Upload folder using huggingface_hub
Browse files- config.json +187 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- tokenizer.json +0 -0
- tokenizer_config.json +942 -0
- trainer_state.json +3359 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_frozen": true,
|
| 3 |
+
"_n_gpu": 1,
|
| 4 |
+
"adafactor": false,
|
| 5 |
+
"adam_beta1": 0.9,
|
| 6 |
+
"adam_beta2": 0.999,
|
| 7 |
+
"adam_epsilon": 1e-06,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"CorrectorEncoderModel"
|
| 10 |
+
],
|
| 11 |
+
"auto_find_batch_size": false,
|
| 12 |
+
"average_tokens_across_devices": true,
|
| 13 |
+
"batch_eval_metrics": false,
|
| 14 |
+
"bf16": true,
|
| 15 |
+
"bf16_full_eval": false,
|
| 16 |
+
"cache_dir": null,
|
| 17 |
+
"cheat_on_train_hypotheses": false,
|
| 18 |
+
"config_name": null,
|
| 19 |
+
"config_overrides": null,
|
| 20 |
+
"corrector_ignore_hypothesis_embedding": false,
|
| 21 |
+
"corrector_model_alias": "checkpoint-180978",
|
| 22 |
+
"corrector_model_from_pretrained": null,
|
| 23 |
+
"data_seed": null,
|
| 24 |
+
"dataloader_drop_last": false,
|
| 25 |
+
"dataloader_num_workers": 2,
|
| 26 |
+
"dataloader_persistent_workers": false,
|
| 27 |
+
"dataloader_pin_memory": true,
|
| 28 |
+
"dataloader_prefetch_factor": null,
|
| 29 |
+
"dataset_name": "nq",
|
| 30 |
+
"ddp_backend": null,
|
| 31 |
+
"ddp_broadcast_buffers": null,
|
| 32 |
+
"ddp_bucket_cap_mb": null,
|
| 33 |
+
"ddp_find_unused_parameters": false,
|
| 34 |
+
"ddp_timeout": 1800,
|
| 35 |
+
"debug": [],
|
| 36 |
+
"decoder_dropout_disabled": false,
|
| 37 |
+
"deepspeed": null,
|
| 38 |
+
"deepspeed_plugin": null,
|
| 39 |
+
"disable_tqdm": true,
|
| 40 |
+
"do_eval": false,
|
| 41 |
+
"do_predict": false,
|
| 42 |
+
"do_train": false,
|
| 43 |
+
"dtype": "float32",
|
| 44 |
+
"embedder_fake_with_zeros": false,
|
| 45 |
+
"embedder_gaussian_noise_level": 0.0,
|
| 46 |
+
"embedder_model_api": null,
|
| 47 |
+
"embedder_model_name": "gte_base",
|
| 48 |
+
"embedder_no_grad": true,
|
| 49 |
+
"embedder_torch_dtype": "float32",
|
| 50 |
+
"embedding_transform_strategy": "repeat",
|
| 51 |
+
"embedding_zero_except_topk": null,
|
| 52 |
+
"embeddings_from_layer_n": null,
|
| 53 |
+
"encoder_dropout_disabled": false,
|
| 54 |
+
"eos_token_id": 1,
|
| 55 |
+
"eval_accumulation_steps": null,
|
| 56 |
+
"eval_delay": 0,
|
| 57 |
+
"eval_do_concat_batches": true,
|
| 58 |
+
"eval_on_start": false,
|
| 59 |
+
"eval_steps": 800,
|
| 60 |
+
"eval_strategy": "no",
|
| 61 |
+
"eval_use_gather_object": false,
|
| 62 |
+
"evaluation_strategy": "steps",
|
| 63 |
+
"exp_group_name": "oct-gte-corrector",
|
| 64 |
+
"exp_name": "",
|
| 65 |
+
"experiment": "corrector",
|
| 66 |
+
"fp16": false,
|
| 67 |
+
"fp16_backend": "auto",
|
| 68 |
+
"fp16_full_eval": false,
|
| 69 |
+
"fp16_opt_level": "O1",
|
| 70 |
+
"freeze_strategy": "none",
|
| 71 |
+
"fsdp": [],
|
| 72 |
+
"fsdp_config": {
|
| 73 |
+
"min_num_params": 0,
|
| 74 |
+
"xla": false,
|
| 75 |
+
"xla_fsdp_grad_ckpt": false,
|
| 76 |
+
"xla_fsdp_v2": false
|
| 77 |
+
},
|
| 78 |
+
"fsdp_min_num_params": 0,
|
| 79 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 80 |
+
"full_determinism": false,
|
| 81 |
+
"gradient_accumulation_steps": 1,
|
| 82 |
+
"gradient_checkpointing": false,
|
| 83 |
+
"gradient_checkpointing_kwargs": null,
|
| 84 |
+
"greater_is_better": false,
|
| 85 |
+
"group_by_length": true,
|
| 86 |
+
"half_precision_backend": "auto",
|
| 87 |
+
"hub_always_push": false,
|
| 88 |
+
"hub_model_id": null,
|
| 89 |
+
"hub_private_repo": null,
|
| 90 |
+
"hub_revision": null,
|
| 91 |
+
"hub_strategy": "every_save",
|
| 92 |
+
"hub_token": null,
|
| 93 |
+
"ignore_data_skip": false,
|
| 94 |
+
"include_for_metrics": [
|
| 95 |
+
"inputs"
|
| 96 |
+
],
|
| 97 |
+
"include_inputs_for_metrics": true,
|
| 98 |
+
"include_num_input_tokens_seen": false,
|
| 99 |
+
"include_tokens_per_second": false,
|
| 100 |
+
"jit_mode_eval": false,
|
| 101 |
+
"label_names": null,
|
| 102 |
+
"label_smoothing_factor": 0.0,
|
| 103 |
+
"learning_rate": 0.002828,
|
| 104 |
+
"length_column_name": "length",
|
| 105 |
+
"liger_kernel_config": null,
|
| 106 |
+
"load_best_model_at_end": true,
|
| 107 |
+
"local_rank": 0,
|
| 108 |
+
"log_level": "passive",
|
| 109 |
+
"log_level_replica": "warning",
|
| 110 |
+
"log_on_each_node": true,
|
| 111 |
+
"logging_dir": "/data/AndriiKoliush/hf/results/corrector/runs/Oct24_12-40-59_ubuntu-gpu",
|
| 112 |
+
"logging_first_step": false,
|
| 113 |
+
"logging_nan_inf_filter": true,
|
| 114 |
+
"logging_steps": 64,
|
| 115 |
+
"logging_strategy": "steps",
|
| 116 |
+
"lr_scheduler_kwargs": {},
|
| 117 |
+
"lr_scheduler_type": "constant_with_warmup",
|
| 118 |
+
"max_eval_samples": 500,
|
| 119 |
+
"max_grad_norm": 1.0,
|
| 120 |
+
"max_seq_length": 32,
|
| 121 |
+
"max_steps": -1,
|
| 122 |
+
"metric_for_best_model": "nq_loss",
|
| 123 |
+
"mock_embedder": false,
|
| 124 |
+
"model_name_or_path": "t5-base",
|
| 125 |
+
"model_revision": "main",
|
| 126 |
+
"mp_parameters": "",
|
| 127 |
+
"neftune_noise_alpha": null,
|
| 128 |
+
"no_cuda": false,
|
| 129 |
+
"num_repeat_tokens": 32,
|
| 130 |
+
"num_train_epochs": 25.0,
|
| 131 |
+
"optim": "adamw_torch_fused",
|
| 132 |
+
"optim_args": null,
|
| 133 |
+
"optim_target_modules": null,
|
| 134 |
+
"output_dir": "/data/AndriiKoliush/hf/results/corrector",
|
| 135 |
+
"overwrite_output_dir": true,
|
| 136 |
+
"pad_token_id": 0,
|
| 137 |
+
"parallelism_config": null,
|
| 138 |
+
"past_index": -1,
|
| 139 |
+
"per_device_eval_batch_size": 200,
|
| 140 |
+
"per_device_train_batch_size": 200,
|
| 141 |
+
"per_gpu_eval_batch_size": null,
|
| 142 |
+
"per_gpu_train_batch_size": null,
|
| 143 |
+
"prediction_loss_only": false,
|
| 144 |
+
"push_to_hub": false,
|
| 145 |
+
"push_to_hub_model_id": null,
|
| 146 |
+
"push_to_hub_organization": null,
|
| 147 |
+
"push_to_hub_token": null,
|
| 148 |
+
"ray_scope": "last",
|
| 149 |
+
"remove_unused_columns": false,
|
| 150 |
+
"report_to": [
|
| 151 |
+
"wandb"
|
| 152 |
+
],
|
| 153 |
+
"restore_callback_states_from_checkpoint": false,
|
| 154 |
+
"resume_from_checkpoint": "/data/AndriiKoliush/hf/results/corrector/checkpoint-9600",
|
| 155 |
+
"run_name": null,
|
| 156 |
+
"save_on_each_node": false,
|
| 157 |
+
"save_only_model": false,
|
| 158 |
+
"save_safetensors": true,
|
| 159 |
+
"save_steps": 320,
|
| 160 |
+
"save_strategy": "steps",
|
| 161 |
+
"save_total_limit": 2,
|
| 162 |
+
"seed": 42,
|
| 163 |
+
"skip_memory_metrics": true,
|
| 164 |
+
"steps_per_epoch": 500000,
|
| 165 |
+
"tf32": null,
|
| 166 |
+
"tokenizer_name": null,
|
| 167 |
+
"torch_compile": false,
|
| 168 |
+
"torch_compile_backend": null,
|
| 169 |
+
"torch_compile_mode": null,
|
| 170 |
+
"torch_empty_cache_steps": null,
|
| 171 |
+
"torchdynamo": null,
|
| 172 |
+
"tpu_metrics_debug": false,
|
| 173 |
+
"tpu_num_cores": null,
|
| 174 |
+
"transformers_version": "4.56.2",
|
| 175 |
+
"use_cpu": false,
|
| 176 |
+
"use_frozen_embeddings_as_input": true,
|
| 177 |
+
"use_ipex": false,
|
| 178 |
+
"use_legacy_prediction_loop": false,
|
| 179 |
+
"use_less_data": -1,
|
| 180 |
+
"use_liger_kernel": false,
|
| 181 |
+
"use_lora": false,
|
| 182 |
+
"use_mps_device": false,
|
| 183 |
+
"use_wandb": true,
|
| 184 |
+
"warmup_ratio": 0.0,
|
| 185 |
+
"warmup_steps": 1600,
|
| 186 |
+
"weight_decay": 0.0
|
| 187 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77b0c298421bd9ad6c45d3f5bbd1b1973353ad055e917f8710a05fd79c4e5255
|
| 3 |
+
size 1125530872
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66d8a8fb15bd720ca5e46acef73134c50093fb4b7239469b2800ae90cbe8cec3
|
| 3 |
+
size 2251221899
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:864f21fe80c56cb3770c0301163bcacea12fc29261ac6e69ff3758e5757fc16c
|
| 3 |
+
size 14917
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5537b850b84764acce128c492c63e1fa9471ee8008cd985cc18969483a3d23f
|
| 3 |
+
size 14917
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d76033929cbfb3c5875dac669a46d02407e996b0314ad9afda6f01802b5af88
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,942 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"32000": {
|
| 29 |
+
"content": "<extra_id_99>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"32001": {
|
| 37 |
+
"content": "<extra_id_98>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"32002": {
|
| 45 |
+
"content": "<extra_id_97>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"32003": {
|
| 53 |
+
"content": "<extra_id_96>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"32004": {
|
| 61 |
+
"content": "<extra_id_95>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"32005": {
|
| 69 |
+
"content": "<extra_id_94>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"32006": {
|
| 77 |
+
"content": "<extra_id_93>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"32007": {
|
| 85 |
+
"content": "<extra_id_92>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"32008": {
|
| 93 |
+
"content": "<extra_id_91>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"32009": {
|
| 101 |
+
"content": "<extra_id_90>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"32010": {
|
| 109 |
+
"content": "<extra_id_89>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"32011": {
|
| 117 |
+
"content": "<extra_id_88>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"32012": {
|
| 125 |
+
"content": "<extra_id_87>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"32013": {
|
| 133 |
+
"content": "<extra_id_86>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"32014": {
|
| 141 |
+
"content": "<extra_id_85>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"32015": {
|
| 149 |
+
"content": "<extra_id_84>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"32016": {
|
| 157 |
+
"content": "<extra_id_83>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"32017": {
|
| 165 |
+
"content": "<extra_id_82>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"32018": {
|
| 173 |
+
"content": "<extra_id_81>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"32019": {
|
| 181 |
+
"content": "<extra_id_80>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"32020": {
|
| 189 |
+
"content": "<extra_id_79>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"32021": {
|
| 197 |
+
"content": "<extra_id_78>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"32022": {
|
| 205 |
+
"content": "<extra_id_77>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"32023": {
|
| 213 |
+
"content": "<extra_id_76>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"32024": {
|
| 221 |
+
"content": "<extra_id_75>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"32025": {
|
| 229 |
+
"content": "<extra_id_74>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"32026": {
|
| 237 |
+
"content": "<extra_id_73>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"32027": {
|
| 245 |
+
"content": "<extra_id_72>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"32028": {
|
| 253 |
+
"content": "<extra_id_71>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32029": {
|
| 261 |
+
"content": "<extra_id_70>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"32030": {
|
| 269 |
+
"content": "<extra_id_69>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"32031": {
|
| 277 |
+
"content": "<extra_id_68>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"32032": {
|
| 285 |
+
"content": "<extra_id_67>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"32033": {
|
| 293 |
+
"content": "<extra_id_66>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"32034": {
|
| 301 |
+
"content": "<extra_id_65>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"32035": {
|
| 309 |
+
"content": "<extra_id_64>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"32036": {
|
| 317 |
+
"content": "<extra_id_63>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"32037": {
|
| 325 |
+
"content": "<extra_id_62>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"32038": {
|
| 333 |
+
"content": "<extra_id_61>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"32039": {
|
| 341 |
+
"content": "<extra_id_60>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"32040": {
|
| 349 |
+
"content": "<extra_id_59>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"32041": {
|
| 357 |
+
"content": "<extra_id_58>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"32042": {
|
| 365 |
+
"content": "<extra_id_57>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"32043": {
|
| 373 |
+
"content": "<extra_id_56>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"32044": {
|
| 381 |
+
"content": "<extra_id_55>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"32045": {
|
| 389 |
+
"content": "<extra_id_54>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"32046": {
|
| 397 |
+
"content": "<extra_id_53>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"32047": {
|
| 405 |
+
"content": "<extra_id_52>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"32048": {
|
| 413 |
+
"content": "<extra_id_51>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"32049": {
|
| 421 |
+
"content": "<extra_id_50>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"32050": {
|
| 429 |
+
"content": "<extra_id_49>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"32051": {
|
| 437 |
+
"content": "<extra_id_48>",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"32052": {
|
| 445 |
+
"content": "<extra_id_47>",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"32053": {
|
| 453 |
+
"content": "<extra_id_46>",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"32054": {
|
| 461 |
+
"content": "<extra_id_45>",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"32055": {
|
| 469 |
+
"content": "<extra_id_44>",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"32056": {
|
| 477 |
+
"content": "<extra_id_43>",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"32057": {
|
| 485 |
+
"content": "<extra_id_42>",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"32058": {
|
| 493 |
+
"content": "<extra_id_41>",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"32059": {
|
| 501 |
+
"content": "<extra_id_40>",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"32060": {
|
| 509 |
+
"content": "<extra_id_39>",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"32061": {
|
| 517 |
+
"content": "<extra_id_38>",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"32062": {
|
| 525 |
+
"content": "<extra_id_37>",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"32063": {
|
| 533 |
+
"content": "<extra_id_36>",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"32064": {
|
| 541 |
+
"content": "<extra_id_35>",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"32065": {
|
| 549 |
+
"content": "<extra_id_34>",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"32066": {
|
| 557 |
+
"content": "<extra_id_33>",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"32067": {
|
| 565 |
+
"content": "<extra_id_32>",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"32068": {
|
| 573 |
+
"content": "<extra_id_31>",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"32069": {
|
| 581 |
+
"content": "<extra_id_30>",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"32070": {
|
| 589 |
+
"content": "<extra_id_29>",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"32071": {
|
| 597 |
+
"content": "<extra_id_28>",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"32072": {
|
| 605 |
+
"content": "<extra_id_27>",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"32073": {
