + "step": 1050 + }, + { + "epoch": 42.01, + "learning_rate": 5.5555555555555545e-05, + "loss": 4.3023, + "step": 1100 + }, + { + "epoch": 44.01, + "learning_rate": 2.7777777777777772e-05, + "loss": 4.2672, + "step": 1150 + }, + { + "epoch": 46.0, + "learning_rate": 0.0, + "loss": 4.2432, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-1200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..9f60bb6bac97ec805fa68623d6d722e5a9be17a5 --- /dev/null +++ b/checkpoint-200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90c8f5eae677d13e071785c274c994d0fb22604c8b9d484d6e693e574f0aded2 +size 1080040817 diff --git a/checkpoint-200/pytorch_model.bin b/checkpoint-200/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..1c2d6b95b13223e9989fd5a67b66c3742509e1ad --- /dev/null +++ b/checkpoint-200/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcac2a1338d885e85c0840537838594c422e2bd94b3af21aef965447614dbd09 +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..290ea14dcf5f12af5bc01c8f71507232fbf6f940 --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.4789, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.2293, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..af1626ced55d707ceb7ad049b62ef9b949f6c1b2 --- /dev/null +++ b/checkpoint-300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9f81b320eff4db72db1803a179720044f3eba030fad99ea74ebb4c5fb0ab544 +size 1080041009 diff --git a/checkpoint-300/pytorch_model.bin b/checkpoint-300/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..c6cfba65915f651f1b2db084965473b81fcf55ea --- /dev/null +++ b/checkpoint-300/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d47298b3a02edd05957fd022ee60ea89f7573cf00c3e1aba7d534e404a69d26d +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..92e44b8b3f756c2873e22fe3bca57fd30ac0a093 --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.4789, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.2293, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.0315, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 6.7959, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..2f77835963b2922dc13b2e9d553ae878c59fd9d9 --- /dev/null +++ b/checkpoint-400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35bab04cf32ab5f42395d2b16de5acc13fd0264df45cf829dca4bd3400ccb7b +size 1080041009 diff --git a/checkpoint-400/pytorch_model.bin b/checkpoint-400/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..64eda7bf92c0fcc21ed75cc4707cf797b84a1b1f --- /dev/null +++ b/checkpoint-400/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:618b008328d5e8460f9621eb3bd0fd8d0dc17c9bb79fcf1b447f0e1280bd4053 +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..0857242d7466ddd322cbcdc7d07dc6b2f8d46519 --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.4789, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.2293, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.0315, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 6.7959, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.4806, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.1992, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-400/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..c3dec0814aca7026d8f443e040d0fa2e7a105b7e --- /dev/null +++ b/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f80b0dbb8993c35a6b694da92445935d65da56dd2b961dffc9bf54ec8aa28c13 +size 1080041009 diff --git a/checkpoint-500/pytorch_model.bin b/checkpoint-500/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..aa242c4d3962126f261085f00911c0a2962a7808 --- /dev/null +++ b/checkpoint-500/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49925fd7feef7abf9a09bf31f37d971b8c58f43492cf62368d8942383666b152 +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..a0b4e4f21caa7c275a23885e706d5751c4bad0be --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.4789, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.2293, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.0315, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 6.7959, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.4806, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.1992, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 5.9306, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 5.6857, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..92eb6a1b3040d2ba083f0c92b1e73cf2b798ef03 --- /dev/null +++ b/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dff49e3ce73967a530479ce04155f8118a479ff857da6450132dd367306ff0d5 +size 1080041009 diff --git a/checkpoint-600/pytorch_model.bin b/checkpoint-600/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..7520335c0d6de0a6007ad64119aa83847cde7702 --- /dev/null +++ b/checkpoint-600/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c8903362ef6e6ea3955e1129b5dd10bf9a374e76fe4c8af00a5671f2e443ff +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..501ff78ede910f0c75b9959f78d8f948698e20c7 --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.4789, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.2293, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.0315, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 6.7959, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.4806, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.1992, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 5.9306, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 5.6857, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.4707, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.2778, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..4a48f51506985891cde2148297eb0ba61504b348 --- /dev/null +++ b/checkpoint-700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd2368c856ae05aa5c9a3928e0fab615837a67eaeeef1b6a3cccb2dcc7da77a +size 1080041009 diff --git a/checkpoint-700/pytorch_model.bin b/checkpoint-700/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..3f1082c4630e4b72e3654ae1add1202e5804c9b1 --- /dev/null +++ b/checkpoint-700/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23cc5601dfa8b80337a969370f224032d972e4a9745002a4f23a87af04b7ab90 +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..152a1b432a0e38ff7b90a850f84b0b90dd573b57 --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.4789, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.2293, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.0315, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 6.7959, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.4806, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.1992, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 5.9306, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 5.6857, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.4707, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.2778, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.0381, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 4.9558, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-700/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..9a0929377b2c58dcf11e1084a7318d0c2a0113ae --- /dev/null +++ b/checkpoint-800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a57368d407e6ef08b0370880ce5f9101ecaec3419e68115de870b3e4d7dd03 +size 1080041009 diff --git a/checkpoint-800/pytorch_model.bin b/checkpoint-800/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..5df1389d6500cce242c028c24dee58b06c716f6e --- /dev/null +++ b/checkpoint-800/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e72a120fa63b2ee259066dcadb33c7b456b49f80b2b0ebbd9b048d3d208c2c0 +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..9143e2b0e64b2200d8edcdca1a8e46d766f8a660 --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.4789, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.2293, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.0315, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 6.7959, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.4806, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.1992, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 5.9306, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 5.6857, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.4707, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.2778, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.0381, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 4.9558, + "step": 700 + }, + { + "epoch": 28.02, + "learning_rate": 0.00025, + "loss": 4.8301, + "step": 750 + }, + { + "epoch": 30.02, + "learning_rate": 0.00022222222222222218, + "loss": 4.7194, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-800/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..1bb72ce2bdb0a6be51ccc8299589aad4ca14dac5 --- /dev/null +++ b/checkpoint-900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c7324f528e6035ea7fd4fecbad8cca7ef15a0f86dcc47035116ad8d1ef94e6 +size 1080041009 diff --git a/checkpoint-900/pytorch_model.bin b/checkpoint-900/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..8e2c93c7e2f41ceb6f83a6d3f42b859f31da53db --- /dev/null +++ b/checkpoint-900/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e596319175e5c663e4b527a3c13e1036b7914f2ed2a440032278c179689e9e0e +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..2c00989d8f7a3927dbf384b61870d251bba9d98f --- /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": 11.1241, + "step": 1 + }, + { + "epoch": 1.02, + "learning_rate": 0.00025, + "loss": 8.9384, + "step": 50 + }, + { + "epoch": 3.02, + "learning_rate": 0.0005, + "loss": 7.7211, + "step": 100 + }, + { + "epoch": 5.02, + "learning_rate": 0.0005833333333333333, + "loss": 7.4789, + "step": 150 + }, + { + "epoch": 7.01, + "learning_rate": 0.0005555555555555556, + "loss": 7.2293, + "step": 200 + }, + { + "epoch": 9.01, + "learning_rate": 0.0005277777777777777, + "loss": 7.0315, + "step": 250 + }, + { + "epoch": 11.01, + "learning_rate": 0.0005, + "loss": 6.7959, + "step": 300 + }, + { + "epoch": 13.01, + "learning_rate": 0.00047222222222222224, + "loss": 6.4806, + "step": 350 + }, + { + "epoch": 15.01, + "learning_rate": 0.00044444444444444436, + "loss": 6.1992, + "step": 400 + }, + { + "epoch": 17.01, + "learning_rate": 0.00041666666666666664, + "loss": 5.9306, + "step": 450 + }, + { + "epoch": 19.0, + "learning_rate": 0.00038888888888888887, + "loss": 5.6857, + "step": 500 + }, + { + "epoch": 21.0, + "learning_rate": 0.0003611111111111111, + "loss": 5.4707, + "step": 550 + }, + { + "epoch": 23.0, + "learning_rate": 0.0003333333333333333, + "loss": 5.2778, + "step": 600 + }, + { + "epoch": 24.02, + "learning_rate": 0.00030555555555555555, + "loss": 5.0381, + "step": 650 + }, + { + "epoch": 26.02, + "learning_rate": 0.0002777777777777778, + "loss": 4.9558, + "step": 700 + }, + { + "epoch": 28.02, + "learning_rate": 0.00025, + "loss": 4.8301, + "step": 750 + }, + { + "epoch": 30.02, + "learning_rate": 0.00022222222222222218, + "loss": 4.7194, + "step": 800 + }, + { + "epoch": 32.02, + "learning_rate": 0.00019444444444444443, + "loss": 4.623, + "step": 850 + }, + { + "epoch": 34.01, + "learning_rate": 0.00016666666666666666, + "loss": 4.5411, + "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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/checkpoint-900/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +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..6936060740784448d57a836960091b26298d13e8 --- /dev/null +++ b/metrics.json @@ -0,0 +1,2507 @@ +{"num_parameters": 134994432, "trainable_parameters": 134994432, "step": 0} +{"train_info/time_between_train_steps": 5.341879367828369, "step": 0} +{"info/global_step": 1, "train_info/time_within_train_step": 19.45829725265503, "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": 11.1241, "train/learning_rate": 4.9999999999999996e-06, "train/epoch": 0.0, "_timestamp": 1737042754, "_runtime": 54}, "step": 1} +{"train_info/time_between_train_steps": 0.03318381309509277, "step": 1} +{"info/global_step": 2, "train_info/time_within_train_step": 13.251178741455078, "step": 2} +{"train_info/time_between_train_steps": 0.005741119384765625, "step": 2} +{"info/global_step": 3, "train_info/time_within_train_step": 13.13468313217163, "step": 3} +{"train_info/time_between_train_steps": 0.005771160125732422, "step": 3} +{"info/global_step": 4, "train_info/time_within_train_step": 13.226929664611816, "step": 4} +{"train_info/time_between_train_steps": 0.00556182861328125, "step": 4} +{"info/global_step": 5, "train_info/time_within_train_step": 13.165278196334839, "step": 5} +{"train_info/time_between_train_steps": 0.0053484439849853516, "step": 5} +{"info/global_step": 6, "train_info/time_within_train_step": 13.230660915374756, "step": 6} +{"train_info/time_between_train_steps": 0.005020618438720703, "step": 6} +{"info/global_step": 7, "train_info/time_within_train_step": 13.182565927505493, "step": 7} +{"train_info/time_between_train_steps": 0.005173206329345703, "step": 7} +{"info/global_step": 8, "train_info/time_within_train_step": 13.164694786071777, "step": 8} +{"train_info/time_between_train_steps": 0.005307912826538086, "step": 8} +{"info/global_step": 9, "train_info/time_within_train_step": 13.149897575378418, "step": 9} +{"train_info/time_between_train_steps": 0.005184650421142578, "step": 9} +{"info/global_step": 10, "train_info/time_within_train_step": 13.149449586868286, "step": 10} +{"train_info/time_between_train_steps": 0.00473785400390625, "step": 10} +{"info/global_step": 11, "train_info/time_within_train_step": 13.155911207199097, "step": 11} +{"train_info/time_between_train_steps": 0.004912853240966797, "step": 11} +{"info/global_step": 12, "train_info/time_within_train_step": 13.176504373550415, "step": 12} +{"train_info/time_between_train_steps": 0.005233287811279297, "step": 12} +{"info/global_step": 13, "train_info/time_within_train_step": 13.169615745544434, "step": 13} +{"train_info/time_between_train_steps": 0.004903316497802734, "step": 13} +{"info/global_step": 14, "train_info/time_within_train_step": 13.168374300003052, "step": 14} +{"train_info/time_between_train_steps": 0.0055217742919921875, "step": 14} +{"info/global_step": 15, "train_info/time_within_train_step": 13.154382467269897, "step": 15} +{"train_info/time_between_train_steps": 0.004853487014770508, "step": 15} +{"info/global_step": 16, "train_info/time_within_train_step": 13.24066710472107, "step": 16} +{"train_info/time_between_train_steps": 0.005544185638427734, "step": 16} +{"info/global_step": 17, "train_info/time_within_train_step": 13.163959503173828, "step": 17} +{"train_info/time_between_train_steps": 0.004591464996337891, "step": 17} +{"info/global_step": 18, "train_info/time_within_train_step": 13.167012691497803, "step": 18} +{"train_info/time_between_train_steps": 0.005379915237426758, "step": 18} +{"info/global_step": 19, "train_info/time_within_train_step": 13.144765377044678, "step": 19} +{"train_info/time_between_train_steps": 0.004580020904541016, "step": 19} +{"info/global_step": 20, "train_info/time_within_train_step": 13.150052309036255, "step": 20} +{"train_info/time_between_train_steps": 0.005242586135864258, "step": 20} +{"info/global_step": 21, "train_info/time_within_train_step": 13.172922849655151, "step": 21} +{"train_info/time_between_train_steps": 0.005218982696533203, "step": 21} +{"info/global_step": 22, "train_info/time_within_train_step": 13.202691078186035, "step": 22} +{"train_info/time_between_train_steps": 0.005577564239501953, "step": 22} +{"info/global_step": 23, "train_info/time_within_train_step": 13.164053440093994, "step": 23} +{"train_info/time_between_train_steps": 0.005643129348754883, "step": 23} +{"info/global_step": 24, "train_info/time_within_train_step": 13.166536331176758, "step": 24} +{"train_info/time_between_train_steps": 0.0049266815185546875, "step": 24} +{"info/global_step": 25, "train_info/time_within_train_step": 13.190185308456421, "step": 25} +{"train_info/time_between_train_steps": 0.0055201053619384766, "step": 25} +{"info/global_step": 26, "train_info/time_within_train_step": 13.228798627853394, "step": 26} +{"train_info/time_between_train_steps": 0.006623268127441406, "step": 26} +{"train_info/time_between_train_steps": 10.443885326385498, "step": 26} +{"info/global_step": 27, "train_info/time_within_train_step": 13.145875692367554, "step": 27} +{"train_info/time_between_train_steps": 0.005497932434082031, "step": 27} +{"info/global_step": 28, "train_info/time_within_train_step": 13.224711179733276, "step": 28} +{"train_info/time_between_train_steps": 0.0053255558013916016, "step": 28} +{"info/global_step": 29, "train_info/time_within_train_step": 13.14865779876709, "step": 29} +{"train_info/time_between_train_steps": 0.005165576934814453, "step": 29} +{"info/global_step": 30, "train_info/time_within_train_step": 13.276388883590698, "step": 30} +{"train_info/time_between_train_steps": 0.004735231399536133, "step": 30} +{"info/global_step": 31, "train_info/time_within_train_step": 13.230443477630615, "step": 31} +{"train_info/time_between_train_steps": 0.005327463150024414, "step": 31} +{"info/global_step": 32, "train_info/time_within_train_step": 13.239940881729126, "step": 32} +{"train_info/time_between_train_steps": 0.0055751800537109375, "step": 32} +{"info/global_step": 33, "train_info/time_within_train_step": 13.154338836669922, "step": 33} +{"train_info/time_between_train_steps": 0.005014657974243164, "step": 33} +{"info/global_step": 34, "train_info/time_within_train_step": 13.155276536941528, "step": 34} +{"train_info/time_between_train_steps": 0.004429340362548828, "step": 34} +{"info/global_step": 35, "train_info/time_within_train_step": 13.140561819076538, "step": 35} +{"train_info/time_between_train_steps": 0.004733085632324219, "step": 35} +{"info/global_step": 36, "train_info/time_within_train_step": 13.14109182357788, "step": 36} +{"train_info/time_between_train_steps": 0.004253864288330078, "step": 36} +{"info/global_step": 37, "train_info/time_within_train_step": 13.143969535827637, "step": 37} +{"train_info/time_between_train_steps": 0.004578113555908203, "step": 37} +{"info/global_step": 38, "train_info/time_within_train_step": 13.149361610412598, "step": 38} +{"train_info/time_between_train_steps": 0.00546574592590332, "step": 38} +{"info/global_step": 39, "train_info/time_within_train_step": 13.150169849395752, "step": 39} +{"train_info/time_between_train_steps": 0.00491642951965332, "step": 39} +{"info/global_step": 40, "train_info/time_within_train_step": 13.15387511253357, "step": 40} +{"train_info/time_between_train_steps": 0.004355907440185547, "step": 40} +{"info/global_step": 41, "train_info/time_within_train_step": 13.157954216003418, "step": 41} +{"train_info/time_between_train_steps": 0.0059299468994140625, "step": 41} +{"info/global_step": 42, "train_info/time_within_train_step": 13.159838914871216, "step": 42} +{"train_info/time_between_train_steps": 0.00480341911315918, "step": 42} +{"info/global_step": 43, "train_info/time_within_train_step": 13.17316484451294, "step": 43} +{"train_info/time_between_train_steps": 0.005639553070068359, "step": 43} +{"info/global_step": 44, "train_info/time_within_train_step": 13.151682376861572, "step": 44} +{"train_info/time_between_train_steps": 0.005049228668212891, "step": 44} +{"info/global_step": 45, "train_info/time_within_train_step": 13.149481534957886, "step": 45} +{"train_info/time_between_train_steps": 0.004628419876098633, "step": 45} +{"info/global_step": 46, "train_info/time_within_train_step": 13.154944658279419, "step": 46} +{"train_info/time_between_train_steps": 0.004220008850097656, "step": 46} +{"info/global_step": 47, "train_info/time_within_train_step": 13.602401971817017, "step": 47} +{"train_info/time_between_train_steps": 0.0050466060638427734, "step": 47} +{"info/global_step": 48, "train_info/time_within_train_step": 13.149479150772095, "step": 48} +{"train_info/time_between_train_steps": 0.0051517486572265625, "step": 48} +{"info/global_step": 49, "train_info/time_within_train_step": 13.172647476196289, "step": 49} +{"train_info/time_between_train_steps": 0.005303859710693359, "step": 49} +{"info/global_step": 50, "train_info/time_within_train_step": 13.139248847961426, "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": 1737043412, "_runtime": 712}, "step": 50} +{"logs": {"train/loss": 8.9384, "train/learning_rate": 0.00025, "train/epoch": 1.02, "_timestamp": 1737043412, "_runtime": 712}, "step": 50} +{"train_info/time_between_train_steps": 0.0372769832611084, "step": 50} +{"info/global_step": 51, "train_info/time_within_train_step": 13.639235019683838, "step": 51} +{"train_info/time_between_train_steps": 0.005589723587036133, "step": 51} +{"info/global_step": 52, "train_info/time_within_train_step": 13.17358660697937, "step": 52} +{"train_info/time_between_train_steps": 0.007062435150146484, "step": 52} +{"train_info/time_between_train_steps": 10.633880615234375, "step": 52} +{"info/global_step": 53, "train_info/time_within_train_step": 13.115977048873901, "step": 53} +{"train_info/time_between_train_steps": 0.0053522586822509766, "step": 53} +{"info/global_step": 54, "train_info/time_within_train_step": 13.226666688919067, "step": 54} +{"train_info/time_between_train_steps": 0.005234718322753906, "step": 54} +{"info/global_step": 55, "train_info/time_within_train_step": 13.161663293838501, "step": 55} +{"train_info/time_between_train_steps": 0.0044901371002197266, "step": 55} +{"info/global_step": 56, "train_info/time_within_train_step": 13.231827974319458, "step": 56} +{"train_info/time_between_train_steps": 0.004762172698974609, "step": 56} +{"info/global_step": 57, "train_info/time_within_train_step": 13.139397144317627, "step": 57} +{"train_info/time_between_train_steps": 0.004548072814941406, "step": 57} +{"info/global_step": 58, "train_info/time_within_train_step": 13.204559087753296, "step": 58} +{"train_info/time_between_train_steps": 0.0052874088287353516, "step": 58} +{"info/global_step": 59, "train_info/time_within_train_step": 13.142924785614014, "step": 59} +{"train_info/time_between_train_steps": 0.0055027008056640625, "step": 59} +{"info/global_step": 60, "train_info/time_within_train_step": 13.142596960067749, "step": 60} +{"train_info/time_between_train_steps": 0.005441188812255859, "step": 60} +{"info/global_step": 61, "train_info/time_within_train_step": 13.154754400253296, "step": 61} +{"train_info/time_between_train_steps": 0.0058705806732177734, "step": 61} +{"info/global_step": 62, "train_info/time_within_train_step": 13.225287437438965, "step": 62} +{"train_info/time_between_train_steps": 0.004548072814941406, "step": 62} +{"info/global_step": 63, "train_info/time_within_train_step": 13.140060663223267, "step": 63} +{"train_info/time_between_train_steps": 0.004973411560058594, "step": 63} +{"info/global_step": 64, "train_info/time_within_train_step": 13.140718698501587, "step": 64} +{"train_info/time_between_train_steps": 0.005087375640869141, "step": 64} +{"info/global_step": 65, "train_info/time_within_train_step": 13.154084205627441, "step": 65} +{"train_info/time_between_train_steps": 0.0053043365478515625, "step": 65} +{"info/global_step": 66, "train_info/time_within_train_step": 13.144970417022705, "step": 66} +{"train_info/time_between_train_steps": 0.005654096603393555, "step": 66} +{"info/global_step": 67, "train_info/time_within_train_step": 13.137373685836792, "step": 67} +{"train_info/time_between_train_steps": 0.004864215850830078, "step": 67} +{"info/global_step": 68, "train_info/time_within_train_step": 13.140449285507202, "step": 68} +{"train_info/time_between_train_steps": 0.0053598880767822266, "step": 68} +{"info/global_step": 69, "train_info/time_within_train_step": 13.155285835266113, "step": 69} +{"train_info/time_between_train_steps": 0.0053174495697021484, "step": 69} +{"info/global_step": 70, "train_info/time_within_train_step": 13.155205965042114, "step": 70} +{"train_info/time_between_train_steps": 0.005241870880126953, "step": 70} +{"info/global_step": 71, "train_info/time_within_train_step": 13.15588665008545, "step": 71} +{"train_info/time_between_train_steps": 0.0058743953704833984, "step": 71} +{"info/global_step": 72, "train_info/time_within_train_step": 13.148597240447998, "step": 72} +{"train_info/time_between_train_steps": 0.005464315414428711, "step": 72} +{"info/global_step": 73, "train_info/time_within_train_step": 13.173031568527222, "step": 73} +{"train_info/time_between_train_steps": 0.00494074821472168, "step": 73} +{"info/global_step": 74, "train_info/time_within_train_step": 13.142777919769287, "step": 74} +{"train_info/time_between_train_steps": 0.005063772201538086, "step": 74} +{"info/global_step": 75, "train_info/time_within_train_step": 13.146424531936646, "step": 75} +{"train_info/time_between_train_steps": 0.005224943161010742, "step": 75} +{"info/global_step": 76, "train_info/time_within_train_step": 13.165661334991455, "step": 76} +{"train_info/time_between_train_steps": 0.0055811405181884766, "step": 76} +{"info/global_step": 77, "train_info/time_within_train_step": 13.25723147392273, "step": 77} +{"train_info/time_between_train_steps": 0.005995512008666992, "step": 77} +{"info/global_step": 78, "train_info/time_within_train_step": 13.198075532913208, "step": 78} +{"train_info/time_between_train_steps": 0.006270170211791992, "step": 78} +{"train_info/time_between_train_steps": 10.789329767227173, "step": 78} +{"info/global_step": 79, "train_info/time_within_train_step": 13.15517807006836, "step": 79} +{"train_info/time_between_train_steps": 0.005273580551147461, "step": 79} +{"info/global_step": 80, "train_info/time_within_train_step": 13.25406789779663, "step": 80} +{"train_info/time_between_train_steps": 0.00546717643737793, "step": 80} +{"info/global_step": 81, "train_info/time_within_train_step": 13.176854848861694, "step": 81} +{"train_info/time_between_train_steps": 0.005694389343261719, "step": 81} +{"info/global_step": 82, "train_info/time_within_train_step": 13.27600646018982, "step": 82} +{"train_info/time_between_train_steps": 0.006003141403198242, "step": 82} +{"info/global_step": 83, "train_info/time_within_train_step": 13.177660465240479, "step": 83} +{"train_info/time_between_train_steps": 0.005461931228637695, "step": 83} +{"info/global_step": 84, "train_info/time_within_train_step": 13.23565149307251, "step": 84} +{"train_info/time_between_train_steps": 0.0051991939544677734, "step": 84} +{"info/global_step": 85, "train_info/time_within_train_step": 13.170952796936035, "step": 85} +{"train_info/time_between_train_steps": 0.005400419235229492, "step": 85} +{"info/global_step": 86, "train_info/time_within_train_step": 13.205217361450195, "step": 86} +{"train_info/time_between_train_steps": 0.004975318908691406, "step": 86} +{"info/global_step": 87, "train_info/time_within_train_step": 13.192613363265991, "step": 87} +{"train_info/time_between_train_steps": 0.0055332183837890625, "step": 87} +{"info/global_step": 88, "train_info/time_within_train_step": 13.178386449813843, "step": 88} +{"train_info/time_between_train_steps": 0.004851102828979492, "step": 88} +{"info/global_step": 89, "train_info/time_within_train_step": 13.171348333358765, "step": 89} +{"train_info/time_between_train_steps": 0.004876375198364258, "step": 89} +{"info/global_step": 90, "train_info/time_within_train_step": 13.16497802734375, "step": 90} +{"train_info/time_between_train_steps": 0.005275249481201172, "step": 90} +{"info/global_step": 91, "train_info/time_within_train_step": 13.174830198287964, "step": 91} +{"train_info/time_between_train_steps": 0.004500389099121094, "step": 91} +{"info/global_step": 92, "train_info/time_within_train_step": 13.282190561294556, "step": 92} +{"train_info/time_between_train_steps": 0.005483388900756836, "step": 92} +{"info/global_step": 93, "train_info/time_within_train_step": 13.17972207069397, "step": 93} +{"train_info/time_between_train_steps": 0.006046772003173828, "step": 93} +{"info/global_step": 94, "train_info/time_within_train_step": 13.162866115570068, "step": 94} +{"train_info/time_between_train_steps": 0.005648136138916016, "step": 94} +{"info/global_step": 95, "train_info/time_within_train_step": 13.190877914428711, "step": 95} +{"train_info/time_between_train_steps": 0.004883289337158203, "step": 95} +{"info/global_step": 96, "train_info/time_within_train_step": 13.168467283248901, "step": 96} +{"train_info/time_between_train_steps": 0.004666328430175781, "step": 96} +{"info/global_step": 97, "train_info/time_within_train_step": 13.171911716461182, "step": 97} +{"train_info/time_between_train_steps": 0.0059735774993896484, "step": 97} +{"info/global_step": 98, "train_info/time_within_train_step": 13.175657272338867, "step": 98} +{"train_info/time_between_train_steps": 0.005578517913818359, "step": 98} +{"info/global_step": 99, "train_info/time_within_train_step": 13.194925785064697, "step": 99} +{"train_info/time_between_train_steps": 0.005052804946899414, "step": 99} +{"info/global_step": 100, "train_info/time_within_train_step": 14.008040428161621, "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": 