ptsv/olmo-7b-lora_tinystories_upsampled_tom_100k
Browse files- README.md +65 -0
- adapter_config.json +38 -0
- adapter_model.safetensors +3 -0
- trainer_state.json +3350 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: allenai/OLMo-7B-0724-hf
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: tinystories_upsampled_tom_100k
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/ptsvil/tom-training/runs/buhb1me4)
|
| 16 |
+
# tinystories_upsampled_tom_100k
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [allenai/OLMo-7B-0724-hf](https://huggingface.co/allenai/OLMo-7B-0724-hf) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.4570
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.002
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 16
|
| 44 |
+
- total_train_batch_size: 256
|
| 45 |
+
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 1
|
| 48 |
+
- num_epochs: 3
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
+
| 23.798 | 1.2784 | 400 | 1.4876 |
|
| 56 |
+
| 23.1742 | 2.5568 | 800 | 1.4636 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
### Framework versions
|
| 60 |
+
|
| 61 |
+
- PEFT 0.14.0
|
| 62 |
+
- Transformers 4.47.0
|
| 63 |
+
- Pytorch 2.4.1+cu121
|
| 64 |
+
- Datasets 3.2.0
|
| 65 |
+
- Tokenizers 0.21.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "allenai/OLMo-7B-0724-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": false,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 16,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.1,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 64,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"o_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
+
"lm_head",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"down_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_rslora": false
|
| 38 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65d9011dcaba0141eb382b85e18d20f542ce3e2b6b96586777beb7493bd65bd5
|
| 3 |
+
size 1477800176
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3350 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.992,
|
| 5 |
+
"eval_steps": 400,
|
| 6 |
+
"global_step": 936,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0064,
|
| 13 |
+
"grad_norm": 0.23147642612457275,
|
| 14 |
+
"learning_rate": 0.001997860962566845,
|
| 15 |
+
"loss": 29.0583,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0128,
|
| 20 |
+
"grad_norm": 1.181070327758789,
|
| 21 |
+
"learning_rate": 0.001993582887700535,
|
| 22 |
+
"loss": 28.9384,
|
| 23 |
+
"step": 4
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0192,
|
| 27 |
+
"grad_norm": 1.9193989038467407,
|
| 28 |
+
"learning_rate": 0.0019893048128342247,
|
| 29 |
+
"loss": 28.118,
|
| 30 |
+
"step": 6
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0256,
|
| 34 |
+
"grad_norm": 4.55759334564209,
|
| 35 |
+
"learning_rate": 0.0019850267379679146,
|
| 36 |
+
"loss": 28.2661,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.032,
|
| 41 |
+
"grad_norm": 6.3390374183654785,
|
| 42 |
+
"learning_rate": 0.0019807486631016045,
|
| 43 |
+
"loss": 27.4742,
|
| 44 |
+
"step": 10
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0384,
|
| 48 |
+
"grad_norm": 4.0472869873046875,
|
| 49 |
+
"learning_rate": 0.0019764705882352944,
|
| 50 |
+
"loss": 27.5481,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0448,
|
| 55 |
+
"grad_norm": Infinity,
|
| 56 |
+
"learning_rate": 0.0019764705882352944,
|
| 57 |
+
"loss": 691.2838,
|
| 58 |
+
"step": 14
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0512,
|
| 62 |
+
"grad_norm": 596.6735229492188,
|
| 63 |
+
"learning_rate": 0.001972192513368984,
|
| 64 |
+
"loss": 614.0375,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0576,
|
| 69 |
+
"grad_norm": 374.73675537109375,
|
| 70 |
+
"learning_rate": 0.001967914438502674,
|
| 71 |
+
"loss": 234.3992,
|
| 72 |
+
"step": 18
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.064,
|
| 76 |
+
"grad_norm": 28.9688777923584,
|
| 77 |
+
"learning_rate": 0.0019636363636363636,
|
| 78 |
+
"loss": 41.9122,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0704,
|
| 83 |
+
"grad_norm": 169.22000122070312,
|
| 84 |
+
"learning_rate": 0.0019593582887700535,
|
| 85 |
+
"loss": 41.3339,
|
| 86 |
+
"step": 22
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.0768,
|
| 90 |
+
"grad_norm": 12.487041473388672,
|
| 91 |
+
"learning_rate": 0.0019550802139037433,
|
| 92 |
+
"loss": 30.189,
|
| 93 |
+
"step": 24
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.0832,
|
| 97 |
+
"grad_norm": 8.636120796203613,
|
| 98 |
+
"learning_rate": 0.001950802139037433,
|
| 99 |
+
"loss": 27.9389,
|
| 100 |
+
"step": 26
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0896,
|
| 104 |
+
"grad_norm": 4.744749069213867,
|
| 105 |
+
"learning_rate": 0.001946524064171123,
|
| 106 |
+
"loss": 27.1649,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.096,
|
| 111 |
+
"grad_norm": 7.722327709197998,
|
| 112 |
+
"learning_rate": 0.0019422459893048128,
|
| 113 |
+
"loss": 27.3547,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1024,
|
| 118 |
+
"grad_norm": 9.445578575134277,
|
| 119 |
+
"learning_rate": 0.0019379679144385026,
|
| 120 |
+
"loss": 26.9296,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1088,
|
| 125 |
+
"grad_norm": 6.174092769622803,
|
| 126 |
+
"learning_rate": 0.0019336898395721925,
|
| 127 |
+
"loss": 27.1266,
|
| 128 |
+
"step": 34
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1152,
|
| 132 |
+
"grad_norm": 356.22625732421875,
|
| 133 |
+
"learning_rate": 0.0019294117647058824,
|
| 134 |
+
"loss": 45.6243,
|
| 135 |
+
"step": 36
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1216,
|
| 139 |
+
"grad_norm": 23.33014488220215,
|
| 140 |
+
"learning_rate": 0.001925133689839572,
|
| 141 |
+
"loss": 32.972,
|
| 142 |
+
"step": 38
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.128,
|
| 146 |
+
"grad_norm": 10.953542709350586,
|
| 147 |
+
"learning_rate": 0.0019208556149732622,
|
| 148 |