|
| 613 |
+
"content": "<extra_id_26>",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"32074": {
|
| 621 |
+
"content": "<extra_id_25>",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"32075": {
|
| 629 |
+
"content": "<extra_id_24>",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"32076": {
|
| 637 |
+
"content": "<extra_id_23>",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"32077": {
|
| 645 |
+
"content": "<extra_id_22>",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"32078": {
|
| 653 |
+
"content": "<extra_id_21>",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"32079": {
|
| 661 |
+
"content": "<extra_id_20>",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"32080": {
|
| 669 |
+
"content": "<extra_id_19>",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"32081": {
|
| 677 |
+
"content": "<extra_id_18>",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"32082": {
|
| 685 |
+
"content": "<extra_id_17>",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"32083": {
|
| 693 |
+
"content": "<extra_id_16>",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"32084": {
|
| 701 |
+
"content": "<extra_id_15>",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"32085": {
|
| 709 |
+
"content": "<extra_id_14>",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"32086": {
|
| 717 |
+
"content": "<extra_id_13>",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"32087": {
|
| 725 |
+
"content": "<extra_id_12>",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"32088": {
|
| 733 |
+
"content": "<extra_id_11>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"32089": {
|
| 741 |
+
"content": "<extra_id_10>",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"32090": {
|
| 749 |
+
"content": "<extra_id_9>",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"32091": {
|
| 757 |
+
"content": "<extra_id_8>",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"32092": {
|
| 765 |
+
"content": "<extra_id_7>",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"32093": {
|
| 773 |
+
"content": "<extra_id_6>",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"32094": {
|
| 781 |
+
"content": "<extra_id_5>",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"32095": {
|
| 789 |
+
"content": "<extra_id_4>",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"32096": {
|
| 797 |
+
"content": "<extra_id_3>",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"32097": {
|
| 805 |
+
"content": "<extra_id_2>",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"32098": {
|
| 813 |
+
"content": "<extra_id_1>",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"32099": {
|
| 821 |
+
"content": "<extra_id_0>",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
}
|
| 828 |
+
},
|
| 829 |
+
"additional_special_tokens": [
|
| 830 |
+
"<extra_id_0>",
|
| 831 |
+
"<extra_id_1>",
|
| 832 |
+
"<extra_id_2>",
|
| 833 |
+
"<extra_id_3>",
|
| 834 |
+
"<extra_id_4>",
|
| 835 |
+
"<extra_id_5>",
|
| 836 |
+
"<extra_id_6>",
|
| 837 |
+
"<extra_id_7>",
|
| 838 |
+
"<extra_id_8>",
|
| 839 |
+
"<extra_id_9>",
|
| 840 |
+
"<extra_id_10>",
|
| 841 |
+
"<extra_id_11>",
|
| 842 |
+
"<extra_id_12>",
|
| 843 |
+
"<extra_id_13>",
|
| 844 |
+
"<extra_id_14>",
|
| 845 |
+
"<extra_id_15>",
|
| 846 |
+
"<extra_id_16>",
|
| 847 |
+
"<extra_id_17>",
|
| 848 |
+
"<extra_id_18>",
|
| 849 |
+
"<extra_id_19>",
|
| 850 |
+
"<extra_id_20>",
|
| 851 |
+
"<extra_id_21>",
|
| 852 |
+
"<extra_id_22>",
|
| 853 |
+
"<extra_id_23>",
|
| 854 |
+
"<extra_id_24>",
|
| 855 |
+
"<extra_id_25>",
|
| 856 |
+
"<extra_id_26>",
|
| 857 |
+
"<extra_id_27>",
|
| 858 |
+
"<extra_id_28>",
|
| 859 |
+
"<extra_id_29>",
|
| 860 |
+
"<extra_id_30>",
|
| 861 |
+
"<extra_id_31>",
|
| 862 |
+
"<extra_id_32>",
|
| 863 |
+
"<extra_id_33>",
|
| 864 |
+
"<extra_id_34>",
|
| 865 |
+
"<extra_id_35>",
|
| 866 |
+
"<extra_id_36>",
|
| 867 |
+
"<extra_id_37>",
|
| 868 |
+
"<extra_id_38>",
|
| 869 |
+
"<extra_id_39>",
|
| 870 |
+
"<extra_id_40>",
|
| 871 |
+
"<extra_id_41>",
|
| 872 |
+
"<extra_id_42>",
|
| 873 |
+
"<extra_id_43>",
|
| 874 |
+
"<extra_id_44>",
|
| 875 |
+
"<extra_id_45>",
|
| 876 |
+
"<extra_id_46>",
|
| 877 |
+
"<extra_id_47>",
|
| 878 |
+
"<extra_id_48>",
|
| 879 |
+
"<extra_id_49>",
|
| 880 |
+
"<extra_id_50>",
|
| 881 |
+
"<extra_id_51>",
|
| 882 |
+
"<extra_id_52>",
|
| 883 |
+
"<extra_id_53>",
|
| 884 |
+
"<extra_id_54>",
|
| 885 |
+
"<extra_id_55>",
|
| 886 |
+
"<extra_id_56>",
|
| 887 |
+
"<extra_id_57>",
|
| 888 |
+
"<extra_id_58>",
|
| 889 |
+
"<extra_id_59>",
|
| 890 |
+
"<extra_id_60>",
|
| 891 |
+
"<extra_id_61>",
|
| 892 |
+
"<extra_id_62>",
|
| 893 |
+
"<extra_id_63>",
|
| 894 |
+
"<extra_id_64>",
|
| 895 |
+
"<extra_id_65>",
|
| 896 |
+
"<extra_id_66>",
|
| 897 |
+
"<extra_id_67>",
|
| 898 |
+
"<extra_id_68>",
|
| 899 |
+
"<extra_id_69>",
|
| 900 |
+
"<extra_id_70>",
|
| 901 |
+
"<extra_id_71>",
|
| 902 |
+
"<extra_id_72>",
|
| 903 |
+
"<extra_id_73>",
|
| 904 |
+
"<extra_id_74>",
|
| 905 |
+
"<extra_id_75>",
|
| 906 |
+
"<extra_id_76>",
|
| 907 |
+
"<extra_id_77>",
|
| 908 |
+
"<extra_id_78>",
|
| 909 |
+
"<extra_id_79>",
|
| 910 |
+
"<extra_id_80>",
|
| 911 |
+
"<extra_id_81>",
|
| 912 |
+
"<extra_id_82>",
|
| 913 |
+
"<extra_id_83>",
|
| 914 |
+
"<extra_id_84>",
|
| 915 |
+
"<extra_id_85>",
|
| 916 |
+
"<extra_id_86>",
|
| 917 |
+
"<extra_id_87>",
|
| 918 |
+
"<extra_id_88>",
|
| 919 |
+
"<extra_id_89>",
|
| 920 |
+
"<extra_id_90>",
|
| 921 |
+
"<extra_id_91>",
|
| 922 |
+
"<extra_id_92>",
|
| 923 |
+
"<extra_id_93>",
|
| 924 |
+
"<extra_id_94>",
|
| 925 |
+
"<extra_id_95>",
|
| 926 |
+
"<extra_id_96>",
|
| 927 |
+
"<extra_id_97>",
|
| 928 |
+
"<extra_id_98>",
|
| 929 |
+
"<extra_id_99>"
|
| 930 |
+
],
|
| 931 |
+
"clean_up_tokenization_spaces": false,
|
| 932 |
+
"eos_token": "</s>",
|
| 933 |
+
"extra_ids": 100,
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"max_length": 32,
|
| 936 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 937 |
+
"pad_token": "<pad>",
|
| 938 |
+
"padding": "max_length",
|
| 939 |
+
"tokenizer_class": "T5Tokenizer",
|
| 940 |
+
"truncation": "max_length",
|
| 941 |
+
"unk_token": "<unk>"
|
| 942 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3359 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.2814258911819887,
|
| 6 |
+
"eval_steps": 800,
|
| 7 |
+
"global_step": 30400,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004803001876172608,
|
| 14 |
+
"grad_norm": 3.330345630645752,
|
| 15 |
+
"learning_rate": 0.0001113525,
|
| 16 |
+
"loss": 4.3152,
|
| 17 |
+
"step": 64
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.009606003752345216,
|
| 21 |
+
"grad_norm": 2.5987207889556885,
|
| 22 |
+
"learning_rate": 0.00022447249999999998,
|
| 23 |
+
"loss": 3.5908,
|
| 24 |
+
"step": 128
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.014409005628517824,
|
| 28 |
+
"grad_norm": 10.176867485046387,
|
| 29 |
+
"learning_rate": 0.00033759249999999996,
|
| 30 |
+
"loss": 3.3927,
|
| 31 |
+
"step": 192
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.01921200750469043,
|
| 35 |
+
"grad_norm": 6.534875869750977,
|
| 36 |
+
"learning_rate": 0.00045071249999999993,
|
| 37 |
+
"loss": 3.3333,
|
| 38 |
+
"step": 256
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02401500938086304,
|
| 42 |
+
"grad_norm": 6.088456630706787,
|
| 43 |
+
"learning_rate": 0.0005638325,
|
| 44 |
+
"loss": 3.2928,
|
| 45 |
+
"step": 320
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.028818011257035647,
|
| 49 |
+
"grad_norm": 6.937580108642578,
|
| 50 |
+
"learning_rate": 0.0006769524999999999,
|
| 51 |
+
"loss": 3.2901,
|
| 52 |
+
"step": 384
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.033621013133208255,
|
| 56 |
+
"grad_norm": 6.744969844818115,
|
| 57 |
+
"learning_rate": 0.0007900724999999999,
|
| 58 |
+
"loss": 3.2589,
|
| 59 |
+
"step": 448
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03842401500938086,
|
| 63 |
+
"grad_norm": 2.2261719703674316,
|
| 64 |
+
"learning_rate": 0.0009031925,
|
| 65 |
+
"loss": 3.231,
|
| 66 |
+
"step": 512
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.04322701688555347,
|
| 70 |
+
"grad_norm": 1.030404806137085,
|
| 71 |
+
"learning_rate": 0.0010163124999999999,
|
| 72 |
+
"loss": 3.2278,
|
| 73 |
+
"step": 576
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.04803001876172608,
|
| 77 |
+
"grad_norm": 1.036293387413025,
|
| 78 |
+
"learning_rate": 0.0011294324999999998,
|
| 79 |
+
"loss": 3.272,
|
| 80 |
+
"step": 640
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.05283302063789869,
|
| 84 |
+
"grad_norm": 1.1835274696350098,
|
| 85 |
+
"learning_rate": 0.0012425525,
|
| 86 |
+
"loss": 3.256,
|
| 87 |
+
"step": 704
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.057636022514071295,
|
| 91 |
+
"grad_norm": 0.8378634452819824,
|
| 92 |
+
"learning_rate": 0.0013556724999999998,
|
| 93 |
+
"loss": 3.27,
|
| 94 |
+
"step": 768
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0624390243902439,
|
| 98 |
+
"grad_norm": 0.7602612972259521,
|
| 99 |
+
"learning_rate": 0.0014687925,
|
| 100 |
+
"loss": 3.2261,
|
| 101 |
+
"step": 832
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.06724202626641651,
|
| 105 |
+
"grad_norm": 0.6387987732887268,
|
| 106 |
+
"learning_rate": 0.0015819124999999997,
|
| 107 |
+
"loss": 3.2153,
|
| 108 |
+
"step": 896
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.07204502814258912,
|
| 112 |
+
"grad_norm": 0.4422095715999603,
|
| 113 |
+
"learning_rate": 0.0016950325,
|
| 114 |
+
"loss": 3.1975,
|
| 115 |
+
"step": 960
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.07684803001876173,
|
| 119 |
+
"grad_norm": 0.39002183079719543,
|
| 120 |
+
"learning_rate": 0.0018081524999999999,
|
| 121 |
+
"loss": 3.1983,
|
| 122 |
+
"step": 1024
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.08165103189493433,
|
| 126 |
+
"grad_norm": 5.926162242889404,
|
| 127 |
+
"learning_rate": 0.0019212724999999996,
|
| 128 |
+
"loss": 3.1763,
|
| 129 |
+
"step": 1088
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.08645403377110694,
|
| 133 |
+
"grad_norm": 0.4173193871974945,
|
| 134 |
+
"learning_rate": 0.0020343924999999996,
|
| 135 |
+
"loss": 3.1833,
|
| 136 |
+
"step": 1152
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.09125703564727955,
|
| 140 |
+
"grad_norm": 0.4136042594909668,
|
| 141 |
+
"learning_rate": 0.0021475125,
|
| 142 |
+
"loss": 3.1846,
|
| 143 |
+
"step": 1216
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.09606003752345216,
|
| 147 |
+
"grad_norm": 0.39301183819770813,
|
| 148 |
+
"learning_rate": 0.0022606324999999996,
|
| 149 |
+
"loss": 3.1739,
|
| 150 |
+
"step": 1280
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.10086303939962477,
|
| 154 |
+
"grad_norm": 0.4910842776298523,
|
| 155 |
+
"learning_rate": 0.0023737525,
|
| 156 |
+
"loss": 3.1614,
|
| 157 |
+
"step": 1344
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.10566604127579737,
|
| 161 |
+
"grad_norm": 0.4039038121700287,
|
| 162 |
+
"learning_rate": 0.0024868725,
|
| 163 |
+
"loss": 3.1577,
|
| 164 |
+
"step": 1408
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.11046904315196998,
|
| 168 |
+
"grad_norm": 0.3286585211753845,
|
| 169 |
+
"learning_rate": 0.0025999925,
|
| 170 |
+
"loss": 3.1458,
|
| 171 |
+
"step": 1472
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.11527204502814259,
|
| 175 |
+
"grad_norm": 0.44095373153686523,
|
| 176 |
+
"learning_rate": 0.0027131125,
|
| 177 |
+
"loss": 3.155,
|
| 178 |
+
"step": 1536
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1200750469043152,
|
| 182 |
+
"grad_norm": 0.40613290667533875,
|
| 183 |
+
"learning_rate": 0.0028262325,
|
| 184 |
+
"loss": 3.1469,
|
| 185 |
+
"step": 1600
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1248780487804878,
|
| 189 |
+
"grad_norm": 0.4613141417503357,
|
| 190 |
+
"learning_rate": 0.002828,
|
| 191 |
+
"loss": 3.1392,
|
| 192 |
+
"step": 1664
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.1296810506566604,
|
| 196 |
+
"grad_norm": 0.3758493661880493,
|
| 197 |
+
"learning_rate": 0.002828,
|
| 198 |
+
"loss": 3.1298,
|
| 199 |
+
"step": 1728
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.13448405253283302,
|
| 203 |
+
"grad_norm": 0.32609787583351135,
|
| 204 |
+
"learning_rate": 0.002828,
|
| 205 |
+
"loss": 3.123,
|
| 206 |
+
"step": 1792
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.13928705440900563,
|
| 210 |
+
"grad_norm": 0.4221761226654053,
|
| 211 |
+
"learning_rate": 0.002828,
|
| 212 |
+
"loss": 3.1076,
|
| 213 |
+
"step": 1856
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.14409005628517824,
|
| 217 |
+
"grad_norm": 0.4372267425060272,
|
| 218 |
+
"learning_rate": 0.002828,
|
| 219 |
+
"loss": 3.098,
|
| 220 |
+
"step": 1920
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.14889305816135084,
|
| 224 |
+
"grad_norm": 0.36804404854774475,
|
| 225 |
+
"learning_rate": 0.002828,
|
| 226 |
+
"loss": 3.0952,
|
| 227 |
+
"step": 1984
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.15369606003752345,
|
| 231 |
+
"grad_norm": 0.314120888710022,
|
| 232 |
+
"learning_rate": 0.002828,
|
| 233 |
+
"loss": 3.0751,
|
| 234 |
+
"step": 2048
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.15849906191369606,
|
| 238 |
+
"grad_norm": 0.3158409297466278,
|
| 239 |
+
"learning_rate": 0.002828,
|
| 240 |
+
"loss": 3.0574,
|
| 241 |
+
"step": 2112
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.16330206378986867,
|
| 245 |
+
"grad_norm": 0.35668376088142395,
|
| 246 |
+
"learning_rate": 0.002828,
|
| 247 |
+
"loss": 3.0598,
|
| 248 |
+
"step": 2176
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.16810506566604128,
|
| 252 |
+
"grad_norm": 0.3429064452648163,
|
| 253 |
+
"learning_rate": 0.002828,
|
| 254 |
+
"loss": 3.0554,
|
| 255 |
+
"step": 2240
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.17290806754221388,
|
| 259 |
+
"grad_norm": 0.37981563806533813,
|
| 260 |
+
"learning_rate": 0.002828,
|
| 261 |
+
"loss": 3.0439,
|
| 262 |
+
"step": 2304
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.1777110694183865,
|
| 266 |
+
"grad_norm": 0.45046043395996094,
|
| 267 |
+
"learning_rate": 0.002828,
|
| 268 |
+
"loss": 3.034,
|
| 269 |
+
"step": 2368
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.1825140712945591,
|
| 273 |
+
"grad_norm": 0.30424681305885315,
|
| 274 |
+
"learning_rate": 0.002828,
|
| 275 |
+
"loss": 3.0408,
|
| 276 |
+
"step": 2432
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.1873170731707317,
|
| 280 |
+
"grad_norm": 0.4374525845050812,
|
| 281 |
+
"learning_rate": 0.002828,
|
| 282 |
+
"loss": 3.0289,
|
| 283 |
+
"step": 2496
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.19212007504690432,
|
| 287 |
+
"grad_norm": 0.4312361776828766,
|
| 288 |
+
"learning_rate": 0.002828,
|
| 289 |
+
"loss": 3.0252,
|
| 290 |
+
"step": 2560
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.19692307692307692,
|
| 294 |
+
"grad_norm": 0.33109021186828613,
|
| 295 |
+
"learning_rate": 0.002828,
|
| 296 |
+
"loss": 3.0094,
|
| 297 |
+
"step": 2624
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.20172607879924953,
|
| 301 |
+
"grad_norm": 0.4393901228904724,
|
| 302 |
+
"learning_rate": 0.002828,
|
| 303 |
+
"loss": 3.0021,
|
| 304 |
+
"step": 2688
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.20652908067542214,
|
| 308 |
+
"grad_norm": 0.44241341948509216,
|
| 309 |
+
"learning_rate": 0.002828,
|
| 310 |
+
"loss": 3.0005,
