Commit ·
ef2a799
1
Parent(s): 99ceb98
Upload folder using huggingface_hub
Browse files- README.md +21 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +32 -0
- train_args.json +123 -0
- training_args.bin +3 -0
- training_logs.json +1595 -0
README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: False
|
| 10 |
+
- load_in_4bit: True
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: nf4
|
| 16 |
+
- bnb_4bit_use_double_quant: True
|
| 17 |
+
- bnb_4bit_compute_dtype: float16
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.5.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "models/llama-13b",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.0,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "SEQ_CLS"
|
| 21 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe01ef7e0abccbec72d8b2b67e547e2bb019a5564d683fbc35a0bc62e6f8e2a0
|
| 3 |
+
size 209811921
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"model_max_length": 2048,
|
| 20 |
+
"pad_token": null,
|
| 21 |
+
"sp_model_kwargs": {},
|
| 22 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"__type": "AddedToken",
|
| 25 |
+
"content": "<unk>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": true,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
"use_default_system_prompt": true
|
| 32 |
+
}
|
train_args.json
ADDED
|
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"initial_model_dir": "models/llama-13b",
|
| 3 |
+
"distribution_id": "code_is_correct",
|
| 4 |
+
"date_trained": "12/10/2023 08:02:53",
|
| 5 |
+
"output_dir": "models/classify_lora/llama-13b-code_is_correct",
|
| 6 |
+
"overwrite_output_dir": false,
|
| 7 |
+
"do_train": false,
|
| 8 |
+
"do_eval": true,
|
| 9 |
+
"do_predict": false,
|
| 10 |
+
"evaluation_strategy": "steps",
|
| 11 |
+
"prediction_loss_only": false,
|
| 12 |
+
"per_device_train_batch_size": 16,
|
| 13 |
+
"per_device_eval_batch_size": 16,
|
| 14 |
+
"per_gpu_train_batch_size": null,
|
| 15 |
+
"per_gpu_eval_batch_size": null,
|
| 16 |
+
"gradient_accumulation_steps": 1,
|
| 17 |
+
"eval_accumulation_steps": null,
|
| 18 |
+
"eval_delay": 0,
|
| 19 |
+
"learning_rate": 0.0002,
|
| 20 |
+
"weight_decay": 0.0,
|
| 21 |
+
"adam_beta1": 0.9,
|
| 22 |
+
"adam_beta2": 0.999,
|
| 23 |
+
"adam_epsilon": 1e-08,
|
| 24 |
+
"max_grad_norm": 0.3,
|
| 25 |
+
"num_train_epochs": 8,
|
| 26 |
+
"max_steps": 150,
|
| 27 |
+
"lr_scheduler_type": "constant",
|
| 28 |
+
"warmup_ratio": 0.03,
|
| 29 |
+
"warmup_steps": 0,
|
| 30 |
+
"log_level": "passive",
|
| 31 |
+
"log_level_replica": "warning",
|
| 32 |
+
"log_on_each_node": true,
|
| 33 |
+
"logging_dir": "models/classify_lora/llama-13b-code_is_correct/runs/Oct12_05-58-34_compute-permanent-node-990",
|
| 34 |
+
"logging_strategy": "steps",
|
| 35 |
+
"logging_first_step": false,
|
| 36 |
+
"logging_steps": 1,
|
| 37 |
+
"logging_nan_inf_filter": true,
|
| 38 |
+
"save_strategy": "steps",
|
| 39 |
+
"save_steps": 25,
|
| 40 |
+
"save_total_limit": 0,
|
| 41 |
+
"save_safetensors": false,
|
| 42 |
+
"save_on_each_node": false,
|
| 43 |
+
"no_cuda": false,
|
| 44 |
+
"use_cpu": false,
|
| 45 |
+
"use_mps_device": false,
|
| 46 |
+
"seed": 42,
|
| 47 |
+
"data_seed": null,
|
| 48 |
+
"jit_mode_eval": false,
|
| 49 |
+
"use_ipex": false,
|
| 50 |
+
"bf16": false,
|
| 51 |
+
"fp16": false,
|
| 52 |
+
"fp16_opt_level": "O1",
|
| 53 |
+
"half_precision_backend": "auto",
|
| 54 |
+
"bf16_full_eval": false,
|
| 55 |
+
"fp16_full_eval": false,
|
| 56 |
+
"tf32": null,
|
| 57 |
+
"local_rank": 1,
|
| 58 |
+
"ddp_backend": null,
|
| 59 |
+
"tpu_num_cores": null,
|
| 60 |
+
"tpu_metrics_debug": false,
|
| 61 |
+
"debug": [],
|
| 62 |
+
"dataloader_drop_last": false,
|
| 63 |
+
"eval_steps": 25,
|
| 64 |
+
"dataloader_num_workers": 0,
|
| 65 |
+
"past_index": -1,
|
| 66 |
+
"run_name": "train|models-classify_lora-llama-13b-code_is_correct",
|
| 67 |
+
"disable_tqdm": false,
|
| 68 |
+
"remove_unused_columns": false,
|
| 69 |
+
"label_names": null,
|
| 70 |
+
"load_best_model_at_end": false,
|
| 71 |
+
"metric_for_best_model": "eval_code_is_correct_score",
|
| 72 |
+
"greater_is_better": true,
|
| 73 |
+
"ignore_data_skip": false,
|
| 74 |
+
"sharded_ddp": [],
|
| 75 |
+
"fsdp": [],
|
| 76 |
+
"fsdp_min_num_params": 0,
|
| 77 |
+
"fsdp_config": {
|
| 78 |
+
"min_num_params": 0,
|
| 79 |
+
"xla": false,
|
| 80 |
+
"xla_fsdp_grad_ckpt": false
|
| 81 |
+
},
|
| 82 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 83 |
+
"deepspeed": "configs/ds_zero_1.json",
|
| 84 |
+
"label_smoothing_factor": 0.0,
|
| 85 |
+
"optim": "paged_adamw_32bit",
|
| 86 |
+
"optim_args": null,
|
| 87 |
+
"adafactor": false,
|
| 88 |
+
"group_by_length": false,
|
| 89 |
+
"length_column_name": "length",
|
| 90 |
+
"report_to": [
|
| 91 |
+
"wandb"
|
| 92 |
+
],
|
| 93 |
+
"ddp_find_unused_parameters": false,
|
| 94 |
+
"ddp_bucket_cap_mb": null,
|
| 95 |
+
"ddp_broadcast_buffers": null,
|
| 96 |
+
"dataloader_pin_memory": true,
|
| 97 |
+
"skip_memory_metrics": true,
|
| 98 |
+
"use_legacy_prediction_loop": false,
|
| 99 |
+
"push_to_hub": false,
|
| 100 |
+
"resume_from_checkpoint": null,
|
| 101 |
+
"hub_model_id": null,
|
| 102 |
+
"hub_strategy": "every_save",
|
| 103 |
+
"hub_token": null,
|
| 104 |
+
"hub_private_repo": false,
|
| 105 |
+
"hub_always_push": false,
|
| 106 |
+
"gradient_checkpointing": false,
|
| 107 |
+
"include_inputs_for_metrics": false,
|
| 108 |
+
"fp16_backend": "auto",
|
| 109 |
+
"push_to_hub_model_id": null,
|
| 110 |
+
"push_to_hub_organization": null,
|
| 111 |
+
"push_to_hub_token": null,
|
| 112 |
+
"_n_gpu": 1,
|
| 113 |
+
"mp_parameters": "",
|
| 114 |
+
"auto_find_batch_size": false,
|
| 115 |
+
"full_determinism": false,
|
| 116 |
+
"torchdynamo": null,
|
| 117 |
+
"ray_scope": "last",
|
| 118 |
+
"ddp_timeout": 1800,
|
| 119 |
+
"torch_compile": false,
|
| 120 |
+
"torch_compile_backend": null,
|
| 121 |
+
"torch_compile_mode": null,
|
| 122 |
+
"dispatch_batches": null
|
| 123 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:203aa755522a0215104716c6384a57e594a3f5f9b8de3aeecf0dac3162fa1bde
|
| 3 |
+
size 5115
|
training_logs.json
ADDED
|
@@ -0,0 +1,1595 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"loss": 0.7004,
|
| 4 |
+
"learning_rate": 0.0002,
|
| 5 |
+
"epoch": 0.05,
|
| 6 |
+
"step": 1
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"loss": 0.7322,
|
| 10 |
+
"learning_rate": 0.0002,
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"step": 2
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"loss": 0.6932,
|
| 16 |
+
"learning_rate": 0.0002,
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"step": 3
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"loss": 0.7077,