+
"loss": 27.1236,
|
| 149 |
+
"step": 40
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.1344,
|
| 153 |
+
"grad_norm": 6.473776340484619,
|
| 154 |
+
"learning_rate": 0.0019165775401069518,
|
| 155 |
+
"loss": 26.9502,
|
| 156 |
+
"step": 42
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.1408,
|
| 160 |
+
"grad_norm": Infinity,
|
| 161 |
+
"learning_rate": 0.001914438502673797,
|
| 162 |
+
"loss": 44.8032,
|
| 163 |
+
"step": 44
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1472,
|
| 167 |
+
"grad_norm": 182.4479217529297,
|
| 168 |
+
"learning_rate": 0.0019101604278074866,
|
| 169 |
+
"loss": 56.3821,
|
| 170 |
+
"step": 46
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.1536,
|
| 174 |
+
"grad_norm": 24.16608238220215,
|
| 175 |
+
"learning_rate": 0.0019058823529411763,
|
| 176 |
+
"loss": 31.7551,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.16,
|
| 181 |
+
"grad_norm": 13.420609474182129,
|
| 182 |
+
"learning_rate": 0.0019016042780748664,
|
| 183 |
+
"loss": 26.8265,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.1664,
|
| 188 |
+
"grad_norm": 6.592583179473877,
|
| 189 |
+
"learning_rate": 0.001897326203208556,
|
| 190 |
+
"loss": 26.9479,
|
| 191 |
+
"step": 52
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.1728,
|
| 195 |
+
"grad_norm": 18.330659866333008,
|
| 196 |
+
"learning_rate": 0.001893048128342246,
|
| 197 |
+
"loss": 26.9247,
|
| 198 |
+
"step": 54
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.1792,
|
| 202 |
+
"grad_norm": 10.113327980041504,
|
| 203 |
+
"learning_rate": 0.0018887700534759358,
|
| 204 |
+
"loss": 26.654,
|
| 205 |
+
"step": 56
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.1856,
|
| 209 |
+
"grad_norm": Infinity,
|
| 210 |
+
"learning_rate": 0.0018866310160427808,
|
| 211 |
+
"loss": 158.5872,
|
| 212 |
+
"step": 58
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.192,
|
| 216 |
+
"grad_norm": 714.9314575195312,
|
| 217 |
+
"learning_rate": 0.0018823529411764706,
|
| 218 |
+
"loss": 245.1731,
|
| 219 |
+
"step": 60
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1984,
|
| 223 |
+
"grad_norm": 20.074459075927734,
|
| 224 |
+
"learning_rate": 0.0018780748663101605,
|
| 225 |
+
"loss": 54.0979,
|
| 226 |
+
"step": 62
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2048,
|
| 230 |
+
"grad_norm": 6.04124641418457,
|
| 231 |
+
"learning_rate": 0.0018737967914438502,
|
| 232 |
+
"loss": 26.655,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.2112,
|
| 237 |
+
"grad_norm": 4.1345906257629395,
|
| 238 |
+
"learning_rate": 0.0018695187165775403,
|
| 239 |
+
"loss": 26.5224,
|
| 240 |
+
"step": 66
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.2176,
|
| 244 |
+
"grad_norm": 5.253076553344727,
|
| 245 |
+
"learning_rate": 0.00186524064171123,
|
| 246 |
+
"loss": 26.2523,
|
| 247 |
+
"step": 68
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.224,
|
| 251 |
+
"grad_norm": 4.040248394012451,
|
| 252 |
+
"learning_rate": 0.00186096256684492,
|
| 253 |
+
"loss": 26.5548,
|
| 254 |
+
"step": 70
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.2304,
|
| 258 |
+
"grad_norm": 4.1401262283325195,
|
| 259 |
+
"learning_rate": 0.0018566844919786097,
|
| 260 |
+
"loss": 26.3328,
|
| 261 |
+
"step": 72
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2368,
|
| 265 |
+
"grad_norm": 4.546834945678711,
|
| 266 |
+
"learning_rate": 0.0018524064171122994,
|
| 267 |
+
"loss": 26.1653,
|
| 268 |
+
"step": 74
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.2432,
|
| 272 |
+
"grad_norm": 3.73606276512146,
|
| 273 |
+
"learning_rate": 0.0018481283422459895,
|
| 274 |
+
"loss": 26.4023,
|
| 275 |
+
"step": 76
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2496,
|
| 279 |
+
"grad_norm": 3.841369390487671,
|
| 280 |
+
"learning_rate": 0.0018438502673796791,
|
| 281 |
+
"loss": 26.2402,
|
| 282 |
+
"step": 78
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.256,
|
| 286 |
+
"grad_norm": 3.3648502826690674,
|
| 287 |
+
"learning_rate": 0.001839572192513369,
|
| 288 |
+
"loss": 26.143,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.2624,
|
| 293 |
+
"grad_norm": 3.7182576656341553,
|
| 294 |
+
"learning_rate": 0.0018352941176470589,
|
| 295 |
+
"loss": 26.5052,
|
| 296 |
+
"step": 82
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.2688,
|
| 300 |
+
"grad_norm": 3.4634881019592285,
|
| 301 |
+
"learning_rate": 0.0018310160427807488,
|
| 302 |
+
"loss": 26.2055,
|
| 303 |
+
"step": 84
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.2752,
|
| 307 |
+
"grad_norm": 3.5876669883728027,
|
| 308 |
+
"learning_rate": 0.0018267379679144384,
|
| 309 |
+
"loss": 26.3232,
|
| 310 |
+
"step": 86
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.2816,
|
| 314 |
+
"grad_norm": 3.0892839431762695,
|
| 315 |
+
"learning_rate": 0.0018224598930481285,
|
| 316 |
+
"loss": 26.0274,
|
| 317 |
+
"step": 88
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.288,
|
| 321 |
+
"grad_norm": 3.4667418003082275,
|
| 322 |
+
"learning_rate": 0.0018181818181818182,
|
| 323 |
+
"loss": 26.0062,
|
| 324 |
+
"step": 90
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2944,
|
| 328 |
+
"grad_norm": 3.052298069000244,
|
| 329 |
+
"learning_rate": 0.001813903743315508,
|
| 330 |
+
"loss": 26.2114,
|
| 331 |
+
"step": 92
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3008,
|
| 335 |
+
"grad_norm": 2.7124950885772705,
|
| 336 |
+
"learning_rate": 0.001809625668449198,
|
| 337 |
+
"loss": 25.9583,
|
| 338 |
+
"step": 94
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.3072,
|
| 342 |
+
"grad_norm": 2.713899612426758,
|
| 343 |
+
"learning_rate": 0.0018053475935828878,
|
| 344 |
+
"loss": 26.0525,
|
| 345 |
+
"step": 96
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.3136,
|
| 349 |
+
"grad_norm": 2.6182234287261963,
|
| 350 |
+
"learning_rate": 0.0018010695187165775,
|
| 351 |
+
"loss": 25.4642,
|
| 352 |
+
"step": 98
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.32,