1737044096, "_runtime": 1396}, "step": 100} +{"logs": {"train/loss": 7.7211, "train/learning_rate": 0.0005, "train/epoch": 3.02, "_timestamp": 1737044096, "_runtime": 1396}, "step": 100} +{"train_info/time_between_train_steps": 102.30396866798401, "step": 100} +{"info/global_step": 101, "train_info/time_within_train_step": 13.612802028656006, "step": 101} +{"train_info/time_between_train_steps": 0.004529476165771484, "step": 101} +{"info/global_step": 102, "train_info/time_within_train_step": 13.107136011123657, "step": 102} +{"train_info/time_between_train_steps": 0.005321502685546875, "step": 102} +{"info/global_step": 103, "train_info/time_within_train_step": 13.134393453598022, "step": 103} +{"train_info/time_between_train_steps": 0.005730152130126953, "step": 103} +{"info/global_step": 104, "train_info/time_within_train_step": 13.186828136444092, "step": 104} +{"train_info/time_between_train_steps": 0.006859779357910156, "step": 104} +{"train_info/time_between_train_steps": 10.473132371902466, "step": 104} +{"info/global_step": 105, "train_info/time_within_train_step": 13.146255016326904, "step": 105} +{"train_info/time_between_train_steps": 0.005334615707397461, "step": 105} +{"info/global_step": 106, "train_info/time_within_train_step": 13.238471269607544, "step": 106} +{"train_info/time_between_train_steps": 0.005179405212402344, "step": 106} +{"info/global_step": 107, "train_info/time_within_train_step": 13.247090339660645, "step": 107} +{"train_info/time_between_train_steps": 0.005358219146728516, "step": 107} +{"info/global_step": 108, "train_info/time_within_train_step": 13.300069332122803, "step": 108} +{"train_info/time_between_train_steps": 0.005569934844970703, "step": 108} +{"info/global_step": 109, "train_info/time_within_train_step": 13.213426351547241, "step": 109} +{"train_info/time_between_train_steps": 0.005628347396850586, "step": 109} +{"info/global_step": 110, "train_info/time_within_train_step": 13.268734216690063, "step": 110} +{"train_info/time_between_train_steps": 0.005057096481323242, "step": 110} +{"info/global_step": 111, "train_info/time_within_train_step": 13.177913904190063, "step": 111} +{"train_info/time_between_train_steps": 0.005673646926879883, "step": 111} +{"info/global_step": 112, "train_info/time_within_train_step": 13.18704104423523, "step": 112} +{"train_info/time_between_train_steps": 0.005171537399291992, "step": 112} +{"info/global_step": 113, "train_info/time_within_train_step": 13.186718463897705, "step": 113} +{"train_info/time_between_train_steps": 0.004957437515258789, "step": 113} +{"info/global_step": 114, "train_info/time_within_train_step": 13.229550838470459, "step": 114} +{"train_info/time_between_train_steps": 0.0057904720306396484, "step": 114} +{"info/global_step": 115, "train_info/time_within_train_step": 13.201695442199707, "step": 115} +{"train_info/time_between_train_steps": 0.005713462829589844, "step": 115} +{"info/global_step": 116, "train_info/time_within_train_step": 13.20363163948059, "step": 116} +{"train_info/time_between_train_steps": 0.005321502685546875, "step": 116} +{"info/global_step": 117, "train_info/time_within_train_step": 13.182183504104614, "step": 117} +{"train_info/time_between_train_steps": 0.005034923553466797, "step": 117} +{"info/global_step": 118, "train_info/time_within_train_step": 13.17190670967102, "step": 118} +{"train_info/time_between_train_steps": 0.004599094390869141, "step": 118} +{"info/global_step": 119, "train_info/time_within_train_step": 13.154213190078735, "step": 119} +{"train_info/time_between_train_steps": 0.005497455596923828, "step": 119} +{"info/global_step": 120, "train_info/time_within_train_step": 13.16507339477539, "step": 120} +{"train_info/time_between_train_steps": 0.005223751068115234, "step": 120} +{"info/global_step": 121, "train_info/time_within_train_step": 13.167367935180664, "step": 121} +{"train_info/time_between_train_steps": 0.004881620407104492, "step": 121} +{"info/global_step": 122, "train_info/time_within_train_step": 13.158356189727783, "step": 122} +{"train_info/time_between_train_steps": 0.0051534175872802734, "step": 122} +{"info/global_step": 123, "train_info/time_within_train_step": 13.322464942932129, "step": 123} +{"train_info/time_between_train_steps": 0.005169391632080078, "step": 123} +{"info/global_step": 124, "train_info/time_within_train_step": 13.172906160354614, "step": 124} +{"train_info/time_between_train_steps": 0.005839824676513672, "step": 124} +{"info/global_step": 125, "train_info/time_within_train_step": 13.165107727050781, "step": 125} +{"train_info/time_between_train_steps": 0.005521059036254883, "step": 125} +{"info/global_step": 126, "train_info/time_within_train_step": 13.17240858078003, "step": 126} +{"train_info/time_between_train_steps": 0.005524635314941406, "step": 126} +{"info/global_step": 127, "train_info/time_within_train_step": 13.17240834236145, "step": 127} +{"train_info/time_between_train_steps": 0.004825115203857422, "step": 127} +{"info/global_step": 128, "train_info/time_within_train_step": 13.199567794799805, "step": 128} +{"train_info/time_between_train_steps": 0.005677700042724609, "step": 128} +{"info/global_step": 129, "train_info/time_within_train_step": 13.179513692855835, "step": 129} +{"train_info/time_between_train_steps": 0.0057010650634765625, "step": 129} +{"info/global_step": 130, "train_info/time_within_train_step": 13.206214904785156, "step": 130} +{"train_info/time_between_train_steps": 0.0067119598388671875, "step": 130} +{"train_info/time_between_train_steps": 10.53109359741211, "step": 130} +{"info/global_step": 131, "train_info/time_within_train_step": 13.149013042449951, "step": 131} +{"train_info/time_between_train_steps": 0.005221843719482422, "step": 131} +{"info/global_step": 132, "train_info/time_within_train_step": 13.237837791442871, "step": 132} +{"train_info/time_between_train_steps": 0.005110740661621094, "step": 132} +{"info/global_step": 133, "train_info/time_within_train_step": 13.147470712661743, "step": 133} +{"train_info/time_between_train_steps": 0.005407810211181641, "step": 133} +{"info/global_step": 134, "train_info/time_within_train_step": 13.249233961105347, "step": 134} +{"train_info/time_between_train_steps": 0.005471944808959961, "step": 134} +{"info/global_step": 135, "train_info/time_within_train_step": 13.155221223831177, "step": 135} +{"train_info/time_between_train_steps": 0.0051364898681640625, "step": 135} +{"info/global_step": 136, "train_info/time_within_train_step": 13.23876690864563, "step": 136} +{"train_info/time_between_train_steps": 0.0057413578033447266, "step": 136} +{"info/global_step": 137, "train_info/time_within_train_step": 13.213905572891235, "step": 137} +{"train_info/time_between_train_steps": 0.005399227142333984, "step": 137} +{"info/global_step": 138, "train_info/time_within_train_step": 13.255499124526978, "step": 138} +{"train_info/time_between_train_steps": 0.004842281341552734, "step": 138} +{"info/global_step": 139, "train_info/time_within_train_step": 13.164149284362793, "step": 139} +{"train_info/time_between_train_steps": 0.005404949188232422, "step": 139} +{"info/global_step": 140, "train_info/time_within_train_step": 13.188229322433472, "step": 140} +{"train_info/time_between_train_steps": 0.005221843719482422, "step": 140} +{"info/global_step": 141, "train_info/time_within_train_step": 13.193656921386719, "step": 141} +{"train_info/time_between_train_steps": 0.0053157806396484375, "step": 141} +{"info/global_step": 142, "train_info/time_within_train_step": 13.168282270431519, "step": 142} +{"train_info/time_between_train_steps": 0.005475044250488281, "step": 142} +{"info/global_step": 143, "train_info/time_within_train_step": 13.183357238769531, "step": 143} +{"train_info/time_between_train_steps": 0.00520777702331543, "step": 143} +{"info/global_step": 144, "train_info/time_within_train_step": 13.18157696723938, "step": 144} +{"train_info/time_between_train_steps": 0.004917144775390625, "step": 144} +{"info/global_step": 145, "train_info/time_within_train_step": 13.182385921478271, "step": 145} +{"train_info/time_between_train_steps": 0.005224704742431641, "step": 145} +{"info/global_step": 146, "train_info/time_within_train_step": 14.016170978546143, "step": 146} +{"train_info/time_between_train_steps": 0.0043315887451171875, "step": 146} +{"info/global_step": 147, "train_info/time_within_train_step": 13.198230981826782, "step": 147} +{"train_info/time_between_train_steps": 0.005725383758544922, "step": 147} +{"info/global_step": 148, "train_info/time_within_train_step": 13.204060316085815, "step": 148} +{"train_info/time_between_train_steps": 0.005270481109619141, "step": 148} +{"info/global_step": 149, "train_info/time_within_train_step": 13.190531969070435, "step": 149} +{"train_info/time_between_train_steps": 0.004749774932861328, "step": 149} +{"info/global_step": 150, "train_info/time_within_train_step": 13.221925973892212, "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": 1737044882, "_runtime": 2182}, "step": 150} +{"logs": {"train/loss": 7.4789, "train/learning_rate": 0.0005833333333333333, "train/epoch": 5.02, "_timestamp": 1737044882, "_runtime": 2182}, "step": 150} +{"train_info/time_between_train_steps": 0.07367372512817383, "step": 150} +{"info/global_step": 151, "train_info/time_within_train_step": 13.206240177154541, "step": 151} +{"train_info/time_between_train_steps": 0.004911184310913086, "step": 151} +{"info/global_step": 152, "train_info/time_within_train_step": 13.200863122940063, "step": 152} +{"train_info/time_between_train_steps": 0.005734443664550781, "step": 152} +{"info/global_step": 153, "train_info/time_within_train_step": 13.200594663619995, "step": 153} +{"train_info/time_between_train_steps": 0.006202220916748047, "step": 153} +{"info/global_step": 154, "train_info/time_within_train_step": 13.344383478164673, "step": 154} +{"train_info/time_between_train_steps": 0.005491733551025391, "step": 154} +{"info/global_step": 155, "train_info/time_within_train_step": 13.23395848274231, "step": 155} +{"train_info/time_between_train_steps": 0.0054852962493896484, "step": 155} +{"info/global_step": 156, "train_info/time_within_train_step": 13.230495929718018, "step": 156} +{"train_info/time_between_train_steps": 0.006577968597412109, "step": 156} +{"train_info/time_between_train_steps": 10.724770307540894, "step": 156} +{"info/global_step": 157, "train_info/time_within_train_step": 13.15213131904602, "step": 157} +{"train_info/time_between_train_steps": 0.005167245864868164, "step": 157} +{"info/global_step": 158, "train_info/time_within_train_step": 13.301049709320068, "step": 158} +{"train_info/time_between_train_steps": 0.005499124526977539, "step": 158} +{"info/global_step": 159, "train_info/time_within_train_step": 13.187465190887451, "step": 159} +{"train_info/time_between_train_steps": 0.004827260971069336, "step": 159} +{"info/global_step": 160, "train_info/time_within_train_step": 13.27657175064087, "step": 160} +{"train_info/time_between_train_steps": 0.0054094791412353516, "step": 160} +{"info/global_step": 161, "train_info/time_within_train_step": 13.189010381698608, "step": 161} +{"train_info/time_between_train_steps": 0.005040884017944336, "step": 161} +{"info/global_step": 162, "train_info/time_within_train_step": 13.267073392868042, "step": 162} +{"train_info/time_between_train_steps": 0.005242347717285156, "step": 162} +{"info/global_step": 163, "train_info/time_within_train_step": 13.191401720046997, "step": 163} +{"train_info/time_between_train_steps": 0.004948139190673828, "step": 163} +{"info/global_step": 164, "train_info/time_within_train_step": 13.19527816772461, "step": 164} +{"train_info/time_between_train_steps": 0.0054476261138916016, "step": 164} +{"info/global_step": 165, "train_info/time_within_train_step": 13.186331033706665, "step": 165} +{"train_info/time_between_train_steps": 0.005594730377197266, "step": 165} +{"info/global_step": 166, "train_info/time_within_train_step": 13.1845383644104, "step": 166} +{"train_info/time_between_train_steps": 0.00532841682434082, "step": 166} +{"info/global_step": 167, "train_info/time_within_train_step": 13.18002986907959, "step": 167} +{"train_info/time_between_train_steps": 0.005265235900878906, "step": 167} +{"info/global_step": 168, "train_info/time_within_train_step": 13.214762926101685, "step": 168} +{"train_info/time_between_train_steps": 0.005212068557739258, "step": 168} +{"info/global_step": 169, "train_info/time_within_train_step": 13.272509813308716, "step": 169} +{"train_info/time_between_train_steps": 0.005418062210083008, "step": 169} +{"info/global_step": 170, "train_info/time_within_train_step": 13.188992500305176, "step": 170} +{"train_info/time_between_train_steps": 0.005531787872314453, "step": 170} +{"info/global_step": 171, "train_info/time_within_train_step": 13.180029392242432, "step": 171} +{"train_info/time_between_train_steps": 0.004845857620239258, "step": 171} +{"info/global_step": 172, "train_info/time_within_train_step": 13.18452787399292, "step": 172} +{"train_info/time_between_train_steps": 0.005185127258300781, "step": 172} +{"info/global_step": 173, "train_info/time_within_train_step": 13.188037395477295, "step": 173} +{"train_info/time_between_train_steps": 0.005201578140258789, "step": 173} +{"info/global_step": 174, "train_info/time_within_train_step": 13.164374113082886, "step": 174} +{"train_info/time_between_train_steps": 0.004591226577758789, "step": 174} +{"info/global_step": 175, "train_info/time_within_train_step": 13.163927793502808, "step": 175} +{"train_info/time_between_train_steps": 0.0056416988372802734, "step": 175} +{"info/global_step": 176, "train_info/time_within_train_step": 13.171661615371704, "step": 176} +{"train_info/time_between_train_steps": 0.005750417709350586, "step": 176} +{"info/global_step": 177, "train_info/time_within_train_step": 13.219597578048706, "step": 177} +{"train_info/time_between_train_steps": 0.005074024200439453, "step": 177} +{"info/global_step": 178, "train_info/time_within_train_step": 13.190776109695435, "step": 178} +{"train_info/time_between_train_steps": 0.005095243453979492, "step": 178} +{"info/global_step": 179, "train_info/time_within_train_step": 13.169349431991577, "step": 179} +{"train_info/time_between_train_steps": 0.004805088043212891, "step": 179} +{"info/global_step": 180, "train_info/time_within_train_step": 13.213438749313354, "step": 180} +{"train_info/time_between_train_steps": 0.005012035369873047, "step": 180} +{"info/global_step": 181, "train_info/time_within_train_step": 13.190218210220337, "step": 181} +{"train_info/time_between_train_steps": 0.00518798828125, "step": 181} +{"info/global_step": 182, "train_info/time_within_train_step": 13.210811138153076, "step": 182} +{"train_info/time_between_train_steps": 0.006075382232666016, "step": 182} +{"train_info/time_between_train_steps": 10.502286434173584, "step": 182} +{"info/global_step": 183, "train_info/time_within_train_step": 13.151325702667236, "step": 183} +{"train_info/time_between_train_steps": 0.004762411117553711, "step": 183} +{"info/global_step": 184, "train_info/time_within_train_step": 13.325183153152466, "step": 184} +{"train_info/time_between_train_steps": 0.005093097686767578, "step": 184} +{"info/global_step": 185, "train_info/time_within_train_step": 13.181628704071045, "step": 185} +{"train_info/time_between_train_steps": 0.0049479007720947266, "step": 185} +{"info/global_step": 186, "train_info/time_within_train_step": 13.280274391174316, "step": 186} +{"train_info/time_between_train_steps": 0.005083560943603516, "step": 186} +{"info/global_step": 187, "train_info/time_within_train_step": 13.170092344284058, "step": 187} +{"train_info/time_between_train_steps": 0.004899263381958008, "step": 187} +{"info/global_step": 188, "train_info/time_within_train_step": 13.250261545181274, "step": 188} +{"train_info/time_between_train_steps": 0.005486249923706055, "step": 188} +{"info/global_step": 189, "train_info/time_within_train_step": 13.215984106063843, "step": 189} +{"train_info/time_between_train_steps": 0.005630970001220703, "step": 189} +{"info/global_step": 190, "train_info/time_within_train_step": 13.207940101623535, "step": 190} +{"train_info/time_between_train_steps": 0.0054836273193359375, "step": 190} +{"info/global_step": 191, "train_info/time_within_train_step": 13.162707567214966, "step": 191} +{"train_info/time_between_train_steps": 0.004604339599609375, "step": 191} +{"info/global_step": 192, "train_info/time_within_train_step": 13.17397665977478, "step": 192} +{"train_info/time_between_train_steps": 0.004971504211425781, "step": 192} +{"info/global_step": 193, "train_info/time_within_train_step": 13.174968957901001, "step": 193} +{"train_info/time_between_train_steps": 0.004608154296875, "step": 193} +{"info/global_step": 194, "train_info/time_within_train_step": 13.166954040527344, "step": 194} +{"train_info/time_between_train_steps": 0.005186796188354492, "step": 194} +{"info/global_step": 195, "train_info/time_within_train_step": 13.16922926902771, "step": 195} +{"train_info/time_between_train_steps": 0.004891395568847656, "step": 195} +{"info/global_step": 196, "train_info/time_within_train_step": 13.171241998672485, "step": 196} +{"train_info/time_between_train_steps": 0.004876613616943359, "step": 196} +{"info/global_step": 197, "train_info/time_within_train_step": 13.169708967208862, "step": 197} +{"train_info/time_between_train_steps": 0.00487518310546875, "step": 197} +{"info/global_step": 198, "train_info/time_within_train_step": 14.955979824066162, "step": 198} +{"train_info/time_between_train_steps": 0.004766702651977539, "step": 198} +{"info/global_step": 199, "train_info/time_within_train_step": 13.35268783569336, "step": 199} +{"train_info/time_between_train_steps": 0.004968881607055664, "step": 199} +{"info/global_step": 200, "train_info/time_within_train_step": 13.34104299545288, "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": 1737045570, "_runtime": 2870}, "step": 200} +{"logs": {"train/loss": 7.2293, "train/learning_rate": 0.0005555555555555556, "train/epoch": 7.01, "_timestamp": 1737045570, "_runtime": 2870}, "step": 200} +{"train_info/time_between_train_steps": 126.62124872207642, "step": 200} +{"info/global_step": 201, "train_info/time_within_train_step": 13.118942499160767, "step": 201} +{"train_info/time_between_train_steps": 0.005221128463745117, "step": 201} +{"info/global_step": 202, "train_info/time_within_train_step": 13.118221521377563, "step": 202} +{"train_info/time_between_train_steps": 0.005968809127807617, "step": 202} +{"info/global_step": 203, "train_info/time_within_train_step": 13.1189546585083, "step": 203} +{"train_info/time_between_train_steps": 0.004874706268310547, "step": 203} +{"info/global_step": 204, "train_info/time_within_train_step": 13.12179946899414, "step": 204} +{"train_info/time_between_train_steps": 0.005143880844116211, "step": 204} +{"info/global_step": 205, "train_info/time_within_train_step": 13.143195390701294, "step": 205} +{"train_info/time_between_train_steps": 0.005477428436279297, "step": 205} +{"info/global_step": 206, "train_info/time_within_train_step": 13.156586647033691, "step": 206} +{"train_info/time_between_train_steps": 0.0045468807220458984, "step": 206} +{"info/global_step": 207, "train_info/time_within_train_step": 13.168870210647583, "step": 207} +{"train_info/time_between_train_steps": 0.00580906867980957, "step": 207} +{"info/global_step": 208, "train_info/time_within_train_step": 13.191502332687378, "step": 208} +{"train_info/time_between_train_steps": 0.007073163986206055, "step": 208} +{"train_info/time_between_train_steps": 10.59921932220459, "step": 208} +{"info/global_step": 209, "train_info/time_within_train_step": 13.145378828048706, "step": 209} +{"train_info/time_between_train_steps": 0.0047760009765625, "step": 209} +{"info/global_step": 210, "train_info/time_within_train_step": 13.251683950424194, "step": 210} +{"train_info/time_between_train_steps": 0.005067586898803711, "step": 210} +{"info/global_step": 211, "train_info/time_within_train_step": 13.1675386428833, "step": 211} +{"train_info/time_between_train_steps": 0.0048863887786865234, "step": 211} +{"info/global_step": 212, "train_info/time_within_train_step": 13.281428813934326, "step": 212} +{"train_info/time_between_train_steps": 0.005448102951049805, "step": 212} +{"info/global_step": 213, "train_info/time_within_train_step": 13.173228025436401, "step": 213} +{"train_info/time_between_train_steps": 0.005419015884399414, "step": 213} +{"info/global_step": 214, "train_info/time_within_train_step": 13.322289943695068, "step": 214} +{"train_info/time_between_train_steps": 0.005179643630981445, "step": 214} +{"info/global_step": 215, "train_info/time_within_train_step": 13.170326471328735, "step": 215} +{"train_info/time_between_train_steps": 0.004679679870605469, "step": 215} +{"info/global_step": 216, "train_info/time_within_train_step": 13.167048215866089, "step": 216} +{"train_info/time_between_train_steps": 0.00521087646484375, "step": 216} +{"info/global_step": 217, "train_info/time_within_train_step": 13.167203187942505, "step": 217} +{"train_info/time_between_train_steps": 0.005279541015625, "step": 217} +{"info/global_step": 218, "train_info/time_within_train_step": 13.19097352027893, "step": 218} +{"train_info/time_between_train_steps": 0.005417346954345703, "step": 218} +{"info/global_step": 219, "train_info/time_within_train_step": 13.193729400634766, "step": 219} +{"train_info/time_between_train_steps": 0.0057141780853271484, "step": 219} +{"info/global_step": 220, "train_info/time_within_train_step": 13.170083999633789, "step": 220} +{"train_info/time_between_train_steps": 0.005083560943603516, "step": 220} +{"info/global_step": 221, "train_info/time_within_train_step": 13.182377338409424, "step": 221} +{"train_info/time_between_train_steps": 0.004842281341552734, "step": 221} +{"info/global_step": 222, "train_info/time_within_train_step": 13.173654079437256, "step": 222} +{"train_info/time_between_train_steps": 0.004940509796142578, "step": 222} +{"info/global_step": 223, "train_info/time_within_train_step": 13.185223817825317, "step": 223} +{"train_info/time_between_train_steps": 0.005337715148925781, "step": 223} +{"info/global_step": 224, "train_info/time_within_train_step": 13.209046363830566, "step": 224} +{"train_info/time_between_train_steps": 0.005442142486572266, "step": 224} +{"info/global_step": 225, "train_info/time_within_train_step": 13.183447360992432, "step": 225} +{"train_info/time_between_train_steps": 0.00526881217956543, "step": 225} +{"info/global_step": 226, "train_info/time_within_train_step": 13.188159704208374, "step": 226} +{"train_info/time_between_train_steps": 0.0052547454833984375, "step": 226} +{"info/global_step": 227, "train_info/time_within_train_step": 13.197381973266602, "step": 227} +{"train_info/time_between_train_steps": 0.005263566970825195, "step": 227} +{"info/global_step": 228, "train_info/time_within_train_step": 13.203139066696167, "step": 228} +{"train_info/time_between_train_steps": 0.005160331726074219, "step": 228} +{"info/global_step": 229, "train_info/time_within_train_step": 13.182689666748047, "step": 229} +{"train_info/time_between_train_steps": 0.004694223403930664, "step": 229} +{"info/global_step": 230, "train_info/time_within_train_step": 13.2624831199646, "step": 230} +{"train_info/time_between_train_steps": 0.005120277404785156, "step": 230} +{"info/global_step": 231, "train_info/time_within_train_step": 13.181472301483154, "step": 231} +{"train_info/time_between_train_steps": 0.0052530765533447266, "step": 231} +{"info/global_step": 232, "train_info/time_within_train_step": 13.197490692138672, "step": 232} +{"train_info/time_between_train_steps": 0.005043983459472656, "step": 232} +{"info/global_step": 233, "train_info/time_within_train_step": 13.211306095123291, "step": 233} +{"train_info/time_between_train_steps": 0.005498647689819336, "step": 233} +{"info/global_step": 234, "train_info/time_within_train_step": 13.211904048919678, "step": 234} +{"train_info/time_between_train_steps": 0.006656169891357422, "step": 234} +{"train_info/time_between_train_steps": 10.683427095413208, "step": 234} +{"info/global_step": 235, "train_info/time_within_train_step": 13.151704788208008, "step": 235} +{"train_info/time_between_train_steps": 0.004960060119628906, "step": 235} +{"info/global_step": 236, "train_info/time_within_train_step": 13.251070499420166, "step": 236} +{"train_info/time_between_train_steps": 0.0049479007720947266, "step": 236} +{"info/global_step": 237, "train_info/time_within_train_step": 13.184623956680298, "step": 237} +{"train_info/time_between_train_steps": 0.005075216293334961, "step": 237} +{"info/global_step": 238, "train_info/time_within_train_step": 13.264856576919556, "step": 238} +{"train_info/time_between_train_steps": 0.004537343978881836, "step": 238} +{"info/global_step": 239, "train_info/time_within_train_step": 13.172405004501343, "step": 239} +{"train_info/time_between_train_steps": 0.0055387020111083984, "step": 239} +{"info/global_step": 240, "train_info/time_within_train_step": 13.258202314376831, "step": 240} +{"train_info/time_between_train_steps": 0.005341529846191406, "step": 240} +{"info/global_step": 241, "train_info/time_within_train_step": 13.20478630065918, "step": 241} +{"train_info/time_between_train_steps": 0.005588531494140625, "step": 241} +{"info/global_step": 242, "train_info/time_within_train_step": 13.20316195487976, "step": 242} +{"train_info/time_between_train_steps": 0.00538325309753418, "step": 242} +{"info/global_step": 243, "train_info/time_within_train_step": 13.190052270889282, "step": 243} +{"train_info/time_between_train_steps": 0.004717588424682617, "step": 243} +{"info/global_step": 244, "train_info/time_within_train_step": 13.203449487686157, "step": 244} +{"train_info/time_between_train_steps": 0.005126953125, "step": 244} +{"info/global_step": 245, "train_info/time_within_train_step": 13.276018857955933, "step": 245} +{"train_info/time_between_train_steps": 0.005391359329223633, "step": 245} +{"info/global_step": 246, "train_info/time_within_train_step": 13.202434539794922, "step": 246} +{"train_info/time_between_train_steps": 0.005336761474609375, "step": 246} +{"info/global_step": 247, "train_info/time_within_train_step": 13.200677633285522, "step": 247} +{"train_info/time_between_train_steps": 0.005172014236450195, "step": 247} +{"info/global_step": 248, "train_info/time_within_train_step": 13.197160005569458, "step": 248} +{"train_info/time_between_train_steps": 0.004851818084716797, "step": 248} +{"info/global_step": 249, "train_info/time_within_train_step": 13.195126295089722, "step": 249} +{"train_info/time_between_train_steps": 0.005462646484375, "step": 249} +{"info/global_step": 250, "train_info/time_within_train_step": 13.194596767425537, "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": 1737046379, "_runtime": 3679}, "step": 250} +{"logs": {"train/loss": 7.0315, "train/learning_rate": 0.0005277777777777777, "train/epoch": 9.01, "_timestamp": 1737046379, "_runtime": 3679}, "step": 250} +{"train_info/time_between_train_steps": 0.04591059684753418, "step": 250} +{"info/global_step": 251, "train_info/time_within_train_step": 13.212579727172852, "step": 251} +{"train_info/time_between_train_steps": 0.00540614128112793, "step": 251} +{"info/global_step": 252, "train_info/time_within_train_step": 13.246488094329834, "step": 252} +{"train_info/time_between_train_steps": 0.0048182010650634766, "step": 252} +{"info/global_step": 253, "train_info/time_within_train_step": 13.215626239776611, "step": 253} +{"train_info/time_between_train_steps": 0.004931926727294922, "step": 253} +{"info/global_step": 254, "train_info/time_within_train_step": 13.221699237823486, "step": 254} +{"train_info/time_between_train_steps": 0.005394697189331055, "step": 254} +{"info/global_step": 255, "train_info/time_within_train_step": 13.220921993255615, "step": 255} +{"train_info/time_between_train_steps": 0.004873752593994141, "step": 255} +{"info/global_step": 256, "train_info/time_within_train_step": 13.218382596969604, "step": 256} +{"train_info/time_between_train_steps": 0.004764080047607422, "step": 256} +{"info/global_step": 257, "train_info/time_within_train_step": 13.220838785171509, "step": 257} +{"train_info/time_between_train_steps": 0.005323648452758789, "step": 257} +{"info/global_step": 258, "train_info/time_within_train_step": 13.22702407836914, "step": 258} +{"train_info/time_between_train_steps": 0.005437135696411133, "step": 258} +{"info/global_step": 259, "train_info/time_within_train_step": 13.256287813186646, "step": 259} +{"train_info/time_between_train_steps": 0.005283832550048828, "step": 259} +{"info/global_step": 260, "train_info/time_within_train_step": 13.343439102172852, "step": 260} +{"train_info/time_between_train_steps": 0.006906986236572266, "step": 260} +{"train_info/time_between_train_steps": 