Upload folder using huggingface_hub
Browse files- hubert/general/07_hubert-base-ls960/all_results.json +21 -0
- hubert/general/07_hubert-base-ls960/args.json +11 -0
- hubert/general/07_hubert-base-ls960/eval_results.json +16 -0
- hubert/general/07_hubert-base-ls960/finetuned_pytorch_model.bin +3 -0
- hubert/general/07_hubert-base-ls960/model.safetensors +3 -0
- hubert/general/07_hubert-base-ls960/model_weights.pt +3 -0
- hubert/general/07_hubert-base-ls960/preprocessor_config.json +9 -0
- hubert/general/07_hubert-base-ls960/train_results.json +8 -0
- hubert/general/07_hubert-base-ls960/trainer_args.json +1 -0
- hubert/general/07_hubert-base-ls960/trainer_state.json +618 -0
- hubert/general/07_hubert-base-ls960/training_args.bin +3 -0
hubert/general/07_hubert-base-ls960/all_results.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_loss": 1.1013392210006714,
|
| 4 |
+
"eval_mse_0": 1.393510103225708,
|
| 5 |
+
"eval_mse_1": 0.8640445470809937,
|
| 6 |
+
"eval_mse_2": 0.8827493190765381,
|
| 7 |
+
"eval_mse_3": 1.2650511264801025,
|
| 8 |
+
"eval_pcc_0": 0.6731441812705756,
|
| 9 |
+
"eval_pcc_1": 0.760422008118168,
|
| 10 |
+
"eval_pcc_2": 0.759085092937088,
|
| 11 |
+
"eval_pcc_3": 0.7037933906921356,
|
| 12 |
+
"eval_runtime": 73.2638,
|
| 13 |
+
"eval_samples": 2500,
|
| 14 |
+
"eval_samples_per_second": 34.123,
|
| 15 |
+
"eval_steps_per_second": 4.272,
|
| 16 |
+
"train_loss": 3.1472203686341436,
|
| 17 |
+
"train_runtime": 5570.0464,
|
| 18 |
+
"train_samples": 2500,
|
| 19 |
+
"train_samples_per_second": 13.465,
|
| 20 |
+
"train_steps_per_second": 1.686
|
| 21 |
+
}
|
hubert/general/07_hubert-base-ls960/args.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"batch_size": 4,
|
| 3 |
+
"model_name": "facebook/hubert-base-ls960",
|
| 4 |
+
"learning_rate": 1e-05,
|
| 5 |
+
"num_train_epochs": 30,
|
| 6 |
+
"save_dir": "./model_saved",
|
| 7 |
+
"freeze_feature_extractor": false,
|
| 8 |
+
"exp_name": "facebook/hubert-base-ls960_lr1e-05_epochs30_batch4",
|
| 9 |
+
"save_dir_path": "./model_saved/facebook/hubert-base-ls960_lr1e-05_epochs30_batch4",
|
| 10 |
+
"save_log_path": "./model_saved/logs/facebook/hubert-base-ls960_lr1e-05_epochs30_batch4"
|
| 11 |
+
}
|
hubert/general/07_hubert-base-ls960/eval_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_loss": 1.1013392210006714,
|
| 4 |
+
"eval_mse_0": 1.393510103225708,
|
| 5 |
+
"eval_mse_1": 0.8640445470809937,
|
| 6 |
+
"eval_mse_2": 0.8827493190765381,
|
| 7 |
+
"eval_mse_3": 1.2650511264801025,
|
| 8 |
+
"eval_pcc_0": 0.6731441812705756,
|
| 9 |
+
"eval_pcc_1": 0.760422008118168,
|
| 10 |
+
"eval_pcc_2": 0.759085092937088,
|
| 11 |
+
"eval_pcc_3": 0.7037933906921356,
|
| 12 |
+
"eval_runtime": 73.2638,
|
| 13 |
+
"eval_samples": 2500,
|
| 14 |
+
"eval_samples_per_second": 34.123,
|
| 15 |
+
"eval_steps_per_second": 4.272
|
| 16 |
+
}
|
hubert/general/07_hubert-base-ls960/finetuned_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab1c36b8d766f95234e145ee6524fd634cd944f3045677b64809b874914b5665
|
| 3 |
+
size 377586072
|
hubert/general/07_hubert-base-ls960/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60fc821bad4f91028d66f71d1e7b7c45965f6c7770fdec90c013b70e50da077c
|
| 3 |
+
size 377524352
|
hubert/general/07_hubert-base-ls960/model_weights.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12491e4f0ade3d99eab3399133b0acae69a33e7c461eb33254a1c025d0b287d2
|
| 3 |
+
size 377583774
|
hubert/general/07_hubert-base-ls960/preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
hubert/general/07_hubert-base-ls960/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"train_loss": 3.1472203686341436,