|
| 22 |
+
"learning_rate": 0.0002,
|
| 23 |
+
"epoch": 0.21,
|
| 24 |
+
"step": 4
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"loss": 0.683,
|
| 28 |
+
"learning_rate": 0.0002,
|
| 29 |
+
"epoch": 0.26,
|
| 30 |
+
"step": 5
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"loss": 0.7367,
|
| 34 |
+
"learning_rate": 0.0002,
|
| 35 |
+
"epoch": 0.32,
|
| 36 |
+
"step": 6
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"loss": 0.6696,
|
| 40 |
+
"learning_rate": 0.0002,
|
| 41 |
+
"epoch": 0.37,
|
| 42 |
+
"step": 7
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"loss": 0.6816,
|
| 46 |
+
"learning_rate": 0.0002,
|
| 47 |
+
"epoch": 0.42,
|
| 48 |
+
"step": 8
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"loss": 0.7249,
|
| 52 |
+
"learning_rate": 0.0002,
|
| 53 |
+
"epoch": 0.47,
|
| 54 |
+
"step": 9
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"loss": 0.7143,
|
| 58 |
+
"learning_rate": 0.0002,
|
| 59 |
+
"epoch": 0.53,
|
| 60 |
+
"step": 10
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"loss": 0.6898,
|
| 64 |
+
"learning_rate": 0.0002,
|
| 65 |
+
"epoch": 0.58,
|
| 66 |
+
"step": 11
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"loss": 0.6921,
|
| 70 |
+
"learning_rate": 0.0002,
|
| 71 |
+
"epoch": 0.63,
|
| 72 |
+
"step": 12
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"loss": 0.6883,
|
| 76 |
+
"learning_rate": 0.0002,
|
| 77 |
+
"epoch": 0.68,
|
| 78 |
+
"step": 13
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"loss": 0.6973,
|
| 82 |
+
"learning_rate": 0.0002,
|
| 83 |
+
"epoch": 0.74,
|
| 84 |
+
"step": 14
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"loss": 0.7143,
|
| 88 |
+
"learning_rate": 0.0002,
|
| 89 |
+
"epoch": 0.79,
|
| 90 |
+
"step": 15
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"loss": 0.6668,
|
| 94 |
+
"learning_rate": 0.0002,
|
| 95 |
+
"epoch": 0.84,
|
| 96 |
+
"step": 16
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"loss": 0.7046,
|
| 100 |
+
"learning_rate": 0.0002,
|
| 101 |
+
"epoch": 0.89,
|
| 102 |
+
"step": 17
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"loss": 0.6849,
|
| 106 |
+
"learning_rate": 0.0002,
|
| 107 |
+
"epoch": 0.95,
|
| 108 |
+
"step": 18
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"loss": 0.6756,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"epoch": 1.0,
|
| 114 |
+
"step": 19
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"loss": 0.6962,
|
| 118 |
+
"learning_rate": 0.0002,
|
| 119 |
+
"epoch": 1.05,
|
| 120 |
+
"step": 20
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"loss": 0.648,
|
| 124 |
+
"learning_rate": 0.0002,
|
| 125 |
+
"epoch": 1.11,
|
| 126 |
+
"step": 21
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"loss": 0.7082,
|
| 130 |
+
"learning_rate": 0.0002,
|
| 131 |
+
"epoch": 1.16,
|
| 132 |
+
"step": 22
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"loss": 0.6706,
|
| 136 |
+
"learning_rate": 0.0002,
|
| 137 |
+
"epoch": 1.21,
|
| 138 |
+
"step": 23
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"loss": 0.7363,
|
| 142 |
+
"learning_rate": 0.0002,
|
| 143 |
+
"epoch": 1.26,
|
| 144 |
+
"step": 24
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"loss": 0.6666,
|
| 148 |
+
"learning_rate": 0.0002,
|
| 149 |
+
"epoch": 1.32,
|
| 150 |
+
"step": 25
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"eval_code_is_correct_loss": 0.6788089275360107,
|
| 154 |
+
"eval_code_is_correct_score": -0.2422185093164444,
|
| 155 |
+
"eval_code_is_correct_brier_score": 0.2422185093164444,
|
| 156 |
+
"eval_code_is_correct_average_probability": 0.5103297829627991,
|
| 157 |
+
"eval_code_is_correct_accuracy": 0.56,
|
| 158 |
+
"eval_code_is_correct_probabilities": [
|
| 159 |
+
0.5360161066055298,
|
| 160 |
+
0.5297089219093323,
|
| 161 |
+
0.5712761282920837,
|
| 162 |
+
0.42497631907463074,
|
| 163 |
+
0.4960133731365204,
|
| 164 |
+
0.5085265636444092,
|
| 165 |
+
0.5326896905899048,
|
| 166 |
+
0.49355220794677734,
|
| 167 |
+
0.46554645895957947,
|
| 168 |
+
0.42035338282585144,
|
| 169 |
+
0.4887016713619232,
|
| 170 |
+
0.43004417419433594,
|
| 171 |
+
0.47448185086250305,
|
| 172 |
+
0.5101436972618103,
|
| 173 |
+
0.5531357526779175,
|
| 174 |
+
0.5649287700653076,
|
| 175 |
+
0.5931124091148376,
|
| 176 |
+
0.45721137523651123,
|
| 177 |
+
0.5910964012145996,
|
| 178 |
+
0.5548848509788513,
|
| 179 |
+
0.5117404460906982,
|
| 180 |
+
0.5237535834312439,
|
| 181 |
+
0.5005296468734741,
|
| 182 |
+
0.4387059807777405,
|
| 183 |
+
0.4531331956386566,
|
| 184 |
+
0.4623565077781677,
|
| 185 |
+
0.5529483556747437,
|
| 186 |
+
0.5602871775627136,
|
| 187 |
+
0.5290127992630005,
|
| 188 |
+
0.48502641916275024,
|
| 189 |
+
0.5573620200157166,
|
| 190 |
+
0.5443336963653564,
|
| 191 |
+
0.43417370319366455,
|
| 192 |
+
0.571002721786499,
|
| 193 |
+
0.5364949107170105,
|
| 194 |
+
0.4765365421772003,
|
| 195 |
+
0.5763438940048218,
|
| 196 |
+
0.5167781114578247,
|
| 197 |
+
0.4962172210216522,
|
| 198 |
+
0.45051077008247375,
|
| 199 |
+
0.5816547274589539,
|
| 200 |
+
0.42688706517219543,
|
| 201 |
+
0.5689108371734619,
|
| 202 |
+
0.4981440007686615,
|
| 203 |
+
0.5417700409889221,
|
| 204 |
+
0.5569514036178589,
|
| 205 |
+
0.47263190150260925,
|
| 206 |
+
0.4741884469985962,
|
| 207 |
+
0.4526112377643585,
|
| 208 |
+
0.48570743203163147,
|
| 209 |
+
0.46209368109703064,
|
| 210 |
+
0.5971618294715881,
|
| 211 |
+
0.4813869595527649,
|
| 212 |
+
0.4937862157821655,
|
| 213 |
+
0.5675031542778015,
|
| 214 |
+
0.5264382362365723,
|
| 215 |
+
0.47280600666999817,
|
| 216 |
+
0.5295760035514832,
|
| 217 |
+
0.4977070987224579,
|
| 218 |
+
0.5580363869667053,
|
| 219 |
+
0.5485188364982605,
|
| 220 |
+
0.49979132413864136,
|
| 221 |
+
0.5156800150871277,
|
| 222 |
+
0.5864205956459045,
|
| 223 |
+
0.5867674350738525,
|
| 224 |
+
0.5723587274551392,
|
| 225 |
+
0.5590366125106812,
|
| 226 |
+
0.49105167388916016,
|
| 227 |
+
0.5177514553070068,
|
| 228 |
+
0.44017159938812256,
|
| 229 |
+
0.6072307229042053,
|
| 230 |
+
0.5222448110580444,
|
| 231 |
+
0.5204848051071167,
|
| 232 |
+
0.5057241916656494,
|
| 233 |
+
0.4764748811721802,
|
| 234 |
+
0.5142781734466553,
|
| 235 |
+
0.5178312659263611,
|
| 236 |
+
0.4987412095069885,
|
| 237 |
+
0.5352400541305542,
|
| 238 |
+
0.4117741882801056,
|
| 239 |
+
0.5038720965385437,
|
| 240 |
+
0.5204145312309265,
|
| 241 |
+
0.4230634272098541,
|
| 242 |
+
0.45601940155029297,
|
| 243 |
+
0.5815764665603638,
|
| 244 |
+
0.5216283202171326,
|
| 245 |
+
0.5572896599769592,
|
| 246 |
+
0.4941575825214386,
|
| 247 |
+
0.4914657771587372,
|
| 248 |
+
0.545746386051178,
|
| 249 |
+
0.5276685953140259,
|
| 250 |
+
0.4675300419330597,