|
| 356 |
+
"grad_norm": 2.3585636615753174,
|
| 357 |
+
"learning_rate": 0.0017967914438502676,
|
| 358 |
+
"loss": 26.0951,
|
| 359 |
+
"step": 100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.3264,
|
| 363 |
+
"grad_norm": 2.5994300842285156,
|
| 364 |
+
"learning_rate": 0.0017925133689839572,
|
| 365 |
+
"loss": 26.1542,
|
| 366 |
+
"step": 102
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.3328,
|
| 370 |
+
"grad_norm": 2.327500581741333,
|
| 371 |
+
"learning_rate": 0.0017882352941176471,
|
| 372 |
+
"loss": 26.0515,
|
| 373 |
+
"step": 104
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.3392,
|
| 377 |
+
"grad_norm": 2.2460238933563232,
|
| 378 |
+
"learning_rate": 0.001783957219251337,
|
| 379 |
+
"loss": 25.722,
|
| 380 |
+
"step": 106
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.3456,
|
| 384 |
+
"grad_norm": 2.0208640098571777,
|
| 385 |
+
"learning_rate": 0.0017796791443850269,
|
| 386 |
+
"loss": 25.8647,
|
| 387 |
+
"step": 108
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.352,
|
| 391 |
+
"grad_norm": 2.1272950172424316,
|
| 392 |
+
"learning_rate": 0.0017754010695187165,
|
| 393 |
+
"loss": 25.8338,
|
| 394 |
+
"step": 110
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.3584,
|
| 398 |
+
"grad_norm": 1.743446946144104,
|
| 399 |
+
"learning_rate": 0.0017711229946524066,
|
| 400 |
+
"loss": 25.6917,
|
| 401 |
+
"step": 112
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3648,
|
| 405 |
+
"grad_norm": 1.884177565574646,
|
| 406 |
+
"learning_rate": 0.0017668449197860963,
|
| 407 |
+
"loss": 25.492,
|
| 408 |
+
"step": 114
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3712,
|
| 412 |
+
"grad_norm": 1.5283397436141968,
|
| 413 |
+
"learning_rate": 0.001762566844919786,
|
| 414 |
+
"loss": 25.7483,
|
| 415 |
+
"step": 116
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.3776,
|
| 419 |
+
"grad_norm": 1.838241457939148,
|
| 420 |
+
"learning_rate": 0.001758288770053476,
|
| 421 |
+
"loss": 26.1345,
|
| 422 |
+
"step": 118
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.384,
|
| 426 |
+
"grad_norm": 1.7873716354370117,
|
| 427 |
+
"learning_rate": 0.0017540106951871657,
|
| 428 |
+
"loss": 25.5023,
|
| 429 |
+
"step": 120
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3904,
|
| 433 |
+
"grad_norm": 1.707553505897522,
|
| 434 |
+
"learning_rate": 0.0017497326203208556,
|
| 435 |
+
"loss": 25.6723,
|
| 436 |
+
"step": 122
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.3968,
|
| 440 |
+
"grad_norm": 1.5225554704666138,
|
| 441 |
+
"learning_rate": 0.0017454545454545455,
|
| 442 |
+
"loss": 25.4451,
|
| 443 |
+
"step": 124
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.4032,
|
| 447 |
+
"grad_norm": 1.5387077331542969,
|
| 448 |
+
"learning_rate": 0.0017411764705882354,
|
| 449 |
+
"loss": 24.9427,
|
| 450 |
+
"step": 126
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.4096,
|
| 454 |
+
"grad_norm": 1.4218844175338745,
|
| 455 |
+
"learning_rate": 0.001736898395721925,
|
| 456 |
+
"loss": 25.2159,
|
| 457 |
+
"step": 128
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.416,
|
| 461 |
+
"grad_norm": 1.4706506729125977,
|
| 462 |
+
"learning_rate": 0.0017326203208556151,
|
| 463 |
+
"loss": 25.5617,
|
| 464 |
+
"step": 130
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.4224,
|
| 468 |
+
"grad_norm": 1.6522170305252075,
|
| 469 |
+
"learning_rate": 0.0017283422459893048,
|
| 470 |
+
"loss": 25.4537,
|
| 471 |
+
"step": 132
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.4288,
|
| 475 |
+
"grad_norm": 1.5547223091125488,
|
| 476 |
+
"learning_rate": 0.0017240641711229947,
|
| 477 |
+
"loss": 25.126,
|
| 478 |
+
"step": 134
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.4352,
|
| 482 |
+
"grad_norm": 1.2542740106582642,
|
| 483 |
+
"learning_rate": 0.0017197860962566845,
|
| 484 |
+
"loss": 25.3198,
|
| 485 |
+
"step": 136
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.4416,
|
| 489 |
+
"grad_norm": 1.3993158340454102,
|
| 490 |
+
"learning_rate": 0.0017155080213903744,
|
| 491 |
+
"loss": 25.4372,
|
| 492 |
+
"step": 138
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.448,
|
| 496 |
+
"grad_norm": 1.3659427165985107,
|
| 497 |
+
"learning_rate": 0.001711229946524064,
|
| 498 |
+
"loss": 25.0459,
|
| 499 |
+
"step": 140
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.4544,
|
| 503 |
+
"grad_norm": 1.124814748764038,
|
| 504 |
+
"learning_rate": 0.0017069518716577542,
|
| 505 |
+
"loss": 25.1648,
|
| 506 |
+
"step": 142
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.4608,
|
| 510 |
+
"grad_norm": 1.0325303077697754,
|
| 511 |
+
"learning_rate": 0.0017026737967914438,
|
| 512 |
+
"loss": 25.4647,
|
| 513 |
+
"step": 144
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.4672,
|
| 517 |
+
"grad_norm": 1.2640491724014282,
|
| 518 |
+
"learning_rate": 0.0016983957219251337,
|
| 519 |
+
"loss": 25.0149,
|
| 520 |
+
"step": 146
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.4736,
|
| 524 |
+
"grad_norm": 1.0942180156707764,
|
| 525 |
+
"learning_rate": 0.0016941176470588236,
|
| 526 |
+
"loss": 25.0814,
|
| 527 |
+
"step": 148
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.48,
|
| 531 |
+
"grad_norm": 1.2712141275405884,
|
| 532 |
+
"learning_rate": 0.0016898395721925135,
|
| 533 |
+
"loss": 25.0341,
|
| 534 |
+
"step": 150
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4864,
|
| 538 |
+
"grad_norm": 1.2034132480621338,
|
| 539 |
+
"learning_rate": 0.0016855614973262031,
|
| 540 |
+
"loss": 25.0647,
|
| 541 |
+
"step": 152
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.4928,
|
| 545 |
+
"grad_norm": 1.2348299026489258,
|
| 546 |
+
"learning_rate": 0.0016812834224598932,
|
| 547 |
+
"loss": 24.7844,
|
| 548 |
+
"step": 154
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.4992,
|
| 552 |
+
"grad_norm": 1.691644549369812,
|
| 553 |
+
"learning_rate": 0.001677005347593583,
|
| 554 |
+
"loss": 24.7689,
|
| 555 |
+
"step": 156