|
| 311 |
+
"step": 2752
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.21133208255159475,
|
| 315 |
+
"grad_norm": 0.36241745948791504,
|
| 316 |
+
"learning_rate": 0.002828,
|
| 317 |
+
"loss": 2.9939,
|
| 318 |
+
"step": 2816
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.21613508442776735,
|
| 322 |
+
"grad_norm": 0.40780672430992126,
|
| 323 |
+
"learning_rate": 0.002828,
|
| 324 |
+
"loss": 2.9788,
|
| 325 |
+
"step": 2880
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.22093808630393996,
|
| 329 |
+
"grad_norm": 0.3944590389728546,
|
| 330 |
+
"learning_rate": 0.002828,
|
| 331 |
+
"loss": 2.9854,
|
| 332 |
+
"step": 2944
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.22574108818011257,
|
| 336 |
+
"grad_norm": 0.40449267625808716,
|
| 337 |
+
"learning_rate": 0.002828,
|
| 338 |
+
"loss": 2.9819,
|
| 339 |
+
"step": 3008
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.23054409005628518,
|
| 343 |
+
"grad_norm": 0.37247487902641296,
|
| 344 |
+
"learning_rate": 0.002828,
|
| 345 |
+
"loss": 2.9827,
|
| 346 |
+
"step": 3072
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.23534709193245779,
|
| 350 |
+
"grad_norm": 0.3732891082763672,
|
| 351 |
+
"learning_rate": 0.002828,
|
| 352 |
+
"loss": 2.9714,
|
| 353 |
+
"step": 3136
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2401500938086304,
|
| 357 |
+
"grad_norm": 0.3168690800666809,
|
| 358 |
+
"learning_rate": 0.002828,
|
| 359 |
+
"loss": 2.9649,
|
| 360 |
+
"step": 3200
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.244953095684803,
|
| 364 |
+
"grad_norm": 0.32185083627700806,
|
| 365 |
+
"learning_rate": 0.002828,
|
| 366 |
+
"loss": 2.9607,
|
| 367 |
+
"step": 3264
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2497560975609756,
|
| 371 |
+
"grad_norm": 0.3293335437774658,
|
| 372 |
+
"learning_rate": 0.002828,
|
| 373 |
+
"loss": 2.9464,
|
| 374 |
+
"step": 3328
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.2545590994371482,
|
| 378 |
+
"grad_norm": 0.39153945446014404,
|
| 379 |
+
"learning_rate": 0.002828,
|
| 380 |
+
"loss": 2.9513,
|
| 381 |
+
"step": 3392
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.2593621013133208,
|
| 385 |
+
"grad_norm": 0.36884990334510803,
|
| 386 |
+
"learning_rate": 0.002828,
|
| 387 |
+
"loss": 2.9418,
|
| 388 |
+
"step": 3456
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.26416510318949343,
|
| 392 |
+
"grad_norm": 0.39196011424064636,
|
| 393 |
+
"learning_rate": 0.002828,
|
| 394 |
+
"loss": 2.9407,
|
| 395 |
+
"step": 3520
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.26896810506566604,
|
| 399 |
+
"grad_norm": 0.36011603474617004,
|
| 400 |
+
"learning_rate": 0.002828,
|
| 401 |
+
"loss": 2.9461,
|
| 402 |
+
"step": 3584
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.27377110694183865,
|
| 406 |
+
"grad_norm": 0.3608081638813019,
|
| 407 |
+
"learning_rate": 0.002828,
|
| 408 |
+
"loss": 2.937,
|
| 409 |
+
"step": 3648
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.27857410881801126,
|
| 413 |
+
"grad_norm": 0.3833774924278259,
|
| 414 |
+
"learning_rate": 0.002828,
|
| 415 |
+
"loss": 2.9254,
|
| 416 |
+
"step": 3712
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.28337711069418386,
|
| 420 |
+
"grad_norm": 0.35225459933280945,
|
| 421 |
+
"learning_rate": 0.002828,
|
| 422 |
+
"loss": 2.9165,
|
| 423 |
+
"step": 3776
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.2881801125703565,
|
| 427 |
+
"grad_norm": 0.39832860231399536,
|
| 428 |
+
"learning_rate": 0.002828,
|
| 429 |
+
"loss": 2.9259,
|
| 430 |
+
"step": 3840
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.2929831144465291,
|
| 434 |
+
"grad_norm": 0.36834558844566345,
|
| 435 |
+
"learning_rate": 0.002828,
|
| 436 |
+
"loss": 2.9186,
|
| 437 |
+
"step": 3904
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.2977861163227017,
|
| 441 |
+
"grad_norm": 0.3877101540565491,
|
| 442 |
+
"learning_rate": 0.002828,
|
| 443 |
+
"loss": 2.9107,
|
| 444 |
+
"step": 3968
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.3025891181988743,
|
| 448 |
+
"grad_norm": 0.40037983655929565,
|
| 449 |
+
"learning_rate": 0.002828,
|
| 450 |
+
"loss": 2.9086,
|
| 451 |
+
"step": 4032
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3073921200750469,
|
| 455 |
+
"grad_norm": 0.35432353615760803,
|
| 456 |
+
"learning_rate": 0.002828,
|
| 457 |
+
"loss": 2.9039,
|
| 458 |
+
"step": 4096
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.3121951219512195,
|
| 462 |
+
"grad_norm": 0.3740752935409546,
|
| 463 |
+
"learning_rate": 0.002828,
|
| 464 |
+
"loss": 2.8973,
|
| 465 |
+
"step": 4160
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.3169981238273921,
|
| 469 |
+
"grad_norm": 0.3972289264202118,
|
| 470 |
+
"learning_rate": 0.002828,
|
| 471 |
+
"loss": 2.8868,
|
| 472 |
+
"step": 4224
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.3218011257035647,
|
| 476 |
+
"grad_norm": 0.3818065822124481,
|
| 477 |
+
"learning_rate": 0.002828,
|
| 478 |
+
"loss": 2.8916,
|
| 479 |
+
"step": 4288
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.32660412757973734,
|
| 483 |
+
"grad_norm": 0.31802886724472046,
|
| 484 |
+
"learning_rate": 0.002828,
|
| 485 |
+
"loss": 2.895,
|
| 486 |
+
"step": 4352
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.33140712945590994,
|
| 490 |
+
"grad_norm": 0.3920498192310333,
|
| 491 |
+
"learning_rate": 0.002828,
|
| 492 |
+
"loss": 2.896,
|
| 493 |
+
"step": 4416
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.33621013133208255,
|
| 497 |
+
"grad_norm": 0.42001602053642273,
|
| 498 |
+
"learning_rate": 0.002828,
|
| 499 |
+
"loss": 2.8757,
|
| 500 |
+
"step": 4480
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.34101313320825516,
|
| 504 |
+
"grad_norm": 0.38037222623825073,
|
| 505 |
+
"learning_rate": 0.002828,
|
| 506 |
+
"loss": 2.8812,
|
| 507 |
+
"step": 4544
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.34581613508442777,
|
| 511 |
+
"grad_norm": 0.6402748823165894,
|
| 512 |
+
"learning_rate": 0.002828,
|
| 513 |
+
"loss": 2.8741,
|
| 514 |
+
"step": 4608
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.3506191369606004,
|
| 518 |
+
"grad_norm": 0.3265625536441803,
|
| 519 |
+
"learning_rate": 0.002828,
|
| 520 |
+
"loss": 2.8659,
|
| 521 |
+
"step": 4672
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.355422138836773,
|
| 525 |
+
"grad_norm": 0.3389698565006256,
|
| 526 |
+
"learning_rate": 0.002828,
|
| 527 |
+
"loss": 2.863,
|
| 528 |
+
"step": 4736
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.3602251407129456,
|
| 532 |
+
"grad_norm": 0.34922096133232117,
|
| 533 |
+
"learning_rate": 0.002828,
|
| 534 |
+
"loss": 2.8555,
|
| 535 |
+
"step": 4800
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.3650281425891182,
|
| 539 |
+
"grad_norm": 0.370980441570282,
|
| 540 |
+
"learning_rate": 0.002828,
|
| 541 |
+
"loss": 2.8624,
|
| 542 |
+
"step": 4864
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.3698311444652908,
|
| 546 |
+
"grad_norm": 0.3553221821784973,
|
| 547 |
+
"learning_rate": 0.002828,
|
| 548 |
+
"loss": 2.8573,
|
| 549 |
+
"step": 4928
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3746341463414634,
|
| 553 |
+
"grad_norm": 0.36796537041664124,
|
| 554 |
+
"learning_rate": 0.002828,
|
| 555 |
+
"loss": 2.8567,
|
| 556 |
+
"step": 4992
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.379437148217636,
|
| 560 |
+
"grad_norm": 0.3615240752696991,
|
| 561 |
+
"learning_rate": 0.002828,
|
| 562 |
+
"loss": 2.8444,
|
| 563 |
+
"step": 5056
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.38424015009380863,
|
| 567 |
+
"grad_norm": 0.4196101427078247,
|
| 568 |
+
"learning_rate": 0.002828,
|
| 569 |
+
"loss": 2.845,
|
| 570 |
+
"step": 5120
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.38904315196998124,
|
| 574 |
+
"grad_norm": 0.334185928106308,
|
| 575 |
+
"learning_rate": 0.002828,
|
| 576 |
+
"loss": 2.8376,
|
| 577 |
+
"step": 5184
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.39384615384615385,
|
| 581 |
+
"grad_norm": 0.30093756318092346,
|
| 582 |
+
"learning_rate": 0.002828,
|
| 583 |
+
"loss": 2.8302,
|
| 584 |
+
"step": 5248
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.39864915572232645,
|
| 588 |
+
"grad_norm": 0.41615140438079834,
|
| 589 |
+
"learning_rate": 0.002828,
|
| 590 |
+
"loss": 2.8365,
|
| 591 |
+
"step": 5312
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.40345215759849906,
|
| 595 |
+
"grad_norm": 0.38547712564468384,
|
| 596 |
+
"learning_rate": 0.002828,
|
| 597 |
+
"loss": 2.833,
|
| 598 |
+
"step": 5376
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.40825515947467167,
|
| 602 |
+
"grad_norm": 0.336453378200531,
|
| 603 |
+
"learning_rate": 0.002828,
|
| 604 |
+
"loss": 2.8289,
|
| 605 |
+
"step": 5440
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.4130581613508443,
|
| 609 |
+
"grad_norm": 0.33043336868286133,
|
| 610 |
+
"learning_rate": 0.002828,
|
| 611 |
+
"loss": 2.8154,
|
| 612 |
+
"step": 5504
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.4178611632270169,
|
| 616 |
+
"grad_norm": 0.33151519298553467,
|
| 617 |
+
"learning_rate": 0.002828,
|
| 618 |
+
"loss": 2.8267,
|
| 619 |
+
"step": 5568
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.4226641651031895,
|
| 623 |
+
"grad_norm": 0.29418498277664185,
|
| 624 |
+
"learning_rate": 0.002828,
|
| 625 |
+
"loss": 2.8167,
|
| 626 |
+
"step": 5632
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.4274671669793621,
|
| 630 |
+
"grad_norm": 0.3507523536682129,
|
| 631 |
+
"learning_rate": 0.002828,
|
| 632 |
+
"loss": 2.8227,
|
| 633 |
+
"step": 5696
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.4322701688555347,
|
| 637 |
+
"grad_norm": 0.36976736783981323,
|
| 638 |
+
"learning_rate": 0.002828,
|
| 639 |
+
"loss": 2.8087,
|
| 640 |
+
"step": 5760
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.4370731707317073,
|
| 644 |
+
"grad_norm": 0.4142448604106903,
|
| 645 |
+
"learning_rate": 0.002828,
|
| 646 |
+
"loss": 2.8191,
|
| 647 |
+
"step": 5824
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.4418761726078799,
|
| 651 |
+
"grad_norm": 0.3893688917160034,
|
| 652 |
+
"learning_rate": 0.002828,
|
| 653 |
+
"loss": 2.8032,
|
| 654 |
+
"step": 5888
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.44667917448405253,
|
| 658 |
+
"grad_norm": 0.3025995194911957,
|
| 659 |
+
"learning_rate": 0.002828,
|
| 660 |
+
"loss": 2.8049,
|
| 661 |
+
"step": 5952
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.45148217636022514,
|
| 665 |
+
"grad_norm": 0.3676198422908783,
|
| 666 |
+
"learning_rate": 0.002828,
|
| 667 |
+
"loss": 2.7976,
|
| 668 |
+
"step": 6016
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.45628517823639775,
|
| 672 |
+
"grad_norm": 0.39022454619407654,
|
| 673 |
+
"learning_rate": 0.002828,
|
| 674 |
+
"loss": 2.796,
|
| 675 |
+
"step": 6080
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.46108818011257036,
|
| 679 |
+
"grad_norm": 0.38986560702323914,
|
| 680 |
+
"learning_rate": 0.002828,
|
| 681 |
+
"loss": 2.791,
|
| 682 |
+
"step": 6144
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.46589118198874296,
|
| 686 |
+
"grad_norm": 0.35879769921302795,
|
| 687 |
+
"learning_rate": 0.002828,
|
| 688 |
+
"loss": 2.7949,
|
| 689 |
+
"step": 6208
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.47069418386491557,
|
| 693 |
+
"grad_norm": 0.44419315457344055,
|
| 694 |
+
"learning_rate": 0.002828,
|
| 695 |
+
"loss": 2.7862,
|
| 696 |
+
"step": 6272
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.4754971857410882,
|
| 700 |
+
"grad_norm": 0.30884304642677307,
|
| 701 |
+
"learning_rate": 0.002828,
|
| 702 |
+
"loss": 2.7864,
|
| 703 |
+
"step": 6336
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.4803001876172608,
|
| 707 |
+
"grad_norm": 0.542960524559021,
|
| 708 |
+
"learning_rate": 0.002828,
|
| 709 |
+
"loss": 2.7842,
|
| 710 |
+
"step": 6400
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.4851031894934334,
|
| 714 |
+
"grad_norm": 0.39032405614852905,
|
| 715 |
+
"learning_rate": 0.002828,
|
| 716 |
+
"loss": 2.7798,
|
| 717 |
+
"step": 6464
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.489906191369606,
|
| 721 |
+
"grad_norm": 0.3760650157928467,
|
| 722 |
+
"learning_rate": 0.002828,
|
| 723 |
+
"loss": 2.78,
|
| 724 |
+
"step": 6528
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.4947091932457786,
|
| 728 |
+
"grad_norm": 0.33309632539749146,
|
| 729 |
+
"learning_rate": 0.002828,
|
| 730 |
+
"loss": 2.7741,
|
| 731 |
+
"step": 6592
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.4995121951219512,
|
| 735 |
+
"grad_norm": 0.37640711665153503,
|
| 736 |
+
"learning_rate": 0.002828,
|
| 737 |
+
"loss": 2.7795,
|
| 738 |
+
"step": 6656
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.5043151969981239,
|
| 742 |
+
"grad_norm": 0.36830273270606995,
|
| 743 |
+
"learning_rate": 0.002828,
|
| 744 |
+
"loss": 2.7596,
|
| 745 |
+
"step": 6720
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.5091181988742964,
|
| 749 |
+
"grad_norm": 0.3751394748687744,
|
| 750 |
+
"learning_rate": 0.002828,
|
| 751 |
+
"loss": 2.761,
|
| 752 |
+
"step": 6784
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.5139212007504691,
|
| 756 |
+
"grad_norm": 0.3472868800163269,
|
| 757 |
+
"learning_rate": 0.002828,
|
| 758 |
+
"loss": 2.7567,
|
| 759 |
+
"step": 6848
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.5187242026266417,
|
| 763 |
+
"grad_norm": 0.3749905526638031,
|
| 764 |
+
"learning_rate": 0.002828,
|
| 765 |
+
"loss": 2.7654,
|
| 766 |
+
"step": 6912
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.5235272045028143,
|
| 770 |
+
"grad_norm": 0.4672335982322693,
|
| 771 |
+
"learning_rate": 0.002828,
|
| 772 |
+
"loss": 2.7467,
|
| 773 |
+
"step": 6976
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.5283302063789869,
|
| 777 |
+
"grad_norm": 0.30083194375038147,
|
| 778 |
+
"learning_rate": 0.002828,
|
| 779 |
+
"loss": 2.7596,
|
| 780 |
+
"step": 7040
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.5331332082551595,
|
| 784 |
+
"grad_norm": 0.34232673048973083,
|
| 785 |
+
"learning_rate": 0.002828,
|
| 786 |
+
"loss": 2.7425,
|
| 787 |
+
"step": 7104
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.5379362101313321,
|
| 791 |
+
"grad_norm": 0.42222973704338074,
|
| 792 |
+
"learning_rate": 0.002828,
|
| 793 |
+
"loss": 2.7486,
|
| 794 |
+
"step": 7168
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.5427392120075047,
|
| 798 |
+
"grad_norm": 0.36008650064468384,
|
| 799 |
+
"learning_rate": 0.002828,
|
| 800 |
+
"loss": 2.7451,
|
| 801 |
+
"step": 7232
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.5475422138836773,
|
| 805 |
+
"grad_norm": 0.34359127283096313,
|
| 806 |
+
"learning_rate": 0.002828,
|
| 807 |
+
"loss": 2.734,
|
| 808 |
+
"step": 7296
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.55234521575985,
|
| 812 |
+
"grad_norm": 0.3953745663166046,
|
| 813 |
+
"learning_rate": 0.002828,
|
| 814 |
+
"loss": 2.7397,
|
| 815 |
+
"step": 7360
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.5571482176360225,
|
| 819 |
+
"grad_norm": 0.36703094840049744,
|
| 820 |
+
"learning_rate": 0.002828,
|
| 821 |
+
"loss": 2.7313,
|
| 822 |
+
"step": 7424
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.5619512195121952,
|
| 826 |
+
"grad_norm": 0.31787919998168945,
|
| 827 |
+
"learning_rate": 0.002828,
|
| 828 |
+
"loss": 2.7363,
|
| 829 |
+
"step": 7488