|
| 4 |
+
"train_runtime": 5570.0464,
|
| 5 |
+
"train_samples": 2500,
|
| 6 |
+
"train_samples_per_second": 13.465,
|
| 7 |
+
"train_steps_per_second": 1.686
|
| 8 |
+
}
|
hubert/general/07_hubert-base-ls960/trainer_args.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"output_dir": "./model_saved/facebook/hubert-base-ls960_lr1e-05_epochs30_batch4", "overwrite_output_dir": false, "do_train": false, "do_eval": true, "do_predict": false, "evaluation_strategy": "epoch", "prediction_loss_only": false, "per_device_train_batch_size": 4, "per_device_eval_batch_size": 4, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 1, "eval_accumulation_steps": null, "eval_delay": 0, "learning_rate": 1e-05, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 30, "max_steps": -1, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 0, "log_level": "info", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "./model_saved/logs/facebook/hubert-base-ls960_lr1e-05_epochs30_batch4", "logging_strategy": "steps", "logging_first_step": false, "logging_steps": 500, "logging_nan_inf_filter": true, "save_strategy": "epoch", "save_steps": 500, "save_total_limit": 3, "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": null, "jit_mode_eval": false, "use_ipex": false, "bf16": false, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": null, "local_rank": 0, "ddp_backend": null, "tpu_num_cores": null, "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": null, "dataloader_num_workers": 0, "past_index": -1, "run_name": "./model_saved/facebook/hubert-base-ls960_lr1e-05_epochs30_batch4", "disable_tqdm": false, "remove_unused_columns": true, "label_names": null, "load_best_model_at_end": false, "metric_for_best_model": null, "greater_is_better": null, "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": null, "deepspeed": null, "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["tensorboard"], "ddp_find_unused_parameters": null, "ddp_bucket_cap_mb": null, "ddp_broadcast_buffers": null, "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": null, "hub_model_id": null, "hub_strategy": "every_save", "hub_token": "<HUB_TOKEN>", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": false, "gradient_checkpointing_kwargs": null, "include_inputs_for_metrics": false, "fp16_backend": "auto", "push_to_hub_model_id": null, "push_to_hub_organization": null, "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": null, "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": null, "torch_compile_mode": null, "dispatch_batches": null, "split_batches": false, "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": null}
|
hubert/general/07_hubert-base-ls960/trainer_state.json
ADDED
|
@@ -0,0 +1,618 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 9390,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_loss": 18.94589614868164,
|
| 14 |
+
"eval_mse_0": 19.138105392456055,
|
| 15 |
+
"eval_mse_1": 20.353334426879883,
|
| 16 |
+
"eval_mse_2": 18.32878875732422,
|
| 17 |
+
"eval_mse_3": 17.96331787109375,
|
| 18 |
+
"eval_pcc_0": -0.019775354078464594,
|
| 19 |
+
"eval_pcc_1": 0.32073229782274965,
|
| 20 |
+
"eval_pcc_2": -0.3686178850416101,
|
| 21 |
+
"eval_pcc_3": -0.184556648828156,
|
| 22 |
+
"eval_runtime": 75.7657,
|
| 23 |
+
"eval_samples_per_second": 32.996,
|
| 24 |
+
"eval_steps_per_second": 4.131,
|
| 25 |
+
"step": 313
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.6,
|
| 29 |
+
"learning_rate": 9.467518636847711e-06,
|
| 30 |
+
"loss": 24.7821,
|
| 31 |
+
"step": 500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.0,