10.511431455612183, "step": 260} +{"info/global_step": 261, "train_info/time_within_train_step": 13.194283485412598, "step": 261} +{"train_info/time_between_train_steps": 0.005501747131347656, "step": 261} +{"info/global_step": 262, "train_info/time_within_train_step": 13.318530559539795, "step": 262} +{"train_info/time_between_train_steps": 0.005057573318481445, "step": 262} +{"info/global_step": 263, "train_info/time_within_train_step": 13.23302435874939, "step": 263} +{"train_info/time_between_train_steps": 0.0047948360443115234, "step": 263} +{"info/global_step": 264, "train_info/time_within_train_step": 13.304540872573853, "step": 264} +{"train_info/time_between_train_steps": 0.005545377731323242, "step": 264} +{"info/global_step": 265, "train_info/time_within_train_step": 13.204633235931396, "step": 265} +{"train_info/time_between_train_steps": 0.00567626953125, "step": 265} +{"info/global_step": 266, "train_info/time_within_train_step": 13.281201124191284, "step": 266} +{"train_info/time_between_train_steps": 0.005368947982788086, "step": 266} +{"info/global_step": 267, "train_info/time_within_train_step": 13.21626591682434, "step": 267} +{"train_info/time_between_train_steps": 0.0048694610595703125, "step": 267} +{"info/global_step": 268, "train_info/time_within_train_step": 13.242326021194458, "step": 268} +{"train_info/time_between_train_steps": 0.00537109375, "step": 268} +{"info/global_step": 269, "train_info/time_within_train_step": 13.211263656616211, "step": 269} +{"train_info/time_between_train_steps": 0.00543975830078125, "step": 269} +{"info/global_step": 270, "train_info/time_within_train_step": 13.197665929794312, "step": 270} +{"train_info/time_between_train_steps": 0.005471706390380859, "step": 270} +{"info/global_step": 271, "train_info/time_within_train_step": 13.226282119750977, "step": 271} +{"train_info/time_between_train_steps": 0.005661487579345703, "step": 271} +{"info/global_step": 272, "train_info/time_within_train_step": 13.245078325271606, "step": 272} +{"train_info/time_between_train_steps": 0.005262613296508789, "step": 272} +{"info/global_step": 273, "train_info/time_within_train_step": 13.21152949333191, "step": 273} +{"train_info/time_between_train_steps": 0.006094455718994141, "step": 273} +{"info/global_step": 274, "train_info/time_within_train_step": 13.220302104949951, "step": 274} +{"train_info/time_between_train_steps": 0.004966259002685547, "step": 274} +{"info/global_step": 275, "train_info/time_within_train_step": 13.280761480331421, "step": 275} +{"train_info/time_between_train_steps": 0.00557255744934082, "step": 275} +{"info/global_step": 276, "train_info/time_within_train_step": 13.208810091018677, "step": 276} +{"train_info/time_between_train_steps": 0.0052661895751953125, "step": 276} +{"info/global_step": 277, "train_info/time_within_train_step": 13.20137357711792, "step": 277} +{"train_info/time_between_train_steps": 0.0055389404296875, "step": 277} +{"info/global_step": 278, "train_info/time_within_train_step": 13.2132568359375, "step": 278} +{"train_info/time_between_train_steps": 0.005178689956665039, "step": 278} +{"info/global_step": 279, "train_info/time_within_train_step": 13.206421613693237, "step": 279} +{"train_info/time_between_train_steps": 0.005364179611206055, "step": 279} +{"info/global_step": 280, "train_info/time_within_train_step": 13.20565128326416, "step": 280} +{"train_info/time_between_train_steps": 0.005413055419921875, "step": 280} +{"info/global_step": 281, "train_info/time_within_train_step": 13.214682817459106, "step": 281} +{"train_info/time_between_train_steps": 0.004945039749145508, "step": 281} +{"info/global_step": 282, "train_info/time_within_train_step": 13.209569931030273, "step": 282} +{"train_info/time_between_train_steps": 0.00576019287109375, "step": 282} +{"info/global_step": 283, "train_info/time_within_train_step": 13.215743780136108, "step": 283} +{"train_info/time_between_train_steps": 0.0058748722076416016, "step": 283} +{"info/global_step": 284, "train_info/time_within_train_step": 13.213992834091187, "step": 284} +{"train_info/time_between_train_steps": 0.005837440490722656, "step": 284} +{"info/global_step": 285, "train_info/time_within_train_step": 13.223006963729858, "step": 285} +{"train_info/time_between_train_steps": 0.006253719329833984, "step": 285} +{"info/global_step": 286, "train_info/time_within_train_step": 13.235671520233154, "step": 286} +{"train_info/time_between_train_steps": 0.006927013397216797, "step": 286} +{"train_info/time_between_train_steps": 10.639873743057251, "step": 286} +{"info/global_step": 287, "train_info/time_within_train_step": 13.18979001045227, "step": 287} +{"train_info/time_between_train_steps": 0.004523515701293945, "step": 287} +{"info/global_step": 288, "train_info/time_within_train_step": 13.343852281570435, "step": 288} +{"train_info/time_between_train_steps": 0.004691600799560547, "step": 288} +{"info/global_step": 289, "train_info/time_within_train_step": 13.218882083892822, "step": 289} +{"train_info/time_between_train_steps": 0.0051326751708984375, "step": 289} +{"info/global_step": 290, "train_info/time_within_train_step": 13.399099349975586, "step": 290} +{"train_info/time_between_train_steps": 0.0059697628021240234, "step": 290} +{"info/global_step": 291, "train_info/time_within_train_step": 13.210557699203491, "step": 291} +{"train_info/time_between_train_steps": 0.005719423294067383, "step": 291} +{"info/global_step": 292, "train_info/time_within_train_step": 13.26978850364685, "step": 292} +{"train_info/time_between_train_steps": 0.005449771881103516, "step": 292} +{"info/global_step": 293, "train_info/time_within_train_step": 13.206105709075928, "step": 293} +{"train_info/time_between_train_steps": 0.004879474639892578, "step": 293} +{"info/global_step": 294, "train_info/time_within_train_step": 13.261883735656738, "step": 294} +{"train_info/time_between_train_steps": 0.005182981491088867, "step": 294} +{"info/global_step": 295, "train_info/time_within_train_step": 13.209128379821777, "step": 295} +{"train_info/time_between_train_steps": 0.005506992340087891, "step": 295} +{"info/global_step": 296, "train_info/time_within_train_step": 13.214346885681152, "step": 296} +{"train_info/time_between_train_steps": 0.004593372344970703, "step": 296} +{"info/global_step": 297, "train_info/time_within_train_step": 13.218366384506226, "step": 297} +{"train_info/time_between_train_steps": 0.005750417709350586, "step": 297} +{"info/global_step": 298, "train_info/time_within_train_step": 13.231994152069092, "step": 298} +{"train_info/time_between_train_steps": 0.0050067901611328125, "step": 298} +{"info/global_step": 299, "train_info/time_within_train_step": 13.237412929534912, "step": 299} +{"train_info/time_between_train_steps": 0.0051000118255615234, "step": 299} +{"info/global_step": 300, "train_info/time_within_train_step": 13.21874475479126, "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": 1737047065, "_runtime": 4365}, "step": 300} +{"logs": {"train/loss": 6.7959, "train/learning_rate": 0.0005, "train/epoch": 11.01, "_timestamp": 1737047065, "_runtime": 4365}, "step": 300} +{"train_info/time_between_train_steps": 75.99965643882751, "step": 300} +{"info/global_step": 301, "train_info/time_within_train_step": 13.280826330184937, "step": 301} +{"train_info/time_between_train_steps": 0.005418539047241211, "step": 301} +{"info/global_step": 302, "train_info/time_within_train_step": 13.142935514450073, "step": 302} +{"train_info/time_between_train_steps": 0.005593061447143555, "step": 302} +{"info/global_step": 303, "train_info/time_within_train_step": 13.137717008590698, "step": 303} +{"train_info/time_between_train_steps": 0.005475282669067383, "step": 303} +{"info/global_step": 304, "train_info/time_within_train_step": 13.16100263595581, "step": 304} +{"train_info/time_between_train_steps": 0.004978656768798828, "step": 304} +{"info/global_step": 305, "train_info/time_within_train_step": 13.164177179336548, "step": 305} +{"train_info/time_between_train_steps": 0.005308866500854492, "step": 305} +{"info/global_step": 306, "train_info/time_within_train_step": 13.280867338180542, "step": 306} +{"train_info/time_between_train_steps": 0.005261659622192383, "step": 306} +{"info/global_step": 307, "train_info/time_within_train_step": 13.209574460983276, "step": 307} +{"train_info/time_between_train_steps": 0.004987955093383789, "step": 307} +{"info/global_step": 308, "train_info/time_within_train_step": 13.192729949951172, "step": 308} +{"train_info/time_between_train_steps": 0.005460262298583984, "step": 308} +{"info/global_step": 309, "train_info/time_within_train_step": 13.223013162612915, "step": 309} +{"train_info/time_between_train_steps": 0.005537271499633789, "step": 309} +{"info/global_step": 310, "train_info/time_within_train_step": 13.198887586593628, "step": 310} +{"train_info/time_between_train_steps": 0.005018711090087891, "step": 310} +{"info/global_step": 311, "train_info/time_within_train_step": 13.197038650512695, "step": 311} +{"train_info/time_between_train_steps": 0.0058078765869140625, "step": 311} +{"info/global_step": 312, "train_info/time_within_train_step": 13.19384765625, "step": 312} +{"train_info/time_between_train_steps": 0.006448030471801758, "step": 312} +{"train_info/time_between_train_steps": 10.66129207611084, "step": 312} +{"info/global_step": 313, "train_info/time_within_train_step": 13.14919900894165, "step": 313} +{"train_info/time_between_train_steps": 0.005263566970825195, "step": 313} +{"info/global_step": 314, "train_info/time_within_train_step": 13.258125066757202, "step": 314} +{"train_info/time_between_train_steps": 0.004654407501220703, "step": 314} +{"info/global_step": 315, "train_info/time_within_train_step": 13.18938684463501, "step": 315} +{"train_info/time_between_train_steps": 0.005466938018798828, "step": 315} +{"info/global_step": 316, "train_info/time_within_train_step": 13.297045230865479, "step": 316} +{"train_info/time_between_train_steps": 0.005214691162109375, "step": 316} +{"info/global_step": 317, "train_info/time_within_train_step": 13.175672769546509, "step": 317} +{"train_info/time_between_train_steps": 0.005666255950927734, "step": 317} +{"info/global_step": 318, "train_info/time_within_train_step": 13.23245120048523, "step": 318} +{"train_info/time_between_train_steps": 0.005465269088745117, "step": 318} +{"info/global_step": 319, "train_info/time_within_train_step": 13.201006174087524, "step": 319} +{"train_info/time_between_train_steps": 0.005663156509399414, "step": 319} +{"info/global_step": 320, "train_info/time_within_train_step": 13.178839683532715, "step": 320} +{"train_info/time_between_train_steps": 0.004494905471801758, "step": 320} +{"info/global_step": 321, "train_info/time_within_train_step": 13.238647222518921, "step": 321} +{"train_info/time_between_train_steps": 0.005426645278930664, "step": 321} +{"info/global_step": 322, "train_info/time_within_train_step": 13.179461479187012, "step": 322} +{"train_info/time_between_train_steps": 0.004864215850830078, "step": 322} +{"info/global_step": 323, "train_info/time_within_train_step": 13.18217921257019, "step": 323} +{"train_info/time_between_train_steps": 0.004540443420410156, "step": 323} +{"info/global_step": 324, "train_info/time_within_train_step": 13.179019927978516, "step": 324} +{"train_info/time_between_train_steps": 0.0055730342864990234, "step": 324} +{"info/global_step": 325, "train_info/time_within_train_step": 13.204355955123901, "step": 325} +{"train_info/time_between_train_steps": 0.005239248275756836, "step": 325} +{"info/global_step": 326, "train_info/time_within_train_step": 13.195542097091675, "step": 326} +{"train_info/time_between_train_steps": 0.005421876907348633, "step": 326} +{"info/global_step": 327, "train_info/time_within_train_step": 13.20623779296875, "step": 327} +{"train_info/time_between_train_steps": 0.0056989192962646484, "step": 327} +{"info/global_step": 328, "train_info/time_within_train_step": 13.212865591049194, "step": 328} +{"train_info/time_between_train_steps": 0.00574803352355957, "step": 328} +{"info/global_step": 329, "train_info/time_within_train_step": 13.210179805755615, "step": 329} +{"train_info/time_between_train_steps": 0.0053026676177978516, "step": 329} +{"info/global_step": 330, "train_info/time_within_train_step": 13.198874950408936, "step": 330} +{"train_info/time_between_train_steps": 0.0050220489501953125, "step": 330} +{"info/global_step": 331, "train_info/time_within_train_step": 13.211985111236572, "step": 331} +{"train_info/time_between_train_steps": 0.005445003509521484, "step": 331} +{"info/global_step": 332, "train_info/time_within_train_step": 13.203563451766968, "step": 332} +{"train_info/time_between_train_steps": 0.005400896072387695, "step": 332} +{"info/global_step": 333, "train_info/time_within_train_step": 13.214694738388062, "step": 333} +{"train_info/time_between_train_steps": 0.004935741424560547, "step": 333} +{"info/global_step": 334, "train_info/time_within_train_step": 13.209763288497925, "step": 334} +{"train_info/time_between_train_steps": 0.005316019058227539, "step": 334} +{"info/global_step": 335, "train_info/time_within_train_step": 13.202476024627686, "step": 335} +{"train_info/time_between_train_steps": 0.005776643753051758, "step": 335} +{"info/global_step": 336, "train_info/time_within_train_step": 13.386465072631836, "step": 336} +{"train_info/time_between_train_steps": 0.005116701126098633, "step": 336} +{"info/global_step": 337, "train_info/time_within_train_step": 13.444527626037598, "step": 337} +{"train_info/time_between_train_steps": 0.0062863826751708984, "step": 337} +{"info/global_step": 338, "train_info/time_within_train_step": 13.22687578201294, "step": 338} +{"train_info/time_between_train_steps": 0.006221294403076172, "step": 338} +{"train_info/time_between_train_steps": 10.525476455688477, "step": 338} +{"info/global_step": 339, "train_info/time_within_train_step": 13.163928031921387, "step": 339} +{"train_info/time_between_train_steps": 0.005178213119506836, "step": 339} +{"info/global_step": 340, "train_info/time_within_train_step": 13.3012535572052, "step": 340} +{"train_info/time_between_train_steps": 0.005006074905395508, "step": 340} +{"info/global_step": 341, "train_info/time_within_train_step": 13.200185060501099, "step": 341} +{"train_info/time_between_train_steps": 0.0053141117095947266, "step": 341} +{"info/global_step": 342, "train_info/time_within_train_step": 13.282264709472656, "step": 342} +{"train_info/time_between_train_steps": 0.005483865737915039, "step": 342} +{"info/global_step": 343, "train_info/time_within_train_step": 13.205373048782349, "step": 343} +{"train_info/time_between_train_steps": 0.005519866943359375, "step": 343} +{"info/global_step": 344, "train_info/time_within_train_step": 13.319211483001709, "step": 344} +{"train_info/time_between_train_steps": 0.005853891372680664, "step": 344} +{"info/global_step": 345, "train_info/time_within_train_step": 13.21583867073059, "step": 345} +{"train_info/time_between_train_steps": 0.005377769470214844, "step": 345} +{"info/global_step": 346, "train_info/time_within_train_step": 13.238174438476562, "step": 346} +{"train_info/time_between_train_steps": 0.005267620086669922, "step": 346} +{"info/global_step": 347, "train_info/time_within_train_step": 13.197386741638184, "step": 347} +{"train_info/time_between_train_steps": 0.005467891693115234, "step": 347} +{"info/global_step": 348, "train_info/time_within_train_step": 13.199200630187988, "step": 348} +{"train_info/time_between_train_steps": 0.004935741424560547, "step": 348} +{"info/global_step": 349, "train_info/time_within_train_step": 13.215962409973145, "step": 349} +{"train_info/time_between_train_steps": 0.005600929260253906, "step": 349} +{"info/global_step": 350, "train_info/time_within_train_step": 13.21779179573059, "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": 1737047825, "_runtime": 5125}, "step": 350} +{"logs": {"train/loss": 6.4806, "train/learning_rate": 0.00047222222222222224, "train/epoch": 13.01, "_timestamp": 1737047825, "_runtime": 5125}, "step": 350} +{"train_info/time_between_train_steps": 0.05901932716369629, "step": 350} +{"info/global_step": 351, "train_info/time_within_train_step": 13.208639860153198, "step": 351} +{"train_info/time_between_train_steps": 0.004856109619140625, "step": 351} +{"info/global_step": 352, "train_info/time_within_train_step": 13.293424367904663, "step": 352} +{"train_info/time_between_train_steps": 0.0049245357513427734, "step": 352} +{"info/global_step": 353, "train_info/time_within_train_step": 13.22171950340271, "step": 353} +{"train_info/time_between_train_steps": 0.00479435920715332, "step": 353} +{"info/global_step": 354, "train_info/time_within_train_step": 13.20740032196045, "step": 354} +{"train_info/time_between_train_steps": 0.005330085754394531, "step": 354} +{"info/global_step": 355, "train_info/time_within_train_step": 13.233175992965698, "step": 355} +{"train_info/time_between_train_steps": 0.0050776004791259766, "step": 355} +{"info/global_step": 356, "train_info/time_within_train_step": 13.227261781692505, "step": 356} +{"train_info/time_between_train_steps": 0.005732536315917969, "step": 356} +{"info/global_step": 357, "train_info/time_within_train_step": 13.204629182815552, "step": 357} +{"train_info/time_between_train_steps": 0.0054934024810791016, "step": 357} +{"info/global_step": 358, "train_info/time_within_train_step": 13.216691017150879, "step": 358} +{"train_info/time_between_train_steps": 0.005049467086791992, "step": 358} +{"info/global_step": 359, "train_info/time_within_train_step": 13.22626519203186, "step": 359} +{"train_info/time_between_train_steps": 0.005640268325805664, "step": 359} +{"info/global_step": 360, "train_info/time_within_train_step": 13.227322578430176, "step": 360} +{"train_info/time_between_train_steps": 0.005647182464599609, "step": 360} +{"info/global_step": 361, "train_info/time_within_train_step": 13.218343019485474, "step": 361} +{"train_info/time_between_train_steps": 0.005414724349975586, "step": 361} +{"info/global_step": 362, "train_info/time_within_train_step": 13.204831600189209, "step": 362} +{"train_info/time_between_train_steps": 0.005405902862548828, "step": 362} +{"info/global_step": 363, "train_info/time_within_train_step": 13.225837230682373, "step": 363} +{"train_info/time_between_train_steps": 0.005528926849365234, "step": 363} +{"info/global_step": 364, "train_info/time_within_train_step": 13.233327388763428, "step": 364} +{"train_info/time_between_train_steps": 0.006748199462890625, "step": 364} +{"train_info/time_between_train_steps": 10.60490083694458, "step": 364} +{"info/global_step": 365, "train_info/time_within_train_step": 13.194355010986328, "step": 365} +{"train_info/time_between_train_steps": 0.006014823913574219, "step": 365} +{"info/global_step": 366, "train_info/time_within_train_step": 13.286036729812622, "step": 366} +{"train_info/time_between_train_steps": 0.005271196365356445, "step": 366} +{"info/global_step": 367, "train_info/time_within_train_step": 13.310539245605469, "step": 367} +{"train_info/time_between_train_steps": 0.0056078433990478516, "step": 367} +{"info/global_step": 368, "train_info/time_within_train_step": 13.28835940361023, "step": 368} +{"train_info/time_between_train_steps": 0.005039215087890625, "step": 368} +{"info/global_step": 369, "train_info/time_within_train_step": 13.217225074768066, "step": 369} +{"train_info/time_between_train_steps": 0.004815101623535156, "step": 369} +{"info/global_step": 370, "train_info/time_within_train_step": 13.268898248672485, "step": 370} +{"train_info/time_between_train_steps": 0.0056607723236083984, "step": 370} +{"info/global_step": 371, "train_info/time_within_train_step": 13.217463254928589, "step": 371} +{"train_info/time_between_train_steps": 0.005623340606689453, "step": 371} +{"info/global_step": 372, "train_info/time_within_train_step": 13.245639324188232, "step": 372} +{"train_info/time_between_train_steps": 0.005274295806884766, "step": 372} +{"info/global_step": 373, "train_info/time_within_train_step": 13.22014045715332, "step": 373} +{"train_info/time_between_train_steps": 0.005582094192504883, "step": 373} +{"info/global_step": 374, "train_info/time_within_train_step": 13.214511156082153, "step": 374} +{"train_info/time_between_train_steps": 0.005173683166503906, "step": 374} +{"info/global_step": 375, "train_info/time_within_train_step": 13.208555936813354, "step": 375} +{"train_info/time_between_train_steps": 0.005455493927001953, "step": 375} +{"info/global_step": 376, "train_info/time_within_train_step": 13.245639562606812, "step": 376} +{"train_info/time_between_train_steps": 0.005275726318359375, "step": 376} +{"info/global_step": 377, "train_info/time_within_train_step": 13.281662940979004, "step": 377} +{"train_info/time_between_train_steps": 0.005554914474487305, "step": 377} +{"info/global_step": 378, "train_info/time_within_train_step": 13.267525434494019, "step": 378} +{"train_info/time_between_train_steps": 0.0054645538330078125, "step": 378} +{"info/global_step": 379, "train_info/time_within_train_step": 13.205099821090698, "step": 379} +{"train_info/time_between_train_steps": 0.005215644836425781, "step": 379} +{"info/global_step": 380, "train_info/time_within_train_step": 13.176911115646362, "step": 380} +{"train_info/time_between_train_steps": 0.005312204360961914, "step": 380} +{"info/global_step": 381, "train_info/time_within_train_step": 13.178213357925415, "step": 381} +{"train_info/time_between_train_steps": 0.005090475082397461, "step": 381} +{"info/global_step": 382, "train_info/time_within_train_step": 13.257058382034302, "step": 382} +{"train_info/time_between_train_steps": 0.005716085433959961, "step": 382} +{"info/global_step": 383, "train_info/time_within_train_step": 13.174957036972046, "step": 383} +{"train_info/time_between_train_steps": 0.00523686408996582, "step": 383} +{"info/global_step": 384, "train_info/time_within_train_step": 13.17165994644165, "step": 384} +{"train_info/time_between_train_steps": 0.005739688873291016, "step": 384} +{"info/global_step": 385, "train_info/time_within_train_step": 13.188951253890991, "step": 385} +{"train_info/time_between_train_steps": 0.005266904830932617, "step": 385} +{"info/global_step": 386, "train_info/time_within_train_step": 13.178306102752686, "step": 386} +{"train_info/time_between_train_steps": 0.005449771881103516, "step": 386} +{"info/global_step": 387, "train_info/time_within_train_step": 13.182306051254272, "step": 387} +{"train_info/time_between_train_steps": 0.005236625671386719, "step": 387} +{"info/global_step": 388, "train_info/time_within_train_step": 13.187787294387817, "step": 388} +{"train_info/time_between_train_steps": 0.005401611328125, "step": 388} +{"info/global_step": 389, "train_info/time_within_train_step": 13.317371606826782, "step": 389} +{"train_info/time_between_train_steps": 0.005072832107543945, "step": 389} +{"info/global_step": 390, "train_info/time_within_train_step": 13.271982669830322, "step": 390} +{"train_info/time_between_train_steps": 0.006028413772583008, "step": 390} +{"train_info/time_between_train_steps": 10.65209698677063, "step": 390} +{"info/global_step": 391, "train_info/time_within_train_step": 13.1468026638031, "step": 391} +{"train_info/time_between_train_steps": 0.005250453948974609, "step": 391} +{"info/global_step": 392, "train_info/time_within_train_step": 13.24791407585144, "step": 392} +{"train_info/time_between_train_steps": 0.00592494010925293, "step": 392} +{"info/global_step": 393, "train_info/time_within_train_step": 13.185999631881714, "step": 393} +{"train_info/time_between_train_steps": 0.004741191864013672, "step": 393} +{"info/global_step": 394, "train_info/time_within_train_step": 13.286385774612427, "step": 394} +{"train_info/time_between_train_steps": 0.005350351333618164, "step": 394} +{"info/global_step": 395, "train_info/time_within_train_step": 13.17417049407959, "step": 395} +{"train_info/time_between_train_steps": 0.00482940673828125, "step": 395} +{"info/global_step": 396, "train_info/time_within_train_step": 13.234559059143066, "step": 396} +{"train_info/time_between_train_steps": 0.0056035518646240234, "step": 396} +{"info/global_step": 397, "train_info/time_within_train_step": 13.258532762527466, "step": 397} +{"train_info/time_between_train_steps": 0.004540920257568359, "step": 397} +{"info/global_step": 398, "train_info/time_within_train_step": 13.188032388687134, "step": 398} +{"train_info/time_between_train_steps": 0.005018711090087891, "step": 398} +{"info/global_step": 399, "train_info/time_within_train_step": 13.165780067443848, "step": 399} +{"train_info/time_between_train_steps": 0.005209445953369141, "step": 399} +{"info/global_step": 400, "train_info/time_within_train_step": 13.175463438034058, "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": 1737048510, "_runtime": 5810}, "step": 400} +{"logs": {"train/loss": 6.1992, "train/learning_rate": 0.00044444444444444436, "train/epoch": 15.01, "_timestamp": 1737048510, "_runtime": 5810}, "step": 400} +{"train_info/time_between_train_steps": 148.34875297546387, "step": 400} +{"info/global_step": 401, "train_info/time_within_train_step": 13.212980270385742, "step": 401} +{"train_info/time_between_train_steps": 0.0049092769622802734, "step": 401} +{"info/global_step": 402, "train_info/time_within_train_step": 13.147717714309692, "step": 402} +{"train_info/time_between_train_steps": 0.005415678024291992, "step": 402} +{"info/global_step": 403, "train_info/time_within_train_step": 13.117762327194214, "step": 403} +{"train_info/time_between_train_steps": 0.004922389984130859, "step": 403} +{"info/global_step": 404, "train_info/time_within_train_step": 13.129891872406006, "step": 404} +{"train_info/time_between_train_steps": 0.005431175231933594, "step": 404} +{"info/global_step": 405, "train_info/time_within_train_step": 13.150403261184692, "step": 405} +{"train_info/time_between_train_steps": 0.005509614944458008, "step": 405} +{"info/global_step": 406, "train_info/time_within_train_step": 13.162954330444336, "step": 406} +{"train_info/time_between_train_steps": 0.005902528762817383, "step": 406} +{"info/global_step": 407, "train_info/time_within_train_step": 13.164884328842163, "step": 407} +{"train_info/time_between_train_steps": 0.004758596420288086, "step": 407} +{"info/global_step": 408, "train_info/time_within_train_step": 13.162170171737671, "step": 408} +{"train_info/time_between_train_steps": 0.0059680938720703125, "step": 408} +{"info/global_step": 409, "train_info/time_within_train_step": 13.182729244232178, "step": 409} +{"train_info/time_between_train_steps": 0.005465507507324219, "step": 409} +{"info/global_step": 410, "train_info/time_within_train_step": 13.18357515335083, "step": 410} +{"train_info/time_between_train_steps": 0.004994869232177734, "step": 410} +{"info/global_step": 411, "train_info/time_within_train_step": 13.180219888687134, "step": 411} +{"train_info/time_between_train_steps": 0.0054891109466552734, "step": 411} +{"info/global_step": 412, "train_info/time_within_train_step": 13.170469522476196, "step": 412} +{"train_info/time_between_train_steps": 0.005516767501831055, "step": 412} +{"info/global_step": 413, "train_info/time_within_train_step": 13.261005163192749, "step": 413} +{"train_info/time_between_train_steps": 0.0057299137115478516, "step": 413} +{"info/global_step": 414, "train_info/time_within_train_step": 13.235034227371216, "step": 414} +{"train_info/time_between_train_steps": 0.005917787551879883, "step": 414} +{"info/global_step": 415, "train_info/time_within_train_step": 13.2017662525177, "step": 415} +{"train_info/time_between_train_steps": 0.006062746047973633, "step": 415} +{"info/global_step": 416, "train_info/time_within_train_step": 13.213852167129517, "step": 416} +{"train_info/time_between_train_steps": 0.006555795669555664, "step": 416} +{"train_info/time_between_train_steps": 10.507061004638672, "step": 416} +{"info/global_step": 417, "train_info/time_within_train_step": 13.17841911315918, "step": 417} +{"train_info/time_between_train_steps": 0.0052967071533203125, "step": 417} +{"info/global_step": 418, "train_info/time_within_train_step": 13.275820970535278, "step": 418} +{"train_info/time_between_train_steps": 0.00539398193359375, "step": 418} +{"info/global_step": 419, "train_info/time_within_train_step": 13.171640396118164, "step": 419} +{"train_info/time_between_train_steps": 0.004400730133056641, "step": 419} +{"info/global_step": 420, "train_info/time_within_train_step": 13.282142639160156, "step": 420} +{"train_info/time_between_train_steps": 0.00555729866027832, "step": 420} +{"info/global_step": 421, "train_info/time_within_train_step": 13.187979698181152, "step": 421} +{"train_info/time_between_train_steps": 0.005812168121337891, "step": 421} +{"info/global_step": 422, "train_info/time_within_train_step": 13.268099546432495, "step": 422} +{"train_info/time_between_train_steps": 