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.5056,
|
| 559 |
+
"grad_norm": 1.4753830432891846,
|
| 560 |
+
"learning_rate": 0.0016727272727272726,
|
| 561 |
+
"loss": 24.941,
|
| 562 |
+
"step": 158
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.512,
|
| 566 |
+
"grad_norm": 0.9928715229034424,
|
| 567 |
+
"learning_rate": 0.0016684491978609627,
|
| 568 |
+
"loss": 25.0275,
|
| 569 |
+
"step": 160
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.5184,
|
| 573 |
+
"grad_norm": 1.1669100522994995,
|
| 574 |
+
"learning_rate": 0.0016641711229946523,
|
| 575 |
+
"loss": 24.9014,
|
| 576 |
+
"step": 162
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.5248,
|
| 580 |
+
"grad_norm": 1.39118230342865,
|
| 581 |
+
"learning_rate": 0.0016598930481283422,
|
| 582 |
+
"loss": 24.6339,
|
| 583 |
+
"step": 164
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.5312,
|
| 587 |
+
"grad_norm": 1.2533951997756958,
|
| 588 |
+
"learning_rate": 0.001655614973262032,
|
| 589 |
+
"loss": 24.6086,
|
| 590 |
+
"step": 166
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.5376,
|
| 594 |
+
"grad_norm": 0.9174675941467285,
|
| 595 |
+
"learning_rate": 0.001651336898395722,
|
| 596 |
+
"loss": 25.0262,
|
| 597 |
+
"step": 168
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.544,
|
| 601 |
+
"grad_norm": 0.9981193542480469,
|
| 602 |
+
"learning_rate": 0.0016470588235294116,
|
| 603 |
+
"loss": 24.6074,
|
| 604 |
+
"step": 170
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.5504,
|
| 608 |
+
"grad_norm": 1.4740686416625977,
|
| 609 |
+
"learning_rate": 0.0016427807486631017,
|
| 610 |
+
"loss": 24.5649,
|
| 611 |
+
"step": 172
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.5568,
|
| 615 |
+
"grad_norm": 1.0988154411315918,
|
| 616 |
+
"learning_rate": 0.0016385026737967914,
|
| 617 |
+
"loss": 24.2709,
|
| 618 |
+
"step": 174
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.5632,
|
| 622 |
+
"grad_norm": 1.1431447267532349,
|
| 623 |
+
"learning_rate": 0.0016342245989304813,
|
| 624 |
+
"loss": 24.7044,
|
| 625 |
+
"step": 176
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5696,
|
| 629 |
+
"grad_norm": 1.2967267036437988,
|
| 630 |
+
"learning_rate": 0.0016299465240641711,
|
| 631 |
+
"loss": 24.803,
|
| 632 |
+
"step": 178
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.576,
|
| 636 |
+
"grad_norm": 1.1269863843917847,
|
| 637 |
+
"learning_rate": 0.001625668449197861,
|
| 638 |
+
"loss": 24.4945,
|
| 639 |
+
"step": 180
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5824,
|
| 643 |
+
"grad_norm": 0.9064795970916748,
|
| 644 |
+
"learning_rate": 0.0016213903743315507,
|
| 645 |
+
"loss": 24.5421,
|
| 646 |
+
"step": 182
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.5888,
|
| 650 |
+
"grad_norm": 0.9420700669288635,
|
| 651 |
+
"learning_rate": 0.0016171122994652408,
|
| 652 |
+
"loss": 24.494,
|
| 653 |
+
"step": 184
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5952,
|
| 657 |
+
"grad_norm": 1.1436915397644043,
|
| 658 |
+
"learning_rate": 0.0016128342245989304,
|
| 659 |
+
"loss": 24.6417,
|
| 660 |
+
"step": 186
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.6016,
|
| 664 |
+
"grad_norm": 0.9322279691696167,
|
| 665 |
+
"learning_rate": 0.0016085561497326205,
|
| 666 |
+
"loss": 24.6154,
|
| 667 |
+
"step": 188
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.608,
|
| 671 |
+
"grad_norm": 1.0101568698883057,
|
| 672 |
+
"learning_rate": 0.0016042780748663102,
|
| 673 |
+
"loss": 24.4768,
|
| 674 |
+
"step": 190
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6144,
|
| 678 |
+
"grad_norm": 1.3874669075012207,
|
| 679 |
+
"learning_rate": 0.0016,
|
| 680 |
+
"loss": 24.6752,
|
| 681 |
+
"step": 192
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.6208,
|
| 685 |
+
"grad_norm": 1.0779438018798828,
|
| 686 |
+
"learning_rate": 0.00159572192513369,
|
| 687 |
+
"loss": 24.7572,
|
| 688 |
+
"step": 194
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.6272,
|
| 692 |
+
"grad_norm": 1.3621560335159302,
|
| 693 |
+
"learning_rate": 0.0015914438502673798,
|
| 694 |
+
"loss": 24.5775,
|
| 695 |
+
"step": 196
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.6336,
|
| 699 |
+
"grad_norm": 1.291939616203308,
|
| 700 |
+
"learning_rate": 0.0015871657754010695,
|
| 701 |
+
"loss": 24.4171,
|
| 702 |
+
"step": 198
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.64,
|
| 706 |
+
"grad_norm": 19.172954559326172,
|
| 707 |
+
"learning_rate": 0.0015828877005347596,
|
| 708 |
+
"loss": 30.6558,
|
| 709 |
+
"step": 200
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.6464,
|
| 713 |
+
"grad_norm": 4.52994441986084,
|
| 714 |
+
"learning_rate": 0.0015786096256684493,
|
| 715 |
+
"loss": 25.1351,
|
| 716 |
+
"step": 202
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.6528,
|
| 720 |
+
"grad_norm": 3.1266472339630127,
|
| 721 |
+
"learning_rate": 0.001574331550802139,
|
| 722 |
+
"loss": 24.8543,
|
| 723 |
+
"step": 204
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.6592,
|
| 727 |
+
"grad_norm": 2.4678471088409424,
|
| 728 |
+
"learning_rate": 0.001570053475935829,
|
| 729 |
+
"loss": 24.716,
|
| 730 |
+
"step": 206
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.6656,
|
| 734 |
+
"grad_norm": 3.5065557956695557,
|
| 735 |
+
"learning_rate": 0.0015657754010695187,
|
| 736 |
+
"loss": 24.6532,
|
| 737 |
+
"step": 208
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.672,
|
| 741 |
+
"grad_norm": 2.501286745071411,
|
| 742 |
+
"learning_rate": 0.0015614973262032086,
|
| 743 |
+
"loss": 24.7766,
|
| 744 |
+
"step": 210
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.6784,
|
| 748 |
+
"grad_norm": 1.9249541759490967,
|
| 749 |
+
"learning_rate": 0.0015572192513368984,
|
| 750 |
+
"loss": 24.2869,
|
| 751 |
+
"step": 212
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.6848,
|
| 755 |
+
"grad_norm": 3.193232297897339,
|
| 756 |
+
"learning_rate": 0.0015529411764705883,
|
| 757 |
+