|
| 35 |
+
"eval_loss": 12.961767196655273,
|
| 36 |
+
"eval_mse_0": 13.211214065551758,
|
| 37 |
+
"eval_mse_1": 13.721579551696777,
|
| 38 |
+
"eval_mse_2": 12.539637565612793,
|
| 39 |
+
"eval_mse_3": 12.374610900878906,
|
| 40 |
+
"eval_pcc_0": -0.009062262413385178,
|
| 41 |
+
"eval_pcc_1": 0.2695844294986198,
|
| 42 |
+
"eval_pcc_2": -0.36371851756242374,
|
| 43 |
+
"eval_pcc_3": -0.16866729239057338,
|
| 44 |
+
"eval_runtime": 72.218,
|
| 45 |
+
"eval_samples_per_second": 34.617,
|
| 46 |
+
"eval_steps_per_second": 4.334,
|
| 47 |
+
"step": 626
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"eval_loss": 8.109458923339844,
|
| 52 |
+
"eval_mse_0": 8.669883728027344,
|
| 53 |
+
"eval_mse_1": 8.422429084777832,
|
| 54 |
+
"eval_mse_2": 7.490826606750488,
|
| 55 |
+
"eval_mse_3": 7.854800224304199,
|
| 56 |
+
"eval_pcc_0": -0.17246720033170176,
|
| 57 |
+
"eval_pcc_1": 0.2338225279513316,
|
| 58 |
+
"eval_pcc_2": -0.2528964758070238,
|
| 59 |
+
"eval_pcc_3": 0.04309485501760695,
|
| 60 |
+
"eval_runtime": 73.4379,
|
| 61 |
+
"eval_samples_per_second": 34.042,
|
| 62 |
+
"eval_steps_per_second": 4.262,
|
| 63 |
+
"step": 939
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 3.19,
|
| 67 |
+
"learning_rate": 8.935037273695422e-06,
|
| 68 |
+
"loss": 12.4671,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"eval_loss": 4.632750511169434,
|
| 74 |
+
"eval_mse_0": 4.868163108825684,
|
| 75 |
+
"eval_mse_1": 4.771997451782227,
|
| 76 |
+
"eval_mse_2": 4.261656284332275,
|
| 77 |
+
"eval_mse_3": 4.629179000854492,
|
| 78 |
+
"eval_pcc_0": -0.19915402708589455,
|
| 79 |
+
"eval_pcc_1": 0.23591560439723908,
|
| 80 |
+
"eval_pcc_2": -0.4264309711862948,
|
| 81 |
+
"eval_pcc_3": 0.19716859436841042,
|
| 82 |
+
"eval_runtime": 74.6129,
|
| 83 |
+
"eval_samples_per_second": 33.506,
|
| 84 |
+
"eval_steps_per_second": 4.195,
|
| 85 |
+
"step": 1252
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 4.79,
|
| 89 |
+
"learning_rate": 8.402555910543132e-06,
|
| 90 |
+
"loss": 5.9073,
|
| 91 |
+
"step": 1500
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 5.0,
|
| 95 |
+
"eval_loss": 2.755162477493286,
|
| 96 |
+
"eval_mse_0": 2.7911458015441895,
|
| 97 |
+
"eval_mse_1": 2.716233253479004,
|
| 98 |
+
"eval_mse_2": 2.5814898014068604,
|
| 99 |
+
"eval_mse_3": 2.931776523590088,
|
| 100 |
+
"eval_pcc_0": -0.08446967595522585,
|
| 101 |
+
"eval_pcc_1": 0.20246978259044154,
|
| 102 |
+
"eval_pcc_2": -0.39574244374984563,
|
| 103 |
+
"eval_pcc_3": 0.2883422015087234,
|
| 104 |
+
"eval_runtime": 74.0178,
|
| 105 |
+
"eval_samples_per_second": 33.776,
|
| 106 |
+
"eval_steps_per_second": 4.229,
|
| 107 |
+
"step": 1565
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 6.0,
|
| 111 |
+
"eval_loss": 2.243074893951416,
|
| 112 |
+
"eval_mse_0": 2.374678611755371,
|
| 113 |
+
"eval_mse_1": 2.093339443206787,
|
| 114 |
+
"eval_mse_2": 2.0916807651519775,
|
| 115 |
+
"eval_mse_3": 2.4126009941101074,
|
| 116 |
+
"eval_pcc_0": -0.25145935146794657,
|
| 117 |
+
"eval_pcc_1": 0.14908576566148435,
|
| 118 |
+
"eval_pcc_2": -0.30361963666492237,
|
| 119 |
+
"eval_pcc_3": 0.2595830433495344,
|
| 120 |
+
"eval_runtime": 73.0741,
|
| 121 |
+
"eval_samples_per_second": 34.212,
|
| 122 |
+
"eval_steps_per_second": 4.283,
|
| 123 |
+
"step": 1878
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 6.39,
|
| 127 |
+
"learning_rate": 7.870074547390843e-06,
|
| 128 |
+
"loss": 3.1594,
|
| 129 |
+
"step": 2000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.0,
|
| 133 |
+
"eval_loss": 2.2267212867736816,
|
| 134 |
+