0.00587153434753418, "step": 422} +{"info/global_step": 423, "train_info/time_within_train_step": 13.196238279342651, "step": 423} +{"train_info/time_between_train_steps": 0.00472712516784668, "step": 423} +{"info/global_step": 424, "train_info/time_within_train_step": 13.20446252822876, "step": 424} +{"train_info/time_between_train_steps": 0.005433559417724609, "step": 424} +{"info/global_step": 425, "train_info/time_within_train_step": 13.192273139953613, "step": 425} +{"train_info/time_between_train_steps": 0.005326271057128906, "step": 425} +{"info/global_step": 426, "train_info/time_within_train_step": 13.191237688064575, "step": 426} +{"train_info/time_between_train_steps": 0.004949808120727539, "step": 426} +{"info/global_step": 427, "train_info/time_within_train_step": 13.184114217758179, "step": 427} +{"train_info/time_between_train_steps": 0.005177497863769531, "step": 427} +{"info/global_step": 428, "train_info/time_within_train_step": 13.343464612960815, "step": 428} +{"train_info/time_between_train_steps": 0.00457000732421875, "step": 428} +{"info/global_step": 429, "train_info/time_within_train_step": 13.199023246765137, "step": 429} +{"train_info/time_between_train_steps": 0.00561976432800293, "step": 429} +{"info/global_step": 430, "train_info/time_within_train_step": 13.195589303970337, "step": 430} +{"train_info/time_between_train_steps": 0.005339384078979492, "step": 430} +{"info/global_step": 431, "train_info/time_within_train_step": 13.194005966186523, "step": 431} +{"train_info/time_between_train_steps": 0.005406618118286133, "step": 431} +{"info/global_step": 432, "train_info/time_within_train_step": 13.199891328811646, "step": 432} +{"train_info/time_between_train_steps": 0.005316257476806641, "step": 432} +{"info/global_step": 433, "train_info/time_within_train_step": 13.184704780578613, "step": 433} +{"train_info/time_between_train_steps": 0.0054721832275390625, "step": 433} +{"info/global_step": 434, "train_info/time_within_train_step": 13.17650842666626, "step": 434} +{"train_info/time_between_train_steps": 0.005568504333496094, "step": 434} +{"info/global_step": 435, "train_info/time_within_train_step": 13.188183307647705, "step": 435} +{"train_info/time_between_train_steps": 0.005822420120239258, "step": 435} +{"info/global_step": 436, "train_info/time_within_train_step": 13.1858229637146, "step": 436} +{"train_info/time_between_train_steps": 0.0052242279052734375, "step": 436} +{"info/global_step": 437, "train_info/time_within_train_step": 13.194653034210205, "step": 437} +{"train_info/time_between_train_steps": 0.005948781967163086, "step": 437} +{"info/global_step": 438, "train_info/time_within_train_step": 13.204422950744629, "step": 438} +{"train_info/time_between_train_steps": 0.0056231021881103516, "step": 438} +{"info/global_step": 439, "train_info/time_within_train_step": 13.188329935073853, "step": 439} +{"train_info/time_between_train_steps": 0.005347251892089844, "step": 439} +{"info/global_step": 440, "train_info/time_within_train_step": 13.194087743759155, "step": 440} +{"train_info/time_between_train_steps": 0.005498170852661133, "step": 440} +{"info/global_step": 441, "train_info/time_within_train_step": 13.237690925598145, "step": 441} +{"train_info/time_between_train_steps": 0.005782604217529297, "step": 441} +{"info/global_step": 442, "train_info/time_within_train_step": 13.217369079589844, "step": 442} +{"train_info/time_between_train_steps": 0.006830453872680664, "step": 442} +{"train_info/time_between_train_steps": 10.576996564865112, "step": 442} +{"info/global_step": 443, "train_info/time_within_train_step": 13.232244968414307, "step": 443} +{"train_info/time_between_train_steps": 0.005182027816772461, "step": 443} +{"info/global_step": 444, "train_info/time_within_train_step": 13.263633728027344, "step": 444} +{"train_info/time_between_train_steps": 0.004436492919921875, "step": 444} +{"info/global_step": 445, "train_info/time_within_train_step": 13.163527727127075, "step": 445} +{"train_info/time_between_train_steps": 0.004895210266113281, "step": 445} +{"info/global_step": 446, "train_info/time_within_train_step": 13.26936674118042, "step": 446} +{"train_info/time_between_train_steps": 0.0055196285247802734, "step": 446} +{"info/global_step": 447, "train_info/time_within_train_step": 13.178394794464111, "step": 447} +{"train_info/time_between_train_steps": 0.005448102951049805, "step": 447} +{"info/global_step": 448, "train_info/time_within_train_step": 13.277512311935425, "step": 448} +{"train_info/time_between_train_steps": 0.005767822265625, "step": 448} +{"info/global_step": 449, "train_info/time_within_train_step": 13.200689554214478, "step": 449} +{"train_info/time_between_train_steps": 0.006141185760498047, "step": 449} +{"info/global_step": 450, "train_info/time_within_train_step": 13.18424677848816, "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": 1737049342, "_runtime": 6642}, "step": 450} +{"logs": {"train/loss": 5.9306, "train/learning_rate": 0.00041666666666666664, "train/epoch": 17.01, "_timestamp": 1737049342, "_runtime": 6642}, "step": 450} +{"train_info/time_between_train_steps": 0.03446245193481445, "step": 450} +{"info/global_step": 451, "train_info/time_within_train_step": 13.201772212982178, "step": 451} +{"train_info/time_between_train_steps": 0.00505828857421875, "step": 451} +{"info/global_step": 452, "train_info/time_within_train_step": 13.23002815246582, "step": 452} +{"train_info/time_between_train_steps": 0.005219697952270508, "step": 452} +{"info/global_step": 453, "train_info/time_within_train_step": 13.215879201889038, "step": 453} +{"train_info/time_between_train_steps": 0.00536346435546875, "step": 453} +{"info/global_step": 454, "train_info/time_within_train_step": 13.21779465675354, "step": 454} +{"train_info/time_between_train_steps": 0.005484104156494141, "step": 454} +{"info/global_step": 455, "train_info/time_within_train_step": 13.183929681777954, "step": 455} +{"train_info/time_between_train_steps": 0.005491495132446289, "step": 455} +{"info/global_step": 456, "train_info/time_within_train_step": 13.176217317581177, "step": 456} +{"train_info/time_between_train_steps": 0.005319833755493164, "step": 456} +{"info/global_step": 457, "train_info/time_within_train_step": 13.18976354598999, "step": 457} +{"train_info/time_between_train_steps": 0.00537419319152832, "step": 457} +{"info/global_step": 458, "train_info/time_within_train_step": 13.207860231399536, "step": 458} +{"train_info/time_between_train_steps": 0.005101442337036133, "step": 458} +{"info/global_step": 459, "train_info/time_within_train_step": 13.260082244873047, "step": 459} +{"train_info/time_between_train_steps": 0.005333423614501953, "step": 459} +{"info/global_step": 460, "train_info/time_within_train_step": 13.200052738189697, "step": 460} +{"train_info/time_between_train_steps": 0.00564265251159668, "step": 460} +{"info/global_step": 461, "train_info/time_within_train_step": 13.168769359588623, "step": 461} +{"train_info/time_between_train_steps": 0.0051953792572021484, "step": 461} +{"info/global_step": 462, "train_info/time_within_train_step": 13.183649063110352, "step": 462} +{"train_info/time_between_train_steps": 0.0051343441009521484, "step": 462} +{"info/global_step": 463, "train_info/time_within_train_step": 13.18059492111206, "step": 463} +{"train_info/time_between_train_steps": 0.005596160888671875, "step": 463} +{"info/global_step": 464, "train_info/time_within_train_step": 13.2001953125, "step": 464} +{"train_info/time_between_train_steps": 0.005579948425292969, "step": 464} +{"info/global_step": 465, "train_info/time_within_train_step": 13.203897476196289, "step": 465} +{"train_info/time_between_train_steps": 0.0060007572174072266, "step": 465} +{"info/global_step": 466, "train_info/time_within_train_step": 13.249372959136963, "step": 466} +{"train_info/time_between_train_steps": 0.005679130554199219, "step": 466} +{"info/global_step": 467, "train_info/time_within_train_step": 13.239611387252808, "step": 467} +{"train_info/time_between_train_steps": 0.005539417266845703, "step": 467} +{"info/global_step": 468, "train_info/time_within_train_step": 13.208423376083374, "step": 468} +{"train_info/time_between_train_steps": 0.006066083908081055, "step": 468} +{"train_info/time_between_train_steps": 10.665156841278076, "step": 468} +{"info/global_step": 469, "train_info/time_within_train_step": 13.161689043045044, "step": 469} +{"train_info/time_between_train_steps": 0.00550079345703125, "step": 469} +{"info/global_step": 470, "train_info/time_within_train_step": 13.293289184570312, "step": 470} +{"train_info/time_between_train_steps": 0.004689455032348633, "step": 470} +{"info/global_step": 471, "train_info/time_within_train_step": 13.182816505432129, "step": 471} +{"train_info/time_between_train_steps": 0.0050008296966552734, "step": 471} +{"info/global_step": 472, "train_info/time_within_train_step": 13.282754182815552, "step": 472} +{"train_info/time_between_train_steps": 0.005288124084472656, "step": 472} +{"info/global_step": 473, "train_info/time_within_train_step": 13.182265520095825, "step": 473} +{"train_info/time_between_train_steps": 0.0051212310791015625, "step": 473} +{"info/global_step": 474, "train_info/time_within_train_step": 13.341218948364258, "step": 474} +{"train_info/time_between_train_steps": 0.005486249923706055, "step": 474} +{"info/global_step": 475, "train_info/time_within_train_step": 13.194531679153442, "step": 475} +{"train_info/time_between_train_steps": 0.005938529968261719, "step": 475} +{"info/global_step": 476, "train_info/time_within_train_step": 13.215264320373535, "step": 476} +{"train_info/time_between_train_steps": 0.005760669708251953, "step": 476} +{"info/global_step": 477, "train_info/time_within_train_step": 13.200871706008911, "step": 477} +{"train_info/time_between_train_steps": 0.005537509918212891, "step": 477} +{"info/global_step": 478, "train_info/time_within_train_step": 13.2268648147583, "step": 478} +{"train_info/time_between_train_steps": 0.005025148391723633, "step": 478} +{"info/global_step": 479, "train_info/time_within_train_step": 14.248652696609497, "step": 479} +{"train_info/time_between_train_steps": 0.004475831985473633, "step": 479} +{"info/global_step": 480, "train_info/time_within_train_step": 13.524529218673706, "step": 480} +{"train_info/time_between_train_steps": 0.0045931339263916016, "step": 480} +{"info/global_step": 481, "train_info/time_within_train_step": 13.437293291091919, "step": 481} +{"train_info/time_between_train_steps": 0.004688262939453125, "step": 481} +{"info/global_step": 482, "train_info/time_within_train_step": 13.19177508354187, "step": 482} +{"train_info/time_between_train_steps": 0.005414247512817383, "step": 482} +{"info/global_step": 483, "train_info/time_within_train_step": 13.206732749938965, "step": 483} +{"train_info/time_between_train_steps": 0.00488734245300293, "step": 483} +{"info/global_step": 484, "train_info/time_within_train_step": 13.207405090332031, "step": 484} +{"train_info/time_between_train_steps": 0.005261898040771484, "step": 484} +{"info/global_step": 485, "train_info/time_within_train_step": 13.188106775283813, "step": 485} +{"train_info/time_between_train_steps": 0.005461692810058594, "step": 485} +{"info/global_step": 486, "train_info/time_within_train_step": 13.192242860794067, "step": 486} +{"train_info/time_between_train_steps": 0.0052890777587890625, "step": 486} +{"info/global_step": 487, "train_info/time_within_train_step": 13.212936401367188, "step": 487} +{"train_info/time_between_train_steps": 0.005276918411254883, "step": 487} +{"info/global_step": 488, "train_info/time_within_train_step": 13.200586318969727, "step": 488} +{"train_info/time_between_train_steps": 0.004814863204956055, "step": 488} +{"info/global_step": 489, "train_info/time_within_train_step": 13.30476188659668, "step": 489} +{"train_info/time_between_train_steps": 0.005351066589355469, "step": 489} +{"info/global_step": 490, "train_info/time_within_train_step": 13.209550142288208, "step": 490} +{"train_info/time_between_train_steps": 0.0056247711181640625, "step": 490} +{"info/global_step": 491, "train_info/time_within_train_step": 13.227623701095581, "step": 491} +{"train_info/time_between_train_steps": 0.0053255558013916016, "step": 491} +{"info/global_step": 492, "train_info/time_within_train_step": 13.206864595413208, "step": 492} +{"train_info/time_between_train_steps": 0.005911827087402344, "step": 492} +{"info/global_step": 493, "train_info/time_within_train_step": 13.228729248046875, "step": 493} +{"train_info/time_between_train_steps": 0.005815267562866211, "step": 493} +{"info/global_step": 494, "train_info/time_within_train_step": 13.229962348937988, "step": 494} +{"train_info/time_between_train_steps": 0.0070040225982666016, "step": 494} +{"train_info/time_between_train_steps": 10.515362739562988, "step": 494} +{"info/global_step": 495, "train_info/time_within_train_step": 13.189202547073364, "step": 495} +{"train_info/time_between_train_steps": 0.005012989044189453, "step": 495} +{"info/global_step": 496, "train_info/time_within_train_step": 13.293740510940552, "step": 496} +{"train_info/time_between_train_steps": 0.005765676498413086, "step": 496} +{"info/global_step": 497, "train_info/time_within_train_step": 13.227241516113281, "step": 497} +{"train_info/time_between_train_steps": 0.0056209564208984375, "step": 497} +{"info/global_step": 498, "train_info/time_within_train_step": 13.737526416778564, "step": 498} +{"train_info/time_between_train_steps": 0.005349636077880859, "step": 498} +{"info/global_step": 499, "train_info/time_within_train_step": 13.192996740341187, "step": 499} +{"train_info/time_between_train_steps": 0.005205631256103516, "step": 499} +{"info/global_step": 500, "train_info/time_within_train_step": 13.268556594848633, "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": 1737050029, "_runtime": 7329}, "step": 500} +{"logs": {"train/loss": 5.6857, "train/learning_rate": 0.00038888888888888887, "train/epoch": 19.0, "_timestamp": 1737050029, "_runtime": 7329}, "step": 500} +{"train_info/time_between_train_steps": 22.46795082092285, "step": 500} +{"info/global_step": 501, "train_info/time_within_train_step": 13.216559648513794, "step": 501} +{"train_info/time_between_train_steps": 0.0045697689056396484, "step": 501} +{"info/global_step": 502, "train_info/time_within_train_step": 13.147637605667114, "step": 502} +{"train_info/time_between_train_steps": 0.00461578369140625, "step": 502} +{"info/global_step": 503, "train_info/time_within_train_step": 13.250190734863281, "step": 503} +{"train_info/time_between_train_steps": 0.004777669906616211, "step": 503} +{"info/global_step": 504, "train_info/time_within_train_step": 13.855538845062256, "step": 504} +{"train_info/time_between_train_steps": 0.0048711299896240234, "step": 504} +{"info/global_step": 505, "train_info/time_within_train_step": 13.175184965133667, "step": 505} +{"train_info/time_between_train_steps": 0.004934787750244141, "step": 505} +{"info/global_step": 506, "train_info/time_within_train_step": 13.18574595451355, "step": 506} +{"train_info/time_between_train_steps": 0.004900932312011719, "step": 506} +{"info/global_step": 507, "train_info/time_within_train_step": 13.187291860580444, "step": 507} +{"train_info/time_between_train_steps": 0.005383491516113281, "step": 507} +{"info/global_step": 508, "train_info/time_within_train_step": 13.208801984786987, "step": 508} +{"train_info/time_between_train_steps": 0.005545377731323242, "step": 508} +{"info/global_step": 509, "train_info/time_within_train_step": 13.19562554359436, "step": 509} +{"train_info/time_between_train_steps": 0.005934238433837891, "step": 509} +{"info/global_step": 510, "train_info/time_within_train_step": 13.190021753311157, "step": 510} +{"train_info/time_between_train_steps": 0.005454063415527344, "step": 510} +{"info/global_step": 511, "train_info/time_within_train_step": 13.206573724746704, "step": 511} +{"train_info/time_between_train_steps": 0.005225181579589844, "step": 511} +{"info/global_step": 512, "train_info/time_within_train_step": 13.194912910461426, "step": 512} +{"train_info/time_between_train_steps": 0.005363941192626953, "step": 512} +{"info/global_step": 513, "train_info/time_within_train_step": 13.236186265945435, "step": 513} +{"train_info/time_between_train_steps": 0.005663633346557617, "step": 513} +{"info/global_step": 514, "train_info/time_within_train_step": 13.204991817474365, "step": 514} +{"train_info/time_between_train_steps": 0.005335807800292969, "step": 514} +{"info/global_step": 515, "train_info/time_within_train_step": 13.198509931564331, "step": 515} +{"train_info/time_between_train_steps": 0.0052032470703125, "step": 515} +{"info/global_step": 516, "train_info/time_within_train_step": 13.206722497940063, "step": 516} +{"train_info/time_between_train_steps": 0.00483393669128418, "step": 516} +{"info/global_step": 517, "train_info/time_within_train_step": 13.205105781555176, "step": 517} +{"train_info/time_between_train_steps": 0.004880666732788086, "step": 517} +{"info/global_step": 518, "train_info/time_within_train_step": 13.218134880065918, "step": 518} +{"train_info/time_between_train_steps": 0.005106210708618164, "step": 518} +{"info/global_step": 519, "train_info/time_within_train_step": 13.22022533416748, "step": 519} +{"train_info/time_between_train_steps": 0.005870819091796875, "step": 519} +{"info/global_step": 520, "train_info/time_within_train_step": 13.311574935913086, "step": 520} +{"train_info/time_between_train_steps": 0.006505250930786133, "step": 520} +{"train_info/time_between_train_steps": 10.47200083732605, "step": 520} +{"info/global_step": 521, "train_info/time_within_train_step": 13.206663846969604, "step": 521} +{"train_info/time_between_train_steps": 0.0051572322845458984, "step": 521} +{"info/global_step": 522, "train_info/time_within_train_step": 13.290821075439453, "step": 522} +{"train_info/time_between_train_steps": 0.004441022872924805, "step": 522} +{"info/global_step": 523, "train_info/time_within_train_step": 13.203594207763672, "step": 523} +{"train_info/time_between_train_steps": 0.005242586135864258, "step": 523} +{"info/global_step": 524, "train_info/time_within_train_step": 13.325321912765503, "step": 524} +{"train_info/time_between_train_steps": 0.005291461944580078, "step": 524} +{"info/global_step": 525, "train_info/time_within_train_step": 13.25770878791809, "step": 525} +{"train_info/time_between_train_steps": 0.00558924674987793, "step": 525} +{"info/global_step": 526, "train_info/time_within_train_step": 13.290424346923828, "step": 526} +{"train_info/time_between_train_steps": 0.005457162857055664, "step": 526} +{"info/global_step": 527, "train_info/time_within_train_step": 13.222482681274414, "step": 527} +{"train_info/time_between_train_steps": 0.005653858184814453, "step": 527} +{"info/global_step": 528, "train_info/time_within_train_step": 13.203970193862915, "step": 528} +{"train_info/time_between_train_steps": 0.004830121994018555, "step": 528} +{"info/global_step": 529, "train_info/time_within_train_step": 13.509991645812988, "step": 529} +{"train_info/time_between_train_steps": 0.004952430725097656, "step": 529} +{"info/global_step": 530, "train_info/time_within_train_step": 14.008671522140503, "step": 530} +{"train_info/time_between_train_steps": 0.004659414291381836, "step": 530} +{"info/global_step": 531, "train_info/time_within_train_step": 13.209994792938232, "step": 531} +{"train_info/time_between_train_steps": 0.005259037017822266, "step": 531} +{"info/global_step": 532, "train_info/time_within_train_step": 13.201552629470825, "step": 532} +{"train_info/time_between_train_steps": 0.005652666091918945, "step": 532} +{"info/global_step": 533, "train_info/time_within_train_step": 13.191179752349854, "step": 533} +{"train_info/time_between_train_steps": 0.005225419998168945, "step": 533} +{"info/global_step": 534, "train_info/time_within_train_step": 13.206180095672607, "step": 534} +{"train_info/time_between_train_steps": 0.005105495452880859, "step": 534} +{"info/global_step": 535, "train_info/time_within_train_step": 13.287266492843628, "step": 535} +{"train_info/time_between_train_steps": 0.0053997039794921875, "step": 535} +{"info/global_step": 536, "train_info/time_within_train_step": 13.20662808418274, "step": 536} +{"train_info/time_between_train_steps": 0.005305051803588867, "step": 536} +{"info/global_step": 537, "train_info/time_within_train_step": 13.19681715965271, "step": 537} +{"train_info/time_between_train_steps": 0.005382061004638672, "step": 537} +{"info/global_step": 538, "train_info/time_within_train_step": 13.206969976425171, "step": 538} +{"train_info/time_between_train_steps": 0.006124258041381836, "step": 538} +{"info/global_step": 539, "train_info/time_within_train_step": 13.210916519165039, "step": 539} +{"train_info/time_between_train_steps": 0.005437374114990234, "step": 539} +{"info/global_step": 540, "train_info/time_within_train_step": 13.201831102371216, "step": 540} +{"train_info/time_between_train_steps": 0.005388021469116211, "step": 540} +{"info/global_step": 541, "train_info/time_within_train_step": 13.201226472854614, "step": 541} +{"train_info/time_between_train_steps": 0.005631208419799805, "step": 541} +{"info/global_step": 542, "train_info/time_within_train_step": 13.233859539031982, "step": 542} +{"train_info/time_between_train_steps": 0.005943775177001953, "step": 542} +{"info/global_step": 543, "train_info/time_within_train_step": 13.233046054840088, "step": 543} +{"train_info/time_between_train_steps": 0.005994081497192383, "step": 543} +{"info/global_step": 544, "train_info/time_within_train_step": 13.220619440078735, "step": 544} +{"train_info/time_between_train_steps": 0.005742311477661133, "step": 544} +{"info/global_step": 545, "train_info/time_within_train_step": 13.225076675415039, "step": 545} +{"train_info/time_between_train_steps": 0.005760908126831055, "step": 545} +{"info/global_step": 546, "train_info/time_within_train_step": 13.242493152618408, "step": 546} +{"train_info/time_between_train_steps": 0.0067975521087646484, "step": 546} +{"train_info/time_between_train_steps": 10.674501419067383, "step": 546} +{"info/global_step": 547, "train_info/time_within_train_step": 13.183487892150879, "step": 547} +{"train_info/time_between_train_steps": 0.004827022552490234, "step": 547} +{"info/global_step": 548, "train_info/time_within_train_step": 13.311896800994873, "step": 548} +{"train_info/time_between_train_steps": 0.004708766937255859, "step": 548} +{"info/global_step": 549, "train_info/time_within_train_step": 13.178213834762573, "step": 549} +{"train_info/time_between_train_steps": 0.005435943603515625, "step": 549} +{"info/global_step": 550, "train_info/time_within_train_step": 13.363791942596436, "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": 1737050740, "_runtime": 8040}, "step": 550} +{"logs": {"train/loss": 5.4707, "train/learning_rate": 0.0003611111111111111, "train/epoch": 21.0, "_timestamp": 1737050740, "_runtime": 8040}, "step": 550} +{"train_info/time_between_train_steps": 0.04084038734436035, "step": 550} +{"info/global_step": 551, "train_info/time_within_train_step": 13.1978600025177, "step": 551} +{"train_info/time_between_train_steps": 0.005759000778198242, "step": 551} +{"info/global_step": 552, "train_info/time_within_train_step": 13.331805944442749, "step": 552} +{"train_info/time_between_train_steps": 0.005625009536743164, "step": 552} +{"info/global_step": 553, "train_info/time_within_train_step": 13.208728790283203, "step": 553} +{"train_info/time_between_train_steps": 0.005659818649291992, "step": 553} +{"info/global_step": 554, "train_info/time_within_train_step": 13.215022802352905, "step": 554} +{"train_info/time_between_train_steps": 0.0051364898681640625, "step": 554} +{"info/global_step": 555, "train_info/time_within_train_step": 13.204893589019775, "step": 555} +{"train_info/time_between_train_steps": 0.005257844924926758, "step": 555} +{"info/global_step": 556, "train_info/time_within_train_step": 13.233222961425781, "step": 556} +{"train_info/time_between_train_steps": 0.00505828857421875, "step": 556} +{"info/global_step": 557, "train_info/time_within_train_step": 13.211674451828003, "step": 557} +{"train_info/time_between_train_steps": 0.0049381256103515625, "step": 557} +{"info/global_step": 558, "train_info/time_within_train_step": 13.204454898834229, "step": 558} +{"train_info/time_between_train_steps": 0.0053005218505859375, "step": 558} +{"info/global_step": 559, "train_info/time_within_train_step": 13.193528652191162, "step": 559} +{"train_info/time_between_train_steps": 0.0055615901947021484, "step": 559} +{"info/global_step": 560, "train_info/time_within_train_step": 13.197650671005249, "step": 560} +{"train_info/time_between_train_steps": 0.005271196365356445, "step": 560} +{"info/global_step": 561, "train_info/time_within_train_step": 13.225960731506348, "step": 561} +{"train_info/time_between_train_steps": 0.00561976432800293, "step": 561} +{"info/global_step": 562, "train_info/time_within_train_step": 13.201424837112427, "step": 562} +{"train_info/time_between_train_steps": 0.005521059036254883, "step": 562} +{"info/global_step": 563, "train_info/time_within_train_step": 13.195968866348267, "step": 563} +{"train_info/time_between_train_steps": 0.0055506229400634766, "step": 563} +{"info/global_step": 564, "train_info/time_within_train_step": 13.196766376495361, "step": 564} +{"train_info/time_between_train_steps": 0.005396127700805664, "step": 564} +{"info/global_step": 565, "train_info/time_within_train_step": 13.29132080078125, "step": 565} +{"train_info/time_between_train_steps": 0.0054798126220703125, "step": 565} +{"info/global_step": 566, "train_info/time_within_train_step": 13.216606140136719, "step": 566} +{"train_info/time_between_train_steps": 0.004984140396118164, "step": 566} +{"info/global_step": 567, "train_info/time_within_train_step": 13.223050355911255, "step": 567} +{"train_info/time_between_train_steps": 0.005371570587158203, "step": 567} +{"info/global_step": 568, "train_info/time_within_train_step": 13.201002359390259, "step": 568} +{"train_info/time_between_train_steps": 0.005472421646118164, "step": 568} +{"info/global_step": 569, "train_info/time_within_train_step": 13.218399286270142, "step": 569} +{"train_info/time_between_train_steps": 0.0057675838470458984, "step": 569} +{"info/global_step": 570, "train_info/time_within_train_step": 13.231508731842041, "step": 570} +{"train_info/time_between_train_steps": 0.005288600921630859, "step": 570} +{"info/global_step": 571, "train_info/time_within_train_step": 13.219089031219482, "step": 571} +{"train_info/time_between_train_steps": 0.005359649658203125, "step": 571} +{"info/global_step": 572, "train_info/time_within_train_step": 13.219732761383057, "step": 572} +{"train_info/time_between_train_steps": 0.006608724594116211, "step": 572} +{"train_info/time_between_train_steps": 10.856376886367798, "step": 572} +{"info/global_step": 573, "train_info/time_within_train_step": 13.234969139099121, "step": 573} +{"train_info/time_between_train_steps": 0.005763053894042969, "step": 573} +{"info/global_step": 574, "train_info/time_within_train_step": 13.316519737243652, "step": 574} +{"train_info/time_between_train_steps": 0.006200075149536133, "step": 574} +{"info/global_step": 575, "train_info/time_within_train_step": 13.193544864654541, "step": 575} +{"train_info/time_between_train_steps": 0.005348682403564453, "step": 575} +{"info/global_step": 576, "train_info/time_within_train_step": 13.285779476165771, "step": 576} +{"train_info/time_between_train_steps": 0.005517244338989258, "step": 576} +{"info/global_step": 577, "train_info/time_within_train_step": 13.22372555732727, "step": 577} +{"train_info/time_between_train_steps": 0.005808115005493164, "step": 577} +{"info/global_step": 578, "train_info/time_within_train_step": 13.30177927017212, "step": 578} +{"train_info/time_between_train_steps": 0.005640506744384766, "step": 578} +{"info/global_step": 579, "train_info/time_within_train_step": 13.20734167098999, "step": 579} +{"train_info/time_between_train_steps": 0.005420207977294922, "step": 579} +{"info/global_step": 580, "train_info/time_within_train_step": 13.330055236816406, "step": 580} +{"train_info/time_between_train_steps": 0.005029439926147461, "step": 580} +{"info/global_step": 581, "train_info/time_within_train_step": 13.202648401260376, "step": 581} +{"train_info/time_between_train_steps": 0.005141496658325195, "step": 581} +{"info/global_step": 582, "train_info/time_within_train_step": 13.203845262527466, "step": 582} +{"train_info/time_between_train_steps": 0.005089759826660156, "step": 582} +{"info/global_step": 583, "train_info/time_within_train_step": 13.197946310043335, "step": 583} +{"train_info/time_between_train_steps": 0.004979610443115234, "step": 583} +{"info/global_step": 584, "train_info/time_within_train_step": 13.186399221420288, "step": 