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.5667542213883677,
|
| 833 |
+
"grad_norm": 0.31179967522621155,
|
| 834 |
+
"learning_rate": 0.002828,
|
| 835 |
+
"loss": 2.7236,
|
| 836 |
+
"step": 7552
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.5715572232645404,
|
| 840 |
+
"grad_norm": 0.3990299105644226,
|
| 841 |
+
"learning_rate": 0.002828,
|
| 842 |
+
"loss": 2.7191,
|
| 843 |
+
"step": 7616
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.576360225140713,
|
| 847 |
+
"grad_norm": 0.3776848018169403,
|
| 848 |
+
"learning_rate": 0.002828,
|
| 849 |
+
"loss": 2.7244,
|
| 850 |
+
"step": 7680
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.5811632270168856,
|
| 854 |
+
"grad_norm": 0.36117562651634216,
|
| 855 |
+
"learning_rate": 0.002828,
|
| 856 |
+
"loss": 2.7131,
|
| 857 |
+
"step": 7744
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.5859662288930582,
|
| 861 |
+
"grad_norm": 0.3219313323497772,
|
| 862 |
+
"learning_rate": 0.002828,
|
| 863 |
+
"loss": 2.7202,
|
| 864 |
+
"step": 7808
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.5907692307692308,
|
| 868 |
+
"grad_norm": 0.4501495957374573,
|
| 869 |
+
"learning_rate": 0.002828,
|
| 870 |
+
"loss": 2.7115,
|
| 871 |
+
"step": 7872
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.5955722326454034,
|
| 875 |
+
"grad_norm": 0.3939913809299469,
|
| 876 |
+
"learning_rate": 0.002828,
|
| 877 |
+
"loss": 2.7076,
|
| 878 |
+
"step": 7936
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.600375234521576,
|
| 882 |
+
"grad_norm": 0.3244933485984802,
|
| 883 |
+
"learning_rate": 0.002828,
|
| 884 |
+
"loss": 2.7047,
|
| 885 |
+
"step": 8000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.6051782363977486,
|
| 889 |
+
"grad_norm": 0.3094891607761383,
|
| 890 |
+
"learning_rate": 0.002828,
|
| 891 |
+
"loss": 2.698,
|
| 892 |
+
"step": 8064
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.6099812382739213,
|
| 896 |
+
"grad_norm": 0.3525580167770386,
|
| 897 |
+
"learning_rate": 0.002828,
|
| 898 |
+
"loss": 2.7056,
|
| 899 |
+
"step": 8128
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.6147842401500938,
|
| 903 |
+
"grad_norm": 0.3058718144893646,
|
| 904 |
+
"learning_rate": 0.002828,
|
| 905 |
+
"loss": 2.6937,
|
| 906 |
+
"step": 8192
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.6195872420262665,
|
| 910 |
+
"grad_norm": 0.31864726543426514,
|
| 911 |
+
"learning_rate": 0.002828,
|
| 912 |
+
"loss": 2.6935,
|
| 913 |
+
"step": 8256
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.624390243902439,
|
| 917 |
+
"grad_norm": 0.3197256028652191,
|
| 918 |
+
"learning_rate": 0.002828,
|
| 919 |
+
"loss": 2.6981,
|
| 920 |
+
"step": 8320
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.6291932457786117,
|
| 924 |
+
"grad_norm": 0.30954182147979736,
|
| 925 |
+
"learning_rate": 0.002828,
|
| 926 |
+
"loss": 2.705,
|
| 927 |
+
"step": 8384
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.6339962476547842,
|
| 931 |
+
"grad_norm": 0.4144911468029022,
|
| 932 |
+
"learning_rate": 0.002828,
|
| 933 |
+
"loss": 2.6832,
|
| 934 |
+
"step": 8448
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.6387992495309569,
|
| 938 |
+
"grad_norm": 0.34720951318740845,
|
| 939 |
+
"learning_rate": 0.002828,
|
| 940 |
+
"loss": 2.6858,
|
| 941 |
+
"step": 8512
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.6436022514071295,
|
| 945 |
+
"grad_norm": 0.30545172095298767,
|
| 946 |
+
"learning_rate": 0.002828,
|
| 947 |
+
"loss": 2.6758,
|
| 948 |
+
"step": 8576
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.6484052532833021,
|
| 952 |
+
"grad_norm": 0.3341416120529175,
|
| 953 |
+
"learning_rate": 0.002828,
|
| 954 |
+
"loss": 2.6673,
|
| 955 |
+
"step": 8640
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.6532082551594747,
|
| 959 |
+
"grad_norm": 0.5191973447799683,
|
| 960 |
+
"learning_rate": 0.002828,
|
| 961 |
+
"loss": 2.6798,
|
| 962 |
+
"step": 8704
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.6580112570356473,
|
| 966 |
+
"grad_norm": 0.44382575154304504,
|
| 967 |
+
"learning_rate": 0.002828,
|
| 968 |
+
"loss": 2.683,
|
| 969 |
+
"step": 8768
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.6628142589118199,
|
| 973 |
+
"grad_norm": 0.45676809549331665,
|
| 974 |
+
"learning_rate": 0.002828,
|
| 975 |
+
"loss": 2.6731,
|
| 976 |
+
"step": 8832
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.6676172607879926,
|
| 980 |
+
"grad_norm": 0.3542475700378418,
|
| 981 |
+
"learning_rate": 0.002828,
|
| 982 |
+
"loss": 2.6813,
|
| 983 |
+
"step": 8896
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.6724202626641651,
|
| 987 |
+
"grad_norm": 0.3976110517978668,
|
| 988 |
+
"learning_rate": 0.002828,
|
| 989 |
+
"loss": 2.6714,
|
| 990 |
+
"step": 8960
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.6772232645403378,
|
| 994 |
+
"grad_norm": 0.37194061279296875,
|
| 995 |
+
"learning_rate": 0.002828,
|
| 996 |
+
"loss": 2.6646,
|
| 997 |
+
"step": 9024
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.6820262664165103,
|
| 1001 |
+
"grad_norm": 0.4080849289894104,
|
| 1002 |
+
"learning_rate": 0.002828,
|
| 1003 |
+
"loss": 2.6638,
|
| 1004 |
+
"step": 9088
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.686829268292683,
|
| 1008 |
+
"grad_norm": 0.3275296986103058,
|
| 1009 |
+
"learning_rate": 0.002828,
|
| 1010 |
+
"loss": 2.6643,
|
| 1011 |
+
"step": 9152
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.6916322701688555,
|
| 1015 |
+
"grad_norm": 0.4300732910633087,
|
| 1016 |
+
"learning_rate": 0.002828,
|
| 1017 |
+
"loss": 2.6545,
|
| 1018 |
+
"step": 9216
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.6964352720450282,
|
| 1022 |
+
"grad_norm": 0.528816282749176,
|
| 1023 |
+
"learning_rate": 0.002828,
|
| 1024 |
+
"loss": 2.6639,
|
| 1025 |
+
"step": 9280
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.7012382739212007,
|
| 1029 |
+
"grad_norm": 0.39729437232017517,
|
| 1030 |
+
"learning_rate": 0.002828,
|
| 1031 |
+
"loss": 2.6669,
|
| 1032 |
+
"step": 9344
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.7060412757973734,
|
| 1036 |
+
"grad_norm": 0.36177024245262146,
|
| 1037 |
+
"learning_rate": 0.002828,
|
| 1038 |
+
"loss": 2.6429,
|
| 1039 |
+
"step": 9408
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.710844277673546,
|
| 1043 |
+
"grad_norm": 0.3488599956035614,
|
| 1044 |
+
"learning_rate": 0.002828,
|
| 1045 |
+
"loss": 2.6409,
|
| 1046 |
+
"step": 9472
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.7156472795497186,
|
| 1050 |
+
"grad_norm": 0.361208438873291,
|
| 1051 |
+
"learning_rate": 0.002828,
|
| 1052 |
+
"loss": 2.6354,
|
| 1053 |
+
"step": 9536
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.7204502814258912,
|
| 1057 |
+
"grad_norm": 0.3307696282863617,
|
| 1058 |
+
"learning_rate": 0.002828,
|
| 1059 |
+
"loss": 2.6398,
|
| 1060 |
+
"step": 9600
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.7252532833020638,
|
| 1064 |
+
"grad_norm": 0.47409588098526,
|
| 1065 |
+
"learning_rate": 0.002828,
|
| 1066 |
+
"loss": 2.6899,
|
| 1067 |
+
"step": 9664
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.7300562851782364,
|
| 1071 |
+
"grad_norm": 0.43482983112335205,
|
| 1072 |
+
"learning_rate": 0.002828,
|
| 1073 |
+
"loss": 2.6675,
|
| 1074 |
+
"step": 9728
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.7348592870544091,
|
| 1078 |
+
"grad_norm": 0.43177512288093567,
|
| 1079 |
+
"learning_rate": 0.002828,
|
| 1080 |
+
"loss": 2.6703,
|
| 1081 |
+
"step": 9792
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.7396622889305816,
|
| 1085 |
+
"grad_norm": 0.5830815434455872,
|
| 1086 |
+
"learning_rate": 0.002828,
|
| 1087 |
+
"loss": 2.6698,
|
| 1088 |
+
"step": 9856
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.7444652908067543,
|
| 1092 |
+
"grad_norm": 0.42559024691581726,
|
| 1093 |
+
"learning_rate": 0.002828,
|
| 1094 |
+
"loss": 2.6687,
|
| 1095 |
+
"step": 9920
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.7492682926829268,
|
| 1099 |
+
"grad_norm": 0.36572182178497314,
|
| 1100 |
+
"learning_rate": 0.002828,
|
| 1101 |
+
"loss": 2.6602,
|
| 1102 |
+
"step": 9984
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.7540712945590995,
|
| 1106 |
+
"grad_norm": 0.42863738536834717,
|
| 1107 |
+
"learning_rate": 0.002828,
|
| 1108 |
+
"loss": 2.6684,
|
| 1109 |
+
"step": 10048
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.758874296435272,
|
| 1113 |
+
"grad_norm": 0.34681934118270874,
|
| 1114 |
+
"learning_rate": 0.002828,
|
| 1115 |
+
"loss": 2.6618,
|
| 1116 |
+
"step": 10112
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.7636772983114447,
|
| 1120 |
+
"grad_norm": 0.40332967042922974,
|
| 1121 |
+
"learning_rate": 0.002828,
|
| 1122 |
+
"loss": 2.6523,
|
| 1123 |
+
"step": 10176
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.7684803001876173,
|
| 1127 |
+
"grad_norm": 0.47137463092803955,
|
| 1128 |
+
"learning_rate": 0.002828,
|
| 1129 |
+
"loss": 2.6543,
|
| 1130 |
+
"step": 10240
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.7732833020637899,
|
| 1134 |
+
"grad_norm": 0.3324384093284607,
|
| 1135 |
+
"learning_rate": 0.002828,
|
| 1136 |
+
"loss": 2.6444,
|
| 1137 |
+
"step": 10304
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.7780863039399625,
|
| 1141 |
+
"grad_norm": 0.3714103698730469,
|
| 1142 |
+
"learning_rate": 0.002828,
|
| 1143 |
+
"loss": 2.6466,
|
| 1144 |
+
"step": 10368
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.7828893058161351,
|
| 1148 |
+
"grad_norm": 0.3684547543525696,
|
| 1149 |
+
"learning_rate": 0.002828,
|
| 1150 |
+
"loss": 2.6497,
|
| 1151 |
+
"step": 10432
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.7876923076923077,
|
| 1155 |
+
"grad_norm": 0.3580617606639862,
|
| 1156 |
+
"learning_rate": 0.002828,
|
| 1157 |
+
"loss": 2.6428,
|
| 1158 |
+
"step": 10496
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.7924953095684804,
|
| 1162 |
+
"grad_norm": 0.4132176339626312,
|
| 1163 |
+
"learning_rate": 0.002828,
|
| 1164 |
+
"loss": 2.6407,
|
| 1165 |
+
"step": 10560
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.7972983114446529,
|
| 1169 |
+
"grad_norm": 0.4079800546169281,
|
| 1170 |
+
"learning_rate": 0.002828,
|
| 1171 |
+
"loss": 2.6374,
|
| 1172 |
+
"step": 10624
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.8021013133208256,
|
| 1176 |
+
"grad_norm": 0.40170854330062866,
|
| 1177 |
+
"learning_rate": 0.002828,
|
| 1178 |
+
"loss": 2.6319,
|
| 1179 |
+
"step": 10688
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.8069043151969981,
|
| 1183 |
+
"grad_norm": 0.4748755097389221,
|
| 1184 |
+
"learning_rate": 0.002828,
|
| 1185 |
+
"loss": 2.6489,
|
| 1186 |
+
"step": 10752
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.8117073170731708,
|
| 1190 |
+
"grad_norm": 0.3806183338165283,
|
| 1191 |
+
"learning_rate": 0.002828,
|
| 1192 |
+
"loss": 2.6363,
|
| 1193 |
+
"step": 10816
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.8165103189493433,
|
| 1197 |
+
"grad_norm": 0.32777532935142517,
|
| 1198 |
+
"learning_rate": 0.002828,
|
| 1199 |
+
"loss": 2.6386,
|
| 1200 |
+
"step": 10880
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.821313320825516,
|
| 1204 |
+
"grad_norm": 0.4884773790836334,
|
| 1205 |
+
"learning_rate": 0.002828,
|
| 1206 |
+
"loss": 2.6293,
|
| 1207 |
+
"step": 10944
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.8261163227016886,
|
| 1211 |
+
"grad_norm": 0.43175649642944336,
|
| 1212 |
+
"learning_rate": 0.002828,
|
| 1213 |
+
"loss": 2.6351,
|
| 1214 |
+
"step": 11008
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.8309193245778612,
|
| 1218 |
+
"grad_norm": 0.44375500082969666,
|
| 1219 |
+
"learning_rate": 0.002828,
|
| 1220 |
+
"loss": 2.6272,
|
| 1221 |
+
"step": 11072
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.8357223264540338,
|
| 1225 |
+
"grad_norm": 0.36503469944000244,
|
| 1226 |
+
"learning_rate": 0.002828,
|
| 1227 |
+
"loss": 2.628,
|
| 1228 |
+
"step": 11136
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.8405253283302064,
|
| 1232 |
+
"grad_norm": 0.3493196368217468,
|
| 1233 |
+
"learning_rate": 0.002828,
|
| 1234 |
+
"loss": 2.6238,
|
| 1235 |
+
"step": 11200
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.845328330206379,
|
| 1239 |
+
"grad_norm": 0.3593812584877014,
|
| 1240 |
+
"learning_rate": 0.002828,
|
| 1241 |
+
"loss": 2.6161,
|
| 1242 |
+
"step": 11264
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.8501313320825516,
|
| 1246 |
+
"grad_norm": 0.4043927788734436,
|
| 1247 |
+
"learning_rate": 0.002828,
|
| 1248 |
+
"loss": 2.6248,
|
| 1249 |
+
"step": 11328
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.8549343339587242,
|
| 1253 |
+
"grad_norm": 0.3805730938911438,
|
| 1254 |
+
"learning_rate": 0.002828,
|
| 1255 |
+
"loss": 2.619,
|
| 1256 |
+
"step": 11392
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.8597373358348969,
|
| 1260 |
+
"grad_norm": 0.40822461247444153,
|
| 1261 |
+
"learning_rate": 0.002828,
|
| 1262 |
+
"loss": 2.619,
|
| 1263 |
+
"step": 11456
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.8645403377110694,
|
| 1267 |
+
"grad_norm": 0.3430253565311432,
|
| 1268 |
+
"learning_rate": 0.002828,
|
| 1269 |
+
"loss": 2.6162,
|
| 1270 |
+
"step": 11520
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.8693433395872421,
|
| 1274 |
+
"grad_norm": 0.3665921688079834,
|
| 1275 |
+
"learning_rate": 0.002828,
|
| 1276 |
+
"loss": 2.6083,
|
| 1277 |
+
"step": 11584
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.8741463414634146,
|
| 1281 |
+
"grad_norm": 0.3768637776374817,
|
| 1282 |
+
"learning_rate": 0.002828,
|
| 1283 |
+
"loss": 2.6085,
|
| 1284 |
+
"step": 11648
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.8789493433395873,
|
| 1288 |
+
"grad_norm": 0.6709098219871521,
|
| 1289 |
+
"learning_rate": 0.002828,
|
| 1290 |
+
"loss": 2.6067,
|
| 1291 |
+
"step": 11712
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.8837523452157598,
|
| 1295 |
+
"grad_norm": 0.37109729647636414,
|
| 1296 |
+
"learning_rate": 0.002828,
|
| 1297 |
+
"loss": 2.5975,
|
| 1298 |
+
"step": 11776
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.8885553470919325,
|
| 1302 |
+
"grad_norm": 0.35545358061790466,
|
| 1303 |
+
"learning_rate": 0.002828,
|
| 1304 |
+
"loss": 2.6086,
|
| 1305 |
+
"step": 11840
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.8933583489681051,
|
| 1309 |
+
"grad_norm": 0.34493309259414673,
|
| 1310 |
+
"learning_rate": 0.002828,
|
| 1311 |
+
"loss": 2.6009,
|
| 1312 |
+
"step": 11904
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.8981613508442777,
|
| 1316 |
+
"grad_norm": 0.35226738452911377,
|
| 1317 |
+
"learning_rate": 0.002828,
|
| 1318 |
+
"loss": 2.5909,
|
| 1319 |
+
"step": 11968
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.9029643527204503,
|
| 1323 |
+
"grad_norm": 0.3626823425292969,
|
| 1324 |
+
"learning_rate": 0.002828,
|
| 1325 |
+
"loss": 2.5954,
|
| 1326 |
+
"step": 12032
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.9077673545966229,
|
| 1330 |
+
"grad_norm": 0.4639281630516052,
|
| 1331 |
+
"learning_rate": 0.002828,
|
| 1332 |
+
"loss": 2.5976,
|
| 1333 |
+
"step": 12096
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.9125703564727955,
|
| 1337 |
+
"grad_norm": 0.425073504447937,
|
| 1338 |
+
"learning_rate": 0.002828,
|
| 1339 |
+
"loss": 2.5846,
|
| 1340 |
+
"step": 12160
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.9173733583489682,