"eval_mse_0": 2.376582384109497,
|
| 135 |
+
"eval_mse_1": 2.0338246822357178,
|
| 136 |
+
"eval_mse_2": 2.078275680541992,
|
| 137 |
+
"eval_mse_3": 2.418203115463257,
|
| 138 |
+
"eval_pcc_0": 0.07131768534893983,
|
| 139 |
+
"eval_pcc_1": 0.08182781865822591,
|
| 140 |
+
"eval_pcc_2": 0.07527145679258421,
|
| 141 |
+
"eval_pcc_3": 0.0689498100772488,
|
| 142 |
+
"eval_runtime": 73.8971,
|
| 143 |
+
"eval_samples_per_second": 33.831,
|
| 144 |
+
"eval_steps_per_second": 4.236,
|
| 145 |
+
"step": 2191
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 7.99,
|
| 149 |
+
"learning_rate": 7.337593184238552e-06,
|
| 150 |
+
"loss": 2.4819,
|
| 151 |
+
"step": 2500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 8.0,
|
| 155 |
+
"eval_loss": 1.6627800464630127,
|
| 156 |
+
"eval_mse_0": 1.8164111375808716,
|
| 157 |
+
"eval_mse_1": 1.4906435012817383,
|
| 158 |
+
"eval_mse_2": 1.5327162742614746,
|
| 159 |
+
"eval_mse_3": 1.8113490343093872,
|
| 160 |
+
"eval_pcc_0": 0.49988249511034794,
|
| 161 |
+
"eval_pcc_1": 0.539094430125511,
|
| 162 |
+
"eval_pcc_2": 0.5300123598493314,
|
| 163 |
+
"eval_pcc_3": 0.5117866791232127,
|
| 164 |
+
"eval_runtime": 75.4446,
|
| 165 |
+
"eval_samples_per_second": 33.137,
|
| 166 |
+
"eval_steps_per_second": 4.149,
|
| 167 |
+
"step": 2504
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 9.0,
|
| 171 |
+
"eval_loss": 1.433442234992981,
|
| 172 |
+
"eval_mse_0": 1.6437568664550781,
|
| 173 |
+
"eval_mse_1": 1.224677324295044,
|
| 174 |
+
"eval_mse_2": 1.2679296731948853,
|
| 175 |
+
"eval_mse_3": 1.5974042415618896,
|
| 176 |
+
"eval_pcc_0": 0.5775330834150761,
|
| 177 |
+
"eval_pcc_1": 0.6409293136357318,
|
| 178 |
+
"eval_pcc_2": 0.6367375165596971,
|
| 179 |
+
"eval_pcc_3": 0.5995155662582619,
|
| 180 |
+
"eval_runtime": 75.6534,
|
| 181 |
+
"eval_samples_per_second": 33.045,
|
| 182 |
+
"eval_steps_per_second": 4.137,
|
| 183 |
+
"step": 2817
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 9.58,
|
| 187 |
+
"learning_rate": 6.805111821086262e-06,
|
| 188 |
+
"loss": 1.3945,
|
| 189 |
+
"step": 3000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.0,
|
| 193 |
+
"eval_loss": 1.499963641166687,
|
| 194 |
+
"eval_mse_0": 1.6864652633666992,
|
| 195 |
+
"eval_mse_1": 1.2988204956054688,
|
| 196 |
+
"eval_mse_2": 1.3645745515823364,
|
| 197 |
+
"eval_mse_3": 1.6499913930892944,
|
| 198 |
+
"eval_pcc_0": 0.5904100816412751,
|
| 199 |
+
"eval_pcc_1": 0.644890519030269,
|
| 200 |
+
"eval_pcc_2": 0.6408895852798253,
|
| 201 |
+
"eval_pcc_3": 0.6067129178848146,
|
| 202 |
+
"eval_runtime": 73.6715,
|
| 203 |
+
"eval_samples_per_second": 33.934,
|
| 204 |
+
"eval_steps_per_second": 4.249,
|
| 205 |
+
"step": 3130
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 11.0,
|
| 209 |
+
"eval_loss": 1.2064470052719116,
|
| 210 |
+
"eval_mse_0": 1.4318058490753174,
|
| 211 |
+
"eval_mse_1": 0.993518054485321,
|
| 212 |
+
"eval_mse_2": 1.0274714231491089,
|
| 213 |
+
"eval_mse_3": 1.3729945421218872,
|
| 214 |
+
"eval_pcc_0": 0.6424657707208132,
|
| 215 |
+
"eval_pcc_1": 0.7167796179736279,
|
| 216 |
+
"eval_pcc_2": 0.7122768087462553,
|
| 217 |
+
"eval_pcc_3": 0.6626173302663154,
|
| 218 |
+
"eval_runtime": 72.9799,
|
| 219 |
+
"eval_samples_per_second": 34.256,
|
| 220 |
+
"eval_steps_per_second": 4.289,
|
| 221 |
+
"step": 3443
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 11.18,
|
| 225 |
+
"learning_rate": 6.272630457933972e-06,
|
| 226 |
+
"loss": 1.0587,
|
| 227 |
+
"step": 3500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 12.0,
|
| 231 |
+
"eval_loss": 1.2195730209350586,