584} +{"train_info/time_between_train_steps": 0.0048236846923828125, "step": 584} +{"info/global_step": 585, "train_info/time_within_train_step": 13.205525159835815, "step": 585} +{"train_info/time_between_train_steps": 0.005564451217651367, "step": 585} +{"info/global_step": 586, "train_info/time_within_train_step": 13.22272515296936, "step": 586} +{"train_info/time_between_train_steps": 0.005391120910644531, "step": 586} +{"info/global_step": 587, "train_info/time_within_train_step": 13.194166898727417, "step": 587} +{"train_info/time_between_train_steps": 0.0055310726165771484, "step": 587} +{"info/global_step": 588, "train_info/time_within_train_step": 13.192536115646362, "step": 588} +{"train_info/time_between_train_steps": 0.005236625671386719, "step": 588} +{"info/global_step": 589, "train_info/time_within_train_step": 13.215857744216919, "step": 589} +{"train_info/time_between_train_steps": 0.005279064178466797, "step": 589} +{"info/global_step": 590, "train_info/time_within_train_step": 13.196637630462646, "step": 590} +{"train_info/time_between_train_steps": 0.0058746337890625, "step": 590} +{"info/global_step": 591, "train_info/time_within_train_step": 13.208642482757568, "step": 591} +{"train_info/time_between_train_steps": 0.005791664123535156, "step": 591} +{"info/global_step": 592, "train_info/time_within_train_step": 13.225572109222412, "step": 592} +{"train_info/time_between_train_steps": 0.005664825439453125, "step": 592} +{"info/global_step": 593, "train_info/time_within_train_step": 13.194149017333984, "step": 593} +{"train_info/time_between_train_steps": 0.0054280757904052734, "step": 593} +{"info/global_step": 594, "train_info/time_within_train_step": 13.19363784790039, "step": 594} +{"train_info/time_between_train_steps": 0.00536036491394043, "step": 594} +{"info/global_step": 595, "train_info/time_within_train_step": 13.2183198928833, "step": 595} +{"train_info/time_between_train_steps": 0.005057334899902344, "step": 595} +{"info/global_step": 596, "train_info/time_within_train_step": 13.305018424987793, "step": 596} +{"train_info/time_between_train_steps": 0.005730628967285156, "step": 596} +{"info/global_step": 597, "train_info/time_within_train_step": 13.212579488754272, "step": 597} +{"train_info/time_between_train_steps": 0.0059854984283447266, "step": 597} +{"info/global_step": 598, "train_info/time_within_train_step": 13.23689317703247, "step": 598} +{"train_info/time_between_train_steps": 0.006499290466308594, "step": 598} +{"train_info/time_between_train_steps": 10.493159770965576, "step": 598} +{"info/global_step": 599, "train_info/time_within_train_step": 13.168731689453125, "step": 599} +{"train_info/time_between_train_steps": 0.005188465118408203, "step": 599} +{"info/global_step": 600, "train_info/time_within_train_step": 13.335242748260498, "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": 1737051424, "_runtime": 8724}, "step": 600} +{"logs": {"train/loss": 5.2778, "train/learning_rate": 0.0003333333333333333, "train/epoch": 23.0, "_timestamp": 1737051424, "_runtime": 8724}, "step": 600} +{"train_info/time_between_train_steps": 24.395132541656494, "step": 600} +{"info/global_step": 601, "train_info/time_within_train_step": 13.133365392684937, "step": 601} +{"train_info/time_between_train_steps": 0.005288600921630859, "step": 601} +{"info/global_step": 602, "train_info/time_within_train_step": 13.467180252075195, "step": 602} +{"train_info/time_between_train_steps": 0.00553584098815918, "step": 602} +{"info/global_step": 603, "train_info/time_within_train_step": 13.21831727027893, "step": 603} +{"train_info/time_between_train_steps": 0.004984617233276367, "step": 603} +{"info/global_step": 604, "train_info/time_within_train_step": 13.294374704360962, "step": 604} +{"train_info/time_between_train_steps": 0.005146026611328125, "step": 604} +{"info/global_step": 605, "train_info/time_within_train_step": 13.178937911987305, "step": 605} +{"train_info/time_between_train_steps": 0.0051670074462890625, "step": 605} +{"info/global_step": 606, "train_info/time_within_train_step": 13.46955132484436, "step": 606} +{"train_info/time_between_train_steps": 0.004703998565673828, "step": 606} +{"info/global_step": 607, "train_info/time_within_train_step": 14.868302345275879, "step": 607} +{"train_info/time_between_train_steps": 0.0049054622650146484, "step": 607} +{"info/global_step": 608, "train_info/time_within_train_step": 13.293064832687378, "step": 608} +{"train_info/time_between_train_steps": 0.00476384162902832, "step": 608} +{"info/global_step": 609, "train_info/time_within_train_step": 13.174901485443115, "step": 609} +{"train_info/time_between_train_steps": 0.005501747131347656, "step": 609} +{"info/global_step": 610, "train_info/time_within_train_step": 13.215401411056519, "step": 610} +{"train_info/time_between_train_steps": 0.005293369293212891, "step": 610} +{"info/global_step": 611, "train_info/time_within_train_step": 13.276737689971924, "step": 611} +{"train_info/time_between_train_steps": 0.005596637725830078, "step": 611} +{"info/global_step": 612, "train_info/time_within_train_step": 13.204551935195923, "step": 612} +{"train_info/time_between_train_steps": 0.005701780319213867, "step": 612} +{"info/global_step": 613, "train_info/time_within_train_step": 13.192720651626587, "step": 613} +{"train_info/time_between_train_steps": 0.005670070648193359, "step": 613} +{"info/global_step": 614, "train_info/time_within_train_step": 13.201709270477295, "step": 614} +{"train_info/time_between_train_steps": 0.005764007568359375, "step": 614} +{"info/global_step": 615, "train_info/time_within_train_step": 13.177093982696533, "step": 615} +{"train_info/time_between_train_steps": 0.005830049514770508, "step": 615} +{"info/global_step": 616, "train_info/time_within_train_step": 13.227700471878052, "step": 616} +{"train_info/time_between_train_steps": 0.004784107208251953, "step": 616} +{"info/global_step": 617, "train_info/time_within_train_step": 13.181104183197021, "step": 617} +{"train_info/time_between_train_steps": 0.005592823028564453, "step": 617} +{"info/global_step": 618, "train_info/time_within_train_step": 13.174140453338623, "step": 618} +{"train_info/time_between_train_steps": 0.005152463912963867, "step": 618} +{"info/global_step": 619, "train_info/time_within_train_step": 13.182125806808472, "step": 619} +{"train_info/time_between_train_steps": 0.005705833435058594, "step": 619} +{"info/global_step": 620, "train_info/time_within_train_step": 13.17974042892456, "step": 620} +{"train_info/time_between_train_steps": 0.0053653717041015625, "step": 620} +{"info/global_step": 621, "train_info/time_within_train_step": 13.185572624206543, "step": 621} +{"train_info/time_between_train_steps": 0.004701852798461914, "step": 621} +{"info/global_step": 622, "train_info/time_within_train_step": 13.199358940124512, "step": 622} +{"train_info/time_between_train_steps": 0.0054035186767578125, "step": 622} +{"info/global_step": 623, "train_info/time_within_train_step": 13.21200966835022, "step": 623} +{"train_info/time_between_train_steps": 0.0053255558013916016, "step": 623} +{"info/global_step": 624, "train_info/time_within_train_step": 13.219584226608276, "step": 624} +{"train_info/time_between_train_steps": 0.006539106369018555, "step": 624} +{"train_info/time_between_train_steps": 10.667308807373047, "step": 624} +{"info/global_step": 625, "train_info/time_within_train_step": 13.182519912719727, "step": 625} +{"train_info/time_between_train_steps": 0.005140781402587891, "step": 625} +{"info/global_step": 626, "train_info/time_within_train_step": 13.344884872436523, "step": 626} +{"train_info/time_between_train_steps": 0.005202770233154297, "step": 626} +{"info/global_step": 627, "train_info/time_within_train_step": 13.20098876953125, "step": 627} +{"train_info/time_between_train_steps": 0.0052907466888427734, "step": 627} +{"info/global_step": 628, "train_info/time_within_train_step": 13.295072078704834, "step": 628} +{"train_info/time_between_train_steps": 0.005571603775024414, "step": 628} +{"info/global_step": 629, "train_info/time_within_train_step": 13.279892206192017, "step": 629} +{"train_info/time_between_train_steps": 0.005072832107543945, "step": 629} +{"info/global_step": 630, "train_info/time_within_train_step": 13.253581047058105, "step": 630} +{"train_info/time_between_train_steps": 0.005310535430908203, "step": 630} +{"info/global_step": 631, "train_info/time_within_train_step": 13.183738231658936, "step": 631} +{"train_info/time_between_train_steps": 0.005195140838623047, "step": 631} +{"info/global_step": 632, "train_info/time_within_train_step": 13.183127164840698, "step": 632} +{"train_info/time_between_train_steps": 0.005340099334716797, "step": 632} +{"info/global_step": 633, "train_info/time_within_train_step": 13.177924156188965, "step": 633} +{"train_info/time_between_train_steps": 0.004795551300048828, "step": 633} +{"info/global_step": 634, "train_info/time_within_train_step": 13.195521354675293, "step": 634} +{"train_info/time_between_train_steps": 0.005375862121582031, "step": 634} +{"info/global_step": 635, "train_info/time_within_train_step": 13.183642625808716, "step": 635} +{"train_info/time_between_train_steps": 0.005436420440673828, "step": 635} +{"info/global_step": 636, "train_info/time_within_train_step": 13.17961859703064, "step": 636} +{"train_info/time_between_train_steps": 0.005267620086669922, "step": 636} +{"info/global_step": 637, "train_info/time_within_train_step": 13.187463283538818, "step": 637} +{"train_info/time_between_train_steps": 0.00487971305847168, "step": 637} +{"info/global_step": 638, "train_info/time_within_train_step": 13.175610065460205, "step": 638} +{"train_info/time_between_train_steps": 0.0049896240234375, "step": 638} +{"info/global_step": 639, "train_info/time_within_train_step": 13.182821989059448, "step": 639} +{"train_info/time_between_train_steps": 0.005142927169799805, "step": 639} +{"info/global_step": 640, "train_info/time_within_train_step": 13.174203157424927, "step": 640} +{"train_info/time_between_train_steps": 0.004888296127319336, "step": 640} +{"info/global_step": 641, "train_info/time_within_train_step": 13.17336392402649, "step": 641} +{"train_info/time_between_train_steps": 0.005339384078979492, "step": 641} +{"info/global_step": 642, "train_info/time_within_train_step": 13.357367277145386, "step": 642} +{"train_info/time_between_train_steps": 0.005364894866943359, "step": 642} +{"info/global_step": 643, "train_info/time_within_train_step": 13.184914112091064, "step": 643} +{"train_info/time_between_train_steps": 0.005775928497314453, "step": 643} +{"info/global_step": 644, "train_info/time_within_train_step": 13.179931163787842, "step": 644} +{"train_info/time_between_train_steps": 0.005108356475830078, "step": 644} +{"info/global_step": 645, "train_info/time_within_train_step": 13.182982444763184, "step": 645} +{"train_info/time_between_train_steps": 0.005497455596923828, "step": 645} +{"info/global_step": 646, "train_info/time_within_train_step": 13.218555212020874, "step": 646} +{"train_info/time_between_train_steps": 0.005641460418701172, "step": 646} +{"info/global_step": 647, "train_info/time_within_train_step": 13.20692777633667, "step": 647} +{"train_info/time_between_train_steps": 0.005054473876953125, "step": 647} +{"info/global_step": 648, "train_info/time_within_train_step": 13.206026554107666, "step": 648} +{"train_info/time_between_train_steps": 0.005471229553222656, "step": 648} +{"info/global_step": 649, "train_info/time_within_train_step": 13.217485189437866, "step": 649} +{"train_info/time_between_train_steps": 0.005714893341064453, "step": 649} +{"info/global_step": 650, "train_info/time_within_train_step": 13.234357357025146, "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": 1737052127, "_runtime": 9427}, "step": 650} +{"logs": {"train/loss": 5.0381, "train/learning_rate": 0.00030555555555555555, "train/epoch": 24.02, "_timestamp": 1737052127, "_runtime": 9427}, "step": 650} +{"train_info/time_between_train_steps": 0.05831480026245117, "step": 650} +{"train_info/time_between_train_steps": 10.7808358669281, "step": 650} +{"info/global_step": 651, "train_info/time_within_train_step": 13.170654296875, "step": 651} +{"train_info/time_between_train_steps": 0.005005836486816406, "step": 651} +{"info/global_step": 652, "train_info/time_within_train_step": 13.26083254814148, "step": 652} +{"train_info/time_between_train_steps": 0.005177021026611328, "step": 652} +{"info/global_step": 653, "train_info/time_within_train_step": 13.174566268920898, "step": 653} +{"train_info/time_between_train_steps": 0.005272626876831055, "step": 653} +{"info/global_step": 654, "train_info/time_within_train_step": 13.314131498336792, "step": 654} +{"train_info/time_between_train_steps": 0.0050847530364990234, "step": 654} +{"info/global_step": 655, "train_info/time_within_train_step": 13.198022842407227, "step": 655} +{"train_info/time_between_train_steps": 0.005906343460083008, "step": 655} +{"info/global_step": 656, "train_info/time_within_train_step": 13.242526292800903, "step": 656} +{"train_info/time_between_train_steps": 0.005391836166381836, "step": 656} +{"info/global_step": 657, "train_info/time_within_train_step": 13.256238460540771, "step": 657} +{"train_info/time_between_train_steps": 0.005161762237548828, "step": 657} +{"info/global_step": 658, "train_info/time_within_train_step": 13.176557302474976, "step": 658} +{"train_info/time_between_train_steps": 0.005168914794921875, "step": 658} +{"info/global_step": 659, "train_info/time_within_train_step": 13.189590692520142, "step": 659} +{"train_info/time_between_train_steps": 0.0045452117919921875, "step": 659} +{"info/global_step": 660, "train_info/time_within_train_step": 13.184401988983154, "step": 660} +{"train_info/time_between_train_steps": 0.004851341247558594, "step": 660} +{"info/global_step": 661, "train_info/time_within_train_step": 13.18346619606018, "step": 661} +{"train_info/time_between_train_steps": 0.0052890777587890625, "step": 661} +{"info/global_step": 662, "train_info/time_within_train_step": 13.16681957244873, "step": 662} +{"train_info/time_between_train_steps": 0.005064725875854492, "step": 662} +{"info/global_step": 663, "train_info/time_within_train_step": 13.183229923248291, "step": 663} +{"train_info/time_between_train_steps": 0.0053255558013916016, "step": 663} +{"info/global_step": 664, "train_info/time_within_train_step": 13.180513858795166, "step": 664} +{"train_info/time_between_train_steps": 0.005172014236450195, "step": 664} +{"info/global_step": 665, "train_info/time_within_train_step": 13.203488111495972, "step": 665} +{"train_info/time_between_train_steps": 0.005209922790527344, "step": 665} +{"info/global_step": 666, "train_info/time_within_train_step": 13.190521478652954, "step": 666} +{"train_info/time_between_train_steps": 0.00483250617980957, "step": 666} +{"info/global_step": 667, "train_info/time_within_train_step": 13.1815664768219, "step": 667} +{"train_info/time_between_train_steps": 0.0051877498626708984, "step": 667} +{"info/global_step": 668, "train_info/time_within_train_step": 13.183344602584839, "step": 668} +{"train_info/time_between_train_steps": 0.00485682487487793, "step": 668} +{"info/global_step": 669, "train_info/time_within_train_step": 13.175718784332275, "step": 669} +{"train_info/time_between_train_steps": 0.0046253204345703125, "step": 669} +{"info/global_step": 670, "train_info/time_within_train_step": 13.177317380905151, "step": 670} +{"train_info/time_between_train_steps": 0.00525212287902832, "step": 670} +{"info/global_step": 671, "train_info/time_within_train_step": 13.18630862236023, "step": 671} +{"train_info/time_between_train_steps": 0.005365848541259766, "step": 671} +{"info/global_step": 672, "train_info/time_within_train_step": 13.285350561141968, "step": 672} +{"train_info/time_between_train_steps": 0.005572319030761719, "step": 672} +{"info/global_step": 673, "train_info/time_within_train_step": 13.18991994857788, "step": 673} +{"train_info/time_between_train_steps": 0.005350828170776367, "step": 673} +{"info/global_step": 674, "train_info/time_within_train_step": 13.214966773986816, "step": 674} +{"train_info/time_between_train_steps": 0.005297660827636719, "step": 674} +{"info/global_step": 675, "train_info/time_within_train_step": 13.199422597885132, "step": 675} +{"train_info/time_between_train_steps": 0.005422353744506836, "step": 675} +{"info/global_step": 676, "train_info/time_within_train_step": 13.227619171142578, "step": 676} +{"train_info/time_between_train_steps": 0.007632732391357422, "step": 676} +{"train_info/time_between_train_steps": 10.535825252532959, "step": 676} +{"info/global_step": 677, "train_info/time_within_train_step": 13.1910719871521, "step": 677} +{"train_info/time_between_train_steps": 0.0052297115325927734, "step": 677} +{"info/global_step": 678, "train_info/time_within_train_step": 14.2997465133667, "step": 678} +{"train_info/time_between_train_steps": 0.0044803619384765625, "step": 678} +{"info/global_step": 679, "train_info/time_within_train_step": 13.179741382598877, "step": 679} +{"train_info/time_between_train_steps": 0.005221843719482422, "step": 679} +{"info/global_step": 680, "train_info/time_within_train_step": 13.264060735702515, "step": 680} +{"train_info/time_between_train_steps": 0.005165576934814453, "step": 680} +{"info/global_step": 681, "train_info/time_within_train_step": 13.18681001663208, "step": 681} +{"train_info/time_between_train_steps": 0.005535125732421875, "step": 681} +{"info/global_step": 682, "train_info/time_within_train_step": 13.319576263427734, "step": 682} +{"train_info/time_between_train_steps": 0.006076812744140625, "step": 682} +{"info/global_step": 683, "train_info/time_within_train_step": 13.200917959213257, "step": 683} +{"train_info/time_between_train_steps": 0.0055408477783203125, "step": 683} +{"info/global_step": 684, "train_info/time_within_train_step": 13.217228174209595, "step": 684} +{"train_info/time_between_train_steps": 0.005374431610107422, "step": 684} +{"info/global_step": 685, "train_info/time_within_train_step": 13.21189284324646, "step": 685} +{"train_info/time_between_train_steps": 0.004907369613647461, "step": 685} +{"info/global_step": 686, "train_info/time_within_train_step": 13.208714485168457, "step": 686} +{"train_info/time_between_train_steps": 0.005501270294189453, "step": 686} +{"info/global_step": 687, "train_info/time_within_train_step": 13.291579246520996, "step": 687} +{"train_info/time_between_train_steps": 0.006043195724487305, "step": 687} +{"info/global_step": 688, "train_info/time_within_train_step": 13.209563970565796, "step": 688} +{"train_info/time_between_train_steps": 0.004517793655395508, "step": 688} +{"info/global_step": 689, "train_info/time_within_train_step": 13.193800687789917, "step": 689} +{"train_info/time_between_train_steps": 0.0052089691162109375, "step": 689} +{"info/global_step": 690, "train_info/time_within_train_step": 13.20499062538147, "step": 690} +{"train_info/time_between_train_steps": 0.004338979721069336, "step": 690} +{"info/global_step": 691, "train_info/time_within_train_step": 13.241718769073486, "step": 691} +{"train_info/time_between_train_steps": 0.0055081844329833984, "step": 691} +{"info/global_step": 692, "train_info/time_within_train_step": 13.214609146118164, "step": 692} +{"train_info/time_between_train_steps": 0.005692005157470703, "step": 692} +{"info/global_step": 693, "train_info/time_within_train_step": 13.196947813034058, "step": 693} +{"train_info/time_between_train_steps": 0.005045175552368164, "step": 693} +{"info/global_step": 694, "train_info/time_within_train_step": 13.216426134109497, "step": 694} +{"train_info/time_between_train_steps": 0.005657672882080078, "step": 694} +{"info/global_step": 695, "train_info/time_within_train_step": 13.253961086273193, "step": 695} +{"train_info/time_between_train_steps": 0.0060884952545166016, "step": 695} +{"info/global_step": 696, "train_info/time_within_train_step": 13.227640867233276, "step": 696} +{"train_info/time_between_train_steps": 0.00590062141418457, "step": 696} +{"info/global_step": 697, "train_info/time_within_train_step": 13.201051235198975, "step": 697} +{"train_info/time_between_train_steps": 0.005490779876708984, "step": 697} +{"info/global_step": 698, "train_info/time_within_train_step": 13.197822093963623, "step": 698} +{"train_info/time_between_train_steps": 0.005345344543457031, "step": 698} +{"info/global_step": 699, "train_info/time_within_train_step": 13.227717161178589, "step": 699} +{"train_info/time_between_train_steps": 0.005216121673583984, "step": 699} +{"info/global_step": 700, "train_info/time_within_train_step": 13.21472454071045, "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": 1737052812, "_runtime": 10112}, "step": 700} +{"logs": {"train/loss": 4.9558, "train/learning_rate": 0.0002777777777777778, "train/epoch": 26.02, "_timestamp": 1737052812, "_runtime": 10112}, "step": 700} +{"train_info/time_between_train_steps": 19.089892864227295, "step": 700} +{"info/global_step": 701, "train_info/time_within_train_step": 13.160679817199707, "step": 701} +{"train_info/time_between_train_steps": 0.0049822330474853516, "step": 701} +{"info/global_step": 702, "train_info/time_within_train_step": 13.414340734481812, "step": 702} +{"train_info/time_between_train_steps": 0.006115913391113281, "step": 702} +{"train_info/time_between_train_steps": 10.693810224533081, "step": 702} +{"info/global_step": 703, "train_info/time_within_train_step": 13.140906810760498, "step": 703} +{"train_info/time_between_train_steps": 0.005215883255004883, "step": 703} +{"info/global_step": 704, "train_info/time_within_train_step": 13.237964630126953, "step": 704} +{"train_info/time_between_train_steps": 0.005239725112915039, "step": 704} +{"info/global_step": 705, "train_info/time_within_train_step": 13.205820560455322, "step": 705} +{"train_info/time_between_train_steps": 0.005101919174194336, "step": 705} +{"info/global_step": 706, "train_info/time_within_train_step": 13.332914590835571, "step": 706} +{"train_info/time_between_train_steps": 0.004986286163330078, "step": 706} +{"info/global_step": 707, "train_info/time_within_train_step": 13.198051452636719, "step": 707} +{"train_info/time_between_train_steps": 0.005808115005493164, "step": 707} +{"info/global_step": 708, "train_info/time_within_train_step": 13.290324449539185, "step": 708} +{"train_info/time_between_train_steps": 0.004930257797241211, "step": 708} +{"info/global_step": 709, "train_info/time_within_train_step": 13.175788164138794, "step": 709} +{"train_info/time_between_train_steps": 0.0057010650634765625, "step": 709} +{"info/global_step": 710, "train_info/time_within_train_step": 13.190034627914429, "step": 710} +{"train_info/time_between_train_steps": 0.005153179168701172, "step": 710} +{"info/global_step": 711, "train_info/time_within_train_step": 13.163442611694336, "step": 711} +{"train_info/time_between_train_steps": 0.005360603332519531, "step": 711} +{"info/global_step": 712, "train_info/time_within_train_step": 13.175198078155518, "step": 712} +{"train_info/time_between_train_steps": 0.004456281661987305, "step": 712} +{"info/global_step": 713, "train_info/time_within_train_step": 13.172335863113403, "step": 713} +{"train_info/time_between_train_steps": 0.00487971305847168, "step": 713} +{"info/global_step": 714, "train_info/time_within_train_step": 13.16527509689331, "step": 714} +{"train_info/time_between_train_steps": 0.005223751068115234, "step": 714} +{"info/global_step": 715, "train_info/time_within_train_step": 13.17757534980774, "step": 715} +{"train_info/time_between_train_steps": 0.005495548248291016, "step": 715} +{"info/global_step": 716, "train_info/time_within_train_step": 13.181330919265747, "step": 716} +{"train_info/time_between_train_steps": 0.0052301883697509766, "step": 716} +{"info/global_step": 717, "train_info/time_within_train_step": 13.184725522994995, "step": 717} +{"train_info/time_between_train_steps": 0.005312681198120117, "step": 717} +{"info/global_step": 718, "train_info/time_within_train_step": 13.249513387680054, "step": 718} +{"train_info/time_between_train_steps": 0.004693746566772461, "step": 718} +{"info/global_step": 719, "train_info/time_within_train_step": 13.18515396118164, "step": 719} +{"train_info/time_between_train_steps": 0.005531787872314453, "step": 719} +{"info/global_step": 720, "train_info/time_within_train_step": 13.170325517654419, "step": 720} +{"train_info/time_between_train_steps": 0.005239248275756836, "step": 720} +{"info/global_step": 721, "train_info/time_within_train_step": 13.182844638824463, "step": 721} +{"train_info/time_between_train_steps": 0.004509925842285156, "step": 721} +{"info/global_step": 722, "train_info/time_within_train_step": 13.17324447631836, "step": 722} +{"train_info/time_between_train_steps": 0.0055141448974609375, "step": 722} +{"info/global_step": 723, "train_info/time_within_train_step": 13.181084156036377, "step": 723} +{"train_info/time_between_train_steps": 0.005726814270019531, "step": 723} +{"info/global_step": 724, "train_info/time_within_train_step": 13.211399555206299, "step": 724} +{"train_info/time_between_train_steps": 0.0052258968353271484, "step": 724} +{"info/global_step": 725, "train_info/time_within_train_step": 13.19911789894104, "step": 725} +{"train_info/time_between_train_steps": 0.005358695983886719, "step": 725} +{"info/global_step": 726, "train_info/time_within_train_step": 13.195388078689575, "step": 726} +{"train_info/time_between_train_steps": 0.005492687225341797, "step": 726} +{"info/global_step": 727, "train_info/time_within_train_step": 13.195635795593262, "step": 727} +{"train_info/time_between_train_steps": 0.005583763122558594, "step": 727} +{"info/global_step": 728, "train_info/time_within_train_step": 13.218538284301758, "step": 728} +{"train_info/time_between_train_steps": 0.006573677062988281, "step": 728} +{"train_info/time_between_train_steps": 11.89335322380066, "step": 728} +{"info/global_step": 729, "train_info/time_within_train_step": 13.170806646347046, "step": 729} +{"train_info/time_between_train_steps": 0.005747079849243164, "step": 729} +{"info/global_step": 730, "train_info/time_within_train_step": 13.247829675674438, "step": 730} +{"train_info/time_between_train_steps": 0.005179166793823242, "step": 730} +{"info/global_step": 731, "train_info/time_within_train_step": 13.178943634033203, "step": 731} +{"train_info/time_between_train_steps": 0.005227088928222656, "step": 731} +{"info/global_step": 732, "train_info/time_within_train_step": 13.259024143218994, "step": 732} +{"train_info/time_between_train_steps": 0.005482912063598633, "step": 732} +{"info/global_step": 733, "train_info/time_within_train_step": 13.260839700698853, "step": 733} +{"train_info/time_between_train_steps": 0.0046460628509521484, "step": 733} +{"info/global_step": 734, "train_info/time_within_train_step": 13.264721393585205, "step": 734} +{"train_info/time_between_train_steps": 0.005579710006713867, "step": 734} +{"info/global_step": 735, "train_info/time_within_train_step": 13.18949580192566, "step": 735} +{"train_info/time_between_train_steps": 0.005242586135864258, "step": 735} +{"info/global_step": 736, "train_info/time_within_train_step": 13.201019525527954, "step": 736} +{"train_info/time_between_train_steps": 0.005362272262573242, "step": 736} +{"info/global_step": 737, "train_info/time_within_train_step": 13.192832469940186, "step": 737} +{"train_info/time_between_train_steps": 0.004785299301147461, "step": 737} +{"info/global_step": 738, "train_info/time_within_train_step": 13.187117576599121, "step": 738} +{"train_info/time_between_train_steps": 0.00502324104309082, "step": 738} +{"info/global_step": 739, "train_info/time_within_train_step": 13.170516967773438, "step": 739} +{"train_info/time_between_train_steps": 0.004736185073852539, "step": 739} +{"info/global_step": 740, "train_info/time_within_train_step": 13.185773372650146, "step": 740} +{"train_info/time_between_train_steps": 0.0054473876953125, "step": 740} +{"info/global_step": 741, "train_info/time_within_train_step": 13.192382574081421, "step": 741} +{"train_info/time_between_train_steps": 0.005198478698730469, "step": 741} +{"info/global_step": 742, "train_info/time_within_train_step": 13.185577154159546, "step": 742} +{"train_info/time_between_train_steps": 0.00457310676574707, "step": 742} +{"info/global_step": 743, "train_info/time_within_train_step": 13.181289911270142, "step": 743} +{"train_info/time_between_train_steps": 0.005359172821044922, "step": 743} +{"info/global_step": 744, "train_info/time_within_train_step": 13.176551818847656, "step": 744} +{"train_info/time_between_train_steps": 0.00522923469543457, "step": 744} +{"info/global_step": 745, "train_info/time_within_train_step": 13.186434030532837, "step": 745} +{"train_info/time_between_train_steps": 0.005653858184814453, "step": 745} +{"info/global_step": 746, "train_info/time_within_train_step": 13.21012258529663, "step": 