"loss": 24.7769,
|
| 758 |
+
"step": 214
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.6912,
|
| 762 |
+
"grad_norm": 2.367741823196411,
|
| 763 |
+
"learning_rate": 0.001548663101604278,
|
| 764 |
+
"loss": 24.7073,
|
| 765 |
+
"step": 216
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.6976,
|
| 769 |
+
"grad_norm": 1.5215927362442017,
|
| 770 |
+
"learning_rate": 0.001544385026737968,
|
| 771 |
+
"loss": 24.8652,
|
| 772 |
+
"step": 218
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.704,
|
| 776 |
+
"grad_norm": 1.8906418085098267,
|
| 777 |
+
"learning_rate": 0.0015401069518716577,
|
| 778 |
+
"loss": 24.7487,
|
| 779 |
+
"step": 220
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.7104,
|
| 783 |
+
"grad_norm": 1.5913176536560059,
|
| 784 |
+
"learning_rate": 0.0015358288770053476,
|
| 785 |
+
"loss": 25.017,
|
| 786 |
+
"step": 222
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.7168,
|
| 790 |
+
"grad_norm": 1.6209039688110352,
|
| 791 |
+
"learning_rate": 0.0015315508021390375,
|
| 792 |
+
"loss": 24.339,
|
| 793 |
+
"step": 224
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.7232,
|
| 797 |
+
"grad_norm": 1.5647910833358765,
|
| 798 |
+
"learning_rate": 0.0015272727272727274,
|
| 799 |
+
"loss": 24.1431,
|
| 800 |
+
"step": 226
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.7296,
|
| 804 |
+
"grad_norm": 1.111008882522583,
|
| 805 |
+
"learning_rate": 0.001522994652406417,
|
| 806 |
+
"loss": 24.3126,
|
| 807 |
+
"step": 228
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.736,
|
| 811 |
+
"grad_norm": 1.259020209312439,
|
| 812 |
+
"learning_rate": 0.0015187165775401071,
|
| 813 |
+
"loss": 24.1569,
|
| 814 |
+
"step": 230
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.7424,
|
| 818 |
+
"grad_norm": 1.2711575031280518,
|
| 819 |
+
"learning_rate": 0.0015144385026737968,
|
| 820 |
+
"loss": 24.4551,
|
| 821 |
+
"step": 232
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.7488,
|
| 825 |
+
"grad_norm": 1.1747275590896606,
|
| 826 |
+
"learning_rate": 0.0015101604278074867,
|
| 827 |
+
"loss": 24.2954,
|
| 828 |
+
"step": 234
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.7552,
|
| 832 |
+
"grad_norm": 1.3041143417358398,
|
| 833 |
+
"learning_rate": 0.0015058823529411766,
|
| 834 |
+
"loss": 24.3246,
|
| 835 |
+
"step": 236
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.7616,
|
| 839 |
+
"grad_norm": 1.2481331825256348,
|
| 840 |
+
"learning_rate": 0.0015016042780748664,
|
| 841 |
+
"loss": 24.3238,
|
| 842 |
+
"step": 238
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.768,
|
| 846 |
+
"grad_norm": 1.1186060905456543,
|
| 847 |
+
"learning_rate": 0.001497326203208556,
|
| 848 |
+
"loss": 24.5642,
|
| 849 |
+
"step": 240
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.7744,
|
| 853 |
+
"grad_norm": 1.3123741149902344,
|
| 854 |
+
"learning_rate": 0.0014930481283422462,
|
| 855 |
+
"loss": 24.5782,
|
| 856 |
+
"step": 242
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.7808,
|
| 860 |
+
"grad_norm": 1.0362588167190552,
|
| 861 |
+
"learning_rate": 0.0014887700534759359,
|
| 862 |
+
"loss": 24.519,
|
| 863 |
+
"step": 244
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.7872,
|
| 867 |
+
"grad_norm": 0.9986498355865479,
|
| 868 |
+
"learning_rate": 0.0014844919786096255,
|
| 869 |
+
"loss": 24.6729,
|
| 870 |
+
"step": 246
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.7936,
|
| 874 |
+
"grad_norm": 1.0757042169570923,
|
| 875 |
+
"learning_rate": 0.0014802139037433156,
|
| 876 |
+
"loss": 24.2834,
|
| 877 |
+
"step": 248
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.8,
|
| 881 |
+
"grad_norm": 1.1017972230911255,
|
| 882 |
+
"learning_rate": 0.0014759358288770053,
|
| 883 |
+
"loss": 23.9501,
|
| 884 |
+
"step": 250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.8064,
|
| 888 |
+
"grad_norm": 1.1957108974456787,
|
| 889 |
+
"learning_rate": 0.0014716577540106952,
|
| 890 |
+
"loss": 24.0922,
|
| 891 |
+
"step": 252
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.8128,
|
| 895 |
+
"grad_norm": 1.1655299663543701,
|
| 896 |
+
"learning_rate": 0.001467379679144385,
|
| 897 |
+
"loss": 24.3735,
|
| 898 |
+
"step": 254
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.8192,
|
| 902 |
+
"grad_norm": 0.9843050837516785,
|
| 903 |
+
"learning_rate": 0.001463101604278075,
|
| 904 |
+
"loss": 24.1656,
|
| 905 |
+
"step": 256
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.8256,
|
| 909 |
+
"grad_norm": 1.0374311208724976,
|
| 910 |
+
"learning_rate": 0.0014588235294117646,
|
| 911 |
+
"loss": 24.2207,
|
| 912 |
+
"step": 258
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.832,
|
| 916 |
+
"grad_norm": 0.9728087186813354,
|
| 917 |
+
"learning_rate": 0.0014545454545454547,
|
| 918 |
+
"loss": 24.1451,
|
| 919 |
+
"step": 260
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.8384,
|
| 923 |
+
"grad_norm": 0.9153401255607605,
|
| 924 |
+
"learning_rate": 0.0014502673796791443,
|
| 925 |
+
"loss": 24.0903,
|
| 926 |
+
"step": 262
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.8448,
|
| 930 |
+
"grad_norm": 1.1150263547897339,
|
| 931 |
+
"learning_rate": 0.0014459893048128342,
|
| 932 |
+
"loss": 24.375,
|
| 933 |
+
"step": 264
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.8512,
|
| 937 |
+
"grad_norm": 1.2261894941329956,
|
| 938 |
+
"learning_rate": 0.001441711229946524,
|
| 939 |
+
"loss": 24.5365,
|
| 940 |
+
"step": 266
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.8576,
|
| 944 |
+
"grad_norm": 0.8708057403564453,
|
| 945 |
+
"learning_rate": 0.001437433155080214,
|
| 946 |
+
"loss": 24.0552,
|
| 947 |
+
"step": 268
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.864,
|
| 951 |
+
"grad_norm": 0.8445040583610535,
|
| 952 |
+
"learning_rate": 0.0014331550802139036,
|
| 953 |
+
"loss": 24.2762,
|
| 954 |
+
"step": 270
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.8704,
|
| 958 |
+
"grad_norm": 1.1743762493133545,
|