|
| 232 |
+
"eval_mse_0": 1.4471089839935303,
|
| 233 |
+
"eval_mse_1": 1.0103874206542969,
|
| 234 |
+
"eval_mse_2": 1.0344873666763306,
|
| 235 |
+
"eval_mse_3": 1.3863112926483154,
|
| 236 |
+
"eval_pcc_0": 0.6393142177222919,
|
| 237 |
+
"eval_pcc_1": 0.7109860207901474,
|
| 238 |
+
"eval_pcc_2": 0.7092582491462749,
|
| 239 |
+
"eval_pcc_3": 0.6574546793040985,
|
| 240 |
+
"eval_runtime": 72.8339,
|
| 241 |
+
"eval_samples_per_second": 34.325,
|
| 242 |
+
"eval_steps_per_second": 4.297,
|
| 243 |
+
"step": 3756
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 12.78,
|
| 247 |
+
"learning_rate": 5.7401490947816826e-06,
|
| 248 |
+
"loss": 0.9281,
|
| 249 |
+
"step": 4000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 13.0,
|
| 253 |
+
"eval_loss": 1.2376728057861328,
|
| 254 |
+
"eval_mse_0": 1.4397125244140625,
|
| 255 |
+
"eval_mse_1": 1.0402178764343262,
|
| 256 |
+
"eval_mse_2": 1.072370171546936,
|
| 257 |
+
"eval_mse_3": 1.3983912467956543,
|
| 258 |
+
"eval_pcc_0": 0.6578162013798159,
|
| 259 |
+
"eval_pcc_1": 0.7165562875046174,
|
| 260 |
+
"eval_pcc_2": 0.715312523140568,
|
| 261 |
+
"eval_pcc_3": 0.6748854371889728,
|
| 262 |
+
"eval_runtime": 74.2124,
|
| 263 |
+
"eval_samples_per_second": 33.687,
|
| 264 |
+
"eval_steps_per_second": 4.218,
|
| 265 |
+
"step": 4069
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 14.0,
|
| 269 |
+
"eval_loss": 1.2460466623306274,
|
| 270 |
+
"eval_mse_0": 1.497269868850708,
|
| 271 |
+
"eval_mse_1": 1.0242962837219238,
|
| 272 |
+
"eval_mse_2": 1.0656968355178833,
|
| 273 |
+
"eval_mse_3": 1.3969237804412842,
|
| 274 |
+
"eval_pcc_0": 0.6604654316296025,
|
| 275 |
+
"eval_pcc_1": 0.7266939645521422,
|
| 276 |
+
"eval_pcc_2": 0.7226343363305833,
|
| 277 |
+
"eval_pcc_3": 0.6765067807861624,
|
| 278 |
+
"eval_runtime": 73.1805,
|
| 279 |
+
"eval_samples_per_second": 34.162,
|
| 280 |
+
"eval_steps_per_second": 4.277,
|
| 281 |
+
"step": 4382
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 14.38,
|
| 285 |
+
"learning_rate": 5.207667731629393e-06,
|
| 286 |
+
"loss": 0.843,
|
| 287 |
+
"step": 4500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 15.0,
|
| 291 |
+
"eval_loss": 1.0952329635620117,
|
| 292 |
+
"eval_mse_0": 1.3052796125411987,
|
| 293 |
+
"eval_mse_1": 0.9198900461196899,
|
| 294 |
+
"eval_mse_2": 0.9201720952987671,
|
| 295 |
+
"eval_mse_3": 1.235589861869812,
|
| 296 |
+
"eval_pcc_0": 0.6880050707527338,
|
| 297 |
+
"eval_pcc_1": 0.7471154923500962,
|
| 298 |
+
"eval_pcc_2": 0.7460546104271563,
|
| 299 |
+
"eval_pcc_3": 0.7095678766320669,
|
| 300 |
+
"eval_runtime": 71.4181,
|
| 301 |
+
"eval_samples_per_second": 35.005,
|
| 302 |
+
"eval_steps_per_second": 4.383,
|
| 303 |
+
"step": 4695
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 15.97,
|
| 307 |
+
"learning_rate": 4.675186368477103e-06,
|
| 308 |
+
"loss": 0.7827,
|
| 309 |
+
"step": 5000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 16.0,
|
| 313 |
+
"eval_loss": 1.2079945802688599,
|
| 314 |
+
"eval_mse_0": 1.4361698627471924,
|
| 315 |
+
"eval_mse_1": 0.9961063265800476,
|
| 316 |
+
"eval_mse_2": 1.0287089347839355,
|
| 317 |
+
"eval_mse_3": 1.3709943294525146,
|
| 318 |
+
"eval_pcc_0": 0.6626336776589729,
|
| 319 |
+
"eval_pcc_1": 0.7225576813560481,
|
| 320 |
+
"eval_pcc_2": 0.722568078532247,
|
| 321 |
+
"eval_pcc_3": 0.6782456875867207,
|
| 322 |
+
"eval_runtime": 74.9371,
|
| 323 |
+
"eval_samples_per_second": 33.361,
|
| 324 |
+
"eval_steps_per_second": 4.177,
|
| 325 |
+
"step": 5008
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 17.0,
|
| 329 |
+