746} +{"train_info/time_between_train_steps": 0.004834175109863281, "step": 746} +{"info/global_step": 747, "train_info/time_within_train_step": 13.177812099456787, "step": 747} +{"train_info/time_between_train_steps": 0.004988431930541992, "step": 747} +{"info/global_step": 748, "train_info/time_within_train_step": 13.173222541809082, "step": 748} +{"train_info/time_between_train_steps": 0.00522303581237793, "step": 748} +{"info/global_step": 749, "train_info/time_within_train_step": 13.287016153335571, "step": 749} +{"train_info/time_between_train_steps": 0.004973173141479492, "step": 749} +{"info/global_step": 750, "train_info/time_within_train_step": 13.237902879714966, "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": 1737053517, "_runtime": 10817}, "step": 750} +{"logs": {"train/loss": 4.8301, "train/learning_rate": 0.00025, "train/epoch": 28.02, "_timestamp": 1737053517, "_runtime": 10817}, "step": 750} +{"train_info/time_between_train_steps": 0.05742001533508301, "step": 750} +{"info/global_step": 751, "train_info/time_within_train_step": 13.241705179214478, "step": 751} +{"train_info/time_between_train_steps": 0.005446434020996094, "step": 751} +{"info/global_step": 752, "train_info/time_within_train_step": 13.213385105133057, "step": 752} +{"train_info/time_between_train_steps": 0.004892587661743164, "step": 752} +{"info/global_step": 753, "train_info/time_within_train_step": 13.212315797805786, "step": 753} +{"train_info/time_between_train_steps": 0.005693674087524414, "step": 753} +{"info/global_step": 754, "train_info/time_within_train_step": 13.228978395462036, "step": 754} +{"train_info/time_between_train_steps": 0.006001710891723633, "step": 754} +{"train_info/time_between_train_steps": 10.508658170700073, "step": 754} +{"info/global_step": 755, "train_info/time_within_train_step": 13.201129913330078, "step": 755} +{"train_info/time_between_train_steps": 0.005303859710693359, "step": 755} +{"info/global_step": 756, "train_info/time_within_train_step": 13.290978908538818, "step": 756} +{"train_info/time_between_train_steps": 0.005257129669189453, "step": 756} +{"info/global_step": 757, "train_info/time_within_train_step": 13.181910753250122, "step": 757} +{"train_info/time_between_train_steps": 0.004937648773193359, "step": 757} +{"info/global_step": 758, "train_info/time_within_train_step": 13.301670551300049, "step": 758} +{"train_info/time_between_train_steps": 0.00526118278503418, "step": 758} +{"info/global_step": 759, "train_info/time_within_train_step": 13.202253580093384, "step": 759} +{"train_info/time_between_train_steps": 0.004868507385253906, "step": 759} +{"info/global_step": 760, "train_info/time_within_train_step": 13.286611557006836, "step": 760} +{"train_info/time_between_train_steps": 0.0055599212646484375, "step": 760} +{"info/global_step": 761, "train_info/time_within_train_step": 13.203149795532227, "step": 761} +{"train_info/time_between_train_steps": 0.00498652458190918, "step": 761} +{"info/global_step": 762, "train_info/time_within_train_step": 13.21272587776184, "step": 762} +{"train_info/time_between_train_steps": 0.004786014556884766, "step": 762} +{"info/global_step": 763, "train_info/time_within_train_step": 13.20361614227295, "step": 763} +{"train_info/time_between_train_steps": 0.00523066520690918, "step": 763} +{"info/global_step": 764, "train_info/time_within_train_step": 13.304739475250244, "step": 764} +{"train_info/time_between_train_steps": 0.005217552185058594, "step": 764} +{"info/global_step": 765, "train_info/time_within_train_step": 13.207385540008545, "step": 765} +{"train_info/time_between_train_steps": 0.005325794219970703, "step": 765} +{"info/global_step": 766, "train_info/time_within_train_step": 13.193612098693848, "step": 766} +{"train_info/time_between_train_steps": 0.005254983901977539, "step": 766} +{"info/global_step": 767, "train_info/time_within_train_step": 13.216299295425415, "step": 767} +{"train_info/time_between_train_steps": 0.005800008773803711, "step": 767} +{"info/global_step": 768, "train_info/time_within_train_step": 13.216627836227417, "step": 768} +{"train_info/time_between_train_steps": 0.005416154861450195, "step": 768} +{"info/global_step": 769, "train_info/time_within_train_step": 13.21320629119873, "step": 769} +{"train_info/time_between_train_steps": 0.005425930023193359, "step": 769} +{"info/global_step": 770, "train_info/time_within_train_step": 13.195130348205566, "step": 770} +{"train_info/time_between_train_steps": 0.005474567413330078, "step": 770} +{"info/global_step": 771, "train_info/time_within_train_step": 13.21696949005127, "step": 771} +{"train_info/time_between_train_steps": 0.005438566207885742, "step": 771} +{"info/global_step": 772, "train_info/time_within_train_step": 13.215248584747314, "step": 772} +{"train_info/time_between_train_steps": 0.0051844120025634766, "step": 772} +{"info/global_step": 773, "train_info/time_within_train_step": 13.212655067443848, "step": 773} +{"train_info/time_between_train_steps": 0.005149126052856445, "step": 773} +{"info/global_step": 774, "train_info/time_within_train_step": 13.212844371795654, "step": 774} +{"train_info/time_between_train_steps": 0.005423784255981445, "step": 774} +{"info/global_step": 775, "train_info/time_within_train_step": 13.206018924713135, "step": 775} +{"train_info/time_between_train_steps": 0.00494384765625, "step": 775} +{"info/global_step": 776, "train_info/time_within_train_step": 13.22278642654419, "step": 776} +{"train_info/time_between_train_steps": 0.004633188247680664, "step": 776} +{"info/global_step": 777, "train_info/time_within_train_step": 13.23990273475647, "step": 777} +{"train_info/time_between_train_steps": 0.005620002746582031, "step": 777} +{"info/global_step": 778, "train_info/time_within_train_step": 13.22768521308899, "step": 778} +{"train_info/time_between_train_steps": 0.005631208419799805, "step": 778} +{"info/global_step": 779, "train_info/time_within_train_step": 13.311846256256104, "step": 779} +{"train_info/time_between_train_steps": 0.005702972412109375, "step": 779} +{"info/global_step": 780, "train_info/time_within_train_step": 13.222596645355225, "step": 780} +{"train_info/time_between_train_steps": 0.006155490875244141, "step": 780} +{"train_info/time_between_train_steps": 10.594658374786377, "step": 780} +{"info/global_step": 781, "train_info/time_within_train_step": 13.183332681655884, "step": 781} +{"train_info/time_between_train_steps": 0.004693508148193359, "step": 781} +{"info/global_step": 782, "train_info/time_within_train_step": 13.30503535270691, "step": 782} +{"train_info/time_between_train_steps": 0.005125761032104492, "step": 782} +{"info/global_step": 783, "train_info/time_within_train_step": 13.190061807632446, "step": 783} +{"train_info/time_between_train_steps": 0.00538182258605957, "step": 783} +{"info/global_step": 784, "train_info/time_within_train_step": 13.299099683761597, "step": 784} +{"train_info/time_between_train_steps": 0.00567936897277832, "step": 784} +{"info/global_step": 785, "train_info/time_within_train_step": 13.20344352722168, "step": 785} +{"train_info/time_between_train_steps": 0.004697084426879883, "step": 785} +{"info/global_step": 786, "train_info/time_within_train_step": 13.267059564590454, "step": 786} +{"train_info/time_between_train_steps": 0.0054035186767578125, "step": 786} +{"info/global_step": 787, "train_info/time_within_train_step": 13.21714973449707, "step": 787} +{"train_info/time_between_train_steps": 0.00558161735534668, "step": 787} +{"info/global_step": 788, "train_info/time_within_train_step": 13.240009069442749, "step": 788} +{"train_info/time_between_train_steps": 0.005381584167480469, "step": 788} +{"info/global_step": 789, "train_info/time_within_train_step": 13.221106767654419, "step": 789} +{"train_info/time_between_train_steps": 0.005512237548828125, "step": 789} +{"info/global_step": 790, "train_info/time_within_train_step": 13.258794784545898, "step": 790} +{"train_info/time_between_train_steps": 0.004708528518676758, "step": 790} +{"info/global_step": 791, "train_info/time_within_train_step": 13.207268953323364, "step": 791} +{"train_info/time_between_train_steps": 0.004689931869506836, "step": 791} +{"info/global_step": 792, "train_info/time_within_train_step": 13.204933166503906, "step": 792} +{"train_info/time_between_train_steps": 0.005159139633178711, "step": 792} +{"info/global_step": 793, "train_info/time_within_train_step": 13.218540668487549, "step": 793} +{"train_info/time_between_train_steps": 0.005235910415649414, "step": 793} +{"info/global_step": 794, "train_info/time_within_train_step": 13.324529647827148, "step": 794} +{"train_info/time_between_train_steps": 0.00501251220703125, "step": 794} +{"info/global_step": 795, "train_info/time_within_train_step": 13.21651005744934, "step": 795} +{"train_info/time_between_train_steps": 0.005239725112915039, "step": 795} +{"info/global_step": 796, "train_info/time_within_train_step": 13.206753969192505, "step": 796} +{"train_info/time_between_train_steps": 0.005451679229736328, "step": 796} +{"info/global_step": 797, "train_info/time_within_train_step": 13.208688974380493, "step": 797} +{"train_info/time_between_train_steps": 0.005249977111816406, "step": 797} +{"info/global_step": 798, "train_info/time_within_train_step": 13.23925256729126, "step": 798} +{"train_info/time_between_train_steps": 0.005344390869140625, "step": 798} +{"info/global_step": 799, "train_info/time_within_train_step": 13.242671489715576, "step": 799} +{"train_info/time_between_train_steps": 0.005574703216552734, "step": 799} +{"info/global_step": 800, "train_info/time_within_train_step": 13.206185579299927, "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": 1737054202, "_runtime": 11502}, "step": 800} +{"logs": {"train/loss": 4.7194, "train/learning_rate": 0.00022222222222222218, "train/epoch": 30.02, "_timestamp": 1737054202, "_runtime": 11502}, "step": 800} +{"train_info/time_between_train_steps": 20.869709730148315, "step": 800} +{"info/global_step": 801, "train_info/time_within_train_step": 13.38227367401123, "step": 801} +{"train_info/time_between_train_steps": 0.005235195159912109, "step": 801} +{"info/global_step": 802, "train_info/time_within_train_step": 13.185057401657104, "step": 802} +{"train_info/time_between_train_steps": 0.005375385284423828, "step": 802} +{"info/global_step": 803, "train_info/time_within_train_step": 13.182324171066284, "step": 803} +{"train_info/time_between_train_steps": 0.005778789520263672, "step": 803} +{"info/global_step": 804, "train_info/time_within_train_step": 13.190622091293335, "step": 804} +{"train_info/time_between_train_steps": 0.005301952362060547, "step": 804} +{"info/global_step": 805, "train_info/time_within_train_step": 13.279751539230347, "step": 805} +{"train_info/time_between_train_steps": 0.005723476409912109, "step": 805} +{"info/global_step": 806, "train_info/time_within_train_step": 13.42247724533081, "step": 806} +{"train_info/time_between_train_steps": 0.006437778472900391, "step": 806} +{"train_info/time_between_train_steps": 10.735528469085693, "step": 806} +{"info/global_step": 807, "train_info/time_within_train_step": 13.177591323852539, "step": 807} +{"train_info/time_between_train_steps": 0.004905223846435547, "step": 807} +{"info/global_step": 808, "train_info/time_within_train_step": 13.320192098617554, "step": 808} +{"train_info/time_between_train_steps": 0.004775285720825195, "step": 808} +{"info/global_step": 809, "train_info/time_within_train_step": 13.34079360961914, "step": 809} +{"train_info/time_between_train_steps": 0.005300283432006836, "step": 809} +{"info/global_step": 810, "train_info/time_within_train_step": 13.572076082229614, "step": 810} +{"train_info/time_between_train_steps": 0.00538945198059082, "step": 810} +{"info/global_step": 811, "train_info/time_within_train_step": 13.239095687866211, "step": 811} +{"train_info/time_between_train_steps": 0.005151987075805664, "step": 811} +{"info/global_step": 812, "train_info/time_within_train_step": 13.282512903213501, "step": 812} +{"train_info/time_between_train_steps": 0.0055506229400634766, "step": 812} +{"info/global_step": 813, "train_info/time_within_train_step": 13.222525835037231, "step": 813} +{"train_info/time_between_train_steps": 0.005236387252807617, "step": 813} +{"info/global_step": 814, "train_info/time_within_train_step": 13.223632097244263, "step": 814} +{"train_info/time_between_train_steps": 0.005191802978515625, "step": 814} +{"info/global_step": 815, "train_info/time_within_train_step": 13.246064186096191, "step": 815} +{"train_info/time_between_train_steps": 0.00534367561340332, "step": 815} +{"info/global_step": 816, "train_info/time_within_train_step": 13.194178581237793, "step": 816} +{"train_info/time_between_train_steps": 0.005172014236450195, "step": 816} +{"info/global_step": 817, "train_info/time_within_train_step": 13.19862985610962, "step": 817} +{"train_info/time_between_train_steps": 0.005542755126953125, "step": 817} +{"info/global_step": 818, "train_info/time_within_train_step": 13.209312915802002, "step": 818} +{"train_info/time_between_train_steps": 0.0054454803466796875, "step": 818} +{"info/global_step": 819, "train_info/time_within_train_step": 13.198171615600586, "step": 819} +{"train_info/time_between_train_steps": 0.005409955978393555, "step": 819} +{"info/global_step": 820, "train_info/time_within_train_step": 13.199603080749512, "step": 820} +{"train_info/time_between_train_steps": 0.005597591400146484, "step": 820} +{"info/global_step": 821, "train_info/time_within_train_step": 13.22672438621521, "step": 821} +{"train_info/time_between_train_steps": 0.005250453948974609, "step": 821} +{"info/global_step": 822, "train_info/time_within_train_step": 13.194680452346802, "step": 822} +{"train_info/time_between_train_steps": 0.005417823791503906, "step": 822} +{"info/global_step": 823, "train_info/time_within_train_step": 13.227886199951172, "step": 823} +{"train_info/time_between_train_steps": 0.005293130874633789, "step": 823} +{"info/global_step": 824, "train_info/time_within_train_step": 13.24824070930481, "step": 824} +{"train_info/time_between_train_steps": 0.005465507507324219, "step": 824} +{"info/global_step": 825, "train_info/time_within_train_step": 13.288672685623169, "step": 825} +{"train_info/time_between_train_steps": 0.004665851593017578, "step": 825} +{"info/global_step": 826, "train_info/time_within_train_step": 13.20938515663147, "step": 826} +{"train_info/time_between_train_steps": 0.005675792694091797, "step": 826} +{"info/global_step": 827, "train_info/time_within_train_step": 13.220248460769653, "step": 827} +{"train_info/time_between_train_steps": 0.005038261413574219, "step": 827} +{"info/global_step": 828, "train_info/time_within_train_step": 13.20510745048523, "step": 828} +{"train_info/time_between_train_steps": 0.005261659622192383, "step": 828} +{"info/global_step": 829, "train_info/time_within_train_step": 13.3372163772583, "step": 829} +{"train_info/time_between_train_steps": 0.005014896392822266, "step": 829} +{"info/global_step": 830, "train_info/time_within_train_step": 13.27339792251587, "step": 830} +{"train_info/time_between_train_steps": 0.0050296783447265625, "step": 830} +{"info/global_step": 831, "train_info/time_within_train_step": 13.208845376968384, "step": 831} +{"train_info/time_between_train_steps": 0.005001068115234375, "step": 831} +{"info/global_step": 832, "train_info/time_within_train_step": 13.246622562408447, "step": 832} +{"train_info/time_between_train_steps": 0.006536006927490234, "step": 832} +{"train_info/time_between_train_steps": 10.502004623413086, "step": 832} +{"info/global_step": 833, "train_info/time_within_train_step": 13.223223686218262, "step": 833} +{"train_info/time_between_train_steps": 0.005288839340209961, "step": 833} +{"info/global_step": 834, "train_info/time_within_train_step": 13.271264791488647, "step": 834} +{"train_info/time_between_train_steps": 0.005062580108642578, "step": 834} +{"info/global_step": 835, "train_info/time_within_train_step": 13.229791641235352, "step": 835} +{"train_info/time_between_train_steps": 0.005249738693237305, "step": 835} +{"info/global_step": 836, "train_info/time_within_train_step": 13.356757164001465, "step": 836} +{"train_info/time_between_train_steps": 0.005452632904052734, "step": 836} +{"info/global_step": 837, "train_info/time_within_train_step": 13.21541976928711, "step": 837} +{"train_info/time_between_train_steps": 0.005379915237426758, "step": 837} +{"info/global_step": 838, "train_info/time_within_train_step": 13.284050226211548, "step": 838} +{"train_info/time_between_train_steps": 0.005466461181640625, "step": 838} +{"info/global_step": 839, "train_info/time_within_train_step": 13.22492241859436, "step": 839} +{"train_info/time_between_train_steps": 0.0055370330810546875, "step": 839} +{"info/global_step": 840, "train_info/time_within_train_step": 13.30359172821045, "step": 840} +{"train_info/time_between_train_steps": 0.0054168701171875, "step": 840} +{"info/global_step": 841, "train_info/time_within_train_step": 13.258368015289307, "step": 841} +{"train_info/time_between_train_steps": 0.005682706832885742, "step": 841} +{"info/global_step": 842, "train_info/time_within_train_step": 13.221595764160156, "step": 842} +{"train_info/time_between_train_steps": 0.006235599517822266, "step": 842} +{"info/global_step": 843, "train_info/time_within_train_step": 13.20155930519104, "step": 843} +{"train_info/time_between_train_steps": 0.005580902099609375, "step": 843} +{"info/global_step": 844, "train_info/time_within_train_step": 13.216662168502808, "step": 844} +{"train_info/time_between_train_steps": 0.0050258636474609375, "step": 844} +{"info/global_step": 845, "train_info/time_within_train_step": 13.221222400665283, "step": 845} +{"train_info/time_between_train_steps": 0.004836082458496094, "step": 845} +{"info/global_step": 846, "train_info/time_within_train_step": 13.226619243621826, "step": 846} +{"train_info/time_between_train_steps": 0.005198001861572266, "step": 846} +{"info/global_step": 847, "train_info/time_within_train_step": 13.21335506439209, "step": 847} +{"train_info/time_between_train_steps": 0.005533456802368164, "step": 847} +{"info/global_step": 848, "train_info/time_within_train_step": 13.218971014022827, "step": 848} +{"train_info/time_between_train_steps": 0.0054759979248046875, "step": 848} +{"info/global_step": 849, "train_info/time_within_train_step": 13.236729860305786, "step": 849} +{"train_info/time_between_train_steps": 0.005321979522705078, "step": 849} +{"info/global_step": 850, "train_info/time_within_train_step": 13.20054292678833, "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": 1737054910, "_runtime": 12210}, "step": 850} +{"logs": {"train/loss": 4.623, "train/learning_rate": 0.00019444444444444443, "train/epoch": 32.02, "_timestamp": 1737054910, "_runtime": 12210}, "step": 850} +{"train_info/time_between_train_steps": 0.04448580741882324, "step": 850} +{"info/global_step": 851, "train_info/time_within_train_step": 13.218347787857056, "step": 851} +{"train_info/time_between_train_steps": 0.005538463592529297, "step": 851} +{"info/global_step": 852, "train_info/time_within_train_step": 13.20578408241272, "step": 852} +{"train_info/time_between_train_steps": 0.005572080612182617, "step": 852} +{"info/global_step": 853, "train_info/time_within_train_step": 13.218349695205688, "step": 853} +{"train_info/time_between_train_steps": 0.005196809768676758, "step": 853} +{"info/global_step": 854, "train_info/time_within_train_step": 13.199446678161621, "step": 854} +{"train_info/time_between_train_steps": 0.005232810974121094, "step": 854} +{"info/global_step": 855, "train_info/time_within_train_step": 13.276461601257324, "step": 855} +{"train_info/time_between_train_steps": 0.005645036697387695, "step": 855} +{"info/global_step": 856, "train_info/time_within_train_step": 13.215794563293457, "step": 856} +{"train_info/time_between_train_steps": 0.005720376968383789, "step": 856} +{"info/global_step": 857, "train_info/time_within_train_step": 13.230914115905762, "step": 857} +{"train_info/time_between_train_steps": 0.0061550140380859375, "step": 857} +{"info/global_step": 858, "train_info/time_within_train_step": 13.227585315704346, "step": 858} +{"train_info/time_between_train_steps": 0.0067806243896484375, "step": 858} +{"train_info/time_between_train_steps": 10.619775772094727, "step": 858} +{"info/global_step": 859, "train_info/time_within_train_step": 13.182934522628784, "step": 859} +{"train_info/time_between_train_steps": 0.005494832992553711, "step": 859} +{"info/global_step": 860, "train_info/time_within_train_step": 13.28990650177002, "step": 860} +{"train_info/time_between_train_steps": 0.005181074142456055, "step": 860} +{"info/global_step": 861, "train_info/time_within_train_step": 13.213180780410767, "step": 861} +{"train_info/time_between_train_steps": 0.005396604537963867, "step": 861} +{"info/global_step": 862, "train_info/time_within_train_step": 13.305638790130615, "step": 862} +{"train_info/time_between_train_steps": 0.005262851715087891, "step": 862} +{"info/global_step": 863, "train_info/time_within_train_step": 13.250451803207397, "step": 863} +{"train_info/time_between_train_steps": 0.005286216735839844, "step": 863} +{"info/global_step": 864, "train_info/time_within_train_step": 13.27286171913147, "step": 864} +{"train_info/time_between_train_steps": 0.005492687225341797, "step": 864} +{"info/global_step": 865, "train_info/time_within_train_step": 13.196282386779785, "step": 865} +{"train_info/time_between_train_steps": 0.00542449951171875, "step": 865} +{"info/global_step": 866, "train_info/time_within_train_step": 13.233465433120728, "step": 866} +{"train_info/time_between_train_steps": 0.00517582893371582, "step": 866} +{"info/global_step": 867, "train_info/time_within_train_step": 13.236348152160645, "step": 867} +{"train_info/time_between_train_steps": 0.0052907466888427734, "step": 867} +{"info/global_step": 868, "train_info/time_within_train_step": 13.195991277694702, "step": 868} +{"train_info/time_between_train_steps": 0.005346059799194336, "step": 868} +{"info/global_step": 869, "train_info/time_within_train_step": 13.202367782592773, "step": 869} +{"train_info/time_between_train_steps": 0.005728721618652344, "step": 869} +{"info/global_step": 870, "train_info/time_within_train_step": 13.29876708984375, "step": 870} +{"train_info/time_between_train_steps": 0.005148887634277344, "step": 870} +{"info/global_step": 871, "train_info/time_within_train_step": 13.243685483932495, "step": 871} +{"train_info/time_between_train_steps": 0.005733013153076172, "step": 871} +{"info/global_step": 872, "train_info/time_within_train_step": 13.202980041503906, "step": 872} +{"train_info/time_between_train_steps": 0.005738496780395508, "step": 872} +{"info/global_step": 873, "train_info/time_within_train_step": 13.225079774856567, "step": 873} +{"train_info/time_between_train_steps": 0.005280256271362305, "step": 873} +{"info/global_step": 874, "train_info/time_within_train_step": 13.20071005821228, "step": 874} +{"train_info/time_between_train_steps": 0.0053479671478271484, "step": 874} +{"info/global_step": 875, "train_info/time_within_train_step": 13.219176769256592, "step": 875} +{"train_info/time_between_train_steps": 0.005655527114868164, "step": 875} +{"info/global_step": 876, "train_info/time_within_train_step": 13.24544906616211, "step": 876} +{"train_info/time_between_train_steps": 0.0054473876953125, "step": 876} +{"info/global_step": 877, "train_info/time_within_train_step": 13.202266693115234, "step": 877} +{"train_info/time_between_train_steps": 0.004971742630004883, "step": 877} +{"info/global_step": 878, "train_info/time_within_train_step": 13.203541278839111, "step": 878} +{"train_info/time_between_train_steps": 0.0052983760833740234, "step": 878} +{"info/global_step": 879, "train_info/time_within_train_step": 13.200033187866211, "step": 879} +{"train_info/time_between_train_steps": 0.0054781436920166016, "step": 879} +{"info/global_step": 880, "train_info/time_within_train_step": 13.208784103393555, "step": 880} +{"train_info/time_between_train_steps": 0.0058422088623046875, "step": 880} +{"info/global_step": 881, "train_info/time_within_train_step": 13.210723400115967, "step": 881} +{"train_info/time_between_train_steps": 0.0054569244384765625, "step": 881} +{"info/global_step": 882, "train_info/time_within_train_step": 13.227864980697632, "step": 882} +{"train_info/time_between_train_steps": 0.005419731140136719, "step": 882} +{"info/global_step": 883, "train_info/time_within_train_step": 13.21371603012085, "step": 883} +{"train_info/time_between_train_steps": 0.006120443344116211, "step": 883} +{"info/global_step": 884, "train_info/time_within_train_step": 13.233490943908691, "step": 884} +{"train_info/time_between_train_steps": 0.006861209869384766, "step": 884} +{"train_info/time_between_train_steps": 10.71556830406189, "step": 884} +{"info/global_step": 885, "train_info/time_within_train_step": 13.277664184570312, "step": 885} +{"train_info/time_between_train_steps": 0.0053555965423583984, "step": 885} +{"info/global_step": 886, "train_info/time_within_train_step": 13.290996074676514, "step": 886} +{"train_info/time_between_train_steps": 0.005505084991455078, "step": 886} +{"info/global_step": 887, "train_info/time_within_train_step": 13.198553323745728, "step": 887} +{"train_info/time_between_train_steps": 0.005474567413330078, "step": 887} +{"info/global_step": 888, "train_info/time_within_train_step": 13.323265314102173, "step": 888} +{"train_info/time_between_train_steps": 0.005508899688720703, "step": 888} +{"info/global_step": 889, "train_info/time_within_train_step": 13.220462322235107, "step": 889} +{"train_info/time_between_train_steps": 0.005274772644042969, "step": 889} +{"info/global_step": 890, "train_info/time_within_train_step": 13.29049038887024, "step": 890} +{"train_info/time_between_train_steps": 0.005953073501586914, "step": 890} +{"info/global_step": 891, "train_info/time_within_train_step": 13.220834255218506, "step": 891} +{"train_info/time_between_train_steps": 0.0058557987213134766, "step": 891} +{"info/global_step": 892, "train_info/time_within_train_step": 13.234601259231567, "step": 892} +{"train_info/time_between_train_steps": 0.005582332611083984, "step": 892} +{"info/global_step": 893, "train_info/time_within_train_step": 13.223713874816895, "step": 893} +{"train_info/time_between_train_steps": 0.005498647689819336, "step": 893} +{"info/global_step": 894, "train_info/time_within_train_step": 13.240808725357056, "step": 894} +{"train_info/time_between_train_steps": 0.0052547454833984375, "step": 894} +{"info/global_step": 895, "train_info/time_within_train_step": 13.20719051361084, "step": 895} +{"train_info/time_between_train_steps": 0.004658937454223633, "step": 895} +{"info/global_step": 896, "train_info/time_within_train_step": 13.203904390335083, "step": 896} +{"train_info/time_between_train_steps": 0.0052945613861083984, "step": 896} +{"info/global_step": 897, "train_info/time_within_train_step": 13.223919868469238, "step": 897} +{"train_info/time_between_train_steps": 0.005079984664916992, "step": 897} +{"info/global_step": 898, "train_info/time_within_train_step": 13.243330717086792, "step": 898} +{"train_info/time_between_train_steps": 0.005530118942260742, "step": 898} +{"info/global_step": 899, "train_info/time_within_train_step": 13.216627597808838, "step": 899} +{"train_info/time_between_train_steps": 0.0054819583892822266, "step": 899} +{"info/global_step": 900, "train_info/time_within_train_step": 13.214789152145386, "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": 1737055595, "_runtime": 12895}, "step": 900} +{"logs": {"train/loss": 4.5411, "train/learning_rate": 0.00016666666666666666, "train/epoch": 34.01, "_timestamp": 1737055595, "_runtime": 12895}, "step": 900} +{"train_info/time_between_train_steps": 40.47445201873779, "step": 900} +{"info/global_step": 901, "train_info/time_within_train_step": 13.336169481277466, "step": 901} +{"train_info/time_between_train_steps": 0.004689216613769531, "step": 901} +{"info/global_step": 902, "train_info/time_within_train_step": 13.148504257202148, "step": 902} +{"train_info/time_between_train_steps": 0.005146026611328125, "step": 902} +{"info/global_step": 903, "train_info/time_within_train_step": 13.71802020072937, "step": 903} +{"train_info/time_between_train_steps": 0.005048513412475586, "step": 903} +{"info/global_step": 904, "train_info/time_within_train_step": 13.589821338653564, "step": 904} +{"train_info/time_between_train_steps": 0.004974842071533203, "step": 904} +{"info/global_step": 905, "train_info/time_within_train_step": 13.241999626159668, "step": 905} +{"train_info/time_between_train_steps": 0.005092144012451172, "step": 905} +{"info/global_step": 906, "train_info/time_within_train_step": 13.18731141090393, "step": 906} +{"train_info/time_between_train_steps": 0.005218029022216797, "step": 