|
| 1344 |
+
"grad_norm": 0.4849206507205963,
|
| 1345 |
+
"learning_rate": 0.002828,
|
| 1346 |
+
"loss": 2.5851,
|
| 1347 |
+
"step": 12224
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.9221763602251407,
|
| 1351 |
+
"grad_norm": 0.3517647385597229,
|
| 1352 |
+
"learning_rate": 0.002828,
|
| 1353 |
+
"loss": 2.5832,
|
| 1354 |
+
"step": 12288
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.9269793621013134,
|
| 1358 |
+
"grad_norm": 0.4217440187931061,
|
| 1359 |
+
"learning_rate": 0.002828,
|
| 1360 |
+
"loss": 2.5777,
|
| 1361 |
+
"step": 12352
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.9317823639774859,
|
| 1365 |
+
"grad_norm": 0.3862438499927521,
|
| 1366 |
+
"learning_rate": 0.002828,
|
| 1367 |
+
"loss": 2.5769,
|
| 1368 |
+
"step": 12416
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.9365853658536586,
|
| 1372 |
+
"grad_norm": 0.4026007056236267,
|
| 1373 |
+
"learning_rate": 0.002828,
|
| 1374 |
+
"loss": 2.5802,
|
| 1375 |
+
"step": 12480
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.9413883677298311,
|
| 1379 |
+
"grad_norm": 0.3353049159049988,
|
| 1380 |
+
"learning_rate": 0.002828,
|
| 1381 |
+
"loss": 2.5741,
|
| 1382 |
+
"step": 12544
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.9461913696060038,
|
| 1386 |
+
"grad_norm": 0.35357797145843506,
|
| 1387 |
+
"learning_rate": 0.002828,
|
| 1388 |
+
"loss": 2.5723,
|
| 1389 |
+
"step": 12608
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.9509943714821764,
|
| 1393 |
+
"grad_norm": 0.35685861110687256,
|
| 1394 |
+
"learning_rate": 0.002828,
|
| 1395 |
+
"loss": 2.5801,
|
| 1396 |
+
"step": 12672
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.955797373358349,
|
| 1400 |
+
"grad_norm": 0.36265361309051514,
|
| 1401 |
+
"learning_rate": 0.002828,
|
| 1402 |
+
"loss": 2.5784,
|
| 1403 |
+
"step": 12736
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.9606003752345216,
|
| 1407 |
+
"grad_norm": 0.4119773805141449,
|
| 1408 |
+
"learning_rate": 0.002828,
|
| 1409 |
+
"loss": 2.5646,
|
| 1410 |
+
"step": 12800
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.9654033771106942,
|
| 1414 |
+
"grad_norm": 0.3662680387496948,
|
| 1415 |
+
"learning_rate": 0.002828,
|
| 1416 |
+
"loss": 2.5693,
|
| 1417 |
+
"step": 12864
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.9702063789868668,
|
| 1421 |
+
"grad_norm": 0.3822716772556305,
|
| 1422 |
+
"learning_rate": 0.002828,
|
| 1423 |
+
"loss": 2.5643,
|
| 1424 |
+
"step": 12928
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.9750093808630395,
|
| 1428 |
+
"grad_norm": 0.3412950038909912,
|
| 1429 |
+
"learning_rate": 0.002828,
|
| 1430 |
+
"loss": 2.5646,
|
| 1431 |
+
"step": 12992
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.979812382739212,
|
| 1435 |
+
"grad_norm": 0.373353511095047,
|
| 1436 |
+
"learning_rate": 0.002828,
|
| 1437 |
+
"loss": 2.5614,
|
| 1438 |
+
"step": 13056
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.9846153846153847,
|
| 1442 |
+
"grad_norm": 10.112526893615723,
|
| 1443 |
+
"learning_rate": 0.002828,
|
| 1444 |
+
"loss": 2.5578,
|
| 1445 |
+
"step": 13120
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.9894183864915572,
|
| 1449 |
+
"grad_norm": 0.36393383145332336,
|
| 1450 |
+
"learning_rate": 0.002828,
|
| 1451 |
+
"loss": 2.5696,
|
| 1452 |
+
"step": 13184
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.9942213883677299,
|
| 1456 |
+
"grad_norm": 0.4176023006439209,
|
| 1457 |
+
"learning_rate": 0.002828,
|
| 1458 |
+
"loss": 2.5533,
|
| 1459 |
+
"step": 13248
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.9990243902439024,
|
| 1463 |
+
"grad_norm": 0.4248984456062317,
|
| 1464 |
+
"learning_rate": 0.002828,
|
| 1465 |
+
"loss": 2.5569,
|
| 1466 |
+
"step": 13312
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.003827392120075,
|
| 1470 |
+
"grad_norm": 0.3931824564933777,
|
| 1471 |
+
"learning_rate": 0.002828,
|
| 1472 |
+
"loss": 2.5246,
|
| 1473 |
+
"step": 13376
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.0086303939962478,
|
| 1477 |
+
"grad_norm": 0.3742982745170593,
|
| 1478 |
+
"learning_rate": 0.002828,
|
| 1479 |
+
"loss": 2.5104,
|
| 1480 |
+
"step": 13440
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.0134333958724202,
|
| 1484 |
+
"grad_norm": 0.4388613998889923,
|
| 1485 |
+
"learning_rate": 0.002828,
|
| 1486 |
+
"loss": 2.519,
|
| 1487 |
+
"step": 13504
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.0182363977485929,
|
| 1491 |
+
"grad_norm": 0.41458427906036377,
|
| 1492 |
+
"learning_rate": 0.002828,
|
| 1493 |
+
"loss": 2.5162,
|
| 1494 |
+
"step": 13568
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.0230393996247655,
|
| 1498 |
+
"grad_norm": 0.3841855227947235,
|
| 1499 |
+
"learning_rate": 0.002828,
|
| 1500 |
+
"loss": 2.5129,
|
| 1501 |
+
"step": 13632
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.027842401500938,
|
| 1505 |
+
"grad_norm": 0.43930500745773315,
|
| 1506 |
+
"learning_rate": 0.002828,
|
| 1507 |
+
"loss": 2.5179,
|
| 1508 |
+
"step": 13696
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.0326454033771106,
|
| 1512 |
+
"grad_norm": 0.3687760531902313,
|
| 1513 |
+
"learning_rate": 0.002828,
|
| 1514 |
+
"loss": 2.5006,
|
| 1515 |
+
"step": 13760
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.0374484052532833,
|
| 1519 |
+
"grad_norm": 0.3823833465576172,
|
| 1520 |
+
"learning_rate": 0.002828,
|
| 1521 |
+
"loss": 2.5039,
|
| 1522 |
+
"step": 13824
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.042251407129456,
|
| 1526 |
+
"grad_norm": 0.40025222301483154,
|
| 1527 |
+
"learning_rate": 0.002828,
|
| 1528 |
+
"loss": 2.5155,
|
| 1529 |
+
"step": 13888
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.0470544090056286,
|
| 1533 |
+
"grad_norm": 0.40790122747421265,
|
| 1534 |
+
"learning_rate": 0.002828,
|
| 1535 |
+
"loss": 2.5064,
|
| 1536 |
+
"step": 13952
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.051857410881801,
|
| 1540 |
+
"grad_norm": 0.42718634009361267,
|
| 1541 |
+
"learning_rate": 0.002828,
|
| 1542 |
+
"loss": 2.5095,
|
| 1543 |
+
"step": 14016
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.0566604127579737,
|
| 1547 |
+
"grad_norm": 0.3305782079696655,
|
| 1548 |
+
"learning_rate": 0.002828,
|
| 1549 |
+
"loss": 2.5,
|
| 1550 |
+
"step": 14080
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.0614634146341464,
|
| 1554 |
+
"grad_norm": 0.37126559019088745,
|
| 1555 |
+
"learning_rate": 0.002828,
|
| 1556 |
+
"loss": 2.5099,
|
| 1557 |
+
"step": 14144
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.0662664165103188,
|
| 1561 |
+
"grad_norm": 0.414987176656723,
|
| 1562 |
+
"learning_rate": 0.002828,
|
| 1563 |
+
"loss": 2.501,
|
| 1564 |
+
"step": 14208
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.0710694183864915,
|
| 1568 |
+
"grad_norm": 0.45917075872421265,
|
| 1569 |
+
"learning_rate": 0.002828,
|
| 1570 |
+
"loss": 2.5062,
|
| 1571 |
+
"step": 14272
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.0758724202626642,
|
| 1575 |
+
"grad_norm": 0.4362465739250183,
|
| 1576 |
+
"learning_rate": 0.002828,
|
| 1577 |
+
"loss": 2.4949,
|
| 1578 |
+
"step": 14336
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.0806754221388368,
|
| 1582 |
+
"grad_norm": 0.40015289187431335,
|
| 1583 |
+
"learning_rate": 0.002828,
|
| 1584 |
+
"loss": 2.4957,
|
| 1585 |
+
"step": 14400
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.0854784240150095,
|
| 1589 |
+
"grad_norm": 0.3781159818172455,
|
| 1590 |
+
"learning_rate": 0.002828,
|
| 1591 |
+
"loss": 2.4979,
|
| 1592 |
+
"step": 14464
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.090281425891182,
|
| 1596 |
+
"grad_norm": 0.4165579676628113,
|
| 1597 |
+
"learning_rate": 0.002828,
|
| 1598 |
+
"loss": 2.4913,
|
| 1599 |
+
"step": 14528
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.0950844277673546,
|
| 1603 |
+
"grad_norm": 0.4100767970085144,
|
| 1604 |
+
"learning_rate": 0.002828,
|
| 1605 |
+
"loss": 2.4978,
|
| 1606 |
+
"step": 14592
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.0998874296435273,
|
| 1610 |
+
"grad_norm": 0.4211256504058838,
|
| 1611 |
+
"learning_rate": 0.002828,
|
| 1612 |
+
"loss": 2.4871,
|
| 1613 |
+
"step": 14656
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.1046904315196997,
|
| 1617 |
+
"grad_norm": 0.390396386384964,
|
| 1618 |
+
"learning_rate": 0.002828,
|
| 1619 |
+
"loss": 2.4933,
|
| 1620 |
+
"step": 14720
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.1094934333958724,
|
| 1624 |
+
"grad_norm": 0.3585355281829834,
|
| 1625 |
+
"learning_rate": 0.002828,
|
| 1626 |
+
"loss": 2.4811,
|
| 1627 |
+
"step": 14784
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.114296435272045,
|
| 1631 |
+
"grad_norm": 0.5148431062698364,
|
| 1632 |
+
"learning_rate": 0.002828,
|
| 1633 |
+
"loss": 2.4888,
|
| 1634 |
+
"step": 14848
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.1190994371482177,
|
| 1638 |
+
"grad_norm": 0.44254639744758606,
|
| 1639 |
+
"learning_rate": 0.002828,
|
| 1640 |
+
"loss": 2.4821,
|
| 1641 |
+
"step": 14912
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.1239024390243904,
|
| 1645 |
+
"grad_norm": 0.3710468113422394,
|
| 1646 |
+
"learning_rate": 0.002828,
|
| 1647 |
+
"loss": 2.4819,
|
| 1648 |
+
"step": 14976
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.1287054409005628,
|
| 1652 |
+
"grad_norm": 0.41197285056114197,
|
| 1653 |
+
"learning_rate": 0.002828,
|
| 1654 |
+
"loss": 2.4842,
|
| 1655 |
+
"step": 15040
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.1335084427767355,
|
| 1659 |
+
"grad_norm": 0.37512508034706116,
|
| 1660 |
+
"learning_rate": 0.002828,
|
| 1661 |
+
"loss": 2.4776,
|
| 1662 |
+
"step": 15104
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.1383114446529081,
|
| 1666 |
+
"grad_norm": 0.4286038279533386,
|
| 1667 |
+
"learning_rate": 0.002828,
|
| 1668 |
+
"loss": 2.4748,
|
| 1669 |
+
"step": 15168
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.1431144465290806,
|
| 1673 |
+
"grad_norm": 0.37446776032447815,
|
| 1674 |
+
"learning_rate": 0.002828,
|
| 1675 |
+
"loss": 2.4727,
|
| 1676 |
+
"step": 15232
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.1479174484052532,
|
| 1680 |
+
"grad_norm": 0.4537597894668579,
|
| 1681 |
+
"learning_rate": 0.002828,
|
| 1682 |
+
"loss": 2.4663,
|
| 1683 |
+
"step": 15296
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.152720450281426,
|
| 1687 |
+
"grad_norm": 0.36247050762176514,
|
| 1688 |
+
"learning_rate": 0.002828,
|
| 1689 |
+
"loss": 2.4699,
|
| 1690 |
+
"step": 15360
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.1575234521575986,
|
| 1694 |
+
"grad_norm": 0.3772297501564026,
|
| 1695 |
+
"learning_rate": 0.002828,
|
| 1696 |
+
"loss": 2.4734,
|
| 1697 |
+
"step": 15424
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.1623264540337712,
|
| 1701 |
+
"grad_norm": 0.3789200186729431,
|
| 1702 |
+
"learning_rate": 0.002828,
|
| 1703 |
+
"loss": 2.4696,
|
| 1704 |
+
"step": 15488
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.1671294559099437,
|
| 1708 |
+
"grad_norm": 0.36870113015174866,
|
| 1709 |
+
"learning_rate": 0.002828,
|
| 1710 |
+
"loss": 2.4671,
|
| 1711 |
+
"step": 15552
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.1719324577861163,
|
| 1715 |
+
"grad_norm": 0.37448298931121826,
|
| 1716 |
+
"learning_rate": 0.002828,
|
| 1717 |
+
"loss": 2.462,
|
| 1718 |
+
"step": 15616
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.176735459662289,
|
| 1722 |
+
"grad_norm": 0.4384878873825073,
|
| 1723 |
+
"learning_rate": 0.002828,
|
| 1724 |
+
"loss": 2.4648,
|
| 1725 |
+
"step": 15680
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.1815384615384614,
|
| 1729 |
+
"grad_norm": 0.37811148166656494,
|
| 1730 |
+
"learning_rate": 0.002828,
|
| 1731 |
+
"loss": 2.4598,
|
| 1732 |
+
"step": 15744
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.186341463414634,
|
| 1736 |
+
"grad_norm": 0.4190385341644287,
|
| 1737 |
+
"learning_rate": 0.002828,
|
| 1738 |
+
"loss": 2.4643,
|
| 1739 |
+
"step": 15808
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.1911444652908068,
|
| 1743 |
+
"grad_norm": 0.48885485529899597,
|
| 1744 |
+
"learning_rate": 0.002828,
|
| 1745 |
+
"loss": 2.4564,
|
| 1746 |
+
"step": 15872
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.1959474671669794,
|
| 1750 |
+
"grad_norm": 0.42267611622810364,
|
| 1751 |
+
"learning_rate": 0.002828,
|
| 1752 |
+
"loss": 2.4671,
|
| 1753 |
+
"step": 15936
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.200750469043152,
|
| 1757 |
+
"grad_norm": 0.3886626064777374,
|
| 1758 |
+
"learning_rate": 0.002828,
|
| 1759 |
+
"loss": 2.4715,
|
| 1760 |
+
"step": 16000
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.2055534709193245,
|
| 1764 |
+
"grad_norm": 0.40871456265449524,
|
| 1765 |
+
"learning_rate": 0.002828,
|
| 1766 |
+
"loss": 2.4558,
|
| 1767 |
+
"step": 16064
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.2103564727954972,
|
| 1771 |
+
"grad_norm": 0.46952739357948303,
|
| 1772 |
+
"learning_rate": 0.002828,
|
| 1773 |
+
"loss": 2.4497,
|
| 1774 |
+
"step": 16128
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.2151594746716698,
|
| 1778 |
+
"grad_norm": 0.41340023279190063,
|
| 1779 |
+
"learning_rate": 0.002828,
|
| 1780 |
+
"loss": 2.4402,
|
| 1781 |
+
"step": 16192
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.2199624765478423,
|
| 1785 |
+
"grad_norm": 0.36176440119743347,
|
| 1786 |
+
"learning_rate": 0.002828,
|
| 1787 |
+
"loss": 2.4473,
|
| 1788 |
+
"step": 16256
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.224765478424015,
|
| 1792 |
+
"grad_norm": 0.4117899239063263,
|
| 1793 |
+
"learning_rate": 0.002828,
|
| 1794 |
+
"loss": 2.443,
|
| 1795 |
+
"step": 16320
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.2295684803001876,
|
| 1799 |
+
"grad_norm": 0.5039286613464355,
|
| 1800 |
+
"learning_rate": 0.002828,
|
| 1801 |
+
"loss": 2.4557,
|
| 1802 |
+
"step": 16384
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.2343714821763603,
|
| 1806 |
+
"grad_norm": 0.3716677129268646,
|
| 1807 |
+
"learning_rate": 0.002828,
|
| 1808 |
+
"loss": 2.4522,
|
| 1809 |
+
"step": 16448
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.239174484052533,
|
| 1813 |
+
"grad_norm": 0.42316168546676636,
|
| 1814 |
+
"learning_rate": 0.002828,
|
| 1815 |
+
"loss": 2.4424,
|
| 1816 |
+
"step": 16512
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.2439774859287054,
|
| 1820 |
+
"grad_norm": 0.5081620216369629,
|
| 1821 |
+
"learning_rate": 0.002828,
|
| 1822 |
+
"loss": 2.4325,
|
| 1823 |
+
"step": 16576
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.248780487804878,
|
| 1827 |
+
"grad_norm": 0.39409589767456055,
|
| 1828 |
+
"learning_rate": 0.002828,
|
| 1829 |
+
"loss": 2.435,
|
| 1830 |
+
"step": 16640
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.2535834896810507,
|
| 1834 |
+
"grad_norm": 0.38638824224472046,
|
| 1835 |
+
"learning_rate": 0.002828,
|
| 1836 |
+
"loss": 2.4363,
|
| 1837 |
+
"step": 16704
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.2583864915572232,
|
| 1841 |
+
"grad_norm": 0.41918718814849854,
|
| 1842 |
+
"learning_rate": 0.002828,
|
| 1843 |
+
"loss": 2.4404,
|
| 1844 |
+
"step": 16768
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.2631894934333958,
|
| 1848 |
+
"grad_norm": 0.3932395279407501,
|
| 1849 |
+
"learning_rate": 0.002828,
|