"eval_loss": 1.1427335739135742,
|
| 330 |
+
"eval_mse_0": 1.377644658088684,
|
| 331 |
+
"eval_mse_1": 0.929233193397522,
|
| 332 |
+
"eval_mse_2": 0.9717167019844055,
|
| 333 |
+
"eval_mse_3": 1.2923420667648315,
|
| 334 |
+
"eval_pcc_0": 0.6856919490222633,
|
| 335 |
+
"eval_pcc_1": 0.7531635931263728,
|
| 336 |
+
"eval_pcc_2": 0.7523105898371623,
|
| 337 |
+
"eval_pcc_3": 0.7096058384985755,
|
| 338 |
+
"eval_runtime": 73.6381,
|
| 339 |
+
"eval_samples_per_second": 33.95,
|
| 340 |
+
"eval_steps_per_second": 4.251,
|
| 341 |
+
"step": 5321
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 17.57,
|
| 345 |
+
"learning_rate": 4.142705005324814e-06,
|
| 346 |
+
"loss": 0.7299,
|
| 347 |
+
"step": 5500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 18.0,
|
| 351 |
+
"eval_loss": 1.1075248718261719,
|
| 352 |
+
"eval_mse_0": 1.369035005569458,
|
| 353 |
+
"eval_mse_1": 0.8825894594192505,
|
| 354 |
+
"eval_mse_2": 0.8975585699081421,
|
| 355 |
+
"eval_mse_3": 1.280916690826416,
|
| 356 |
+
"eval_pcc_0": 0.6798550006684007,
|
| 357 |
+
"eval_pcc_1": 0.7520715179427919,
|
| 358 |
+
"eval_pcc_2": 0.7516719197918724,
|
| 359 |
+
"eval_pcc_3": 0.7046185974825382,
|
| 360 |
+
"eval_runtime": 72.6208,
|
| 361 |
+
"eval_samples_per_second": 34.425,
|
| 362 |
+
"eval_steps_per_second": 4.31,
|
| 363 |
+
"step": 5634
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 19.0,
|
| 367 |
+
"eval_loss": 1.1430003643035889,
|
| 368 |
+
"eval_mse_0": 1.3781789541244507,
|
| 369 |
+
"eval_mse_1": 0.9454674124717712,
|
| 370 |
+
"eval_mse_2": 0.9471389651298523,
|
| 371 |
+
"eval_mse_3": 1.3012163639068604,
|
| 372 |
+
"eval_pcc_0": 0.6817389618828931,
|
| 373 |
+
"eval_pcc_1": 0.7499565210734432,
|
| 374 |
+
"eval_pcc_2": 0.7499963974231123,
|
| 375 |
+
"eval_pcc_3": 0.7029371882182629,
|
| 376 |
+
"eval_runtime": 74.1904,
|
| 377 |
+
"eval_samples_per_second": 33.697,
|
| 378 |
+
"eval_steps_per_second": 4.219,
|
| 379 |
+
"step": 5947
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 19.17,
|
| 383 |
+
"learning_rate": 3.6102236421725247e-06,
|
| 384 |
+
"loss": 0.6645,
|
| 385 |
+
"step": 6000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 20.0,
|
| 389 |
+
"eval_loss": 1.060410976409912,
|
| 390 |
+
"eval_mse_0": 1.2819561958312988,
|
| 391 |
+
"eval_mse_1": 0.8739719986915588,
|
| 392 |
+
"eval_mse_2": 0.8855644464492798,
|
| 393 |
+
"eval_mse_3": 1.200150489807129,
|
| 394 |
+
"eval_pcc_0": 0.686409776218007,
|
| 395 |
+
"eval_pcc_1": 0.7559929058426073,
|
| 396 |
+
"eval_pcc_2": 0.756017821540729,
|
| 397 |
+
"eval_pcc_3": 0.7105563780813466,
|
| 398 |
+
"eval_runtime": 74.9259,
|
| 399 |
+
"eval_samples_per_second": 33.366,
|
| 400 |
+
"eval_steps_per_second": 4.177,
|
| 401 |
+
"step": 6260
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 20.77,
|
| 405 |
+
"learning_rate": 3.0777422790202343e-06,
|
| 406 |
+
"loss": 0.6454,
|
| 407 |
+
"step": 6500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 21.0,
|
| 411 |
+
"eval_loss": 1.0913147926330566,
|
| 412 |
+
"eval_mse_0": 1.3480528593063354,
|
| 413 |
+
"eval_mse_1": 0.8806869387626648,
|
| 414 |
+
"eval_mse_2": 0.8995609283447266,
|
| 415 |
+
"eval_mse_3": 1.2369579076766968,
|
| 416 |
+
"eval_pcc_0": 0.6837673111340477,
|
| 417 |
+
"eval_pcc_1": 0.7554596596417744,
|
| 418 |
+
"eval_pcc_2": 0.7548029849507781,
|
| 419 |
+
"eval_pcc_3": 0.7090283355638027,
|
| 420 |
+
"eval_runtime": 73.0718,
|
| 421 |
+
"eval_samples_per_second": 34.213,
|
| 422 |
+
"eval_steps_per_second": 4.283,
|
| 423 |
+
"step": 6573
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 22.0,
|