|
| 251 |
+
0.47495853900909424,
|
| 252 |
+
0.4216349720954895,
|
| 253 |
+
0.6105045676231384,
|
| 254 |
+
0.4074248671531677,
|
| 255 |
+
0.48389774560928345,
|
| 256 |
+
0.43395885825157166,
|
| 257 |
+
0.554872453212738,
|
| 258 |
+
0.5081204175949097
|
| 259 |
+
],
|
| 260 |
+
"eval_code_is_correct_runtime": 67.7492,
|
| 261 |
+
"eval_code_is_correct_samples_per_second": 1.476,
|
| 262 |
+
"eval_code_is_correct_steps_per_second": 0.059,
|
| 263 |
+
"epoch": 1.32,
|
| 264 |
+
"step": 25
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"loss": 0.6611,
|
| 268 |
+
"learning_rate": 0.0002,
|
| 269 |
+
"epoch": 1.37,
|
| 270 |
+
"step": 26
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"loss": 0.6909,
|
| 274 |
+
"learning_rate": 0.0002,
|
| 275 |
+
"epoch": 1.42,
|
| 276 |
+
"step": 27
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"loss": 0.6235,
|
| 280 |
+
"learning_rate": 0.0002,
|
| 281 |
+
"epoch": 1.47,
|
| 282 |
+
"step": 28
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"loss": 0.7308,
|
| 286 |
+
"learning_rate": 0.0002,
|
| 287 |
+
"epoch": 1.53,
|
| 288 |
+
"step": 29
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"loss": 0.7595,
|
| 292 |
+
"learning_rate": 0.0002,
|
| 293 |
+
"epoch": 1.58,
|
| 294 |
+
"step": 30
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"loss": 0.6369,
|
| 298 |
+
"learning_rate": 0.0002,
|
| 299 |
+
"epoch": 1.63,
|
| 300 |
+
"step": 31
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"loss": 0.6853,
|
| 304 |
+
"learning_rate": 0.0002,
|
| 305 |
+
"epoch": 1.68,
|
| 306 |
+
"step": 32
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"loss": 0.6916,
|
| 310 |
+
"learning_rate": 0.0002,
|
| 311 |
+
"epoch": 1.74,
|
| 312 |
+
"step": 33
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"loss": 0.5824,
|
| 316 |
+
"learning_rate": 0.0002,
|
| 317 |
+
"epoch": 1.79,
|
| 318 |
+
"step": 34
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"loss": 0.6258,
|
| 322 |
+
"learning_rate": 0.0002,
|
| 323 |
+
"epoch": 1.84,
|
| 324 |
+
"step": 35
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"loss": 0.7912,
|
| 328 |
+
"learning_rate": 0.0002,
|
| 329 |
+
"epoch": 1.89,
|
| 330 |
+
"step": 36
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"loss": 0.6382,
|
| 334 |
+
"learning_rate": 0.0002,
|
| 335 |
+
"epoch": 1.95,
|
| 336 |
+
"step": 37
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"loss": 0.9123,
|
| 340 |
+
"learning_rate": 0.0002,
|
| 341 |
+
"epoch": 2.0,
|
| 342 |
+
"step": 38
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"loss": 0.5432,
|
| 346 |
+
"learning_rate": 0.0002,
|
| 347 |
+
"epoch": 2.05,
|
| 348 |
+
"step": 39
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"loss": 0.6325,
|
| 352 |
+
"learning_rate": 0.0002,
|
| 353 |
+
"epoch": 2.11,
|
| 354 |
+
"step": 40
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"loss": 0.6731,
|
| 358 |
+
"learning_rate": 0.0002,
|
| 359 |
+
"epoch": 2.16,
|
| 360 |
+
"step": 41
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"loss": 0.5489,
|
| 364 |
+
"learning_rate": 0.0002,
|
| 365 |
+
"epoch": 2.21,
|
| 366 |
+
"step": 42
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"loss": 0.6372,
|
| 370 |
+
"learning_rate": 0.0002,
|
| 371 |
+
"epoch": 2.26,
|
| 372 |
+
"step": 43
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"loss": 0.7034,
|
| 376 |
+
"learning_rate": 0.0002,
|
| 377 |
+
"epoch": 2.32,
|
| 378 |
+
"step": 44
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"loss": 0.512,
|
| 382 |
+
"learning_rate": 0.0002,
|
| 383 |
+
"epoch": 2.37,
|
| 384 |
+
"step": 45
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"loss": 0.6945,
|
| 388 |
+
"learning_rate": 0.0002,
|
| 389 |
+
"epoch": 2.42,
|
| 390 |
+
"step": 46
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"loss": 0.5883,
|
| 394 |
+
"learning_rate": 0.0002,
|
| 395 |
+
"epoch": 2.47,
|
| 396 |
+
"step": 47
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"loss": 0.5311,
|
| 400 |
+
"learning_rate": 0.0002,
|
| 401 |
+
"epoch": 2.53,
|
| 402 |
+
"step": 48
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"loss": 0.5292,
|
| 406 |
+
"learning_rate": 0.0002,
|
| 407 |
+
"epoch": 2.58,
|
| 408 |
+
"step": 49
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"loss": 0.5541,
|
| 412 |
+
"learning_rate": 0.0002,
|
| 413 |
+
"epoch": 2.63,
|
| 414 |
+
"step": 50
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"eval_code_is_correct_loss": 0.5940853357315063,
|
| 418 |
+
"eval_code_is_correct_score": -0.19792629778385162,
|
| 419 |
+
"eval_code_is_correct_brier_score": 0.19792629778385162,
|
| 420 |
+
"eval_code_is_correct_average_probability": 0.6069728136062622,
|
| 421 |
+
"eval_code_is_correct_accuracy": 0.69,
|
| 422 |
+
"eval_code_is_correct_probabilities": [
|
| 423 |
+
0.824921190738678,
|
| 424 |
+
0.46786367893218994,
|
| 425 |
+
0.6803945302963257,
|
| 426 |
+
0.3338681757450104,
|
| 427 |
+
0.4255507290363312,
|
| 428 |
+
0.8192625641822815,
|
| 429 |
+
0.6870703101158142,
|
| 430 |
+
0.5385801196098328,
|
| 431 |
+
0.4014917314052582,
|
| 432 |
+
0.2137792408466339,
|
| 433 |
+
0.5761697888374329,
|
| 434 |
+
0.2802768051624298,
|
| 435 |
+
0.4230016767978668,
|
| 436 |
+
0.7144221067428589,
|
| 437 |
+
0.702923059463501,
|
| 438 |
+
0.7705851197242737,
|
| 439 |
+
0.7801277041435242,
|
| 440 |
+
0.18786321580410004,
|
| 441 |
+
0.8821263909339905,
|
| 442 |
+
0.7419917583465576,
|
| 443 |
+
0.8037750720977783,
|
| 444 |
+
0.7353634238243103,
|
| 445 |
+
0.525610625743866,
|
| 446 |
+
0.199602872133255,
|
| 447 |
+
0.3059692978858948,
|
| 448 |
+
0.354174941778183,
|
| 449 |
+
0.8103994727134705,
|
| 450 |
+
0.7111828327178955,
|
| 451 |
+
0.7084280252456665,
|
| 452 |
+
0.5410431623458862,
|
| 453 |
+
0.7837337255477905,
|
| 454 |
+
0.6090495586395264,
|
| 455 |
+
0.12445675581693649,
|
| 456 |
+
0.7169621586799622,
|
| 457 |
+
0.8234235048294067,
|
| 458 |
+
0.8735712766647339,
|
| 459 |
+
0.7732588052749634,
|
| 460 |
+
0.43631064891815186,
|
| 461 |
+
0.5443180799484253,
|
| 462 |
+
0.348981112241745,
|
| 463 |
+
0.8432489633560181,
|
| 464 |
+
0.32388389110565186,
|
| 465 |
+
0.9644874334335327,
|
| 466 |
+
0.6631470918655396,
|
| 467 |
+
0.7456516623497009,
|
| 468 |
+
0.7492141127586365,
|
| 469 |
+
0.4318337142467499,
|
| 470 |
+
0.46674731373786926,
|
| 471 |
+
0.4367634654045105,
|
| 472 |
+
0.4380766749382019,
|
| 473 |
+
0.39654305577278137,
|
| 474 |
+
0.9517335295677185,
|
| 475 |
+
0.36624813079833984,
|
| 476 |
+
0.645854115486145,
|
| 477 |
+
0.8562455177307129,
|
| 478 |
+
0.7007656693458557,
|
| 479 |
+
0.6245970726013184,
|
| 480 |
+
0.7546803951263428,
|
| 481 |
+