| 1850 |
+
"loss": 2.4403,
|
| 1851 |
+
"step": 16832
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.2679924953095685,
|
| 1855 |
+
"grad_norm": 0.3787371814250946,
|
| 1856 |
+
"learning_rate": 0.002828,
|
| 1857 |
+
"loss": 2.4386,
|
| 1858 |
+
"step": 16896
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.2727954971857411,
|
| 1862 |
+
"grad_norm": 0.40612953901290894,
|
| 1863 |
+
"learning_rate": 0.002828,
|
| 1864 |
+
"loss": 2.4219,
|
| 1865 |
+
"step": 16960
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.2775984990619138,
|
| 1869 |
+
"grad_norm": 0.4243071675300598,
|
| 1870 |
+
"learning_rate": 0.002828,
|
| 1871 |
+
"loss": 2.4261,
|
| 1872 |
+
"step": 17024
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.2824015009380862,
|
| 1876 |
+
"grad_norm": 0.4240303039550781,
|
| 1877 |
+
"learning_rate": 0.002828,
|
| 1878 |
+
"loss": 2.444,
|
| 1879 |
+
"step": 17088
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.287204502814259,
|
| 1883 |
+
"grad_norm": 0.4888259470462799,
|
| 1884 |
+
"learning_rate": 0.002828,
|
| 1885 |
+
"loss": 2.4344,
|
| 1886 |
+
"step": 17152
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.2920075046904316,
|
| 1890 |
+
"grad_norm": 0.4678399860858917,
|
| 1891 |
+
"learning_rate": 0.002828,
|
| 1892 |
+
"loss": 2.4306,
|
| 1893 |
+
"step": 17216
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.296810506566604,
|
| 1897 |
+
"grad_norm": 0.38733649253845215,
|
| 1898 |
+
"learning_rate": 0.002828,
|
| 1899 |
+
"loss": 2.431,
|
| 1900 |
+
"step": 17280
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.3016135084427767,
|
| 1904 |
+
"grad_norm": 0.38587358593940735,
|
| 1905 |
+
"learning_rate": 0.002828,
|
| 1906 |
+
"loss": 2.4205,
|
| 1907 |
+
"step": 17344
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 1.3064165103189493,
|
| 1911 |
+
"grad_norm": 0.39998751878738403,
|
| 1912 |
+
"learning_rate": 0.002828,
|
| 1913 |
+
"loss": 2.4336,
|
| 1914 |
+
"step": 17408
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.311219512195122,
|
| 1918 |
+
"grad_norm": 0.36294978857040405,
|
| 1919 |
+
"learning_rate": 0.002828,
|
| 1920 |
+
"loss": 2.4238,
|
| 1921 |
+
"step": 17472
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.3160225140712947,
|
| 1925 |
+
"grad_norm": 0.3924562633037567,
|
| 1926 |
+
"learning_rate": 0.002828,
|
| 1927 |
+
"loss": 2.4197,
|
| 1928 |
+
"step": 17536
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.320825515947467,
|
| 1932 |
+
"grad_norm": 0.3837553560733795,
|
| 1933 |
+
"learning_rate": 0.002828,
|
| 1934 |
+
"loss": 2.4243,
|
| 1935 |
+
"step": 17600
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.3256285178236398,
|
| 1939 |
+
"grad_norm": 0.38875913619995117,
|
| 1940 |
+
"learning_rate": 0.002828,
|
| 1941 |
+
"loss": 2.4172,
|
| 1942 |
+
"step": 17664
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.3304315196998124,
|
| 1946 |
+
"grad_norm": 0.41738125681877136,
|
| 1947 |
+
"learning_rate": 0.002828,
|
| 1948 |
+
"loss": 2.4225,
|
| 1949 |
+
"step": 17728
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.3352345215759849,
|
| 1953 |
+
"grad_norm": 0.3645491898059845,
|
| 1954 |
+
"learning_rate": 0.002828,
|
| 1955 |
+
"loss": 2.4151,
|
| 1956 |
+
"step": 17792
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.3400375234521575,
|
| 1960 |
+
"grad_norm": 0.43829870223999023,
|
| 1961 |
+
"learning_rate": 0.002828,
|
| 1962 |
+
"loss": 2.4099,
|
| 1963 |
+
"step": 17856
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 1.3448405253283302,
|
| 1967 |
+
"grad_norm": 0.3851640820503235,
|
| 1968 |
+
"learning_rate": 0.002828,
|
| 1969 |
+
"loss": 2.4168,
|
| 1970 |
+
"step": 17920
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.3496435272045029,
|
| 1974 |
+
"grad_norm": 0.36147060990333557,
|
| 1975 |
+
"learning_rate": 0.002828,
|
| 1976 |
+
"loss": 2.4085,
|
| 1977 |
+
"step": 17984
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.3544465290806755,
|
| 1981 |
+
"grad_norm": 0.42050638794898987,
|
| 1982 |
+
"learning_rate": 0.002828,
|
| 1983 |
+
"loss": 2.4121,
|
| 1984 |
+
"step": 18048
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 1.359249530956848,
|
| 1988 |
+
"grad_norm": 0.3830699920654297,
|
| 1989 |
+
"learning_rate": 0.002828,
|
| 1990 |
+
"loss": 2.4095,
|
| 1991 |
+
"step": 18112
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.3640525328330206,
|
| 1995 |
+
"grad_norm": 0.3830968737602234,
|
| 1996 |
+
"learning_rate": 0.002828,
|
| 1997 |
+
"loss": 2.4077,
|
| 1998 |
+
"step": 18176
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 1.3688555347091933,
|
| 2002 |
+
"grad_norm": 0.3880060017108917,
|
| 2003 |
+
"learning_rate": 0.002828,
|
| 2004 |
+
"loss": 2.4124,
|
| 2005 |
+
"step": 18240
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 1.3736585365853657,
|
| 2009 |
+
"grad_norm": 0.45445796847343445,
|
| 2010 |
+
"learning_rate": 0.002828,
|
| 2011 |
+
"loss": 2.4014,
|
| 2012 |
+
"step": 18304
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.3784615384615384,
|
| 2016 |
+
"grad_norm": 0.3750540316104889,
|
| 2017 |
+
"learning_rate": 0.002828,
|
| 2018 |
+
"loss": 2.4003,
|
| 2019 |
+
"step": 18368
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.383264540337711,
|
| 2023 |
+
"grad_norm": 0.3783455193042755,
|
| 2024 |
+
"learning_rate": 0.002828,
|
| 2025 |
+
"loss": 2.3983,
|
| 2026 |
+
"step": 18432
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.3880675422138837,
|
| 2030 |
+
"grad_norm": 0.40336528420448303,
|
| 2031 |
+
"learning_rate": 0.002828,
|
| 2032 |
+
"loss": 2.4105,
|
| 2033 |
+
"step": 18496
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.3928705440900564,
|
| 2037 |
+
"grad_norm": 0.43220385909080505,
|
| 2038 |
+
"learning_rate": 0.002828,
|
| 2039 |
+
"loss": 2.4018,
|
| 2040 |
+
"step": 18560
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.3976735459662288,
|
| 2044 |
+
"grad_norm": 0.4069630205631256,
|
| 2045 |
+
"learning_rate": 0.002828,
|
| 2046 |
+
"loss": 2.4049,
|
| 2047 |
+
"step": 18624
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.4024765478424015,
|
| 2051 |
+
"grad_norm": 0.3866819441318512,
|
| 2052 |
+
"learning_rate": 0.002828,
|
| 2053 |
+
"loss": 2.3917,
|
| 2054 |
+
"step": 18688
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 1.4072795497185742,
|
| 2058 |
+
"grad_norm": 0.3699668347835541,
|
| 2059 |
+
"learning_rate": 0.002828,
|
| 2060 |
+
"loss": 2.3908,
|
| 2061 |
+
"step": 18752
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.4120825515947466,
|
| 2065 |
+
"grad_norm": 0.377645879983902,
|
| 2066 |
+
"learning_rate": 0.002828,
|
| 2067 |
+
"loss": 2.3957,
|
| 2068 |
+
"step": 18816
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 1.4168855534709193,
|
| 2072 |
+
"grad_norm": 0.36612892150878906,
|
| 2073 |
+
"learning_rate": 0.002828,
|
| 2074 |
+
"loss": 2.3973,
|
| 2075 |
+
"step": 18880
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 1.421688555347092,
|
| 2079 |
+
"grad_norm": 0.385735422372818,
|
| 2080 |
+
"learning_rate": 0.002828,
|
| 2081 |
+
"loss": 2.3952,
|
| 2082 |
+
"step": 18944
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.4264915572232646,
|
| 2086 |
+
"grad_norm": 0.4026818871498108,
|
| 2087 |
+
"learning_rate": 0.002828,
|
| 2088 |
+
"loss": 2.3908,
|
| 2089 |
+
"step": 19008
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.4312945590994373,
|
| 2093 |
+
"grad_norm": 0.39212891459465027,
|
| 2094 |
+
"learning_rate": 0.002828,
|
| 2095 |
+
"loss": 2.3923,
|
| 2096 |
+
"step": 19072
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.4360975609756097,
|
| 2100 |
+
"grad_norm": 0.43533411622047424,
|
| 2101 |
+
"learning_rate": 0.002828,
|
| 2102 |
+
"loss": 2.3918,
|
| 2103 |
+
"step": 19136
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.4409005628517824,
|
| 2107 |
+
"grad_norm": 0.4136466383934021,
|
| 2108 |
+
"learning_rate": 0.002828,
|
| 2109 |
+
"loss": 2.3885,
|
| 2110 |
+
"step": 19200
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 1.445703564727955,
|
| 2114 |
+
"grad_norm": 0.38349345326423645,
|
| 2115 |
+
"learning_rate": 0.002828,
|
| 2116 |
+
"loss": 2.3891,
|
| 2117 |
+
"step": 19264
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.4505065666041275,
|
| 2121 |
+
"grad_norm": 0.42666760087013245,
|
| 2122 |
+
"learning_rate": 0.002828,
|
| 2123 |
+
"loss": 2.3725,
|
| 2124 |
+
"step": 19328
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.4553095684803001,
|
| 2128 |
+
"grad_norm": 0.3926577866077423,
|
| 2129 |
+
"learning_rate": 0.002828,
|
| 2130 |
+
"loss": 2.3885,
|
| 2131 |
+
"step": 19392
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 1.4601125703564728,
|
| 2135 |
+
"grad_norm": 0.3736414611339569,
|
| 2136 |
+
"learning_rate": 0.002828,
|
| 2137 |
+
"loss": 2.3855,
|
| 2138 |
+
"step": 19456
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.4649155722326455,
|
| 2142 |
+
"grad_norm": 0.36343908309936523,
|
| 2143 |
+
"learning_rate": 0.002828,
|
| 2144 |
+
"loss": 2.3773,
|
| 2145 |
+
"step": 19520
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 1.4697185741088181,
|
| 2149 |
+
"grad_norm": 0.380211740732193,
|
| 2150 |
+
"learning_rate": 0.002828,
|
| 2151 |
+
"loss": 2.3809,
|
| 2152 |
+
"step": 19584
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 1.4745215759849906,
|
| 2156 |
+
"grad_norm": 0.40481454133987427,
|
| 2157 |
+
"learning_rate": 0.002828,
|
| 2158 |
+
"loss": 2.375,
|
| 2159 |
+
"step": 19648
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.4793245778611632,
|
| 2163 |
+
"grad_norm": 0.45368635654449463,
|
| 2164 |
+
"learning_rate": 0.002828,
|
| 2165 |
+
"loss": 2.3707,
|
| 2166 |
+
"step": 19712
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.484127579737336,
|
| 2170 |
+
"grad_norm": 0.4029395580291748,
|
| 2171 |
+
"learning_rate": 0.002828,
|
| 2172 |
+
"loss": 2.3733,
|
| 2173 |
+
"step": 19776
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.4889305816135083,
|
| 2177 |
+
"grad_norm": 0.3748946785926819,
|
| 2178 |
+
"learning_rate": 0.002828,
|
| 2179 |
+
"loss": 2.3739,
|
| 2180 |
+
"step": 19840
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.493733583489681,
|
| 2184 |
+
"grad_norm": 0.36640551686286926,
|
| 2185 |
+
"learning_rate": 0.002828,
|
| 2186 |
+
"loss": 2.3652,
|
| 2187 |
+
"step": 19904
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.4985365853658537,
|
| 2191 |
+
"grad_norm": 0.4150533676147461,
|
| 2192 |
+
"learning_rate": 0.002828,
|
| 2193 |
+
"loss": 2.3709,
|
| 2194 |
+
"step": 19968
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.5033395872420263,
|
| 2198 |
+
"grad_norm": 0.49730879068374634,
|
| 2199 |
+
"learning_rate": 0.002828,
|
| 2200 |
+
"loss": 2.3668,
|
| 2201 |
+
"step": 20032
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 1.508142589118199,
|
| 2205 |
+
"grad_norm": 0.37675461173057556,
|
| 2206 |
+
"learning_rate": 0.002828,
|
| 2207 |
+
"loss": 2.3695,
|
| 2208 |
+
"step": 20096
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 1.5129455909943714,
|
| 2212 |
+
"grad_norm": 0.3647516965866089,
|
| 2213 |
+
"learning_rate": 0.002828,
|
| 2214 |
+
"loss": 2.3733,
|
| 2215 |
+
"step": 20160
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 1.517748592870544,
|
| 2219 |
+
"grad_norm": 1.2981253862380981,
|
| 2220 |
+
"learning_rate": 0.002828,
|
| 2221 |
+
"loss": 2.369,
|
| 2222 |
+
"step": 20224
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 1.5225515947467168,
|
| 2226 |
+
"grad_norm": 0.5044511556625366,
|
| 2227 |
+
"learning_rate": 0.002828,
|
| 2228 |
+
"loss": 2.3578,
|
| 2229 |
+
"step": 20288
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 1.5273545966228892,
|
| 2233 |
+
"grad_norm": 0.3651883006095886,
|
| 2234 |
+
"learning_rate": 0.002828,
|
| 2235 |
+
"loss": 2.3601,
|
| 2236 |
+
"step": 20352
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 1.532157598499062,
|
| 2240 |
+
"grad_norm": 0.4419403076171875,
|
| 2241 |
+
"learning_rate": 0.002828,
|
| 2242 |
+
"loss": 2.3607,
|
| 2243 |
+
"step": 20416
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 1.5369606003752345,
|
| 2247 |
+
"grad_norm": 0.38631224632263184,
|
| 2248 |
+
"learning_rate": 0.002828,
|
| 2249 |
+
"loss": 2.3619,
|
| 2250 |
+
"step": 20480
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 1.5417636022514072,
|
| 2254 |
+
"grad_norm": 0.34725359082221985,
|
| 2255 |
+
"learning_rate": 0.002828,
|
| 2256 |
+
"loss": 2.3573,
|
| 2257 |
+
"step": 20544
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 1.5465666041275798,
|
| 2261 |
+
"grad_norm": 0.3991786241531372,
|
| 2262 |
+
"learning_rate": 0.002828,
|
| 2263 |
+
"loss": 2.357,
|
| 2264 |
+
"step": 20608
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 1.5513696060037523,
|
| 2268 |
+
"grad_norm": 0.3595084846019745,
|
| 2269 |
+
"learning_rate": 0.002828,
|
| 2270 |
+
"loss": 2.357,
|
| 2271 |
+
"step": 20672
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 1.556172607879925,
|
| 2275 |
+
"grad_norm": 0.4021853804588318,
|
| 2276 |
+
"learning_rate": 0.002828,
|
| 2277 |
+
"loss": 2.3537,
|
| 2278 |
+
"step": 20736
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 1.5609756097560976,
|
| 2282 |
+
"grad_norm": 0.3939075767993927,
|
| 2283 |
+
"learning_rate": 0.002828,
|
| 2284 |
+
"loss": 2.3594,
|
| 2285 |
+
"step": 20800
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 1.56577861163227,
|
| 2289 |
+
"grad_norm": 0.3889540135860443,
|
| 2290 |
+
"learning_rate": 0.002828,
|
| 2291 |
+
"loss": 2.3573,
|
| 2292 |
+
"step": 20864
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 1.570581613508443,
|
| 2296 |
+
"grad_norm": 0.41366517543792725,
|
| 2297 |
+
"learning_rate": 0.002828,
|
| 2298 |
+
"loss": 2.3442,
|
| 2299 |
+
"step": 20928
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 1.5753846153846154,
|
| 2303 |
+
"grad_norm": 0.37127187848091125,
|
| 2304 |
+
"learning_rate": 0.002828,
|
| 2305 |
+
"loss": 2.3457,
|
| 2306 |
+
"step": 20992
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 1.580187617260788,
|
| 2310 |
+
"grad_norm": 0.4014946520328522,
|
| 2311 |
+
"learning_rate": 0.002828,
|
| 2312 |
+
"loss": 2.3457,
|
| 2313 |
+
"step": 21056
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 1.5849906191369607,
|
| 2317 |
+
"grad_norm": 0.35794708132743835,
|
| 2318 |
+
"learning_rate": 0.002828,
|
| 2319 |
+
"loss": 2.3508,
|
| 2320 |
+
"step": 21120
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 1.5897936210131332,
|
| 2324 |
+
"grad_norm": 0.3924767076969147,
|
| 2325 |
+
"learning_rate": 0.002828,
|
| 2326 |
+
"loss": 2.3451,
|
| 2327 |
+
"step": 21184
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 1.5945966228893058,
|
| 2331 |
+
"grad_norm": 0.34789031744003296,
|
| 2332 |
+
"learning_rate": 0.002828,
|
| 2333 |
+
"loss": 2.3444,
|
| 2334 |
+
"step": 21248
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 1.5993996247654785,
|
| 2338 |
+
"grad_norm": 0.37461933493614197,
|
| 2339 |
+
"learning_rate": 0.002828,
|
| 2340 |
+
"loss": 2.3385,
|
| 2341 |
+
"step": 21312
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 1.604202626641651,
|
| 2345 |
+
"grad_norm": 0.40146076679229736,
|
| 2346 |
+
"learning_rate": 0.002828,
|
| 2347 |
+
"loss": 2.3406,
|
| 2348 |
+
"step": 21376
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 1.6090056285178238,
|
| 2352 |
+
"grad_norm": 0.4080921411514282,
|
| 2353 |
+
"learning_rate": 0.002828,
|
| 2354 |
+
"loss": 2.3423,
|
| 2355 |
+
"step": 21440