906} +{"info/global_step": 907, "train_info/time_within_train_step": 13.199920415878296, "step": 907} +{"train_info/time_between_train_steps": 0.005059480667114258, "step": 907} +{"info/global_step": 908, "train_info/time_within_train_step": 13.584242343902588, "step": 908} +{"train_info/time_between_train_steps": 0.004820585250854492, "step": 908} +{"info/global_step": 909, "train_info/time_within_train_step": 13.426933765411377, "step": 909} +{"train_info/time_between_train_steps": 0.005469560623168945, "step": 909} +{"info/global_step": 910, "train_info/time_within_train_step": 13.231250762939453, "step": 910} +{"train_info/time_between_train_steps": 0.0069828033447265625, "step": 910} +{"train_info/time_between_train_steps": 10.452324151992798, "step": 910} +{"info/global_step": 911, "train_info/time_within_train_step": 13.19846773147583, "step": 911} +{"train_info/time_between_train_steps": 0.0054705142974853516, "step": 911} +{"info/global_step": 912, "train_info/time_within_train_step": 13.33894658088684, "step": 912} +{"train_info/time_between_train_steps": 0.005761861801147461, "step": 912} +{"info/global_step": 913, "train_info/time_within_train_step": 13.21510934829712, "step": 913} +{"train_info/time_between_train_steps": 0.005213022232055664, "step": 913} +{"info/global_step": 914, "train_info/time_within_train_step": 13.295490026473999, "step": 914} +{"train_info/time_between_train_steps": 0.005585908889770508, "step": 914} +{"info/global_step": 915, "train_info/time_within_train_step": 13.204621076583862, "step": 915} +{"train_info/time_between_train_steps": 0.005089282989501953, "step": 915} +{"info/global_step": 916, "train_info/time_within_train_step": 13.362154245376587, "step": 916} +{"train_info/time_between_train_steps": 0.005482912063598633, "step": 916} +{"info/global_step": 917, "train_info/time_within_train_step": 13.20676589012146, "step": 917} +{"train_info/time_between_train_steps": 0.005490303039550781, "step": 917} +{"info/global_step": 918, "train_info/time_within_train_step": 13.22027587890625, "step": 918} +{"train_info/time_between_train_steps": 0.005525827407836914, "step": 918} +{"info/global_step": 919, "train_info/time_within_train_step": 13.196197748184204, "step": 919} +{"train_info/time_between_train_steps": 0.005392313003540039, "step": 919} +{"info/global_step": 920, "train_info/time_within_train_step": 13.224495887756348, "step": 920} +{"train_info/time_between_train_steps": 0.0056514739990234375, "step": 920} +{"info/global_step": 921, "train_info/time_within_train_step": 13.19566798210144, "step": 921} +{"train_info/time_between_train_steps": 0.005341291427612305, "step": 921} +{"info/global_step": 922, "train_info/time_within_train_step": 13.211809873580933, "step": 922} +{"train_info/time_between_train_steps": 0.005789518356323242, "step": 922} +{"info/global_step": 923, "train_info/time_within_train_step": 13.205172777175903, "step": 923} +{"train_info/time_between_train_steps": 0.0048291683197021484, "step": 923} +{"info/global_step": 924, "train_info/time_within_train_step": 13.200548648834229, "step": 924} +{"train_info/time_between_train_steps": 0.005012989044189453, "step": 924} +{"info/global_step": 925, "train_info/time_within_train_step": 13.227501630783081, "step": 925} +{"train_info/time_between_train_steps": 0.0049250125885009766, "step": 925} +{"info/global_step": 926, "train_info/time_within_train_step": 13.208083391189575, "step": 926} +{"train_info/time_between_train_steps": 0.0047762393951416016, "step": 926} +{"info/global_step": 927, "train_info/time_within_train_step": 13.201693534851074, "step": 927} +{"train_info/time_between_train_steps": 0.004507303237915039, "step": 927} +{"info/global_step": 928, "train_info/time_within_train_step": 13.197470664978027, "step": 928} +{"train_info/time_between_train_steps": 0.005225658416748047, "step": 928} +{"info/global_step": 929, "train_info/time_within_train_step": 13.287719249725342, "step": 929} +{"train_info/time_between_train_steps": 0.00542449951171875, "step": 929} +{"info/global_step": 930, "train_info/time_within_train_step": 13.236427307128906, "step": 930} +{"train_info/time_between_train_steps": 0.005506038665771484, "step": 930} +{"info/global_step": 931, "train_info/time_within_train_step": 13.227270126342773, "step": 931} +{"train_info/time_between_train_steps": 0.0047419071197509766, "step": 931} +{"info/global_step": 932, "train_info/time_within_train_step": 13.30310583114624, "step": 932} +{"train_info/time_between_train_steps": 0.0049402713775634766, "step": 932} +{"info/global_step": 933, "train_info/time_within_train_step": 13.210286617279053, "step": 933} +{"train_info/time_between_train_steps": 0.0056493282318115234, "step": 933} +{"info/global_step": 934, "train_info/time_within_train_step": 13.25534987449646, "step": 934} +{"train_info/time_between_train_steps": 0.005639791488647461, "step": 934} +{"info/global_step": 935, "train_info/time_within_train_step": 13.233177661895752, "step": 935} +{"train_info/time_between_train_steps": 0.005721569061279297, "step": 935} +{"info/global_step": 936, "train_info/time_within_train_step": 13.264710903167725, "step": 936} +{"train_info/time_between_train_steps": 0.006476640701293945, "step": 936} +{"train_info/time_between_train_steps": 10.563908576965332, "step": 936} +{"info/global_step": 937, "train_info/time_within_train_step": 13.211062669754028, "step": 937} +{"train_info/time_between_train_steps": 0.005294084548950195, "step": 937} +{"info/global_step": 938, "train_info/time_within_train_step": 13.330444812774658, "step": 938} +{"train_info/time_between_train_steps": 0.004518747329711914, "step": 938} +{"info/global_step": 939, "train_info/time_within_train_step": 13.227583408355713, "step": 939} +{"train_info/time_between_train_steps": 0.005423069000244141, "step": 939} +{"info/global_step": 940, "train_info/time_within_train_step": 13.322293043136597, "step": 940} +{"train_info/time_between_train_steps": 0.005262851715087891, "step": 940} +{"info/global_step": 941, "train_info/time_within_train_step": 13.198443174362183, "step": 941} +{"train_info/time_between_train_steps": 0.005493879318237305, "step": 941} +{"info/global_step": 942, "train_info/time_within_train_step": 13.276567220687866, "step": 942} +{"train_info/time_between_train_steps": 0.0052258968353271484, "step": 942} +{"info/global_step": 943, "train_info/time_within_train_step": 13.210678577423096, "step": 943} +{"train_info/time_between_train_steps": 0.005600929260253906, "step": 943} +{"info/global_step": 944, "train_info/time_within_train_step": 13.219952583312988, "step": 944} +{"train_info/time_between_train_steps": 0.005212306976318359, "step": 944} +{"info/global_step": 945, "train_info/time_within_train_step": 13.203330755233765, "step": 945} +{"train_info/time_between_train_steps": 0.005247354507446289, "step": 945} +{"info/global_step": 946, "train_info/time_within_train_step": 13.220962524414062, "step": 946} +{"train_info/time_between_train_steps": 0.005613088607788086, "step": 946} +{"info/global_step": 947, "train_info/time_within_train_step": 13.28234076499939, "step": 947} +{"train_info/time_between_train_steps": 0.005364418029785156, "step": 947} +{"info/global_step": 948, "train_info/time_within_train_step": 13.229076862335205, "step": 948} +{"train_info/time_between_train_steps": 0.005037069320678711, "step": 948} +{"info/global_step": 949, "train_info/time_within_train_step": 13.213359117507935, "step": 949} +{"train_info/time_between_train_steps": 0.0049419403076171875, "step": 949} +{"info/global_step": 950, "train_info/time_within_train_step": 13.205986738204956, "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": 1737056324, "_runtime": 13624}, "step": 950} +{"logs": {"train/loss": 4.4663, "train/learning_rate": 0.0001388888888888889, "train/epoch": 36.01, "_timestamp": 1737056324, "_runtime": 13624}, "step": 950} +{"train_info/time_between_train_steps": 0.06057906150817871, "step": 950} +{"info/global_step": 951, "train_info/time_within_train_step": 13.231016874313354, "step": 951} +{"train_info/time_between_train_steps": 0.005624294281005859, "step": 951} +{"info/global_step": 952, "train_info/time_within_train_step": 13.19479513168335, "step": 952} +{"train_info/time_between_train_steps": 0.005237102508544922, "step": 952} +{"info/global_step": 953, "train_info/time_within_train_step": 13.19496202468872, "step": 953} +{"train_info/time_between_train_steps": 0.004892826080322266, "step": 953} +{"info/global_step": 954, "train_info/time_within_train_step": 13.190503120422363, "step": 954} +{"train_info/time_between_train_steps": 0.005105018615722656, "step": 954} +{"info/global_step": 955, "train_info/time_within_train_step": 13.211592197418213, "step": 955} +{"train_info/time_between_train_steps": 0.005136728286743164, "step": 955} +{"info/global_step": 956, "train_info/time_within_train_step": 13.217054843902588, "step": 956} +{"train_info/time_between_train_steps": 0.005533933639526367, "step": 956} +{"info/global_step": 957, "train_info/time_within_train_step": 13.208527565002441, "step": 957} +{"train_info/time_between_train_steps": 0.005180835723876953, "step": 957} +{"info/global_step": 958, "train_info/time_within_train_step": 13.208542346954346, "step": 958} +{"train_info/time_between_train_steps": 0.004661083221435547, "step": 958} +{"info/global_step": 959, "train_info/time_within_train_step": 13.205034971237183, "step": 959} +{"train_info/time_between_train_steps": 0.005666971206665039, "step": 959} +{"info/global_step": 960, "train_info/time_within_train_step": 13.229631900787354, "step": 960} +{"train_info/time_between_train_steps": 0.004796504974365234, "step": 960} +{"info/global_step": 961, "train_info/time_within_train_step": 13.223724126815796, "step": 961} +{"train_info/time_between_train_steps": 0.006074666976928711, "step": 961} +{"info/global_step": 962, "train_info/time_within_train_step": 13.327489614486694, "step": 962} +{"train_info/time_between_train_steps": 0.006833553314208984, "step": 962} +{"train_info/time_between_train_steps": 10.645278692245483, "step": 962} +{"info/global_step": 963, "train_info/time_within_train_step": 13.186999797821045, "step": 963} +{"train_info/time_between_train_steps": 0.0055963993072509766, "step": 963} +{"info/global_step": 964, "train_info/time_within_train_step": 13.275125980377197, "step": 964} +{"train_info/time_between_train_steps": 0.0055675506591796875, "step": 964} +{"info/global_step": 965, "train_info/time_within_train_step": 13.202761173248291, "step": 965} +{"train_info/time_between_train_steps": 0.005218982696533203, "step": 965} +{"info/global_step": 966, "train_info/time_within_train_step": 13.32650637626648, "step": 966} +{"train_info/time_between_train_steps": 0.0054302215576171875, "step": 966} +{"info/global_step": 967, "train_info/time_within_train_step": 13.208907127380371, "step": 967} +{"train_info/time_between_train_steps": 0.0054416656494140625, "step": 967} +{"info/global_step": 968, "train_info/time_within_train_step": 13.270282983779907, "step": 968} +{"train_info/time_between_train_steps": 0.006033182144165039, "step": 968} +{"info/global_step": 969, "train_info/time_within_train_step": 13.21804404258728, "step": 969} +{"train_info/time_between_train_steps": 0.005335092544555664, "step": 969} +{"info/global_step": 970, "train_info/time_within_train_step": 13.208613157272339, "step": 970} +{"train_info/time_between_train_steps": 0.004874229431152344, "step": 970} +{"info/global_step": 971, "train_info/time_within_train_step": 13.191987991333008, "step": 971} +{"train_info/time_between_train_steps": 0.0049686431884765625, "step": 971} +{"info/global_step": 972, "train_info/time_within_train_step": 13.221971988677979, "step": 972} +{"train_info/time_between_train_steps": 0.005289316177368164, "step": 972} +{"info/global_step": 973, "train_info/time_within_train_step": 13.214333772659302, "step": 973} +{"train_info/time_between_train_steps": 0.0059816837310791016, "step": 973} +{"info/global_step": 974, "train_info/time_within_train_step": 13.204325437545776, "step": 974} +{"train_info/time_between_train_steps": 0.005239009857177734, "step": 974} +{"info/global_step": 975, "train_info/time_within_train_step": 13.204617500305176, "step": 975} +{"train_info/time_between_train_steps": 0.0049474239349365234, "step": 975} +{"info/global_step": 976, "train_info/time_within_train_step": 13.207037448883057, "step": 976} +{"train_info/time_between_train_steps": 0.005112409591674805, "step": 976} +{"info/global_step": 977, "train_info/time_within_train_step": 13.284881114959717, "step": 977} +{"train_info/time_between_train_steps": 0.005590200424194336, "step": 977} +{"info/global_step": 978, "train_info/time_within_train_step": 13.200589895248413, "step": 978} +{"train_info/time_between_train_steps": 0.00579833984375, "step": 978} +{"info/global_step": 979, "train_info/time_within_train_step": 13.201815366744995, "step": 979} +{"train_info/time_between_train_steps": 0.0053822994232177734, "step": 979} +{"info/global_step": 980, "train_info/time_within_train_step": 13.198500156402588, "step": 980} +{"train_info/time_between_train_steps": 0.00495600700378418, "step": 980} +{"info/global_step": 981, "train_info/time_within_train_step": 13.189708948135376, "step": 981} +{"train_info/time_between_train_steps": 0.005379676818847656, "step": 981} +{"info/global_step": 982, "train_info/time_within_train_step": 13.22143816947937, "step": 982} +{"train_info/time_between_train_steps": 0.005251407623291016, "step": 982} +{"info/global_step": 983, "train_info/time_within_train_step": 13.23727822303772, "step": 983} +{"train_info/time_between_train_steps": 0.00538945198059082, "step": 983} +{"info/global_step": 984, "train_info/time_within_train_step": 13.21987247467041, "step": 984} +{"train_info/time_between_train_steps": 0.005536317825317383, "step": 984} +{"info/global_step": 985, "train_info/time_within_train_step": 13.223111391067505, "step": 985} +{"train_info/time_between_train_steps": 0.005608797073364258, "step": 985} +{"info/global_step": 986, "train_info/time_within_train_step": 13.202087163925171, "step": 986} +{"train_info/time_between_train_steps": 0.005398988723754883, "step": 986} +{"info/global_step": 987, "train_info/time_within_train_step": 13.237247705459595, "step": 987} +{"train_info/time_between_train_steps": 0.005852460861206055, "step": 987} +{"info/global_step": 988, "train_info/time_within_train_step": 13.253164291381836, "step": 988} +{"train_info/time_between_train_steps": 0.006232738494873047, "step": 988} +{"train_info/time_between_train_steps": 10.416973114013672, "step": 988} +{"info/global_step": 989, "train_info/time_within_train_step": 13.189018726348877, "step": 989} +{"train_info/time_between_train_steps": 0.005242109298706055, "step": 989} +{"info/global_step": 990, "train_info/time_within_train_step": 13.298049211502075, "step": 990} +{"train_info/time_between_train_steps": 0.005548000335693359, "step": 990} +{"info/global_step": 991, "train_info/time_within_train_step": 13.226899862289429, "step": 991} +{"train_info/time_between_train_steps": 0.004366159439086914, "step": 991} +{"info/global_step": 992, "train_info/time_within_train_step": 13.36499285697937, "step": 992} +{"train_info/time_between_train_steps": 0.0053751468658447266, "step": 992} +{"info/global_step": 993, "train_info/time_within_train_step": 13.182828187942505, "step": 993} +{"train_info/time_between_train_steps": 0.0051043033599853516, "step": 993} +{"info/global_step": 994, "train_info/time_within_train_step": 13.29361343383789, "step": 994} +{"train_info/time_between_train_steps": 0.005692481994628906, "step": 994} +{"info/global_step": 995, "train_info/time_within_train_step": 13.233416318893433, "step": 995} +{"train_info/time_between_train_steps": 0.0054972171783447266, "step": 995} +{"info/global_step": 996, "train_info/time_within_train_step": 13.216500520706177, "step": 996} +{"train_info/time_between_train_steps": 0.0053501129150390625, "step": 996} +{"info/global_step": 997, "train_info/time_within_train_step": 13.205802917480469, "step": 997} +{"train_info/time_between_train_steps": 0.004750967025756836, "step": 997} +{"info/global_step": 998, "train_info/time_within_train_step": 13.201389074325562, "step": 998} +{"train_info/time_between_train_steps": 0.00463557243347168, "step": 998} +{"info/global_step": 999, "train_info/time_within_train_step": 13.180566310882568, "step": 999} +{"train_info/time_between_train_steps": 0.005825996398925781, "step": 999} +{"info/global_step": 1000, "train_info/time_within_train_step": 13.209980726242065, "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": 1737057008, "_runtime": 14308}, "step": 1000} +{"logs": {"train/loss": 4.4012, "train/learning_rate": 0.00011111111111111109, "train/epoch": 38.01, "_timestamp": 1737057008, "_runtime": 14308}, "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": 1737057009, "_runtime": 14309}, "step": 1000} +{"logs": {"eval/loss": 5.870090961456299, "eval/runtime": 1.066, "eval/samples_per_second": 80.673, "eval/steps_per_second": 5.628, "train/epoch": 38.01, "_timestamp": 1737057009, "_runtime": 14309}, "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": 1737057009, "_runtime": 14309}, "step": 1000} +{"logs": {"eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 5.870090961456299, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 354.281204736473, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 1.066, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 80.673, "train/epoch": 38.01, "_timestamp": 1737057009, "_runtime": 14309}, "step": 1000} +{"train_info/time_between_train_steps": 19.276880025863647, "step": 1000} +{"info/global_step": 1001, "train_info/time_within_train_step": 13.147186756134033, "step": 1001} +{"train_info/time_between_train_steps": 0.005415678024291992, "step": 1001} +{"info/global_step": 1002, "train_info/time_within_train_step": 13.147433042526245, "step": 1002} +{"train_info/time_between_train_steps": 0.004947185516357422, "step": 1002} +{"info/global_step": 1003, "train_info/time_within_train_step": 13.175288915634155, "step": 1003} +{"train_info/time_between_train_steps": 0.005250453948974609, "step": 1003} +{"info/global_step": 1004, "train_info/time_within_train_step": 13.156339406967163, "step": 1004} +{"train_info/time_between_train_steps": 0.005232810974121094, "step": 1004} +{"info/global_step": 1005, "train_info/time_within_train_step": 13.14917516708374, "step": 1005} +{"train_info/time_between_train_steps": 0.00565028190612793, "step": 1005} +{"info/global_step": 1006, "train_info/time_within_train_step": 13.166565179824829, "step": 1006} +{"train_info/time_between_train_steps": 0.0051708221435546875, "step": 1006} +{"info/global_step": 1007, "train_info/time_within_train_step": 13.193110466003418, "step": 1007} +{"train_info/time_between_train_steps": 0.005606174468994141, "step": 1007} +{"info/global_step": 1008, "train_info/time_within_train_step": 13.27113127708435, "step": 1008} +{"train_info/time_between_train_steps": 0.005220651626586914, "step": 1008} +{"info/global_step": 1009, "train_info/time_within_train_step": 13.233887910842896, "step": 1009} +{"train_info/time_between_train_steps": 0.005127906799316406, "step": 1009} +{"info/global_step": 1010, "train_info/time_within_train_step": 13.192960500717163, "step": 1010} +{"train_info/time_between_train_steps": 0.004790782928466797, "step": 1010} +{"info/global_step": 1011, "train_info/time_within_train_step": 13.194833755493164, "step": 1011} +{"train_info/time_between_train_steps": 0.004954338073730469, "step": 1011} +{"info/global_step": 1012, "train_info/time_within_train_step": 13.212467908859253, "step": 1012} +{"train_info/time_between_train_steps": 0.0054395198822021484, "step": 1012} +{"info/global_step": 1013, "train_info/time_within_train_step": 13.185999393463135, "step": 1013} +{"train_info/time_between_train_steps": 0.0057141780853271484, "step": 1013} +{"info/global_step": 1014, "train_info/time_within_train_step": 13.207642078399658, "step": 1014} +{"train_info/time_between_train_steps": 0.005746364593505859, "step": 1014} +{"train_info/time_between_train_steps": 10.52459454536438, "step": 1014} +{"info/global_step": 1015, "train_info/time_within_train_step": 13.17338228225708, "step": 1015} +{"train_info/time_between_train_steps": 0.005192279815673828, "step": 1015} +{"info/global_step": 1016, "train_info/time_within_train_step": 13.310530185699463, "step": 1016} +{"train_info/time_between_train_steps": 0.0050506591796875, "step": 1016} +{"info/global_step": 1017, "train_info/time_within_train_step": 13.184394836425781, "step": 1017} +{"train_info/time_between_train_steps": 0.005061149597167969, "step": 1017} +{"info/global_step": 1018, "train_info/time_within_train_step": 13.295445442199707, "step": 1018} +{"train_info/time_between_train_steps": 0.005544185638427734, "step": 1018} +{"info/global_step": 1019, "train_info/time_within_train_step": 13.187042951583862, "step": 1019} +{"train_info/time_between_train_steps": 0.00531315803527832, "step": 1019} +{"info/global_step": 1020, "train_info/time_within_train_step": 13.281595230102539, "step": 1020} +{"train_info/time_between_train_steps": 0.0053327083587646484, "step": 1020} +{"info/global_step": 1021, "train_info/time_within_train_step": 13.187550067901611, "step": 1021} +{"train_info/time_between_train_steps": 0.005233287811279297, "step": 1021} +{"info/global_step": 1022, "train_info/time_within_train_step": 13.199665784835815, "step": 1022} +{"train_info/time_between_train_steps": 0.005362987518310547, "step": 1022} +{"info/global_step": 1023, "train_info/time_within_train_step": 13.262939691543579, "step": 1023} +{"train_info/time_between_train_steps": 0.005633354187011719, "step": 1023} +{"info/global_step": 1024, "train_info/time_within_train_step": 13.192545652389526, "step": 1024} +{"train_info/time_between_train_steps": 0.005231380462646484, "step": 1024} +{"info/global_step": 1025, "train_info/time_within_train_step": 13.168689012527466, "step": 1025} +{"train_info/time_between_train_steps": 0.005203962326049805, "step": 1025} +{"info/global_step": 1026, "train_info/time_within_train_step": 13.170169830322266, "step": 1026} +{"train_info/time_between_train_steps": 0.004952907562255859, "step": 1026} +{"info/global_step": 1027, "train_info/time_within_train_step": 13.172708749771118, "step": 1027} +{"train_info/time_between_train_steps": 0.005462169647216797, "step": 1027} +{"info/global_step": 1028, "train_info/time_within_train_step": 13.177136421203613, "step": 1028} +{"train_info/time_between_train_steps": 0.005166292190551758, "step": 1028} +{"info/global_step": 1029, "train_info/time_within_train_step": 13.334009408950806, "step": 1029} +{"train_info/time_between_train_steps": 0.0051763057708740234, "step": 1029} +{"info/global_step": 1030, "train_info/time_within_train_step": 13.216388940811157, "step": 1030} +{"train_info/time_between_train_steps": 0.004443168640136719, "step": 1030} +{"info/global_step": 1031, "train_info/time_within_train_step": 13.193440914154053, "step": 1031} +{"train_info/time_between_train_steps": 0.005297183990478516, "step": 1031} +{"info/global_step": 1032, "train_info/time_within_train_step": 13.20174241065979, "step": 1032} +{"train_info/time_between_train_steps": 0.005414247512817383, "step": 1032} +{"info/global_step": 1033, "train_info/time_within_train_step": 13.189868688583374, "step": 1033} +{"train_info/time_between_train_steps": 0.004817485809326172, "step": 1033} +{"info/global_step": 1034, "train_info/time_within_train_step": 13.197611808776855, "step": 1034} +{"train_info/time_between_train_steps": 0.005666255950927734, "step": 1034} +{"info/global_step": 1035, "train_info/time_within_train_step": 13.194452285766602, "step": 1035} +{"train_info/time_between_train_steps": 0.005162715911865234, "step": 1035} +{"info/global_step": 1036, "train_info/time_within_train_step": 13.194797039031982, "step": 1036} +{"train_info/time_between_train_steps": 0.0051114559173583984, "step": 1036} +{"info/global_step": 1037, "train_info/time_within_train_step": 13.198422193527222, "step": 1037} +{"train_info/time_between_train_steps": 0.0050199031829833984, "step": 1037} +{"info/global_step": 1038, "train_info/time_within_train_step": 13.214438915252686, "step": 1038} +{"train_info/time_between_train_steps": 0.005918741226196289, "step": 1038} +{"info/global_step": 1039, "train_info/time_within_train_step": 13.289689064025879, "step": 1039} +{"train_info/time_between_train_steps": 0.005315065383911133, "step": 1039} +{"info/global_step": 1040, "train_info/time_within_train_step": 13.215545892715454, "step": 1040} +{"train_info/time_between_train_steps": 0.006578207015991211, "step": 1040} +{"train_info/time_between_train_steps": 10.606188535690308, "step": 1040} +{"info/global_step": 1041, "train_info/time_within_train_step": 13.167196989059448, "step": 1041} +{"train_info/time_between_train_steps": 0.00471806526184082, "step": 1041} +{"info/global_step": 1042, "train_info/time_within_train_step": 13.312280654907227, "step": 1042} +{"train_info/time_between_train_steps": 0.005681037902832031, "step": 1042} +{"info/global_step": 1043, "train_info/time_within_train_step": 13.198612451553345, "step": 1043} +{"train_info/time_between_train_steps": 0.005284309387207031, "step": 1043} +{"info/global_step": 1044, "train_info/time_within_train_step": 13.309254884719849, "step": 1044} +{"train_info/time_between_train_steps": 0.005186796188354492, "step": 1044} +{"info/global_step": 1045, "train_info/time_within_train_step": 13.180286407470703, "step": 1045} +{"train_info/time_between_train_steps": 0.005356311798095703, "step": 1045} +{"info/global_step": 1046, "train_info/time_within_train_step": 13.24649715423584, "step": 1046} +{"train_info/time_between_train_steps": 0.005202054977416992, "step": 1046} +{"info/global_step": 1047, "train_info/time_within_train_step": 13.18971300125122, "step": 1047} +{"train_info/time_between_train_steps": 0.0053975582122802734, "step": 1047} +{"info/global_step": 1048, "train_info/time_within_train_step": 13.206676006317139, "step": 1048} +{"train_info/time_between_train_steps": 0.005547285079956055, "step": 1048} +{"info/global_step": 1049, "train_info/time_within_train_step": 13.167010307312012, "step": 1049} +{"train_info/time_between_train_steps": 0.005383729934692383, "step": 1049} +{"info/global_step": 1050, "train_info/time_within_train_step": 13.178553342819214, "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": 1737057712, "_runtime": 15012}, "step": 1050} +{"logs": {"train/loss": 4.3477, "train/learning_rate": 8.333333333333333e-05, "train/epoch": 40.01, "_timestamp": 1737057712, "_runtime": 15012}, "step": 1050} +{"train_info/time_between_train_steps": 0.057271480560302734, "step": 1050} +{"info/global_step": 1051, "train_info/time_within_train_step": 13.188792705535889, "step": 1051} +{"train_info/time_between_train_steps": 0.004609346389770508, "step": 1051} +{"info/global_step": 1052, "train_info/time_within_train_step": 13.206124067306519, "step": 1052} +{"train_info/time_between_train_steps": 0.0051784515380859375, "step": 1052} +{"info/global_step": 1053, "train_info/time_within_train_step": 13.182154893875122, "step": 1053} +{"train_info/time_between_train_steps": 0.005486726760864258, "step": 1053} +{"info/global_step": 1054, "train_info/time_within_train_step": 13.259780406951904, "step": 1054} +{"train_info/time_between_train_steps": 0.00579524040222168, "step": 1054} +{"info/global_step": 1055, "train_info/time_within_train_step": 13.191592454910278, "step": 1055} +{"train_info/time_between_train_steps": 0.004906415939331055, "step": 1055} +{"info/global_step": 1056, "train_info/time_within_train_step": 13.1782386302948, "step": 1056} +{"train_info/time_between_train_steps": 0.005480766296386719, "step": 1056} +{"info/global_step": 1057, "train_info/time_within_train_step": 13.181713342666626, "step": 1057} +{"train_info/time_between_train_steps": 0.005309581756591797, "step": 1057} +{"info/global_step": 1058, "train_info/time_within_train_step": 13.164136171340942, "step": 1058} +{"train_info/time_between_train_steps": 0.0055484771728515625, "step": 1058} +{"info/global_step": 1059, "train_info/time_within_train_step": 13.186127424240112, "step": 1059} +{"train_info/time_between_train_steps": 0.005476713180541992, "step": 1059} +{"info/global_step": 1060, "train_info/time_within_train_step": 13.168910026550293, "step": 1060} +{"train_info/time_between_train_steps": 0.005001544952392578, "step": 1060} +{"info/global_step": 1061, "train_info/time_within_train_step": 13.209404945373535, "step": 1061} +{"train_info/time_between_train_steps": 0.005606174468994141, "step": 1061} +{"info/global_step": 1062, "train_info/time_within_train_step": 13.191547393798828, "step": 1062} +{"train_info/time_between_train_steps": 0.0052525997161865234, "step": 1062} +{"info/global_step": 