0.6691403388977051,
|
| 482 |
+
0.8129599094390869,
|
| 483 |
+
0.5258075594902039,
|
| 484 |
+
0.6954044103622437,
|
| 485 |
+
0.36306533217430115,
|
| 486 |
+
0.9693009853363037,
|
| 487 |
+
0.6357976198196411,
|
| 488 |
+
0.7374253869056702,
|
| 489 |
+
0.5900733470916748,
|
| 490 |
+
0.540191650390625,
|
| 491 |
+
0.6071694493293762,
|
| 492 |
+
0.3094453513622284,
|
| 493 |
+
0.8251391649246216,
|
| 494 |
+
0.8399093151092529,
|
| 495 |
+
0.8712323307991028,
|
| 496 |
+
0.5785478949546814,
|
| 497 |
+
0.5815758109092712,
|
| 498 |
+
0.7164744138717651,
|
| 499 |
+
0.5060900449752808,
|
| 500 |
+
0.6983495950698853,
|
| 501 |
+
0.7523359656333923,
|
| 502 |
+
0.14946384727954865,
|
| 503 |
+
0.7415146827697754,
|
| 504 |
+
0.34309232234954834,
|
| 505 |
+
0.23558610677719116,
|
| 506 |
+
0.43409526348114014,
|
| 507 |
+
0.7354661226272583,
|
| 508 |
+
0.7268248200416565,
|
| 509 |
+
0.7648622989654541,
|
| 510 |
+
0.7701873779296875,
|
| 511 |
+
0.4304506778717041,
|
| 512 |
+
0.7484250068664551,
|
| 513 |
+
0.7701525688171387,
|
| 514 |
+
0.3247123658657074,
|
| 515 |
+
0.6498774886131287,
|
| 516 |
+
0.34104210138320923,
|
| 517 |
+
0.9773394465446472,
|
| 518 |
+
0.27353885769844055,
|
| 519 |
+
0.747333824634552,
|
| 520 |
+
0.5845430493354797,
|
| 521 |
+
0.8978924751281738,
|
| 522 |
+
0.6838365793228149
|
| 523 |
+
],
|
| 524 |
+
"eval_code_is_correct_runtime": 67.7443,
|
| 525 |
+
"eval_code_is_correct_samples_per_second": 1.476,
|
| 526 |
+
"eval_code_is_correct_steps_per_second": 0.059,
|
| 527 |
+
"epoch": 2.63,
|
| 528 |
+
"step": 50
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"loss": 0.5214,
|
| 532 |
+
"learning_rate": 0.0002,
|
| 533 |
+
"epoch": 2.68,
|
| 534 |
+
"step": 51
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"loss": 0.7301,
|
| 538 |
+
"learning_rate": 0.0002,
|
| 539 |
+
"epoch": 2.74,
|
| 540 |
+
"step": 52
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"loss": 0.53,
|
| 544 |
+
"learning_rate": 0.0002,
|
| 545 |
+
"epoch": 2.79,
|
| 546 |
+
"step": 53
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"loss": 0.5241,
|
| 550 |
+
"learning_rate": 0.0002,
|
| 551 |
+
"epoch": 2.84,
|
| 552 |
+
"step": 54
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"loss": 0.4484,
|
| 556 |
+
"learning_rate": 0.0002,
|
| 557 |
+
"epoch": 2.89,
|
| 558 |
+
"step": 55
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"loss": 0.5665,
|
| 562 |
+
"learning_rate": 0.0002,
|
| 563 |
+
"epoch": 2.95,
|
| 564 |
+
"step": 56
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"loss": 0.4578,
|
| 568 |
+
"learning_rate": 0.0002,
|
| 569 |
+
"epoch": 3.0,
|
| 570 |
+
"step": 57
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"loss": 0.4425,
|
| 574 |
+
"learning_rate": 0.0002,
|
| 575 |
+
"epoch": 3.05,
|
| 576 |
+
"step": 58
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"loss": 0.4053,
|
| 580 |
+
"learning_rate": 0.0002,
|
| 581 |
+
"epoch": 3.11,
|
| 582 |
+
"step": 59
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"loss": 0.4992,
|
| 586 |
+
"learning_rate": 0.0002,
|
| 587 |
+
"epoch": 3.16,
|
| 588 |
+
"step": 60
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"loss": 0.2353,
|
| 592 |
+
"learning_rate": 0.0002,
|
| 593 |
+
"epoch": 3.21,
|
| 594 |
+
"step": 61
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"loss": 0.3383,
|
| 598 |
+
"learning_rate": 0.0002,
|
| 599 |
+
"epoch": 3.26,
|
| 600 |
+
"step": 62
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"loss": 0.6835,
|
| 604 |
+
"learning_rate": 0.0002,
|
| 605 |
+
"epoch": 3.32,
|
| 606 |
+
"step": 63
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"loss": 0.6729,
|
| 610 |
+
"learning_rate": 0.0002,
|
| 611 |
+
"epoch": 3.37,
|
| 612 |
+
"step": 64
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"loss": 0.6045,
|
| 616 |
+
"learning_rate": 0.0002,
|
| 617 |
+
"epoch": 3.42,
|
| 618 |
+
"step": 65
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"loss": 0.324,
|
| 622 |
+
"learning_rate": 0.0002,
|
| 623 |
+
"epoch": 3.47,
|
| 624 |
+
"step": 66
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"loss": 0.3726,
|
| 628 |
+
"learning_rate": 0.0002,
|
| 629 |
+
"epoch": 3.53,
|
| 630 |
+
"step": 67
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"loss": 0.3529,
|
| 634 |
+
"learning_rate": 0.0002,
|
| 635 |
+
"epoch": 3.58,
|
| 636 |
+
"step": 68
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"loss": 0.4642,
|
| 640 |
+
"learning_rate": 0.0002,
|
| 641 |
+
"epoch": 3.63,
|
| 642 |
+
"step": 69
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"loss": 0.4211,
|
| 646 |
+
"learning_rate": 0.0002,
|
| 647 |
+
"epoch": 3.68,
|
| 648 |
+
"step": 70
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"loss": 0.298,
|
| 652 |
+
"learning_rate": 0.0002,
|
| 653 |
+
"epoch": 3.74,
|
| 654 |
+
"step": 71
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"loss": 0.3618,
|
| 658 |
+
"learning_rate": 0.0002,
|
| 659 |
+
"epoch": 3.79,
|
| 660 |
+
"step": 72
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"loss": 0.4728,
|
| 664 |
+
"learning_rate": 0.0002,
|
| 665 |
+
"epoch": 3.84,
|
| 666 |
+
"step": 73
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"loss": 0.402,
|
| 670 |
+
"learning_rate": 0.0002,
|
| 671 |
+
"epoch": 3.89,
|
| 672 |
+
"step": 74
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"loss": 0.4046,
|
| 676 |
+
"learning_rate": 0.0002,
|
| 677 |
+
"epoch": 3.95,
|
| 678 |
+
"step": 75
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"eval_code_is_correct_loss": 0.47848281264305115,
|
| 682 |
+
"eval_code_is_correct_score": -0.15475420653820038,
|
| 683 |
+
"eval_code_is_correct_brier_score": 0.15475420653820038,
|
| 684 |
+
"eval_code_is_correct_average_probability": 0.6844885945320129,
|
| 685 |
+
"eval_code_is_correct_accuracy": 0.76,
|
| 686 |
+
"eval_code_is_correct_probabilities": [
|
| 687 |
+
0.9683555960655212,
|
| 688 |
+
0.44921836256980896,
|
| 689 |
+
0.7495419383049011,
|
| 690 |
+
0.2939276099205017,
|
| 691 |
+
0.34451109170913696,
|
| 692 |
+
0.9546052813529968,
|
| 693 |
+
0.6665733456611633,
|
| 694 |
+
0.6185269951820374,
|
| 695 |
+
0.7960335612297058,
|
| 696 |
+
0.24308358132839203,
|
| 697 |
+
0.6751048564910889,
|
| 698 |
+
0.3198447823524475,
|
| 699 |
+
0.6380735635757446,
|
| 700 |
+
0.9478679895401001,
|
| 701 |
+
0.5936516523361206,
|
| 702 |
+
0.6253194212913513,
|
| 703 |
+
0.8495998978614807,
|
| 704 |
+
0.3085791766643524,
|
| 705 |
+
0.7716754674911499,
|
| 706 |
+
0.7831162214279175,
|
| 707 |
+
0.9598362445831299,
|
| 708 |
+
0.5667487382888794,
|
| 709 |
+
0.5415951609611511,
|
| 710 |
+
0.20470955967903137,
|
| 711 |
+
0.5040990710258484,
|