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 1.6138086303939962,
|
| 2359 |
+
"grad_norm": 0.40802744030952454,
|
| 2360 |
+
"learning_rate": 0.002828,
|
| 2361 |
+
"loss": 2.3377,
|
| 2362 |
+
"step": 21504
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 1.618611632270169,
|
| 2366 |
+
"grad_norm": 0.420188307762146,
|
| 2367 |
+
"learning_rate": 0.002828,
|
| 2368 |
+
"loss": 2.3399,
|
| 2369 |
+
"step": 21568
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 1.6234146341463416,
|
| 2373 |
+
"grad_norm": 0.40739214420318604,
|
| 2374 |
+
"learning_rate": 0.002828,
|
| 2375 |
+
"loss": 2.34,
|
| 2376 |
+
"step": 21632
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 1.628217636022514,
|
| 2380 |
+
"grad_norm": 0.41674676537513733,
|
| 2381 |
+
"learning_rate": 0.002828,
|
| 2382 |
+
"loss": 2.3326,
|
| 2383 |
+
"step": 21696
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 1.6330206378986867,
|
| 2387 |
+
"grad_norm": 0.41856762766838074,
|
| 2388 |
+
"learning_rate": 0.002828,
|
| 2389 |
+
"loss": 2.3366,
|
| 2390 |
+
"step": 21760
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 1.6378236397748593,
|
| 2394 |
+
"grad_norm": 0.39763346314430237,
|
| 2395 |
+
"learning_rate": 0.002828,
|
| 2396 |
+
"loss": 2.3339,
|
| 2397 |
+
"step": 21824
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 1.6426266416510318,
|
| 2401 |
+
"grad_norm": 0.3777034282684326,
|
| 2402 |
+
"learning_rate": 0.002828,
|
| 2403 |
+
"loss": 2.343,
|
| 2404 |
+
"step": 21888
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 1.6474296435272047,
|
| 2408 |
+
"grad_norm": 0.3617188036441803,
|
| 2409 |
+
"learning_rate": 0.002828,
|
| 2410 |
+
"loss": 2.3341,
|
| 2411 |
+
"step": 21952
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 1.652232645403377,
|
| 2415 |
+
"grad_norm": 0.4504718482494354,
|
| 2416 |
+
"learning_rate": 0.002828,
|
| 2417 |
+
"loss": 2.3295,
|
| 2418 |
+
"step": 22016
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 1.6570356472795498,
|
| 2422 |
+
"grad_norm": 0.37388357520103455,
|
| 2423 |
+
"learning_rate": 0.002828,
|
| 2424 |
+
"loss": 2.3408,
|
| 2425 |
+
"step": 22080
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 1.6618386491557224,
|
| 2429 |
+
"grad_norm": 0.3807313144207001,
|
| 2430 |
+
"learning_rate": 0.002828,
|
| 2431 |
+
"loss": 2.3249,
|
| 2432 |
+
"step": 22144
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 1.6666416510318949,
|
| 2436 |
+
"grad_norm": 0.4428509771823883,
|
| 2437 |
+
"learning_rate": 0.002828,
|
| 2438 |
+
"loss": 2.3347,
|
| 2439 |
+
"step": 22208
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 1.6714446529080675,
|
| 2443 |
+
"grad_norm": 0.39028382301330566,
|
| 2444 |
+
"learning_rate": 0.002828,
|
| 2445 |
+
"loss": 2.336,
|
| 2446 |
+
"step": 22272
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 1.6762476547842402,
|
| 2450 |
+
"grad_norm": 0.482424259185791,
|
| 2451 |
+
"learning_rate": 0.002828,
|
| 2452 |
+
"loss": 2.3212,
|
| 2453 |
+
"step": 22336
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 1.6810506566604126,
|
| 2457 |
+
"grad_norm": 0.39801299571990967,
|
| 2458 |
+
"learning_rate": 0.002828,
|
| 2459 |
+
"loss": 2.314,
|
| 2460 |
+
"step": 22400
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 1.6858536585365855,
|
| 2464 |
+
"grad_norm": 0.4351527988910675,
|
| 2465 |
+
"learning_rate": 0.002828,
|
| 2466 |
+
"loss": 2.3223,
|
| 2467 |
+
"step": 22464
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 1.690656660412758,
|
| 2471 |
+
"grad_norm": 0.4509490430355072,
|
| 2472 |
+
"learning_rate": 0.002828,
|
| 2473 |
+
"loss": 2.3246,
|
| 2474 |
+
"step": 22528
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.6954596622889306,
|
| 2478 |
+
"grad_norm": 0.35885152220726013,
|
| 2479 |
+
"learning_rate": 0.002828,
|
| 2480 |
+
"loss": 2.319,
|
| 2481 |
+
"step": 22592
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 1.7002626641651033,
|
| 2485 |
+
"grad_norm": 0.4146900177001953,
|
| 2486 |
+
"learning_rate": 0.002828,
|
| 2487 |
+
"loss": 2.3214,
|
| 2488 |
+
"step": 22656
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 1.7050656660412757,
|
| 2492 |
+
"grad_norm": 0.40194573998451233,
|
| 2493 |
+
"learning_rate": 0.002828,
|
| 2494 |
+
"loss": 2.322,
|
| 2495 |
+
"step": 22720
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 1.7098686679174484,
|
| 2499 |
+
"grad_norm": 0.43570390343666077,
|
| 2500 |
+
"learning_rate": 0.002828,
|
| 2501 |
+
"loss": 2.3241,
|
| 2502 |
+
"step": 22784
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 1.714671669793621,
|
| 2506 |
+
"grad_norm": 0.35558512806892395,
|
| 2507 |
+
"learning_rate": 0.002828,
|
| 2508 |
+
"loss": 2.3193,
|
| 2509 |
+
"step": 22848
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 1.7194746716697935,
|
| 2513 |
+
"grad_norm": 0.3700902760028839,
|
| 2514 |
+
"learning_rate": 0.002828,
|
| 2515 |
+
"loss": 2.3219,
|
| 2516 |
+
"step": 22912
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 1.7242776735459664,
|
| 2520 |
+
"grad_norm": 0.4287453591823578,
|
| 2521 |
+
"learning_rate": 0.002828,
|
| 2522 |
+
"loss": 2.3078,
|
| 2523 |
+
"step": 22976
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 1.7290806754221388,
|
| 2527 |
+
"grad_norm": 0.41843536496162415,
|
| 2528 |
+
"learning_rate": 0.002828,
|
| 2529 |
+
"loss": 2.3103,
|
| 2530 |
+
"step": 23040
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 1.7338836772983115,
|
| 2534 |
+
"grad_norm": 0.3938317596912384,
|
| 2535 |
+
"learning_rate": 0.002828,
|
| 2536 |
+
"loss": 2.3176,
|
| 2537 |
+
"step": 23104
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 1.7386866791744842,
|
| 2541 |
+
"grad_norm": 0.44625958800315857,
|
| 2542 |
+
"learning_rate": 0.002828,
|
| 2543 |
+
"loss": 2.307,
|
| 2544 |
+
"step": 23168
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 1.7434896810506566,
|
| 2548 |
+
"grad_norm": 0.4598078727722168,
|
| 2549 |
+
"learning_rate": 0.002828,
|
| 2550 |
+
"loss": 2.2958,
|
| 2551 |
+
"step": 23232
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 1.7482926829268293,
|
| 2555 |
+
"grad_norm": 0.4126788377761841,
|
| 2556 |
+
"learning_rate": 0.002828,
|
| 2557 |
+
"loss": 2.3094,
|
| 2558 |
+
"step": 23296
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 1.753095684803002,
|
| 2562 |
+
"grad_norm": 0.3801914155483246,
|
| 2563 |
+
"learning_rate": 0.002828,
|
| 2564 |
+
"loss": 2.3048,
|
| 2565 |
+
"step": 23360
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 1.7578986866791744,
|
| 2569 |
+
"grad_norm": 0.4619985818862915,
|
| 2570 |
+
"learning_rate": 0.002828,
|
| 2571 |
+
"loss": 2.3069,
|
| 2572 |
+
"step": 23424
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 1.7627016885553473,
|
| 2576 |
+
"grad_norm": 0.4068593680858612,
|
| 2577 |
+
"learning_rate": 0.002828,
|
| 2578 |
+
"loss": 2.299,
|
| 2579 |
+
"step": 23488
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 1.7675046904315197,
|
| 2583 |
+
"grad_norm": 0.36146870255470276,
|
| 2584 |
+
"learning_rate": 0.002828,
|
| 2585 |
+
"loss": 2.3042,
|
| 2586 |
+
"step": 23552
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 1.7723076923076924,
|
| 2590 |
+
"grad_norm": 0.3995908200740814,
|
| 2591 |
+
"learning_rate": 0.002828,
|
| 2592 |
+
"loss": 2.3006,
|
| 2593 |
+
"step": 23616
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 1.777110694183865,
|
| 2597 |
+
"grad_norm": 0.3970596492290497,
|
| 2598 |
+
"learning_rate": 0.002828,
|
| 2599 |
+
"loss": 2.313,
|
| 2600 |
+
"step": 23680
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 1.7819136960600375,
|
| 2604 |
+
"grad_norm": 0.4287073612213135,
|
| 2605 |
+
"learning_rate": 0.002828,
|
| 2606 |
+
"loss": 2.2974,
|
| 2607 |
+
"step": 23744
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 1.7867166979362101,
|
| 2611 |
+
"grad_norm": 0.41250482201576233,
|
| 2612 |
+
"learning_rate": 0.002828,
|
| 2613 |
+
"loss": 2.2937,
|
| 2614 |
+
"step": 23808
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 1.7915196998123828,
|
| 2618 |
+
"grad_norm": 0.411668062210083,
|
| 2619 |
+
"learning_rate": 0.002828,
|
| 2620 |
+
"loss": 2.2994,
|
| 2621 |
+
"step": 23872
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 1.7963227016885552,
|
| 2625 |
+
"grad_norm": 0.4834740459918976,
|
| 2626 |
+
"learning_rate": 0.002828,
|
| 2627 |
+
"loss": 2.2895,
|
| 2628 |
+
"step": 23936
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 1.8011257035647281,
|
| 2632 |
+
"grad_norm": 0.3624022603034973,
|
| 2633 |
+
"learning_rate": 0.002828,
|
| 2634 |
+
"loss": 2.2888,
|
| 2635 |
+
"step": 24000
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 1.8059287054409006,
|
| 2639 |
+
"grad_norm": 0.36700454354286194,
|
| 2640 |
+
"learning_rate": 0.002828,
|
| 2641 |
+
"loss": 2.2917,
|
| 2642 |
+
"step": 24064
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 1.8107317073170732,
|
| 2646 |
+
"grad_norm": 0.3666454255580902,
|
| 2647 |
+
"learning_rate": 0.002828,
|
| 2648 |
+
"loss": 2.2896,
|
| 2649 |
+
"step": 24128
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 1.8155347091932459,
|
| 2653 |
+
"grad_norm": 0.4110506474971771,
|
| 2654 |
+
"learning_rate": 0.002828,
|
| 2655 |
+
"loss": 2.2947,
|
| 2656 |
+
"step": 24192
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 1.8203377110694183,
|
| 2660 |
+
"grad_norm": 0.3604464530944824,
|
| 2661 |
+
"learning_rate": 0.002828,
|
| 2662 |
+
"loss": 2.289,
|
| 2663 |
+
"step": 24256
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 1.825140712945591,
|
| 2667 |
+
"grad_norm": 0.40807706117630005,
|
| 2668 |
+
"learning_rate": 0.002828,
|
| 2669 |
+
"loss": 2.288,
|
| 2670 |
+
"step": 24320
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 1.8299437148217637,
|
| 2674 |
+
"grad_norm": 0.3632533848285675,
|
| 2675 |
+
"learning_rate": 0.002828,
|
| 2676 |
+
"loss": 2.29,
|
| 2677 |
+
"step": 24384
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 1.834746716697936,
|
| 2681 |
+
"grad_norm": 0.38520562648773193,
|
| 2682 |
+
"learning_rate": 0.002828,
|
| 2683 |
+
"loss": 2.2805,
|
| 2684 |
+
"step": 24448
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 1.839549718574109,
|
| 2688 |
+
"grad_norm": 0.4228810966014862,
|
| 2689 |
+
"learning_rate": 0.002828,
|
| 2690 |
+
"loss": 2.2842,
|
| 2691 |
+
"step": 24512
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 1.8443527204502814,
|
| 2695 |
+
"grad_norm": 0.4542325735092163,
|
| 2696 |
+
"learning_rate": 0.002828,
|
| 2697 |
+
"loss": 2.2781,
|
| 2698 |
+
"step": 24576
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 1.849155722326454,
|
| 2702 |
+
"grad_norm": 0.37316882610321045,
|
| 2703 |
+
"learning_rate": 0.002828,
|
| 2704 |
+
"loss": 2.2829,
|
| 2705 |
+
"step": 24640
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 1.8539587242026268,
|
| 2709 |
+
"grad_norm": 0.5505624413490295,
|
| 2710 |
+
"learning_rate": 0.002828,
|
| 2711 |
+
"loss": 2.2942,
|
| 2712 |
+
"step": 24704
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 1.8587617260787992,
|
| 2716 |
+
"grad_norm": 0.4269484281539917,
|
| 2717 |
+
"learning_rate": 0.002828,
|
| 2718 |
+
"loss": 2.2793,
|
| 2719 |
+
"step": 24768
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 1.8635647279549719,
|
| 2723 |
+
"grad_norm": 0.407760888338089,
|
| 2724 |
+
"learning_rate": 0.002828,
|
| 2725 |
+
"loss": 2.2803,
|
| 2726 |
+
"step": 24832
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 1.8683677298311445,
|
| 2730 |
+
"grad_norm": 0.4192192554473877,
|
| 2731 |
+
"learning_rate": 0.002828,
|
| 2732 |
+
"loss": 2.2818,
|
| 2733 |
+
"step": 24896
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 1.873170731707317,
|
| 2737 |
+
"grad_norm": 0.3924838602542877,
|
| 2738 |
+
"learning_rate": 0.002828,
|
| 2739 |
+
"loss": 2.2757,
|
| 2740 |
+
"step": 24960
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 1.8779737335834898,
|
| 2744 |
+
"grad_norm": 0.3799656629562378,
|
| 2745 |
+
"learning_rate": 0.002828,
|
| 2746 |
+
"loss": 2.2695,
|
| 2747 |
+
"step": 25024
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 1.8827767354596623,
|
| 2751 |
+
"grad_norm": 0.40570494532585144,
|
| 2752 |
+
"learning_rate": 0.002828,
|
| 2753 |
+
"loss": 2.2801,
|
| 2754 |
+
"step": 25088
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 1.887579737335835,
|
| 2758 |
+
"grad_norm": 0.3898228704929352,
|
| 2759 |
+
"learning_rate": 0.002828,
|
| 2760 |
+
"loss": 2.2709,
|
| 2761 |
+
"step": 25152
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 1.8923827392120076,
|
| 2765 |
+
"grad_norm": 0.393216073513031,
|
| 2766 |
+
"learning_rate": 0.002828,
|
| 2767 |
+
"loss": 2.282,
|
| 2768 |
+
"step": 25216
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 1.89718574108818,
|
| 2772 |
+
"grad_norm": 0.4247749149799347,
|
| 2773 |
+
"learning_rate": 0.002828,
|
| 2774 |
+
"loss": 2.2776,
|
| 2775 |
+
"step": 25280
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 1.9019887429643527,
|
| 2779 |
+
"grad_norm": 0.4670035243034363,
|
| 2780 |
+
"learning_rate": 0.002828,
|
| 2781 |
+
"loss": 2.2754,
|
| 2782 |
+
"step": 25344
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 1.9067917448405254,
|
| 2786 |
+
"grad_norm": 0.40336644649505615,
|
| 2787 |
+
"learning_rate": 0.002828,
|
| 2788 |
+
"loss": 2.2768,
|
| 2789 |
+
"step": 25408
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 1.9115947467166978,
|
| 2793 |
+
"grad_norm": 0.48462921380996704,
|
| 2794 |
+
"learning_rate": 0.002828,
|
| 2795 |
+
"loss": 2.2634,
|
| 2796 |
+
"step": 25472
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 1.9163977485928707,
|
| 2800 |
+
"grad_norm": 0.44047805666923523,
|
| 2801 |
+
"learning_rate": 0.002828,
|
| 2802 |
+
"loss": 2.2674,
|
| 2803 |
+
"step": 25536
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 1.9212007504690432,
|
| 2807 |
+
"grad_norm": 0.4221409261226654,
|
| 2808 |
+
"learning_rate": 0.002828,
|
| 2809 |
+
"loss": 2.2724,
|
| 2810 |
+
"step": 25600
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 1.9260037523452158,
|
| 2814 |
+
"grad_norm": 0.4272362291812897,
|
| 2815 |
+
"learning_rate": 0.002828,
|
| 2816 |
+
"loss": 2.2683,
|
| 2817 |
+
"step": 25664
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 1.9308067542213885,
|
| 2821 |
+
"grad_norm": 0.4309645891189575,
|
| 2822 |
+
"learning_rate": 0.002828,
|
| 2823 |
+
"loss": 2.2612,
|
| 2824 |
+
"step": 25728
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 1.935609756097561,
|
| 2828 |
+
"grad_norm": 0.4220867156982422,
|
| 2829 |
+
"learning_rate": 0.002828,
|
| 2830 |
+
"loss": 2.2665,
|
| 2831 |
+
"step": 25792
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 1.9404127579737336,
|
| 2835 |
+
"grad_norm": 0.3765920102596283,
|
| 2836 |
+
"learning_rate": 0.002828,
|
| 2837 |
+
"loss": 2.2652,
|
| 2838 |
+
"step": 25856
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 1.9452157598499062,
|
| 2842 |
+
"grad_norm": 0.44643986225128174,
|
| 2843 |
+
"learning_rate": 0.002828,
|
| 2844 |
+
"loss": 2.2627,
|
| 2845 |
+
"step": 25920
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 1.9500187617260787,
|
| 2849 |
+
"grad_norm": 0.4022061824798584,
|
| 2850 |
+
"learning_rate": 0.002828,
|
| 2851 |
+
"loss": 2.2665,
|
| 2852 |
+
"step": 25984
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 1.9548217636022516,
|
| 2856 |
+
"grad_norm": 0.3935778737068176,
|
| 2857 |
+
"learning_rate": 0.002828,
|
| 2858 |
+
"loss": 2.2585,
|
| 2859 |
+
"step": 26048