| 959 |
+
"learning_rate": 0.0014288770053475937,
|
| 960 |
+
"loss": 24.4677,
|
| 961 |
+
"step": 272
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.8768,
|
| 965 |
+
"grad_norm": 1.5417506694793701,
|
| 966 |
+
"learning_rate": 0.0014245989304812834,
|
| 967 |
+
"loss": 24.3304,
|
| 968 |
+
"step": 274
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.8832,
|
| 972 |
+
"grad_norm": 1.1955397129058838,
|
| 973 |
+
"learning_rate": 0.0014203208556149733,
|
| 974 |
+
"loss": 24.2557,
|
| 975 |
+
"step": 276
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.8896,
|
| 979 |
+
"grad_norm": 0.8730282187461853,
|
| 980 |
+
"learning_rate": 0.0014160427807486632,
|
| 981 |
+
"loss": 24.2498,
|
| 982 |
+
"step": 278
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.896,
|
| 986 |
+
"grad_norm": 1.2659244537353516,
|
| 987 |
+
"learning_rate": 0.001411764705882353,
|
| 988 |
+
"loss": 24.1083,
|
| 989 |
+
"step": 280
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.9024,
|
| 993 |
+
"grad_norm": 1.3372520208358765,
|
| 994 |
+
"learning_rate": 0.0014074866310160427,
|
| 995 |
+
"loss": 24.3094,
|
| 996 |
+
"step": 282
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.9088,
|
| 1000 |
+
"grad_norm": 0.9774726033210754,
|
| 1001 |
+
"learning_rate": 0.0014032085561497328,
|
| 1002 |
+
"loss": 24.2246,
|
| 1003 |
+
"step": 284
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.9152,
|
| 1007 |
+
"grad_norm": 1.2357187271118164,
|
| 1008 |
+
"learning_rate": 0.0013989304812834225,
|
| 1009 |
+
"loss": 23.8482,
|
| 1010 |
+
"step": 286
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.9216,
|
| 1014 |
+
"grad_norm": 0.8730471730232239,
|
| 1015 |
+
"learning_rate": 0.0013946524064171121,
|
| 1016 |
+
"loss": 24.1488,
|
| 1017 |
+
"step": 288
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.928,
|
| 1021 |
+
"grad_norm": 1.1759275197982788,
|
| 1022 |
+
"learning_rate": 0.0013903743315508022,
|
| 1023 |
+
"loss": 24.0689,
|
| 1024 |
+
"step": 290
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.9344,
|
| 1028 |
+
"grad_norm": 1.0625526905059814,
|
| 1029 |
+
"learning_rate": 0.0013860962566844919,
|
| 1030 |
+
"loss": 23.9011,
|
| 1031 |
+
"step": 292
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.9408,
|
| 1035 |
+
"grad_norm": 0.9794639945030212,
|
| 1036 |
+
"learning_rate": 0.0013818181818181818,
|
| 1037 |
+
"loss": 24.1742,
|
| 1038 |
+
"step": 294
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.9472,
|
| 1042 |
+
"grad_norm": 0.8726012110710144,
|
| 1043 |
+
"learning_rate": 0.0013775401069518716,
|
| 1044 |
+
"loss": 24.2234,
|
| 1045 |
+
"step": 296
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.9536,
|
| 1049 |
+
"grad_norm": 0.9825778007507324,
|
| 1050 |
+
"learning_rate": 0.0013732620320855615,
|
| 1051 |
+
"loss": 23.993,
|
| 1052 |
+
"step": 298
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.96,
|
| 1056 |
+
"grad_norm": 1.0842067003250122,
|
| 1057 |
+
"learning_rate": 0.0013689839572192512,
|
| 1058 |
+
"loss": 24.1026,
|
| 1059 |
+
"step": 300
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.9664,
|
| 1063 |
+
"grad_norm": 0.9663395881652832,
|
| 1064 |
+
"learning_rate": 0.0013647058823529413,
|
| 1065 |
+
"loss": 24.1273,
|
| 1066 |
+
"step": 302
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.9728,
|
| 1070 |
+
"grad_norm": 1.0321509838104248,
|
| 1071 |
+
"learning_rate": 0.001360427807486631,
|
| 1072 |
+
"loss": 24.0919,
|
| 1073 |
+
"step": 304
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.9792,
|
| 1077 |
+
"grad_norm": 1.0301271677017212,
|
| 1078 |
+
"learning_rate": 0.001356149732620321,
|
| 1079 |
+
"loss": 23.9162,
|
| 1080 |
+
"step": 306
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.9856,
|
| 1084 |
+
"grad_norm": 1.1476960182189941,
|
| 1085 |
+
"learning_rate": 0.0013518716577540107,
|
| 1086 |
+
"loss": 23.9016,
|
| 1087 |
+
"step": 308
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.992,
|
| 1091 |
+
"grad_norm": 1.044398307800293,
|
| 1092 |
+
"learning_rate": 0.0013475935828877006,
|
| 1093 |
+
"loss": 24.11,
|
| 1094 |
+
"step": 310
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.9984,
|
| 1098 |
+
"grad_norm": 1.3517370223999023,
|
| 1099 |
+
"learning_rate": 0.0013433155080213905,
|
| 1100 |
+
"loss": 23.9528,
|
| 1101 |
+
"step": 312
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.0032,
|
| 1105 |
+
"grad_norm": 1.1732239723205566,
|
| 1106 |
+
"learning_rate": 0.0013390374331550803,
|
| 1107 |
+
"loss": 18.1742,
|
| 1108 |
+
"step": 314
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.0096,
|
| 1112 |
+
"grad_norm": 1.0016353130340576,
|
| 1113 |
+
"learning_rate": 0.00133475935828877,
|
| 1114 |
+
"loss": 23.7102,
|
| 1115 |
+
"step": 316
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.016,
|
| 1119 |
+
"grad_norm": 1.3539528846740723,
|
| 1120 |
+
"learning_rate": 0.00133048128342246,
|
| 1121 |
+
"loss": 23.8078,
|
| 1122 |
+
"step": 318
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.0224,
|
| 1126 |
+
"grad_norm": 1.2378896474838257,
|
| 1127 |
+
"learning_rate": 0.0013262032085561498,
|
| 1128 |
+
"loss": 24.2912,
|
| 1129 |
+
"step": 320
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.0288,
|
| 1133 |
+
"grad_norm": 1.118072748184204,
|
| 1134 |
+
"learning_rate": 0.0013219251336898396,
|
| 1135 |
+
"loss": 23.9082,
|
| 1136 |
+
"step": 322
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.0352,
|
| 1140 |
+
"grad_norm": 1.4039278030395508,
|
| 1141 |
+
"learning_rate": 0.0013176470588235295,
|
| 1142 |
+
"loss": 24.1193,
|
| 1143 |
+
"step": 324
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.0416,
|
| 1147 |
+
"grad_norm": 0.9324209094047546,
|
| 1148 |
+
"learning_rate": 0.0013133689839572194,
|
| 1149 |
+
"loss": 23.9758,
|
| 1150 |
+
"step": 326
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.048,
|
| 1154 |
+
"grad_norm": 1.21006178855896,
|
| 1155 |
+
"learning_rate": 0.001309090909090909,
|
| 1156 |