| 712 |
+
0.3724431097507477,
|
| 713 |
+
0.8682514429092407,
|
| 714 |
+
0.7767794728279114,
|
| 715 |
+
0.7808045744895935,
|
| 716 |
+
0.5015738010406494,
|
| 717 |
+
0.7318475842475891,
|
| 718 |
+
0.7234196066856384,
|
| 719 |
+
0.4821881353855133,
|
| 720 |
+
0.6735180616378784,
|
| 721 |
+
0.8447625637054443,
|
| 722 |
+
0.9881181120872498,
|
| 723 |
+
0.7274037599563599,
|
| 724 |
+
0.5772131085395813,
|
| 725 |
+
0.6710129380226135,
|
| 726 |
+
0.3252182602882385,
|
| 727 |
+
0.8553206920623779,
|
| 728 |
+
0.2691892981529236,
|
| 729 |
+
0.9974000453948975,
|
| 730 |
+
0.8067336082458496,
|
| 731 |
+
0.7142802476882935,
|
| 732 |
+
0.7670422792434692,
|
| 733 |
+
0.36208221316337585,
|
| 734 |
+
0.9332921504974365,
|
| 735 |
+
0.8860767483711243,
|
| 736 |
+
0.40401703119277954,
|
| 737 |
+
0.35290971398353577,
|
| 738 |
+
0.997400164604187,
|
| 739 |
+
0.4895634353160858,
|
| 740 |
+
0.8298471570014954,
|
| 741 |
+
0.8764240741729736,
|
| 742 |
+
0.6197875142097473,
|
| 743 |
+
0.8558983206748962,
|
| 744 |
+
0.8380407691001892,
|
| 745 |
+
0.8485222458839417,
|
| 746 |
+
0.555997908115387,
|
| 747 |
+
0.26674920320510864,
|
| 748 |
+
0.8279209733009338,
|
| 749 |
+
0.41571998596191406,
|
| 750 |
+
0.9991807341575623,
|
| 751 |
+
0.8207216858863831,
|
| 752 |
+
0.7336632609367371,
|
| 753 |
+
0.6954337358474731,
|
| 754 |
+
0.6488922238349915,
|
| 755 |
+
0.922136127948761,
|
| 756 |
+
0.4455629289150238,
|
| 757 |
+
0.8186019062995911,
|
| 758 |
+
0.9768170714378357,
|
| 759 |
+
0.9885281324386597,
|
| 760 |
+
0.8712007999420166,
|
| 761 |
+
0.8978477716445923,
|
| 762 |
+
0.8873462677001953,
|
| 763 |
+
0.6821259260177612,
|
| 764 |
+
0.8775141835212708,
|
| 765 |
+
0.7657942771911621,
|
| 766 |
+
0.2309243381023407,
|
| 767 |
+
0.8537100553512573,
|
| 768 |
+
0.13663502037525177,
|
| 769 |
+
0.1426939070224762,
|
| 770 |
+
0.6065592169761658,
|
| 771 |
+
0.7732885479927063,
|
| 772 |
+
0.7179746031761169,
|
| 773 |
+
0.8297063112258911,
|
| 774 |
+
0.9848968982696533,
|
| 775 |
+
0.24758392572402954,
|
| 776 |
+
0.757599949836731,
|
| 777 |
+
0.9647876620292664,
|
| 778 |
+
0.4051612615585327,
|
| 779 |
+
0.8224207758903503,
|
| 780 |
+
0.8955028653144836,
|
| 781 |
+
0.9978285431861877,
|
| 782 |
+
0.4562136232852936,
|
| 783 |
+
0.9620097875595093,
|
| 784 |
+
0.9017798900604248,
|
| 785 |
+
0.8915098905563354,
|
| 786 |
+
0.6497373580932617
|
| 787 |
+
],
|
| 788 |
+
"eval_code_is_correct_runtime": 67.7494,
|
| 789 |
+
"eval_code_is_correct_samples_per_second": 1.476,
|
| 790 |
+
"eval_code_is_correct_steps_per_second": 0.059,
|
| 791 |
+
"epoch": 3.95,
|
| 792 |
+
"step": 75
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"loss": 0.3116,
|
| 796 |
+
"learning_rate": 0.0002,
|
| 797 |
+
"epoch": 4.0,
|
| 798 |
+
"step": 76
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"loss": 0.3615,
|
| 802 |
+
"learning_rate": 0.0002,
|
| 803 |
+
"epoch": 4.05,
|
| 804 |
+
"step": 77
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"loss": 0.2709,
|
| 808 |
+
"learning_rate": 0.0002,
|
| 809 |
+
"epoch": 4.11,
|
| 810 |
+
"step": 78
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"loss": 0.3665,
|
| 814 |
+
"learning_rate": 0.0002,
|
| 815 |
+
"epoch": 4.16,
|
| 816 |
+
"step": 79
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"loss": 0.1072,
|
| 820 |
+
"learning_rate": 0.0002,
|
| 821 |
+
"epoch": 4.21,
|
| 822 |
+
"step": 80
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"loss": 0.2752,
|
| 826 |
+
"learning_rate": 0.0002,
|
| 827 |
+
"epoch": 4.26,
|
| 828 |
+
"step": 81
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"loss": 0.1764,
|
| 832 |
+
"learning_rate": 0.0002,
|
| 833 |
+
"epoch": 4.32,
|
| 834 |
+
"step": 82
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"loss": 0.1275,
|
| 838 |
+
"learning_rate": 0.0002,
|
| 839 |
+
"epoch": 4.37,
|
| 840 |
+
"step": 83
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"loss": 0.3218,
|
| 844 |
+
"learning_rate": 0.0002,
|
| 845 |
+
"epoch": 4.42,
|
| 846 |
+
"step": 84
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"loss": 0.3217,
|
| 850 |
+
"learning_rate": 0.0002,
|
| 851 |
+
"epoch": 4.47,
|
| 852 |
+
"step": 85
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"loss": 0.3257,
|
| 856 |
+
"learning_rate": 0.0002,
|
| 857 |
+
"epoch": 4.53,
|
| 858 |
+
"step": 86
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"loss": 0.2085,
|
| 862 |
+
"learning_rate": 0.0002,
|
| 863 |
+
"epoch": 4.58,
|
| 864 |
+
"step": 87
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"loss": 0.5161,
|
| 868 |
+
"learning_rate": 0.0002,
|
| 869 |
+
"epoch": 4.63,
|
| 870 |
+
"step": 88
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"loss": 0.3032,
|
| 874 |
+
"learning_rate": 0.0002,
|
| 875 |
+
"epoch": 4.68,
|
| 876 |
+
"step": 89
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"loss": 0.1597,
|
| 880 |
+
"learning_rate": 0.0002,
|
| 881 |
+
"epoch": 4.74,
|
| 882 |
+
"step": 90
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"loss": 0.3244,
|
| 886 |
+
"learning_rate": 0.0002,
|
| 887 |
+
"epoch": 4.79,
|
| 888 |
+
"step": 91
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"loss": 0.2538,
|
| 892 |
+
"learning_rate": 0.0002,
|
| 893 |
+
"epoch": 4.84,
|
| 894 |
+
"step": 92
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"loss": 0.3986,
|
| 898 |
+
"learning_rate": 0.0002,
|
| 899 |
+
"epoch": 4.89,
|
| 900 |
+
"step": 93
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"loss": 0.1784,
|
| 904 |
+
"learning_rate": 0.0002,
|
| 905 |
+
"epoch": 4.95,
|
| 906 |
+
"step": 94
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"loss": 0.0902,
|
| 910 |
+
"learning_rate": 0.0002,
|
| 911 |
+
"epoch": 5.0,
|
| 912 |
+
"step": 95
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"loss": 0.1785,
|
| 916 |
+
"learning_rate": 0.0002,
|
| 917 |
+
"epoch": 5.05,
|
| 918 |
+
"step": 96
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"loss": 0.1223,
|
| 922 |
+
"learning_rate": 0.0002,
|
| 923 |
+
"epoch": 5.11,
|
| 924 |
+
"step": 97
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"loss": 0.1473,
|
| 928 |
+
"learning_rate": 0.0002,
|
| 929 |
+
"epoch": 5.16,
|
| 930 |
+
"step": 98
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"loss": 0.1615,
|
| 934 |
+
"learning_rate": 0.0002,
|
| 935 |
+
"epoch": 5.21,
|
| 936 |
+
"step": 99
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"loss": 0.1691,
|
| 940 |
+
"learning_rate": 0.0002,
|
| 941 |
+
"epoch": 5.26,
|
| 942 |
+
"step": 100
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"eval_code_is_correct_loss": 0.7131536602973938,
|
| 946 |
+
"eval_code_is_correct_score": -0.21241626143455505,