| 427 |
+
"eval_loss": 1.111764669418335,
|
| 428 |
+
"eval_mse_0": 1.3963850736618042,
|
| 429 |
+
"eval_mse_1": 0.8774217963218689,
|
| 430 |
+
"eval_mse_2": 0.893271803855896,
|
| 431 |
+
"eval_mse_3": 1.2799782752990723,
|
| 432 |
+
"eval_pcc_0": 0.6798838503405358,
|
| 433 |
+
"eval_pcc_1": 0.7570017423206189,
|
| 434 |
+
"eval_pcc_2": 0.757041717977088,
|
| 435 |
+
"eval_pcc_3": 0.7062723355094601,
|
| 436 |
+
"eval_runtime": 70.7308,
|
| 437 |
+
"eval_samples_per_second": 35.345,
|
| 438 |
+
"eval_steps_per_second": 4.425,
|
| 439 |
+
"step": 6886
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 22.36,
|
| 443 |
+
"learning_rate": 2.5452609158679447e-06,
|
| 444 |
+
"loss": 0.6451,
|
| 445 |
+
"step": 7000
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 23.0,
|
| 449 |
+
"eval_loss": 1.0672656297683716,
|
| 450 |
+
"eval_mse_0": 1.316848874092102,
|
| 451 |
+
"eval_mse_1": 0.8607810735702515,
|
| 452 |
+
"eval_mse_2": 0.872856080532074,
|
| 453 |
+
"eval_mse_3": 1.2185744047164917,
|
| 454 |
+
"eval_pcc_0": 0.6866213535541608,
|
| 455 |
+
"eval_pcc_1": 0.759712315973289,
|
| 456 |
+
"eval_pcc_2": 0.7588455538653228,
|
| 457 |
+
"eval_pcc_3": 0.7126122806060791,
|
| 458 |
+
"eval_runtime": 73.7131,
|
| 459 |
+
"eval_samples_per_second": 33.915,
|
| 460 |
+
"eval_steps_per_second": 4.246,
|
| 461 |
+
"step": 7199
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 23.96,
|
| 465 |
+
"learning_rate": 2.012779552715655e-06,
|
| 466 |
+
"loss": 0.5837,
|
| 467 |
+
"step": 7500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 24.0,
|
| 471 |
+
"eval_loss": 1.076933741569519,
|
| 472 |
+
"eval_mse_0": 1.3098905086517334,
|
| 473 |
+
"eval_mse_1": 0.8767925500869751,
|
| 474 |
+
"eval_mse_2": 0.9001609086990356,
|
| 475 |
+
"eval_mse_3": 1.220892071723938,
|
| 476 |
+
"eval_pcc_0": 0.6822292707008807,
|
| 477 |
+
"eval_pcc_1": 0.7553535719073036,
|
| 478 |
+
"eval_pcc_2": 0.7556848269181466,
|
| 479 |
+
"eval_pcc_3": 0.7083728835989292,
|
| 480 |
+
"eval_runtime": 74.3456,
|
| 481 |
+
"eval_samples_per_second": 33.627,
|
| 482 |
+
"eval_steps_per_second": 4.21,
|
| 483 |
+
"step": 7512
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 25.0,
|
| 487 |
+
"eval_loss": 1.09120512008667,
|
| 488 |
+
"eval_mse_0": 1.3491629362106323,
|
| 489 |
+
"eval_mse_1": 0.8790355324745178,
|
| 490 |
+
"eval_mse_2": 0.8941197395324707,
|
| 491 |
+
"eval_mse_3": 1.2425047159194946,
|
| 492 |
+
"eval_pcc_0": 0.6761379971411909,
|
| 493 |
+
"eval_pcc_1": 0.7561999137628518,
|
| 494 |
+
"eval_pcc_2": 0.7567834065253972,
|
| 495 |
+
"eval_pcc_3": 0.7044710761405555,
|
| 496 |
+
"eval_runtime": 73.763,
|
| 497 |
+
"eval_samples_per_second": 33.892,
|
| 498 |
+
"eval_steps_per_second": 4.243,
|
| 499 |
+
"step": 7825
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 25.56,
|
| 503 |
+
"learning_rate": 1.4802981895633654e-06,
|
| 504 |
+
"loss": 0.5693,
|
| 505 |
+
"step": 8000
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 26.0,
|
| 509 |
+
"eval_loss": 1.0818767547607422,
|
| 510 |
+
"eval_mse_0": 1.351433515548706,
|
| 511 |
+
"eval_mse_1": 0.8575886487960815,
|
| 512 |
+
"eval_mse_2": 0.8774282336235046,
|
| 513 |
+
"eval_mse_3": 1.241055965423584,
|
| 514 |
+
"eval_pcc_0": 0.6794353901749828,
|
| 515 |
+
"eval_pcc_1": 0.7614911067180761,
|
| 516 |
+
"eval_pcc_2": 0.7605933258531665,
|
| 517 |
+
"eval_pcc_3": 0.7074136018860306,
|
| 518 |
+
"eval_runtime": 73.8611,
|
| 519 |
+
"eval_samples_per_second": 33.847,
|
| 520 |
+
"eval_steps_per_second": 4.238,
|
| 521 |
+
"step": 8138
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 27.0,