+
"loss": 24.0922,
|
| 1157 |
+
"step": 328
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.0544,
|
| 1161 |
+
"grad_norm": 1.083890438079834,
|
| 1162 |
+
"learning_rate": 0.0013048128342245992,
|
| 1163 |
+
"loss": 23.9699,
|
| 1164 |
+
"step": 330
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.0608,
|
| 1168 |
+
"grad_norm": 0.8704414367675781,
|
| 1169 |
+
"learning_rate": 0.0013005347593582888,
|
| 1170 |
+
"loss": 23.6364,
|
| 1171 |
+
"step": 332
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.0672,
|
| 1175 |
+
"grad_norm": 0.9826658964157104,
|
| 1176 |
+
"learning_rate": 0.0012962566844919785,
|
| 1177 |
+
"loss": 24.1282,
|
| 1178 |
+
"step": 334
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.0735999999999999,
|
| 1182 |
+
"grad_norm": 1.005998969078064,
|
| 1183 |
+
"learning_rate": 0.0012919786096256686,
|
| 1184 |
+
"loss": 24.0106,
|
| 1185 |
+
"step": 336
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.08,
|
| 1189 |
+
"grad_norm": 0.9576805233955383,
|
| 1190 |
+
"learning_rate": 0.0012877005347593582,
|
| 1191 |
+
"loss": 23.7264,
|
| 1192 |
+
"step": 338
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.0864,
|
| 1196 |
+
"grad_norm": 0.9244794845581055,
|
| 1197 |
+
"learning_rate": 0.0012834224598930481,
|
| 1198 |
+
"loss": 23.7184,
|
| 1199 |
+
"step": 340
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.0928,
|
| 1203 |
+
"grad_norm": 0.8726948499679565,
|
| 1204 |
+
"learning_rate": 0.001279144385026738,
|
| 1205 |
+
"loss": 23.8847,
|
| 1206 |
+
"step": 342
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.0992,
|
| 1210 |
+
"grad_norm": 1.184464931488037,
|
| 1211 |
+
"learning_rate": 0.0012748663101604279,
|
| 1212 |
+
"loss": 23.9564,
|
| 1213 |
+
"step": 344
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.1056,
|
| 1217 |
+
"grad_norm": 1.0483590364456177,
|
| 1218 |
+
"learning_rate": 0.0012705882352941175,
|
| 1219 |
+
"loss": 24.0259,
|
| 1220 |
+
"step": 346
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.112,
|
| 1224 |
+
"grad_norm": 0.85725998878479,
|
| 1225 |
+
"learning_rate": 0.0012663101604278076,
|
| 1226 |
+
"loss": 23.9331,
|
| 1227 |
+
"step": 348
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.1184,
|
| 1231 |
+
"grad_norm": 0.9352357387542725,
|
| 1232 |
+
"learning_rate": 0.0012620320855614973,
|
| 1233 |
+
"loss": 23.9268,
|
| 1234 |
+
"step": 350
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.1248,
|
| 1238 |
+
"grad_norm": 0.9234675765037537,
|
| 1239 |
+
"learning_rate": 0.0012577540106951872,
|
| 1240 |
+
"loss": 24.0202,
|
| 1241 |
+
"step": 352
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.1312,
|
| 1245 |
+
"grad_norm": 0.8931582570075989,
|
| 1246 |
+
"learning_rate": 0.001253475935828877,
|
| 1247 |
+
"loss": 23.7643,
|
| 1248 |
+
"step": 354
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.1376,
|
| 1252 |
+
"grad_norm": 0.9177488684654236,
|
| 1253 |
+
"learning_rate": 0.001249197860962567,
|
| 1254 |
+
"loss": 23.7432,
|
| 1255 |
+
"step": 356
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.144,
|
| 1259 |
+
"grad_norm": 0.8955037593841553,
|
| 1260 |
+
"learning_rate": 0.0012449197860962566,
|
| 1261 |
+
"loss": 23.7637,
|
| 1262 |
+
"step": 358
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.1504,
|
| 1266 |
+
"grad_norm": 1.0113520622253418,
|
| 1267 |
+
"learning_rate": 0.0012406417112299467,
|
| 1268 |
+
"loss": 23.931,
|
| 1269 |
+
"step": 360
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.1568,
|
| 1273 |
+
"grad_norm": 0.8994941711425781,
|
| 1274 |
+
"learning_rate": 0.0012363636363636364,
|
| 1275 |
+
"loss": 23.7517,
|
| 1276 |
+
"step": 362
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.1632,
|
| 1280 |
+
"grad_norm": 0.9318895936012268,
|
| 1281 |
+
"learning_rate": 0.0012320855614973262,
|
| 1282 |
+
"loss": 23.8983,
|
| 1283 |
+
"step": 364
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.1696,
|
| 1287 |
+
"grad_norm": 1.0647019147872925,
|
| 1288 |
+
"learning_rate": 0.0012278074866310161,
|
| 1289 |
+
"loss": 23.8213,
|
| 1290 |
+
"step": 366
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.176,
|
| 1294 |
+
"grad_norm": 1.132948637008667,
|
| 1295 |
+
"learning_rate": 0.001223529411764706,
|
| 1296 |
+
"loss": 23.6347,
|
| 1297 |
+
"step": 368
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.1824,
|
| 1301 |
+
"grad_norm": 0.9466244578361511,
|
| 1302 |
+
"learning_rate": 0.0012192513368983957,
|
| 1303 |
+
"loss": 23.9028,
|
| 1304 |
+
"step": 370
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.1888,
|
| 1308 |
+
"grad_norm": 0.9593258500099182,
|
| 1309 |
+
"learning_rate": 0.0012149732620320858,
|
| 1310 |
+
"loss": 23.98,
|
| 1311 |
+
"step": 372
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.1952,
|
| 1315 |
+
"grad_norm": 1.0898252725601196,
|
| 1316 |
+
"learning_rate": 0.0012106951871657754,
|
| 1317 |
+
"loss": 23.5301,
|
| 1318 |
+
"step": 374
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.2016,
|
| 1322 |
+
"grad_norm": 1.0035079717636108,
|
| 1323 |
+
"learning_rate": 0.001206417112299465,
|
| 1324 |
+
"loss": 23.6481,
|
| 1325 |
+
"step": 376
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.208,
|
| 1329 |
+
"grad_norm": 0.890784502029419,
|
| 1330 |
+
"learning_rate": 0.0012021390374331552,
|
| 1331 |
+
"loss": 23.638,
|
| 1332 |
+
"step": 378
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 1.2144,
|
| 1336 |
+
"grad_norm": 1.0010117292404175,
|
| 1337 |
+
"learning_rate": 0.0011978609625668448,
|
| 1338 |
+
"loss": 23.7085,
|
| 1339 |
+
"step": 380
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.2208,
|
| 1343 |
+
"grad_norm": 0.92851322889328,
|
| 1344 |
+
"learning_rate": 0.0011935828877005347,
|
| 1345 |
+
"loss": 23.9561,
|
| 1346 |
+
"step": 382
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.2272,
|
| 1350 |
+
"grad_norm": 0.966708242893219,
|
| 1351 |
+
"learning_rate": 0.0011893048128342246,
|
| 1352 |
+
"loss": 23.5308,
|