|
| 947 |
+
"eval_code_is_correct_brier_score": 0.21241626143455505,
|
| 948 |
+
"eval_code_is_correct_average_probability": 0.7060017585754395,
|
| 949 |
+
"eval_code_is_correct_accuracy": 0.73,
|
| 950 |
+
"eval_code_is_correct_probabilities": [
|
| 951 |
+
0.9998742341995239,
|
| 952 |
+
0.24125896394252777,
|
| 953 |
+
0.5266091823577881,
|
| 954 |
+
0.9446415901184082,
|
| 955 |
+
0.658671498298645,
|
| 956 |
+
0.999782145023346,
|
| 957 |
+
0.4476185441017151,
|
| 958 |
+
0.9995893836021423,
|
| 959 |
+
0.9987817406654358,
|
| 960 |
+
0.9846014976501465,
|
| 961 |
+
0.6241582632064819,
|
| 962 |
+
0.9147050380706787,
|
| 963 |
+
0.9970441460609436,
|
| 964 |
+
0.999207079410553,
|
| 965 |
+
0.03215882182121277,
|
| 966 |
+
0.08953133225440979,
|
| 967 |
+
0.923194944858551,
|
| 968 |
+
0.9589815735816956,
|
| 969 |
+
0.2918163537979126,
|
| 970 |
+
0.7663164734840393,
|
| 971 |
+
0.9991129040718079,
|
| 972 |
+
0.12000331282615662,
|
| 973 |
+
0.15813884139060974,
|
| 974 |
+
0.8554588556289673,
|
| 975 |
+
0.9006542563438416,
|
| 976 |
+
0.9951829314231873,
|
| 977 |
+
0.48046576976776123,
|
| 978 |
+
0.2053559571504593,
|
| 979 |
+
0.8127390146255493,
|
| 980 |
+
0.9593634605407715,
|
| 981 |
+
0.11686976253986359,
|
| 982 |
+
0.124169260263443,
|
| 983 |
+
0.9974563717842102,
|
| 984 |
+
0.04802563041448593,
|
| 985 |
+
0.8246001601219177,
|
| 986 |
+
0.9987502098083496,
|
| 987 |
+
0.015473408624529839,
|
| 988 |
+
0.0645429939031601,
|
| 989 |
+
0.49971136450767517,
|
| 990 |
+
0.9124832153320312,
|
| 991 |
+
0.39771828055381775,
|
| 992 |
+
0.7872201204299927,
|
| 993 |
+
0.9997814297676086,
|
| 994 |
+
0.987456738948822,
|
| 995 |
+
0.1562322974205017,
|
| 996 |
+
0.7515577673912048,
|
| 997 |
+
0.8418968319892883,
|
| 998 |
+
0.9998055100440979,
|
| 999 |
+
0.9988735318183899,
|
| 1000 |
+
0.8924939036369324,
|
| 1001 |
+
0.9951292276382446,
|
| 1002 |
+
0.999900221824646,
|
| 1003 |
+
0.9838736653327942,
|
| 1004 |
+
0.994502067565918,
|
| 1005 |
+
0.7390810251235962,
|
| 1006 |
+
0.04368113726377487,
|
| 1007 |
+
0.9977819323539734,
|
| 1008 |
+
0.9505625367164612,
|
| 1009 |
+
0.9955796599388123,
|
| 1010 |
+
0.06847873330116272,
|
| 1011 |
+
0.001323648844845593,
|
| 1012 |
+
0.9979519248008728,
|
| 1013 |
+
0.5310106873512268,
|
| 1014 |
+
0.9994561076164246,
|
| 1015 |
+
0.3053685426712036,
|
| 1016 |
+
0.8901605606079102,
|
| 1017 |
+
0.6555763483047485,
|
| 1018 |
+
0.9988672733306885,
|
| 1019 |
+
0.9997801184654236,
|
| 1020 |
+
0.9971674084663391,
|
| 1021 |
+
0.5509296655654907,
|
| 1022 |
+
0.9994674324989319,
|
| 1023 |
+
0.9999033212661743,
|
| 1024 |
+
0.9959565997123718,
|
| 1025 |
+
0.99689781665802,
|
| 1026 |
+
0.994744062423706,
|
| 1027 |
+
0.6479522585868835,
|
| 1028 |
+
0.9884534478187561,
|
| 1029 |
+
0.8599462509155273,
|
| 1030 |
+
0.8442027568817139,
|
| 1031 |
+
0.9853453040122986,
|
| 1032 |
+
0.015567261725664139,
|
| 1033 |
+
0.17351527512073517,
|
| 1034 |
+
0.9978513717651367,
|
| 1035 |
+
0.29119962453842163,
|
| 1036 |
+
0.5376598834991455,
|
| 1037 |
+
0.06629227846860886,
|
| 1038 |
+
0.9998811483383179,
|
| 1039 |
+
0.030417898669838905,
|
| 1040 |
+
0.8476421236991882,
|
| 1041 |
+
0.9996863603591919,
|
| 1042 |
+
0.185418501496315,
|
| 1043 |
+
0.9999172687530518,
|
| 1044 |
+
0.9991611242294312,
|
| 1045 |
+
0.9999512434005737,
|
| 1046 |
+
0.9985194802284241,
|
| 1047 |
+
0.9991263747215271,
|
| 1048 |
+
0.9992461204528809,
|
| 1049 |
+
0.5890063047409058,
|
| 1050 |
+
0.5609598159790039
|
| 1051 |
+
],
|
| 1052 |
+
"eval_code_is_correct_runtime": 67.7473,
|
| 1053 |
+
"eval_code_is_correct_samples_per_second": 1.476,
|
| 1054 |
+
"eval_code_is_correct_steps_per_second": 0.059,
|
| 1055 |
+
"epoch": 5.26,
|
| 1056 |
+
"step": 100
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"loss": 0.5527,
|
| 1060 |
+
"learning_rate": 0.0002,
|
| 1061 |
+
"epoch": 5.32,
|
| 1062 |
+
"step": 101
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"loss": 0.5535,
|
| 1066 |
+
"learning_rate": 0.0002,
|
| 1067 |
+
"epoch": 5.37,
|
| 1068 |
+
"step": 102
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"loss": 0.4444,
|
| 1072 |
+
"learning_rate": 0.0002,
|
| 1073 |
+
"epoch": 5.42,
|
| 1074 |
+
"step": 103
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"loss": 0.1897,
|
| 1078 |
+
"learning_rate": 0.0002,
|
| 1079 |
+
"epoch": 5.47,
|
| 1080 |
+
"step": 104
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"loss": 0.015,
|
| 1084 |
+
"learning_rate": 0.0002,
|
| 1085 |
+
"epoch": 5.53,
|
| 1086 |
+
"step": 105
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"loss": 0.6378,
|
| 1090 |
+
"learning_rate": 0.0002,
|
| 1091 |
+
"epoch": 5.58,
|
| 1092 |
+
"step": 106
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"loss": 0.5394,
|
| 1096 |
+
"learning_rate": 0.0002,
|
| 1097 |
+
"epoch": 5.63,
|
| 1098 |
+
"step": 107
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"loss": 0.3359,
|
| 1102 |
+
"learning_rate": 0.0002,
|
| 1103 |
+
"epoch": 5.68,
|
| 1104 |
+
"step": 108
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"loss": 0.2657,
|
| 1108 |
+
"learning_rate": 0.0002,
|
| 1109 |
+
"epoch": 5.74,
|
| 1110 |
+
"step": 109
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"loss": 0.2404,
|
| 1114 |
+
"learning_rate": 0.0002,
|
| 1115 |
+
"epoch": 5.79,
|
| 1116 |
+
"step": 110
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"loss": 0.5007,
|
| 1120 |
+
"learning_rate": 0.0002,
|
| 1121 |
+
"epoch": 5.84,
|
| 1122 |
+
"step": 111
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"loss": 0.5109,
|
| 1126 |
+
"learning_rate": 0.0002,
|
| 1127 |
+
"epoch": 5.89,
|
| 1128 |
+
"step": 112
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"loss": 0.1953,
|
| 1132 |
+
"learning_rate": 0.0002,
|
| 1133 |
+
"epoch": 5.95,
|
| 1134 |
+
"step": 113
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"loss": 0.0324,
|
| 1138 |
+
"learning_rate": 0.0002,
|
| 1139 |
+
"epoch": 6.0,
|
| 1140 |
+
"step": 114
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"loss": 0.3503,
|
| 1144 |
+
"learning_rate": 0.0002,
|
| 1145 |
+
"epoch": 6.05,
|
| 1146 |
+
"step": 115
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"loss": 0.2595,
|
| 1150 |
+
"learning_rate": 0.0002,
|
| 1151 |
+
"epoch": 6.11,
|
| 1152 |
+
"step": 116
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"loss": 0.4104,
|
| 1156 |
+
"learning_rate": 0.0002,
|
| 1157 |
+
"epoch": 6.16,
|
| 1158 |
+
"step": 117
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"loss": 0.1498,
|
| 1162 |
+
"learning_rate": 0.0002,
|
| 1163 |
+
"epoch": 6.21,
|
| 1164 |
+
"step": 118
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"loss": 0.1297,