|
| 525 |
+
"eval_loss": 1.0856553316116333,
|
| 526 |
+
"eval_mse_0": 1.3681873083114624,
|
| 527 |
+
"eval_mse_1": 0.8559284210205078,
|
| 528 |
+
"eval_mse_2": 0.8700718879699707,
|
| 529 |
+
"eval_mse_3": 1.24843430519104,
|
| 530 |
+
"eval_pcc_0": 0.6753323346540409,
|
| 531 |
+
"eval_pcc_1": 0.7621902060084675,
|
| 532 |
+
"eval_pcc_2": 0.7619371075126602,
|
| 533 |
+
"eval_pcc_3": 0.7058783059518169,
|
| 534 |
+
"eval_runtime": 73.8756,
|
| 535 |
+
"eval_samples_per_second": 33.841,
|
| 536 |
+
"eval_steps_per_second": 4.237,
|
| 537 |
+
"step": 8451
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 27.16,
|
| 541 |
+
"learning_rate": 9.478168264110757e-07,
|
| 542 |
+
"loss": 0.5244,
|
| 543 |
+
"step": 8500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 28.0,
|
| 547 |
+
"eval_loss": 1.103684902191162,
|
| 548 |
+
"eval_mse_0": 1.3912023305892944,
|
| 549 |
+
"eval_mse_1": 0.8692779541015625,
|
| 550 |
+
"eval_mse_2": 0.8875213861465454,
|
| 551 |
+
"eval_mse_3": 1.2667373418807983,
|
| 552 |
+
"eval_pcc_0": 0.6708340688666804,
|
| 553 |
+
"eval_pcc_1": 0.7587780609368837,
|
| 554 |
+
"eval_pcc_2": 0.7584120400378815,
|
| 555 |
+
"eval_pcc_3": 0.7017121818356558,
|
| 556 |
+
"eval_runtime": 73.4244,
|
| 557 |
+
"eval_samples_per_second": 34.049,
|
| 558 |
+
"eval_steps_per_second": 4.263,
|
| 559 |
+
"step": 8764
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 28.75,
|
| 563 |
+
"learning_rate": 4.1533546325878595e-07,
|
| 564 |
+
"loss": 0.5299,
|
| 565 |
+
"step": 9000
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 29.0,
|
| 569 |
+
"eval_loss": 1.0909972190856934,
|
| 570 |
+
"eval_mse_0": 1.3671704530715942,
|
| 571 |
+
"eval_mse_1": 0.8662821054458618,
|
| 572 |
+
"eval_mse_2": 0.8858506083488464,
|
| 573 |
+
"eval_mse_3": 1.2446855306625366,
|
| 574 |
+
"eval_pcc_0": 0.6729560663499426,
|
| 575 |
+
"eval_pcc_1": 0.7592557191672585,
|
| 576 |
+
"eval_pcc_2": 0.7581404959595723,
|
| 577 |
+
"eval_pcc_3": 0.7034362955177479,
|
| 578 |
+
"eval_runtime": 72.2418,
|
| 579 |
+
"eval_samples_per_second": 34.606,
|
| 580 |
+
"eval_steps_per_second": 4.333,
|
| 581 |
+
"step": 9077
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 30.0,
|
| 585 |
+
"eval_loss": 1.1013392210006714,
|
| 586 |
+
"eval_mse_0": 1.393510103225708,
|
| 587 |
+
"eval_mse_1": 0.8640445470809937,
|
| 588 |
+
"eval_mse_2": 0.8827493190765381,
|
| 589 |
+
"eval_mse_3": 1.2650511264801025,
|
| 590 |
+
"eval_pcc_0": 0.6731441812705756,
|
| 591 |
+
"eval_pcc_1": 0.760422008118168,
|
| 592 |
+
"eval_pcc_2": 0.759085092937088,
|
| 593 |
+
"eval_pcc_3": 0.7037933906921356,
|
| 594 |
+
"eval_runtime": 73.525,
|
| 595 |
+
"eval_samples_per_second": 34.002,
|
| 596 |
+
"eval_steps_per_second": 4.257,
|
| 597 |
+
"step": 9390
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 30.0,
|
| 601 |
+
"step": 9390,
|
| 602 |
+
"total_flos": 0.0,
|
| 603 |
+
"train_loss": 3.1472203686341436,
|
| 604 |
+
"train_runtime": 5570.0464,
|
| 605 |
+
"train_samples_per_second": 13.465,
|
| 606 |
+
"train_steps_per_second": 1.686
|
| 607 |
+
}
|
| 608 |
+
],
|
| 609 |
+
"logging_steps": 500,
|
| 610 |
+
"max_steps": 9390,
|
| 611 |
+
"num_input_tokens_seen": 0,
|
| 612 |
+
"num_train_epochs": 30,
|
| 613 |
+
"save_steps": 500,
|
| 614 |
+
"total_flos": 0.0,
|
| 615 |
+
"train_batch_size": 8,
|
| 616 |
+
"trial_name": null,
|
| 617 |
+
"trial_params": null
|
| 618 |
+
}
|
hubert/general/07_hubert-base-ls960/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94eb05aaa43d9bcf4385ee300f61830564e451bdd5432f97f58648a82ed546e3
|
| 3 |
+
size 4792
|