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 1.959624765478424,
|
| 2863 |
+
"grad_norm": 0.3877500295639038,
|
| 2864 |
+
"learning_rate": 0.002828,
|
| 2865 |
+
"loss": 2.2629,
|
| 2866 |
+
"step": 26112
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 1.9644277673545967,
|
| 2870 |
+
"grad_norm": 0.3891729712486267,
|
| 2871 |
+
"learning_rate": 0.002828,
|
| 2872 |
+
"loss": 2.2594,
|
| 2873 |
+
"step": 26176
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 1.9692307692307693,
|
| 2877 |
+
"grad_norm": 0.3616099953651428,
|
| 2878 |
+
"learning_rate": 0.002828,
|
| 2879 |
+
"loss": 2.2601,
|
| 2880 |
+
"step": 26240
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 1.9740337711069418,
|
| 2884 |
+
"grad_norm": 0.3855280578136444,
|
| 2885 |
+
"learning_rate": 0.002828,
|
| 2886 |
+
"loss": 2.2677,
|
| 2887 |
+
"step": 26304
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 1.9788367729831144,
|
| 2891 |
+
"grad_norm": 0.44039493799209595,
|
| 2892 |
+
"learning_rate": 0.002828,
|
| 2893 |
+
"loss": 2.2641,
|
| 2894 |
+
"step": 26368
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 1.983639774859287,
|
| 2898 |
+
"grad_norm": 0.37217262387275696,
|
| 2899 |
+
"learning_rate": 0.002828,
|
| 2900 |
+
"loss": 2.2603,
|
| 2901 |
+
"step": 26432
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 1.9884427767354595,
|
| 2905 |
+
"grad_norm": 0.3942553997039795,
|
| 2906 |
+
"learning_rate": 0.002828,
|
| 2907 |
+
"loss": 2.2508,
|
| 2908 |
+
"step": 26496
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 1.9932457786116324,
|
| 2912 |
+
"grad_norm": 0.3975297808647156,
|
| 2913 |
+
"learning_rate": 0.002828,
|
| 2914 |
+
"loss": 2.2466,
|
| 2915 |
+
"step": 26560
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 1.9980487804878049,
|
| 2919 |
+
"grad_norm": 0.39197394251823425,
|
| 2920 |
+
"learning_rate": 0.002828,
|
| 2921 |
+
"loss": 2.2515,
|
| 2922 |
+
"step": 26624
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 2.0028517823639773,
|
| 2926 |
+
"grad_norm": 0.38722801208496094,
|
| 2927 |
+
"learning_rate": 0.002828,
|
| 2928 |
+
"loss": 2.2354,
|
| 2929 |
+
"step": 26688
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 2.00765478424015,
|
| 2933 |
+
"grad_norm": 0.38619640469551086,
|
| 2934 |
+
"learning_rate": 0.002828,
|
| 2935 |
+
"loss": 2.2152,
|
| 2936 |
+
"step": 26752
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 2.0124577861163226,
|
| 2940 |
+
"grad_norm": 0.49529945850372314,
|
| 2941 |
+
"learning_rate": 0.002828,
|
| 2942 |
+
"loss": 2.2167,
|
| 2943 |
+
"step": 26816
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 2.0172607879924955,
|
| 2947 |
+
"grad_norm": 0.4199656844139099,
|
| 2948 |
+
"learning_rate": 0.002828,
|
| 2949 |
+
"loss": 2.2092,
|
| 2950 |
+
"step": 26880
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 2.022063789868668,
|
| 2954 |
+
"grad_norm": 0.45820868015289307,
|
| 2955 |
+
"learning_rate": 0.002828,
|
| 2956 |
+
"loss": 2.2249,
|
| 2957 |
+
"step": 26944
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 2.0268667917448404,
|
| 2961 |
+
"grad_norm": 0.4006725251674652,
|
| 2962 |
+
"learning_rate": 0.002828,
|
| 2963 |
+
"loss": 2.2165,
|
| 2964 |
+
"step": 27008
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 2.0316697936210133,
|
| 2968 |
+
"grad_norm": 0.4596467614173889,
|
| 2969 |
+
"learning_rate": 0.002828,
|
| 2970 |
+
"loss": 2.2154,
|
| 2971 |
+
"step": 27072
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 2.0364727954971857,
|
| 2975 |
+
"grad_norm": 0.38660213351249695,
|
| 2976 |
+
"learning_rate": 0.002828,
|
| 2977 |
+
"loss": 2.2062,
|
| 2978 |
+
"step": 27136
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 2.041275797373358,
|
| 2982 |
+
"grad_norm": 0.44082361459732056,
|
| 2983 |
+
"learning_rate": 0.002828,
|
| 2984 |
+
"loss": 2.2124,
|
| 2985 |
+
"step": 27200
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 2.046078799249531,
|
| 2989 |
+
"grad_norm": 0.3886605203151703,
|
| 2990 |
+
"learning_rate": 0.002828,
|
| 2991 |
+
"loss": 2.2182,
|
| 2992 |
+
"step": 27264
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 2.0508818011257035,
|
| 2996 |
+
"grad_norm": 0.41386017203330994,
|
| 2997 |
+
"learning_rate": 0.002828,
|
| 2998 |
+
"loss": 2.2168,
|
| 2999 |
+
"step": 27328
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 2.055684803001876,
|
| 3003 |
+
"grad_norm": 0.411478191614151,
|
| 3004 |
+
"learning_rate": 0.002828,
|
| 3005 |
+
"loss": 2.2092,
|
| 3006 |
+
"step": 27392
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 2.060487804878049,
|
| 3010 |
+
"grad_norm": 0.47288912534713745,
|
| 3011 |
+
"learning_rate": 0.002828,
|
| 3012 |
+
"loss": 2.21,
|
| 3013 |
+
"step": 27456
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 2.0652908067542213,
|
| 3017 |
+
"grad_norm": 0.36384883522987366,
|
| 3018 |
+
"learning_rate": 0.002828,
|
| 3019 |
+
"loss": 2.2095,
|
| 3020 |
+
"step": 27520
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 2.070093808630394,
|
| 3024 |
+
"grad_norm": 0.40636852383613586,
|
| 3025 |
+
"learning_rate": 0.002828,
|
| 3026 |
+
"loss": 2.2092,
|
| 3027 |
+
"step": 27584
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 2.0748968105065666,
|
| 3031 |
+
"grad_norm": 0.4425170421600342,
|
| 3032 |
+
"learning_rate": 0.002828,
|
| 3033 |
+
"loss": 2.212,
|
| 3034 |
+
"step": 27648
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 2.079699812382739,
|
| 3038 |
+
"grad_norm": 0.48468896746635437,
|
| 3039 |
+
"learning_rate": 0.002828,
|
| 3040 |
+
"loss": 2.2078,
|
| 3041 |
+
"step": 27712
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 2.084502814258912,
|
| 3045 |
+
"grad_norm": 0.40420570969581604,
|
| 3046 |
+
"learning_rate": 0.002828,
|
| 3047 |
+
"loss": 2.2158,
|
| 3048 |
+
"step": 27776
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 2.0893058161350844,
|
| 3052 |
+
"grad_norm": 0.44314709305763245,
|
| 3053 |
+
"learning_rate": 0.002828,
|
| 3054 |
+
"loss": 2.2121,
|
| 3055 |
+
"step": 27840
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 2.0941088180112573,
|
| 3059 |
+
"grad_norm": 0.5187743306159973,
|
| 3060 |
+
"learning_rate": 0.002828,
|
| 3061 |
+
"loss": 2.2138,
|
| 3062 |
+
"step": 27904
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 2.0989118198874297,
|
| 3066 |
+
"grad_norm": 0.4796048104763031,
|
| 3067 |
+
"learning_rate": 0.002828,
|
| 3068 |
+
"loss": 2.2027,
|
| 3069 |
+
"step": 27968
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 2.103714821763602,
|
| 3073 |
+
"grad_norm": 0.43605130910873413,
|
| 3074 |
+
"learning_rate": 0.002828,
|
| 3075 |
+
"loss": 2.2029,
|
| 3076 |
+
"step": 28032
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 2.108517823639775,
|
| 3080 |
+
"grad_norm": 0.4523628056049347,
|
| 3081 |
+
"learning_rate": 0.002828,
|
| 3082 |
+
"loss": 2.2038,
|
| 3083 |
+
"step": 28096
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 2.1133208255159475,
|
| 3087 |
+
"grad_norm": 0.4183247983455658,
|
| 3088 |
+
"learning_rate": 0.002828,
|
| 3089 |
+
"loss": 2.2026,
|
| 3090 |
+
"step": 28160
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 2.11812382739212,
|
| 3094 |
+
"grad_norm": 0.5113268494606018,
|
| 3095 |
+
"learning_rate": 0.002828,
|
| 3096 |
+
"loss": 2.1998,
|
| 3097 |
+
"step": 28224
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 2.122926829268293,
|
| 3101 |
+
"grad_norm": 0.40837016701698303,
|
| 3102 |
+
"learning_rate": 0.002828,
|
| 3103 |
+
"loss": 2.2054,
|
| 3104 |
+
"step": 28288
|
| 3105 |
+
},
|
| 3106 |
+
{
|
| 3107 |
+
"epoch": 2.1277298311444652,
|
| 3108 |
+
"grad_norm": 0.40093889832496643,
|
| 3109 |
+
"learning_rate": 0.002828,
|
| 3110 |
+
"loss": 2.208,
|
| 3111 |
+
"step": 28352
|
| 3112 |
+
},
|
| 3113 |
+
{
|
| 3114 |
+
"epoch": 2.1325328330206377,
|
| 3115 |
+
"grad_norm": 0.3988894820213318,
|
| 3116 |
+
"learning_rate": 0.002828,
|
| 3117 |
+
"loss": 2.2028,
|
| 3118 |
+
"step": 28416
|
| 3119 |
+
},
|
| 3120 |
+
{
|
| 3121 |
+
"epoch": 2.1373358348968106,
|
| 3122 |
+
"grad_norm": 0.42024731636047363,
|
| 3123 |
+
"learning_rate": 0.002828,
|
| 3124 |
+
"loss": 2.1952,
|
| 3125 |
+
"step": 28480
|
| 3126 |
+
},
|
| 3127 |
+
{
|
| 3128 |
+
"epoch": 2.142138836772983,
|
| 3129 |
+
"grad_norm": 0.38691264390945435,
|
| 3130 |
+
"learning_rate": 0.002828,
|
| 3131 |
+
"loss": 2.2035,
|
| 3132 |
+
"step": 28544
|
| 3133 |
+
},
|
| 3134 |
+
{
|
| 3135 |
+
"epoch": 2.146941838649156,
|
| 3136 |
+
"grad_norm": 0.41956332325935364,
|
| 3137 |
+
"learning_rate": 0.002828,
|
| 3138 |
+
"loss": 2.196,
|
| 3139 |
+
"step": 28608
|
| 3140 |
+
},
|
| 3141 |
+
{
|
| 3142 |
+
"epoch": 2.1517448405253283,
|
| 3143 |
+
"grad_norm": 0.4035188555717468,
|
| 3144 |
+
"learning_rate": 0.002828,
|
| 3145 |
+
"loss": 2.2038,
|
| 3146 |
+
"step": 28672
|
| 3147 |
+
},
|
| 3148 |
+
{
|
| 3149 |
+
"epoch": 2.1565478424015008,
|
| 3150 |
+
"grad_norm": 0.35282230377197266,
|
| 3151 |
+
"learning_rate": 0.002828,
|
| 3152 |
+
"loss": 2.1835,
|
| 3153 |
+
"step": 28736
|
| 3154 |
+
},
|
| 3155 |
+
{
|
| 3156 |
+
"epoch": 2.1613508442776737,
|
| 3157 |
+
"grad_norm": 0.43618568778038025,
|
| 3158 |
+
"learning_rate": 0.002828,
|
| 3159 |
+
"loss": 2.1946,
|
| 3160 |
+
"step": 28800
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 2.166153846153846,
|
| 3164 |
+
"grad_norm": 0.4310976564884186,
|
| 3165 |
+
"learning_rate": 0.002828,
|
| 3166 |
+
"loss": 2.1873,
|
| 3167 |
+
"step": 28864
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 2.170956848030019,
|
| 3171 |
+
"grad_norm": 0.4475420415401459,
|
| 3172 |
+
"learning_rate": 0.002828,
|
| 3173 |
+
"loss": 2.1946,
|
| 3174 |
+
"step": 28928
|
| 3175 |
+
},
|
| 3176 |
+
{
|
| 3177 |
+
"epoch": 2.1757598499061914,
|
| 3178 |
+
"grad_norm": 0.4384845197200775,
|
| 3179 |
+
"learning_rate": 0.002828,
|
| 3180 |
+
"loss": 2.1935,
|
| 3181 |
+
"step": 28992
|
| 3182 |
+
},
|
| 3183 |
+
{
|
| 3184 |
+
"epoch": 2.180562851782364,
|
| 3185 |
+
"grad_norm": 0.40141811966896057,
|
| 3186 |
+
"learning_rate": 0.002828,
|
| 3187 |
+
"loss": 2.1925,
|
| 3188 |
+
"step": 29056
|
| 3189 |
+
},
|
| 3190 |
+
{
|
| 3191 |
+
"epoch": 2.1853658536585368,
|
| 3192 |
+
"grad_norm": 0.3754780888557434,
|
| 3193 |
+
"learning_rate": 0.002828,
|
| 3194 |
+
"loss": 2.19,
|
| 3195 |
+
"step": 29120
|
| 3196 |
+
},
|
| 3197 |
+
{
|
| 3198 |
+
"epoch": 2.190168855534709,
|
| 3199 |
+
"grad_norm": 0.40471306443214417,
|
| 3200 |
+
"learning_rate": 0.002828,
|
| 3201 |
+
"loss": 2.1915,
|
| 3202 |
+
"step": 29184
|
| 3203 |
+
},
|
| 3204 |
+
{
|
| 3205 |
+
"epoch": 2.1949718574108816,
|
| 3206 |
+
"grad_norm": 1.464024543762207,
|
| 3207 |
+
"learning_rate": 0.002828,
|
| 3208 |
+
"loss": 2.1909,
|
| 3209 |
+
"step": 29248
|
| 3210 |
+
},
|
| 3211 |
+
{
|
| 3212 |
+
"epoch": 2.1997748592870545,
|
| 3213 |
+
"grad_norm": 0.3818819522857666,
|
| 3214 |
+
"learning_rate": 0.002828,
|
| 3215 |
+
"loss": 2.1915,
|
| 3216 |
+
"step": 29312
|
| 3217 |
+
},
|
| 3218 |
+
{
|
| 3219 |
+
"epoch": 2.204577861163227,
|
| 3220 |
+
"grad_norm": 0.3688436448574066,
|
| 3221 |
+
"learning_rate": 0.002828,
|
| 3222 |
+
"loss": 2.184,
|
| 3223 |
+
"step": 29376
|
| 3224 |
+
},
|
| 3225 |
+
{
|
| 3226 |
+
"epoch": 2.2093808630393994,
|
| 3227 |
+
"grad_norm": 0.4367921054363251,
|
| 3228 |
+
"learning_rate": 0.002828,
|
| 3229 |
+
"loss": 2.185,
|
| 3230 |
+
"step": 29440
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"epoch": 2.2141838649155723,
|
| 3234 |
+
"grad_norm": 0.3566763401031494,
|
| 3235 |
+
"learning_rate": 0.002828,
|
| 3236 |
+
"loss": 2.1871,
|
| 3237 |
+
"step": 29504
|
| 3238 |
+
},
|
| 3239 |
+
{
|
| 3240 |
+
"epoch": 2.2189868667917447,
|
| 3241 |
+
"grad_norm": 0.4481133222579956,
|
| 3242 |
+
"learning_rate": 0.002828,
|
| 3243 |
+
"loss": 2.1826,
|
| 3244 |
+
"step": 29568
|
| 3245 |
+
},
|
| 3246 |
+
{
|
| 3247 |
+
"epoch": 2.2237898686679176,
|
| 3248 |
+
"grad_norm": 0.44622039794921875,
|
| 3249 |
+
"learning_rate": 0.002828,
|
| 3250 |
+
"loss": 2.1885,
|
| 3251 |
+
"step": 29632
|
| 3252 |
+
},
|
| 3253 |
+
{
|
| 3254 |
+
"epoch": 2.22859287054409,
|
| 3255 |
+
"grad_norm": 0.4857657253742218,
|
| 3256 |
+
"learning_rate": 0.002828,
|
| 3257 |
+
"loss": 2.1784,
|
| 3258 |
+
"step": 29696
|
| 3259 |
+
},
|
| 3260 |
+
{
|
| 3261 |
+
"epoch": 2.2333958724202625,
|
| 3262 |
+
"grad_norm": 0.41923773288726807,
|
| 3263 |
+
"learning_rate": 0.002828,
|
| 3264 |
+
"loss": 2.1807,
|
| 3265 |
+
"step": 29760
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 2.2381988742964354,
|
| 3269 |
+
"grad_norm": 0.4176802933216095,
|
| 3270 |
+
"learning_rate": 0.002828,
|
| 3271 |
+
"loss": 2.1798,
|
| 3272 |
+
"step": 29824
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 2.243001876172608,
|
| 3276 |
+
"grad_norm": 0.4086935520172119,
|
| 3277 |
+
"learning_rate": 0.002828,
|
| 3278 |
+
"loss": 2.1739,
|
| 3279 |
+
"step": 29888
|
| 3280 |
+
},
|
| 3281 |
+
{
|
| 3282 |
+
"epoch": 2.2478048780487807,
|
| 3283 |
+
"grad_norm": 0.40138566493988037,
|
| 3284 |
+
"learning_rate": 0.002828,
|
| 3285 |
+
"loss": 2.1857,
|
| 3286 |
+
"step": 29952
|
| 3287 |
+
},
|
| 3288 |
+
{
|
| 3289 |
+
"epoch": 2.252607879924953,
|
| 3290 |
+
"grad_norm": 0.393996000289917,
|
| 3291 |
+
"learning_rate": 0.002828,
|
| 3292 |
+
"loss": 2.1818,
|
| 3293 |
+
"step": 30016
|
| 3294 |
+
},
|
| 3295 |
+
{
|
| 3296 |
+
"epoch": 2.2574108818011256,
|
| 3297 |
+
"grad_norm": 0.3962005078792572,
|
| 3298 |
+
"learning_rate": 0.002828,
|
| 3299 |
+
"loss": 2.1724,
|
| 3300 |
+
"step": 30080
|
| 3301 |
+
},
|
| 3302 |
+
{
|
| 3303 |
+
"epoch": 2.2622138836772985,
|
| 3304 |
+
"grad_norm": 0.41648438572883606,
|
| 3305 |
+
"learning_rate": 0.002828,
|
| 3306 |
+
"loss": 2.1835,
|
| 3307 |
+
"step": 30144
|
| 3308 |
+
},
|
| 3309 |
+
{
|
| 3310 |
+
"epoch": 2.267016885553471,
|
| 3311 |
+
"grad_norm": 0.3810112774372101,
|
| 3312 |
+
"learning_rate": 0.002828,
|
| 3313 |
+
"loss": 2.1736,
|
| 3314 |
+
"step": 30208
|
| 3315 |
+
},
|
| 3316 |
+
{
|
| 3317 |
+
"epoch": 2.2718198874296434,
|
| 3318 |
+
"grad_norm": 0.4520975649356842,
|
| 3319 |
+
"learning_rate": 0.002828,
|
| 3320 |
+
"loss": 2.1793,
|
| 3321 |
+
"step": 30272
|
| 3322 |
+
},
|
| 3323 |
+
{
|
| 3324 |
+
"epoch": 2.2766228893058162,
|
| 3325 |
+
"grad_norm": 0.4406943917274475,
|
| 3326 |
+
"learning_rate": 0.002828,
|
| 3327 |
+
"loss": 2.1732,
|
| 3328 |
+
"step": 30336
|
| 3329 |
+
},
|
| 3330 |
+
{
|
| 3331 |
+
"epoch": 2.2814258911819887,
|
| 3332 |
+
"grad_norm": 0.4186633825302124,
|
| 3333 |
+
"learning_rate": 0.002828,
|
| 3334 |
+
"loss": 2.1774,
|
| 3335 |
+
"step": 30400
|
| 3336 |
+
}
|
| 3337 |
+
],
|
| 3338 |
+
"logging_steps": 64,
|
| 3339 |
+
"max_steps": 333125,
|
| 3340 |
+
"num_input_tokens_seen": 0,
|
| 3341 |
+
"num_train_epochs": 25,
|
| 3342 |
+
"save_steps": 320,
|
| 3343 |
+
"stateful_callbacks": {
|
| 3344 |
+
"TrainerControl": {
|
| 3345 |
+
"args": {
|
| 3346 |
+
"should_epoch_stop": false,
|
| 3347 |
+
"should_evaluate": false,
|
| 3348 |
+
"should_log": false,
|
| 3349 |
+
"should_save": true,
|
| 3350 |
+
"should_training_stop": false
|
| 3351 |
+
},
|
| 3352 |
+
"attributes": {}
|
| 3353 |
+
}
|
| 3354 |
+
},
|
| 3355 |
+
"total_flos": 5.993193875177472e+17,
|
| 3356 |
+
"train_batch_size": 200,
|
| 3357 |
+
"trial_name": null,
|
| 3358 |
+
"trial_params": null
|
| 3359 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d46a719a41da21455580c94cce6fb974c62aaeeb7939aeac255d2feda5f9da65
|
| 3 |
+
size 6289
|