|
| 1168 |
+
"learning_rate": 0.0002,
|
| 1169 |
+
"epoch": 6.26,
|
| 1170 |
+
"step": 119
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"loss": 0.1723,
|
| 1174 |
+
"learning_rate": 0.0002,
|
| 1175 |
+
"epoch": 6.32,
|
| 1176 |
+
"step": 120
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"loss": 0.1331,
|
| 1180 |
+
"learning_rate": 0.0002,
|
| 1181 |
+
"epoch": 6.37,
|
| 1182 |
+
"step": 121
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"loss": 0.2478,
|
| 1186 |
+
"learning_rate": 0.0002,
|
| 1187 |
+
"epoch": 6.42,
|
| 1188 |
+
"step": 122
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"loss": 0.3555,
|
| 1192 |
+
"learning_rate": 0.0002,
|
| 1193 |
+
"epoch": 6.47,
|
| 1194 |
+
"step": 123
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"loss": 0.2095,
|
| 1198 |
+
"learning_rate": 0.0002,
|
| 1199 |
+
"epoch": 6.53,
|
| 1200 |
+
"step": 124
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"loss": 0.1896,
|
| 1204 |
+
"learning_rate": 0.0002,
|
| 1205 |
+
"epoch": 6.58,
|
| 1206 |
+
"step": 125
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"eval_code_is_correct_loss": 0.4567447602748871,
|
| 1210 |
+
"eval_code_is_correct_score": -0.14007602632045746,
|
| 1211 |
+
"eval_code_is_correct_brier_score": 0.14007602632045746,
|
| 1212 |
+
"eval_code_is_correct_average_probability": 0.7727714776992798,
|
| 1213 |
+
"eval_code_is_correct_accuracy": 0.82,
|
| 1214 |
+
"eval_code_is_correct_probabilities": [
|
| 1215 |
+
0.9987679123878479,
|
| 1216 |
+
0.4806418716907501,
|
| 1217 |
+
0.7848430871963501,
|
| 1218 |
+
0.3105872571468353,
|
| 1219 |
+
0.5165024399757385,
|
| 1220 |
+
0.998405396938324,
|
| 1221 |
+
0.8343289494514465,
|
| 1222 |
+
0.9901788234710693,
|
| 1223 |
+
0.9813113808631897,
|
| 1224 |
+
0.7574440240859985,
|
| 1225 |
+
0.7910118699073792,
|
| 1226 |
+
0.06982726603746414,
|
| 1227 |
+
0.9809978604316711,
|
| 1228 |
+
0.9973791837692261,
|
| 1229 |
+
0.5600104928016663,
|
| 1230 |
+
0.7603288888931274,
|
| 1231 |
+
0.9818860292434692,
|
| 1232 |
+
0.3341038227081299,
|
| 1233 |
+
0.9702696800231934,
|
| 1234 |
+
0.9806032776832581,
|
| 1235 |
+
0.9957588315010071,
|
| 1236 |
+
0.5696340203285217,
|
| 1237 |
+
0.7143341898918152,
|
| 1238 |
+
0.16743437945842743,
|
| 1239 |
+
0.7721751928329468,
|
| 1240 |
+
0.1173228770494461,
|
| 1241 |
+
0.8101537823677063,
|
| 1242 |
+
0.9562052488327026,
|
| 1243 |
+
0.906458854675293,
|
| 1244 |
+
0.8179009556770325,
|
| 1245 |
+
0.7743387222290039,
|
| 1246 |
+
0.8904827237129211,
|
| 1247 |
+
0.8322084546089172,
|
| 1248 |
+
0.8095942139625549,
|
| 1249 |
+
0.9716352224349976,
|
| 1250 |
+
0.9985573887825012,
|
| 1251 |
+
0.1670643389225006,
|
| 1252 |
+
0.748282253742218,
|
| 1253 |
+
0.7800930142402649,
|
| 1254 |
+
0.14132891595363617,
|
| 1255 |
+
0.8936496376991272,
|
| 1256 |
+
0.36719489097595215,
|
| 1257 |
+
0.9985307455062866,
|
| 1258 |
+
0.9869412779808044,
|
| 1259 |
+
0.6673361659049988,
|
| 1260 |
+
0.9174671769142151,
|
| 1261 |
+
0.9842150807380676,
|
| 1262 |
+
0.997148334980011,
|
| 1263 |
+
0.985522985458374,
|
| 1264 |
+
0.8499152064323425,
|
| 1265 |
+
0.9198179244995117,
|
| 1266 |
+
0.9993763566017151,
|
| 1267 |
+
0.6242245435714722,
|
| 1268 |
+
0.9891676902770996,
|
| 1269 |
+
0.9344865083694458,
|
| 1270 |
+
0.8665608763694763,
|
| 1271 |
+
0.9534940719604492,
|
| 1272 |
+
0.9868246912956238,
|
| 1273 |
+
0.989677906036377,
|
| 1274 |
+
0.6916028261184692,
|
| 1275 |
+
0.05886725336313248,
|
| 1276 |
+
0.9953218102455139,
|
| 1277 |
+
0.9273397922515869,
|
| 1278 |
+
0.9996368885040283,
|
| 1279 |
+
0.12487627565860748,
|
| 1280 |
+
0.9797862768173218,
|
| 1281 |
+
0.9216504693031311,
|
| 1282 |
+
0.9686106443405151,
|
| 1283 |
+
0.997191846370697,
|
| 1284 |
+
0.9759156703948975,
|
| 1285 |
+
0.7190247178077698,
|
| 1286 |
+
0.9861569404602051,
|
| 1287 |
+
0.9982544779777527,
|
| 1288 |
+
0.9947845339775085,
|
| 1289 |
+
0.9661282896995544,
|
| 1290 |
+
0.9940819144248962,
|
| 1291 |
+
0.7725122570991516,
|
| 1292 |
+
0.9937759637832642,
|
| 1293 |
+
0.8750337362289429,
|
| 1294 |
+
0.15745404362678528,
|
| 1295 |
+
0.9853953123092651,
|
| 1296 |
+
0.0993090569972992,
|
| 1297 |
+
0.07436255365610123,
|
| 1298 |
+
0.9853988885879517,
|
| 1299 |
+
0.7725264430046082,
|
| 1300 |
+
0.4874012768268585,
|
| 1301 |
+
0.1029394119977951,
|
| 1302 |
+
0.9995567202568054,
|
| 1303 |
+
0.013778586871922016,
|
| 1304 |
+
0.9781476855278015,
|
| 1305 |
+
0.9989705085754395,
|
| 1306 |
+
0.26722535490989685,
|
| 1307 |
+
0.9956694841384888,
|
| 1308 |
+
0.9968309998512268,
|
| 1309 |
+
0.9996675252914429,
|
| 1310 |
+
0.82625812292099,
|
| 1311 |
+
0.9978654980659485,
|
| 1312 |
+
0.9962685108184814,
|
| 1313 |
+
0.9435150027275085,
|
| 1314 |
+
0.7261157631874084
|
| 1315 |
+
],
|
| 1316 |
+
"eval_code_is_correct_runtime": 67.7467,
|
| 1317 |
+
"eval_code_is_correct_samples_per_second": 1.476,
|
| 1318 |
+
"eval_code_is_correct_steps_per_second": 0.059,
|
| 1319 |
+
"epoch": 6.58,
|
| 1320 |
+
"step": 125
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"loss": 0.1246,
|
| 1324 |
+
"learning_rate": 0.0002,
|
| 1325 |
+
"epoch": 6.63,
|
| 1326 |
+
"step": 126
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"loss": 0.1277,
|
| 1330 |
+
"learning_rate": 0.0002,
|
| 1331 |
+
"epoch": 6.68,
|
| 1332 |
+
"step": 127
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"loss": 0.0844,
|
| 1336 |
+
"learning_rate": 0.0002,
|
| 1337 |
+
"epoch": 6.74,
|
| 1338 |
+
"step": 128
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"loss": 0.1287,
|
| 1342 |
+
"learning_rate": 0.0002,
|
| 1343 |
+
"epoch": 6.79,
|
| 1344 |
+
"step": 129
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"loss": 0.0997,
|
| 1348 |
+
"learning_rate": 0.0002,
|
| 1349 |
+
"epoch": 6.84,
|
| 1350 |
+
"step": 130
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"loss": 0.0979,
|
| 1354 |
+
"learning_rate": 0.0002,
|
| 1355 |
+
"epoch": 6.89,
|
| 1356 |
+
"step": 131
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"loss": 0.0433,
|
| 1360 |
+
"learning_rate": 0.0002,
|
| 1361 |
+
"epoch": 6.95,
|
| 1362 |
+
"step": 132
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"loss": 0.2242,
|
| 1366 |
+
"learning_rate": 0.0002,
|
| 1367 |
+
"epoch": 7.0,
|
| 1368 |
+
"step": 133
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"loss": 0.0423,
|
| 1372 |
+
"learning_rate": 0.0002,
|
| 1373 |
+
"epoch": 7.05,
|
| 1374 |
+
"step": 134
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"loss": 0.1313,
|
| 1378 |
+
"learning_rate": 0.0002,
|
| 1379 |
+
"epoch": 7.11,
|
| 1380 |
+
"step": 135
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"loss": 0.1776,