1063, "train_info/time_within_train_step": 13.17050051689148, "step": 1063} +{"train_info/time_between_train_steps": 0.0052907466888427734, "step": 1063} +{"info/global_step": 1064, "train_info/time_within_train_step": 13.185519933700562, "step": 1064} +{"train_info/time_between_train_steps": 0.005618095397949219, "step": 1064} +{"info/global_step": 1065, "train_info/time_within_train_step": 13.204183101654053, "step": 1065} +{"train_info/time_between_train_steps": 0.005818367004394531, "step": 1065} +{"info/global_step": 1066, "train_info/time_within_train_step": 13.214410305023193, "step": 1066} +{"train_info/time_between_train_steps": 0.006245136260986328, "step": 1066} +{"train_info/time_between_train_steps": 10.43641448020935, "step": 1066} +{"info/global_step": 1067, "train_info/time_within_train_step": 13.180796384811401, "step": 1067} +{"train_info/time_between_train_steps": 0.005553245544433594, "step": 1067} +{"info/global_step": 1068, "train_info/time_within_train_step": 13.32941722869873, "step": 1068} +{"train_info/time_between_train_steps": 0.0054378509521484375, "step": 1068} +{"info/global_step": 1069, "train_info/time_within_train_step": 13.268695592880249, "step": 1069} +{"train_info/time_between_train_steps": 0.005627632141113281, "step": 1069} +{"info/global_step": 1070, "train_info/time_within_train_step": 13.294207572937012, "step": 1070} +{"train_info/time_between_train_steps": 0.0058536529541015625, "step": 1070} +{"info/global_step": 1071, "train_info/time_within_train_step": 13.17404055595398, "step": 1071} +{"train_info/time_between_train_steps": 0.0054874420166015625, "step": 1071} +{"info/global_step": 1072, "train_info/time_within_train_step": 13.261865854263306, "step": 1072} +{"train_info/time_between_train_steps": 0.0052182674407958984, "step": 1072} +{"info/global_step": 1073, "train_info/time_within_train_step": 13.180067539215088, "step": 1073} +{"train_info/time_between_train_steps": 0.005352497100830078, "step": 1073} +{"info/global_step": 1074, "train_info/time_within_train_step": 13.19809103012085, "step": 1074} +{"train_info/time_between_train_steps": 0.005248546600341797, "step": 1074} +{"info/global_step": 1075, "train_info/time_within_train_step": 13.18021559715271, "step": 1075} +{"train_info/time_between_train_steps": 0.0054476261138916016, "step": 1075} +{"info/global_step": 1076, "train_info/time_within_train_step": 13.18731164932251, "step": 1076} +{"train_info/time_between_train_steps": 0.005454301834106445, "step": 1076} +{"info/global_step": 1077, "train_info/time_within_train_step": 13.312854528427124, "step": 1077} +{"train_info/time_between_train_steps": 0.005372285842895508, "step": 1077} +{"info/global_step": 1078, "train_info/time_within_train_step": 13.168608665466309, "step": 1078} +{"train_info/time_between_train_steps": 0.004773378372192383, "step": 1078} +{"info/global_step": 1079, "train_info/time_within_train_step": 13.169583559036255, "step": 1079} +{"train_info/time_between_train_steps": 0.004837751388549805, "step": 1079} +{"info/global_step": 1080, "train_info/time_within_train_step": 13.176129579544067, "step": 1080} +{"train_info/time_between_train_steps": 0.00559687614440918, "step": 1080} +{"info/global_step": 1081, "train_info/time_within_train_step": 13.168606281280518, "step": 1081} +{"train_info/time_between_train_steps": 0.0051767826080322266, "step": 1081} +{"info/global_step": 1082, "train_info/time_within_train_step": 13.178347826004028, "step": 1082} +{"train_info/time_between_train_steps": 0.005099773406982422, "step": 1082} +{"info/global_step": 1083, "train_info/time_within_train_step": 13.177026510238647, "step": 1083} +{"train_info/time_between_train_steps": 0.005197763442993164, "step": 1083} +{"info/global_step": 1084, "train_info/time_within_train_step": 13.266534090042114, "step": 1084} +{"train_info/time_between_train_steps": 0.0043773651123046875, "step": 1084} +{"info/global_step": 1085, "train_info/time_within_train_step": 13.176082134246826, "step": 1085} +{"train_info/time_between_train_steps": 0.005868196487426758, "step": 1085} +{"info/global_step": 1086, "train_info/time_within_train_step": 13.173802852630615, "step": 1086} +{"train_info/time_between_train_steps": 0.005665302276611328, "step": 1086} +{"info/global_step": 1087, "train_info/time_within_train_step": 13.174156188964844, "step": 1087} +{"train_info/time_between_train_steps": 0.005514383316040039, "step": 1087} +{"info/global_step": 1088, "train_info/time_within_train_step": 13.173200130462646, "step": 1088} +{"train_info/time_between_train_steps": 0.005571603775024414, "step": 1088} +{"info/global_step": 1089, "train_info/time_within_train_step": 13.170568227767944, "step": 1089} +{"train_info/time_between_train_steps": 0.0053331851959228516, "step": 1089} +{"info/global_step": 1090, "train_info/time_within_train_step": 13.199569702148438, "step": 1090} +{"train_info/time_between_train_steps": 0.005584239959716797, "step": 1090} +{"info/global_step": 1091, "train_info/time_within_train_step": 13.219906091690063, "step": 1091} +{"train_info/time_between_train_steps": 0.005450010299682617, "step": 1091} +{"info/global_step": 1092, "train_info/time_within_train_step": 13.217494010925293, "step": 1092} +{"train_info/time_between_train_steps": 0.006143808364868164, "step": 1092} +{"train_info/time_between_train_steps": 10.527897596359253, "step": 1092} +{"info/global_step": 1093, "train_info/time_within_train_step": 13.158228635787964, "step": 1093} +{"train_info/time_between_train_steps": 0.004822969436645508, "step": 1093} +{"info/global_step": 1094, "train_info/time_within_train_step": 13.267173767089844, "step": 1094} +{"train_info/time_between_train_steps": 0.005281686782836914, "step": 1094} +{"info/global_step": 1095, "train_info/time_within_train_step": 13.21380877494812, "step": 1095} +{"train_info/time_between_train_steps": 0.00520777702331543, "step": 1095} +{"info/global_step": 1096, "train_info/time_within_train_step": 13.299773216247559, "step": 1096} +{"train_info/time_between_train_steps": 0.005469083786010742, "step": 1096} +{"info/global_step": 1097, "train_info/time_within_train_step": 13.19633936882019, "step": 1097} +{"train_info/time_between_train_steps": 0.005263566970825195, "step": 1097} +{"info/global_step": 1098, "train_info/time_within_train_step": 13.27751088142395, "step": 1098} +{"train_info/time_between_train_steps": 0.005572795867919922, "step": 1098} +{"info/global_step": 1099, "train_info/time_within_train_step": 13.30969500541687, "step": 1099} +{"train_info/time_between_train_steps": 0.005254507064819336, "step": 1099} +{"info/global_step": 1100, "train_info/time_within_train_step": 13.207144260406494, "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": 1737058395, "_runtime": 15695}, "step": 1100} +{"logs": {"train/loss": 4.3023, "train/learning_rate": 5.5555555555555545e-05, "train/epoch": 42.01, "_timestamp": 1737058395, "_runtime": 15695}, "step": 1100} +{"train_info/time_between_train_steps": 26.82300591468811, "step": 1100} +{"info/global_step": 1101, "train_info/time_within_train_step": 13.224396705627441, "step": 1101} +{"train_info/time_between_train_steps": 0.005262851715087891, "step": 1101} +{"info/global_step": 1102, "train_info/time_within_train_step": 13.137445449829102, "step": 1102} +{"train_info/time_between_train_steps": 0.005566120147705078, "step": 1102} +{"info/global_step": 1103, "train_info/time_within_train_step": 13.13473391532898, "step": 1103} +{"train_info/time_between_train_steps": 0.0045623779296875, "step": 1103} +{"info/global_step": 1104, "train_info/time_within_train_step": 13.139227390289307, "step": 1104} +{"train_info/time_between_train_steps": 0.0051538944244384766, "step": 1104} +{"info/global_step": 1105, "train_info/time_within_train_step": 13.145913124084473, "step": 1105} +{"train_info/time_between_train_steps": 0.00532078742980957, "step": 1105} +{"info/global_step": 1106, "train_info/time_within_train_step": 13.173501968383789, "step": 1106} +{"train_info/time_between_train_steps": 0.005319118499755859, "step": 1106} +{"info/global_step": 1107, "train_info/time_within_train_step": 13.174205780029297, "step": 1107} +{"train_info/time_between_train_steps": 0.0056955814361572266, "step": 1107} +{"info/global_step": 1108, "train_info/time_within_train_step": 13.177700757980347, "step": 1108} +{"train_info/time_between_train_steps": 0.00458216667175293, "step": 1108} +{"info/global_step": 1109, "train_info/time_within_train_step": 13.171527624130249, "step": 1109} +{"train_info/time_between_train_steps": 0.005486726760864258, "step": 1109} +{"info/global_step": 1110, "train_info/time_within_train_step": 13.248459100723267, "step": 1110} +{"train_info/time_between_train_steps": 0.004685640335083008, "step": 1110} +{"info/global_step": 1111, "train_info/time_within_train_step": 13.226650953292847, "step": 1111} +{"train_info/time_between_train_steps": 0.005497455596923828, "step": 1111} +{"info/global_step": 1112, "train_info/time_within_train_step": 13.176406383514404, "step": 1112} +{"train_info/time_between_train_steps": 0.005089998245239258, "step": 1112} +{"info/global_step": 1113, "train_info/time_within_train_step": 13.1647367477417, "step": 1113} +{"train_info/time_between_train_steps": 0.005284309387207031, "step": 1113} +{"info/global_step": 1114, "train_info/time_within_train_step": 13.169930934906006, "step": 1114} +{"train_info/time_between_train_steps": 0.005658626556396484, "step": 1114} +{"info/global_step": 1115, "train_info/time_within_train_step": 13.277616500854492, "step": 1115} +{"train_info/time_between_train_steps": 0.005488395690917969, "step": 1115} +{"info/global_step": 1116, "train_info/time_within_train_step": 13.200241327285767, "step": 1116} +{"train_info/time_between_train_steps": 0.005507946014404297, "step": 1116} +{"info/global_step": 1117, "train_info/time_within_train_step": 13.18615460395813, "step": 1117} +{"train_info/time_between_train_steps": 0.0057337284088134766, "step": 1117} +{"info/global_step": 1118, "train_info/time_within_train_step": 13.205022811889648, "step": 1118} +{"train_info/time_between_train_steps": 0.007075071334838867, "step": 1118} +{"train_info/time_between_train_steps": 10.656638622283936, "step": 1118} +{"info/global_step": 1119, "train_info/time_within_train_step": 13.17721939086914, "step": 1119} +{"train_info/time_between_train_steps": 0.005985260009765625, "step": 1119} +{"info/global_step": 1120, "train_info/time_within_train_step": 13.324576377868652, "step": 1120} +{"train_info/time_between_train_steps": 0.0057201385498046875, "step": 1120} +{"info/global_step": 1121, "train_info/time_within_train_step": 13.190988063812256, "step": 1121} +{"train_info/time_between_train_steps": 0.005556821823120117, "step": 1121} +{"info/global_step": 1122, "train_info/time_within_train_step": 13.331072330474854, "step": 1122} +{"train_info/time_between_train_steps": 0.005625009536743164, "step": 1122} +{"info/global_step": 1123, "train_info/time_within_train_step": 13.18838882446289, "step": 1123} +{"train_info/time_between_train_steps": 0.005557060241699219, "step": 1123} +{"info/global_step": 1124, "train_info/time_within_train_step": 13.305116891860962, "step": 1124} +{"train_info/time_between_train_steps": 0.005509853363037109, "step": 1124} +{"info/global_step": 1125, "train_info/time_within_train_step": 13.191326141357422, "step": 1125} +{"train_info/time_between_train_steps": 0.005564451217651367, "step": 1125} +{"info/global_step": 1126, "train_info/time_within_train_step": 13.187167882919312, "step": 1126} +{"train_info/time_between_train_steps": 0.005122184753417969, "step": 1126} +{"info/global_step": 1127, "train_info/time_within_train_step": 13.80437445640564, "step": 1127} +{"train_info/time_between_train_steps": 0.004868745803833008, "step": 1127} +{"info/global_step": 1128, "train_info/time_within_train_step": 14.283502578735352, "step": 1128} +{"train_info/time_between_train_steps": 0.004777669906616211, "step": 1128} +{"info/global_step": 1129, "train_info/time_within_train_step": 13.199712991714478, "step": 1129} +{"train_info/time_between_train_steps": 0.004678249359130859, "step": 1129} +{"info/global_step": 1130, "train_info/time_within_train_step": 13.274026155471802, "step": 1130} +{"train_info/time_between_train_steps": 0.005234241485595703, "step": 1130} +{"info/global_step": 1131, "train_info/time_within_train_step": 13.208648920059204, "step": 1131} +{"train_info/time_between_train_steps": 0.005455493927001953, "step": 1131} +{"info/global_step": 1132, "train_info/time_within_train_step": 13.192566633224487, "step": 1132} +{"train_info/time_between_train_steps": 0.0048525333404541016, "step": 1132} +{"info/global_step": 1133, "train_info/time_within_train_step": 13.187655448913574, "step": 1133} +{"train_info/time_between_train_steps": 0.005208492279052734, "step": 1133} +{"info/global_step": 1134, "train_info/time_within_train_step": 13.21338438987732, "step": 1134} +{"train_info/time_between_train_steps": 0.005370140075683594, "step": 1134} +{"info/global_step": 1135, "train_info/time_within_train_step": 13.201330184936523, "step": 1135} +{"train_info/time_between_train_steps": 0.005486249923706055, "step": 1135} +{"info/global_step": 1136, "train_info/time_within_train_step": 13.192150115966797, "step": 1136} +{"train_info/time_between_train_steps": 0.00526738166809082, "step": 1136} +{"info/global_step": 1137, "train_info/time_within_train_step": 13.1925687789917, "step": 1137} +{"train_info/time_between_train_steps": 0.005139350891113281, "step": 1137} +{"info/global_step": 1138, "train_info/time_within_train_step": 13.205855369567871, "step": 1138} +{"train_info/time_between_train_steps": 0.005475521087646484, "step": 1138} +{"info/global_step": 1139, "train_info/time_within_train_step": 13.198524475097656, "step": 1139} +{"train_info/time_between_train_steps": 0.005594015121459961, "step": 1139} +{"info/global_step": 1140, "train_info/time_within_train_step": 13.184688091278076, "step": 1140} +{"train_info/time_between_train_steps": 0.0050199031829833984, "step": 1140} +{"info/global_step": 1141, "train_info/time_within_train_step": 13.22530722618103, "step": 1141} +{"train_info/time_between_train_steps": 0.0046541690826416016, "step": 1141} +{"info/global_step": 1142, "train_info/time_within_train_step": 13.212628602981567, "step": 1142} +{"train_info/time_between_train_steps": 0.005658864974975586, "step": 1142} +{"info/global_step": 1143, "train_info/time_within_train_step": 13.198895692825317, "step": 1143} +{"train_info/time_between_train_steps": 0.006232738494873047, "step": 1143} +{"info/global_step": 1144, "train_info/time_within_train_step": 13.227750301361084, "step": 1144} +{"train_info/time_between_train_steps": 0.006174325942993164, "step": 1144} +{"train_info/time_between_train_steps": 10.440244913101196, "step": 1144} +{"info/global_step": 1145, "train_info/time_within_train_step": 13.239970445632935, "step": 1145} +{"train_info/time_between_train_steps": 0.004984855651855469, "step": 1145} +{"info/global_step": 1146, "train_info/time_within_train_step": 13.253899097442627, "step": 1146} +{"train_info/time_between_train_steps": 0.0053522586822509766, "step": 1146} +{"info/global_step": 1147, "train_info/time_within_train_step": 13.183964252471924, "step": 1147} +{"train_info/time_between_train_steps": 0.0050122737884521484, "step": 1147} +{"info/global_step": 1148, "train_info/time_within_train_step": 13.273884534835815, "step": 1148} +{"train_info/time_between_train_steps": 0.004457950592041016, "step": 1148} +{"info/global_step": 1149, "train_info/time_within_train_step": 13.171608686447144, "step": 1149} +{"train_info/time_between_train_steps": 0.005924701690673828, "step": 1149} +{"info/global_step": 1150, "train_info/time_within_train_step": 13.280721426010132, "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": 1737059109, "_runtime": 16409}, "step": 1150} +{"logs": {"train/loss": 4.2672, "train/learning_rate": 2.7777777777777772e-05, "train/epoch": 44.01, "_timestamp": 1737059109, "_runtime": 16409}, "step": 1150} +{"train_info/time_between_train_steps": 0.038926124572753906, "step": 1150} +{"info/global_step": 1151, "train_info/time_within_train_step": 13.267935037612915, "step": 1151} +{"train_info/time_between_train_steps": 0.00532984733581543, "step": 1151} +{"info/global_step": 1152, "train_info/time_within_train_step": 13.192461490631104, "step": 1152} +{"train_info/time_between_train_steps": 0.005430459976196289, "step": 1152} +{"info/global_step": 1153, "train_info/time_within_train_step": 13.171416521072388, "step": 1153} +{"train_info/time_between_train_steps": 0.005283832550048828, "step": 1153} +{"info/global_step": 1154, "train_info/time_within_train_step": 13.195699691772461, "step": 1154} +{"train_info/time_between_train_steps": 0.0053212642669677734, "step": 1154} +{"info/global_step": 1155, "train_info/time_within_train_step": 13.186625719070435, "step": 1155} +{"train_info/time_between_train_steps": 0.005650997161865234, "step": 1155} +{"info/global_step": 1156, "train_info/time_within_train_step": 13.166862726211548, "step": 1156} +{"train_info/time_between_train_steps": 0.005499601364135742, "step": 1156} +{"info/global_step": 1157, "train_info/time_within_train_step": 13.16654086112976, "step": 1157} +{"train_info/time_between_train_steps": 0.004778146743774414, "step": 1157} +{"info/global_step": 1158, "train_info/time_within_train_step": 13.179560422897339, "step": 1158} +{"train_info/time_between_train_steps": 0.00523066520690918, "step": 1158} +{"info/global_step": 1159, "train_info/time_within_train_step": 13.172922134399414, "step": 1159} +{"train_info/time_between_train_steps": 0.005377769470214844, "step": 1159} +{"info/global_step": 1160, "train_info/time_within_train_step": 13.250147819519043, "step": 1160} +{"train_info/time_between_train_steps": 0.005265235900878906, "step": 1160} +{"info/global_step": 1161, "train_info/time_within_train_step": 13.177978277206421, "step": 1161} +{"train_info/time_between_train_steps": 0.005568265914916992, "step": 1161} +{"info/global_step": 1162, "train_info/time_within_train_step": 13.170612096786499, "step": 1162} +{"train_info/time_between_train_steps": 0.005223274230957031, "step": 1162} +{"info/global_step": 1163, "train_info/time_within_train_step": 13.19501805305481, "step": 1163} +{"train_info/time_between_train_steps": 0.005663871765136719, "step": 1163} +{"info/global_step": 1164, "train_info/time_within_train_step": 13.208466529846191, "step": 1164} +{"train_info/time_between_train_steps": 0.005616426467895508, "step": 1164} +{"info/global_step": 1165, "train_info/time_within_train_step": 13.176138639450073, "step": 1165} +{"train_info/time_between_train_steps": 0.005564689636230469, "step": 1165} +{"info/global_step": 1166, "train_info/time_within_train_step": 13.174161195755005, "step": 1166} +{"train_info/time_between_train_steps": 0.005399227142333984, "step": 1166} +{"info/global_step": 1167, "train_info/time_within_train_step": 13.173403263092041, "step": 1167} +{"train_info/time_between_train_steps": 0.00503849983215332, "step": 1167} +{"info/global_step": 1168, "train_info/time_within_train_step": 13.18580150604248, "step": 1168} +{"train_info/time_between_train_steps": 0.005667209625244141, "step": 1168} +{"info/global_step": 1169, "train_info/time_within_train_step": 13.216773509979248, "step": 1169} +{"train_info/time_between_train_steps": 0.005724668502807617, "step": 1169} +{"info/global_step": 1170, "train_info/time_within_train_step": 13.208699464797974, "step": 1170} +{"train_info/time_between_train_steps": 0.005922555923461914, "step": 1170} +{"train_info/time_between_train_steps": 10.595479011535645, "step": 1170} +{"info/global_step": 1171, "train_info/time_within_train_step": 13.181618452072144, "step": 1171} +{"train_info/time_between_train_steps": 0.00476527214050293, "step": 1171} +{"info/global_step": 1172, "train_info/time_within_train_step": 13.25531530380249, "step": 1172} +{"train_info/time_between_train_steps": 0.005173921585083008, "step": 1172} +{"info/global_step": 1173, "train_info/time_within_train_step": 13.192556381225586, "step": 1173} +{"train_info/time_between_train_steps": 0.005311727523803711, "step": 1173} +{"info/global_step": 1174, "train_info/time_within_train_step": 13.27979326248169, "step": 1174} +{"train_info/time_between_train_steps": 0.005272626876831055, "step": 1174} +{"info/global_step": 1175, "train_info/time_within_train_step": 13.26850152015686, "step": 1175} +{"train_info/time_between_train_steps": 0.004800558090209961, "step": 1175} +{"info/global_step": 1176, "train_info/time_within_train_step": 13.408208131790161, "step": 1176} +{"train_info/time_between_train_steps": 0.005970954895019531, "step": 1176} +{"info/global_step": 1177, "train_info/time_within_train_step": 13.190756559371948, "step": 1177} +{"train_info/time_between_train_steps": 0.004647016525268555, "step": 1177} +{"info/global_step": 1178, "train_info/time_within_train_step": 13.169890642166138, "step": 1178} +{"train_info/time_between_train_steps": 0.005360126495361328, "step": 1178} +{"info/global_step": 1179, "train_info/time_within_train_step": 13.15923261642456, "step": 1179} +{"train_info/time_between_train_steps": 0.0048084259033203125, "step": 1179} +{"info/global_step": 1180, "train_info/time_within_train_step": 13.170878410339355, "step": 1180} +{"train_info/time_between_train_steps": 0.004804372787475586, "step": 1180} +{"info/global_step": 1181, "train_info/time_within_train_step": 13.190874099731445, "step": 1181} +{"train_info/time_between_train_steps": 0.005489349365234375, "step": 1181} +{"info/global_step": 1182, "train_info/time_within_train_step": 13.163503170013428, "step": 1182} +{"train_info/time_between_train_steps": 0.005380392074584961, "step": 1182} +{"info/global_step": 1183, "train_info/time_within_train_step": 13.168360471725464, "step": 1183} +{"train_info/time_between_train_steps": 0.004936933517456055, "step": 1183} +{"info/global_step": 1184, "train_info/time_within_train_step": 13.179615497589111, "step": 1184} +{"train_info/time_between_train_steps": 0.005456686019897461, "step": 1184} +{"info/global_step": 1185, "train_info/time_within_train_step": 13.178948402404785, "step": 1185} +{"train_info/time_between_train_steps": 0.0053806304931640625, "step": 1185} +{"info/global_step": 1186, "train_info/time_within_train_step": 13.17396354675293, "step": 1186} +{"train_info/time_between_train_steps": 0.005360603332519531, "step": 1186} +{"info/global_step": 1187, "train_info/time_within_train_step": 13.175595760345459, "step": 1187} +{"train_info/time_between_train_steps": 0.004824638366699219, "step": 1187} +{"info/global_step": 1188, "train_info/time_within_train_step": 13.163361072540283, "step": 1188} +{"train_info/time_between_train_steps": 0.004589080810546875, "step": 1188} +{"info/global_step": 1189, "train_info/time_within_train_step": 13.162657499313354, "step": 1189} +{"train_info/time_between_train_steps": 0.0052907466888427734, "step": 1189} +{"info/global_step": 1190, "train_info/time_within_train_step": 13.201241493225098, "step": 1190} +{"train_info/time_between_train_steps": 0.0051844120025634766, "step": 1190} +{"info/global_step": 1191, "train_info/time_within_train_step": 13.25533676147461, "step": 1191} +{"train_info/time_between_train_steps": 0.005115032196044922, "step": 1191} +{"info/global_step": 1192, "train_info/time_within_train_step": 13.182570219039917, "step": 1192} +{"train_info/time_between_train_steps": 0.005234718322753906, "step": 1192} +{"info/global_step": 1193, "train_info/time_within_train_step": 13.178301811218262, "step": 1193} +{"train_info/time_between_train_steps": 0.005263090133666992, "step": 1193} +{"info/global_step": 1194, "train_info/time_within_train_step": 13.20762300491333, "step": 1194} +{"train_info/time_between_train_steps": 0.005234718322753906, "step": 1194} +{"info/global_step": 1195, "train_info/time_within_train_step": 13.208556175231934, "step": 1195} +{"train_info/time_between_train_steps": 0.005255937576293945, "step": 1195} +{"info/global_step": 1196, "train_info/time_within_train_step": 13.194562673568726, "step": 1196} +{"train_info/time_between_train_steps": 0.0059239864349365234, "step": 1196} +{"train_info/time_between_train_steps": 10.573098421096802, "step": 1196} +{"info/global_step": 1197, "train_info/time_within_train_step": 13.160787105560303, "step": 1197} +{"train_info/time_between_train_steps": 0.005249977111816406, "step": 1197} +{"info/global_step": 1198, "train_info/time_within_train_step": 13.249573707580566, "step": 1198} +{"train_info/time_between_train_steps": 0.005099296569824219, "step": 1198} +{"info/global_step": 1199, "train_info/time_within_train_step": 13.197823286056519, "step": 1199} +{"train_info/time_between_train_steps": 0.00466156005859375, "step": 1199} +{"info/global_step": 1200, "train_info/time_within_train_step": 13.240851402282715, "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": 1737059793, "_runtime": 17093}, "step": 1200} +{"logs": {"train/loss": 4.2432, "train/learning_rate": 0.0, "train/epoch": 46.0, "_timestamp": 1737059793, "_runtime": 17093}, "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": 1737059818, "_runtime": 17118}, "step": 1200} +{"logs": {"train/train_runtime": 17120.5206, "train/train_samples_per_second": 35.887, "train/train_steps_per_second": 0.07, "train/total_flos": 3.28623853142016e+17, "train/train_loss": 5.625780965487162, "train/epoch": 46.0, "_timestamp": 1737059818, "_runtime": 17118}, "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": 1737059832, "_runtime": 17132}, "step": 1200} +{"logs": {"eval/loss": 5.892154216766357, "eval/runtime": 1.4705, "eval/samples_per_second": 58.485, "eval/steps_per_second": 4.08, "train/epoch": 46.0, "_timestamp": 1737059832, "_runtime": 17132}, "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": 1737059832, "_runtime": 17132}, "step": 1200} +{"logs": {"eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_loss": 5.892154216766357, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_ppl": 362.1846688755089, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_runtime": 1.4705, "eval//scratch/ykyao/projects/multilingual-LM/training/multilingual_dataset.py_samples_per_second": 58.485, "train/epoch": 46.0, "_timestamp": 1737059832, "_runtime": 17132}, "step": 1200} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100755 index 0000000000000000000000000000000000000000..17c024ca0e094247bb38d452d459d97910925044 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce201bd9ca56e628228455cacae4efbd1418527b3c8281dcc8bebcb391013333 +size 552615017 diff --git a/shuffle_local3_ar_AR_randinit_seed53.log b/shuffle_local3_ar_AR_randinit_seed53.log new file mode 100755 index 0000000000000000000000000000000000000000..fda7454f73c6d70a16f69791405670bd8e6c7816 --- /dev/null +++ b/shuffle_local3_ar_AR_randinit_seed53.log @@ -0,0 +1,121 @@ +|=>> 01/16 [16:49:46] - mistral - INFO :: Starting Run: shuffle_local3_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_local3_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 [16:49:59] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Concatenating tokenized data using EOS token +|=>> 01/16 [16:49:59] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Chunking tokens into sublists of 1024 +|=>> 01/16 [16:50:00] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Writing dataset as space-separated sequences of tokens +|=>> 01/16 [16:50:09] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Generating examples from = /scratch/ykyao/projects//multilingual-LM/data/multilingual/multilingual_data_perturbed/shuffle_local3_ar/dev +|=>> 01/16 [16:50:09] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Total sentences: 5082 +|=>> 01/16 [16:50:09] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Loading pre-tokenized data +|=>> 01/16 [16:50:09] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Concatenating tokenized data using EOS token +|=>> 01/16 [16:50:09] - datasets_modules.datasets.multilingual_dataset.622766c60cbb8f561ebaa3b973324d0a680a5fd9ae7223c01dd7f116023232f5.multilingual_dataset - INFO :: Chunking tokens into sublists of 1024 +|=>> 01/16 [16:50:09] - 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_local3_ar_AR_randinit/babylm_shuffle_local3_ar_AR_randinit_seed53/runs/shuffle_local3_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_local3_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 [16:51:37] - mistral - INFO :: Training... +|=>> 01/16 [16:51:37] - mistral.core.callbacks - INFO :: Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true" +|=>> 01/16 [21:37:11] - mistral - INFO :: ...and that's all folks! +|=>> 01/16 [21:37:11] - 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..006c07924faddf67fe4ba295c190482de566f21b --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa73a2dd7a818156d96708937b893bedc7965ca9dad3c293776514e47f951 +size 3183