|
| 1384 |
+
"learning_rate": 0.0002,
|
| 1385 |
+
"epoch": 7.16,
|
| 1386 |
+
"step": 136
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"loss": 0.0513,
|
| 1390 |
+
"learning_rate": 0.0002,
|
| 1391 |
+
"epoch": 7.21,
|
| 1392 |
+
"step": 137
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"loss": 0.0166,
|
| 1396 |
+
"learning_rate": 0.0002,
|
| 1397 |
+
"epoch": 7.26,
|
| 1398 |
+
"step": 138
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"loss": 0.1085,
|
| 1402 |
+
"learning_rate": 0.0002,
|
| 1403 |
+
"epoch": 7.32,
|
| 1404 |
+
"step": 139
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"loss": 0.1359,
|
| 1408 |
+
"learning_rate": 0.0002,
|
| 1409 |
+
"epoch": 7.37,
|
| 1410 |
+
"step": 140
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"loss": 0.3451,
|
| 1414 |
+
"learning_rate": 0.0002,
|
| 1415 |
+
"epoch": 7.42,
|
| 1416 |
+
"step": 141
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"loss": 0.3083,
|
| 1420 |
+
"learning_rate": 0.0002,
|
| 1421 |
+
"epoch": 7.47,
|
| 1422 |
+
"step": 142
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"loss": 0.0116,
|
| 1426 |
+
"learning_rate": 0.0002,
|
| 1427 |
+
"epoch": 7.53,
|
| 1428 |
+
"step": 143
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"loss": 0.0504,
|
| 1432 |
+
"learning_rate": 0.0002,
|
| 1433 |
+
"epoch": 7.58,
|
| 1434 |
+
"step": 144
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"loss": 0.049,
|
| 1438 |
+
"learning_rate": 0.0002,
|
| 1439 |
+
"epoch": 7.63,
|
| 1440 |
+
"step": 145
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"loss": 0.0906,
|
| 1444 |
+
"learning_rate": 0.0002,
|
| 1445 |
+
"epoch": 7.68,
|
| 1446 |
+
"step": 146
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"loss": 0.1394,
|
| 1450 |
+
"learning_rate": 0.0002,
|
| 1451 |
+
"epoch": 7.74,
|
| 1452 |
+
"step": 147
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"loss": 0.0492,
|
| 1456 |
+
"learning_rate": 0.0002,
|
| 1457 |
+
"epoch": 7.79,
|
| 1458 |
+
"step": 148
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"loss": 0.0513,
|
| 1462 |
+
"learning_rate": 0.0002,
|
| 1463 |
+
"epoch": 7.84,
|
| 1464 |
+
"step": 149
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"loss": 0.0248,
|
| 1468 |
+
"learning_rate": 0.0002,
|
| 1469 |
+
"epoch": 7.89,
|
| 1470 |
+
"step": 150
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"eval_code_is_correct_loss": 0.8317287564277649,
|
| 1474 |
+
"eval_code_is_correct_score": -0.16410262882709503,
|
| 1475 |
+
"eval_code_is_correct_brier_score": 0.16410262882709503,
|
| 1476 |
+
"eval_code_is_correct_average_probability": 0.7992724776268005,
|
| 1477 |
+
"eval_code_is_correct_accuracy": 0.81,
|
| 1478 |
+
"eval_code_is_correct_probabilities": [
|
| 1479 |
+
0.9999188184738159,
|
| 1480 |
+
0.9416216611862183,
|
| 1481 |
+
0.9813385009765625,
|
| 1482 |
+
0.16267889738082886,
|
| 1483 |
+
0.521327793598175,
|
| 1484 |
+
0.9999769926071167,
|
| 1485 |
+
0.9942213296890259,
|
| 1486 |
+
0.999913215637207,
|
| 1487 |
+
0.9997870326042175,
|
| 1488 |
+
0.9944077730178833,
|
| 1489 |
+
0.9233108758926392,
|
| 1490 |
+
0.006665369495749474,
|
| 1491 |
+
0.994364857673645,
|
| 1492 |
+
0.99979168176651,
|
| 1493 |
+
0.13727723062038422,
|
| 1494 |
+
0.8380267024040222,
|
| 1495 |
+
0.999836802482605,
|
| 1496 |
+
0.6078657507896423,
|
| 1497 |
+
0.9981252551078796,
|
| 1498 |
+
0.9990299940109253,
|
| 1499 |
+
0.9997946619987488,
|
| 1500 |
+
0.7654120326042175,
|
| 1501 |
+
0.9162885546684265,
|
| 1502 |
+
0.032905738800764084,
|
| 1503 |
+
0.8361085653305054,
|
| 1504 |
+
0.43142011761665344,
|
| 1505 |
+
0.9244018793106079,
|
| 1506 |
+
0.9802189469337463,
|
| 1507 |
+
0.9970953464508057,
|
| 1508 |
+
0.28045544028282166,
|
| 1509 |
+
0.9703474640846252,
|
| 1510 |
+
0.9523987174034119,
|
| 1511 |
+
0.9937481880187988,
|
| 1512 |
+
0.6890085935592651,
|
| 1513 |
+
0.9996067881584167,
|
| 1514 |
+
0.9997078776359558,
|
| 1515 |
+
0.018358726054430008,
|
| 1516 |
+
0.7913146615028381,
|
| 1517 |
+
0.9718425869941711,
|
| 1518 |
+
0.051817361265420914,
|
| 1519 |
+
0.9650564193725586,
|
| 1520 |
+
0.039147596806287766,
|
| 1521 |
+
0.9999592304229736,
|
| 1522 |
+
0.9997337460517883,
|
| 1523 |
+
0.9772196412086487,
|
| 1524 |
+
0.9988301396369934,
|
| 1525 |
+
0.006023730617016554,
|
| 1526 |
+
0.9997532963752747,
|
| 1527 |
+
0.9996465444564819,
|
| 1528 |
+
0.8749299645423889,
|
| 1529 |
+
0.9997159838676453,
|
| 1530 |
+
0.999969482421875,
|
| 1531 |
+
0.47189682722091675,
|
| 1532 |
+
0.9998407363891602,
|
| 1533 |
+
0.9996135830879211,
|
| 1534 |
+
0.992363691329956,
|
| 1535 |
+
0.9981967806816101,
|
| 1536 |
+
0.999813973903656,
|
| 1537 |
+
0.9998838901519775,
|
| 1538 |
+
0.5446488857269287,
|
| 1539 |
+
0.0003066202625632286,
|
| 1540 |
+
0.999956488609314,
|
| 1541 |
+
0.9962054491043091,
|
| 1542 |
+
0.99986732006073,
|
| 1543 |
+
0.9834662079811096,
|
| 1544 |
+
0.9997921586036682,
|
| 1545 |
+
0.9902730584144592,
|
| 1546 |
+
0.9985108971595764,
|
| 1547 |
+
0.9999505281448364,
|
| 1548 |
+
0.9998027682304382,
|
| 1549 |
+
0.9723180532455444,
|
| 1550 |
+
0.9994682669639587,
|
| 1551 |
+
0.9999501705169678,
|
| 1552 |
+
0.9999010562896729,
|
| 1553 |
+
0.9973589777946472,
|
| 1554 |
+
0.9999006986618042,
|
| 1555 |
+
0.9960615038871765,
|
| 1556 |
+
0.9998500347137451,
|
| 1557 |
+
0.9986233711242676,
|
| 1558 |
+
0.008311701007187366,
|
| 1559 |
+
0.9997389912605286,
|
| 1560 |
+
0.017625167965888977,
|
| 1561 |
+
0.0008023975533433259,
|
| 1562 |
+
0.9993647933006287,
|
| 1563 |
+
0.9838919639587402,
|
| 1564 |
+
0.43106237053871155,
|
| 1565 |
+
0.0007903283112682402,
|
| 1566 |
+
0.9999732971191406,
|
| 1567 |
+
0.00020203986787237227,
|
| 1568 |
+
0.9997217059135437,
|
| 1569 |
+
0.9999573230743408,
|
| 1570 |
+
0.001714992569759488,
|
| 1571 |
+
0.9998447895050049,
|
| 1572 |
+
0.9997473359107971,
|
| 1573 |
+
0.9999877214431763,
|
| 1574 |
+
0.9988928437232971,
|
| 1575 |
+
0.9996260404586792,
|
| 1576 |
+
0.9999154806137085,
|
| 1577 |
+
0.9983515739440918,
|
| 1578 |
+
0.9881762266159058
|
| 1579 |
+
],
|
| 1580 |
+
"eval_code_is_correct_runtime": 67.7436,
|
| 1581 |
+
"eval_code_is_correct_samples_per_second": 1.476,
|
| 1582 |
+
"eval_code_is_correct_steps_per_second": 0.059,
|
| 1583 |
+
"epoch": 7.89,
|
| 1584 |
+
"step": 150
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"train_runtime": 7451.7189,
|
| 1588 |
+
"train_samples_per_second": 0.644,
|
| 1589 |
+
"train_steps_per_second": 0.02,
|
| 1590 |
+
"total_flos": 0.0,
|
| 1591 |
+
"train_loss": 0.41071448507408304,
|
| 1592 |
+
"epoch": 7.89,
|
| 1593 |
+
"step": 150
|
| 1594 |
+
}
|
| 1595 |
+
]
|