| 1353 |
+
"step": 384
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.2336,
|
| 1357 |
+
"grad_norm": 0.9790504574775696,
|
| 1358 |
+
"learning_rate": 0.0011850267379679145,
|
| 1359 |
+
"loss": 23.8811,
|
| 1360 |
+
"step": 386
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.24,
|
| 1364 |
+
"grad_norm": 0.9370564818382263,
|
| 1365 |
+
"learning_rate": 0.0011807486631016041,
|
| 1366 |
+
"loss": 23.6945,
|
| 1367 |
+
"step": 388
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.2464,
|
| 1371 |
+
"grad_norm": 1.0068321228027344,
|
| 1372 |
+
"learning_rate": 0.0011764705882352942,
|
| 1373 |
+
"loss": 23.7471,
|
| 1374 |
+
"step": 390
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.2528000000000001,
|
| 1378 |
+
"grad_norm": 0.880582332611084,
|
| 1379 |
+
"learning_rate": 0.001172192513368984,
|
| 1380 |
+
"loss": 23.4096,
|
| 1381 |
+
"step": 392
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.2591999999999999,
|
| 1385 |
+
"grad_norm": 0.8774146437644958,
|
| 1386 |
+
"learning_rate": 0.0011679144385026738,
|
| 1387 |
+
"loss": 23.7207,
|
| 1388 |
+
"step": 394
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.2656,
|
| 1392 |
+
"grad_norm": 1.070694923400879,
|
| 1393 |
+
"learning_rate": 0.0011636363636363637,
|
| 1394 |
+
"loss": 23.6461,
|
| 1395 |
+
"step": 396
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.272,
|
| 1399 |
+
"grad_norm": 1.0852477550506592,
|
| 1400 |
+
"learning_rate": 0.0011593582887700535,
|
| 1401 |
+
"loss": 23.8393,
|
| 1402 |
+
"step": 398
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.2784,
|
| 1406 |
+
"grad_norm": 0.9843823313713074,
|
| 1407 |
+
"learning_rate": 0.0011550802139037432,
|
| 1408 |
+
"loss": 23.798,
|
| 1409 |
+
"step": 400
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.2784,
|
| 1413 |
+
"eval_loss": 1.4875859022140503,
|
| 1414 |
+
"eval_runtime": 1157.3489,
|
| 1415 |
+
"eval_samples_per_second": 8.64,
|
| 1416 |
+
"eval_steps_per_second": 1.08,
|
| 1417 |
+
"step": 400
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.2848,
|
| 1421 |
+
"grad_norm": 0.9516158103942871,
|
| 1422 |
+
"learning_rate": 0.0011508021390374333,
|
| 1423 |
+
"loss": 23.8632,
|
| 1424 |
+
"step": 402
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.2912,
|
| 1428 |
+
"grad_norm": 0.9639537930488586,
|
| 1429 |
+
"learning_rate": 0.001146524064171123,
|
| 1430 |
+
"loss": 23.7238,
|
| 1431 |
+
"step": 404
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.2976,
|
| 1435 |
+
"grad_norm": 1.018441081047058,
|
| 1436 |
+
"learning_rate": 0.0011422459893048128,
|
| 1437 |
+
"loss": 23.5542,
|
| 1438 |
+
"step": 406
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.304,
|
| 1442 |
+
"grad_norm": 0.9791119694709778,
|
| 1443 |
+
"learning_rate": 0.0011379679144385027,
|
| 1444 |
+
"loss": 23.5262,
|
| 1445 |
+
"step": 408
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.3104,
|
| 1449 |
+
"grad_norm": 0.9863831996917725,
|
| 1450 |
+
"learning_rate": 0.0011336898395721926,
|
| 1451 |
+
"loss": 23.763,
|
| 1452 |
+
"step": 410
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.3168,
|
| 1456 |
+
"grad_norm": 0.9786751866340637,
|
| 1457 |
+
"learning_rate": 0.0011294117647058823,
|
| 1458 |
+
"loss": 23.6861,
|
| 1459 |
+
"step": 412
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.3232,
|
| 1463 |
+
"grad_norm": 0.9191985130310059,
|
| 1464 |
+
"learning_rate": 0.0011251336898395724,
|
| 1465 |
+
"loss": 23.5714,
|
| 1466 |
+
"step": 414
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.3296000000000001,
|
| 1470 |
+
"grad_norm": 1.1038320064544678,
|
| 1471 |
+
"learning_rate": 0.001120855614973262,
|
| 1472 |
+
"loss": 23.6797,
|
| 1473 |
+
"step": 416
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.336,
|
| 1477 |
+
"grad_norm": 0.9039956331253052,
|
| 1478 |
+
"learning_rate": 0.0011165775401069521,
|
| 1479 |
+
"loss": 23.5835,
|
| 1480 |
+
"step": 418
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.3424,
|
| 1484 |
+
"grad_norm": 0.9752773642539978,
|
| 1485 |
+
"learning_rate": 0.0011122994652406418,
|
| 1486 |
+
"loss": 23.8994,
|
| 1487 |
+
"step": 420
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.3488,
|
| 1491 |
+
"grad_norm": 1.058692455291748,
|
| 1492 |
+
"learning_rate": 0.0011080213903743314,
|
| 1493 |
+
"loss": 23.7038,
|
| 1494 |
+
"step": 422
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.3552,
|
| 1498 |
+
"grad_norm": 0.89438396692276,
|
| 1499 |
+
"learning_rate": 0.0011037433155080215,
|
| 1500 |
+
"loss": 23.6139,
|
| 1501 |
+
"step": 424
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.3616,
|
| 1505 |
+
"grad_norm": 0.9645833373069763,
|
| 1506 |
+
"learning_rate": 0.0010994652406417112,
|
| 1507 |
+
"loss": 23.603,
|
| 1508 |
+
"step": 426
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.3679999999999999,
|
| 1512 |
+
"grad_norm": 0.9102054834365845,
|
| 1513 |
+
"learning_rate": 0.001095187165775401,
|
| 1514 |
+
"loss": 23.6805,
|
| 1515 |
+
"step": 428
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.3744,
|
| 1519 |
+
"grad_norm": 1.066123366355896,
|
| 1520 |
+
"learning_rate": 0.001090909090909091,
|
| 1521 |
+
"loss": 23.623,
|
| 1522 |
+
"step": 430
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.3808,
|
| 1526 |
+
"grad_norm": 0.9730815291404724,
|
| 1527 |
+
"learning_rate": 0.0010866310160427808,
|
| 1528 |
+
"loss": 23.9918,
|
| 1529 |
+
"step": 432
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.3872,
|
| 1533 |
+
"grad_norm": 0.953152596950531,
|
| 1534 |
+
"learning_rate": 0.0010823529411764705,
|
| 1535 |
+
"loss": 23.5223,
|
| 1536 |
+
"step": 434
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.3936,
|
| 1540 |
+
"grad_norm": 0.9269129633903503,
|
| 1541 |
+
"learning_rate": 0.0010780748663101606,
|
| 1542 |
+
"loss": 23.5794,
|
| 1543 |
+
"step": 436
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.4,
|
| 1547 |
+
"grad_norm": 1.0842361450195312,
|
| 1548 |
+
"learning_rate": 0.0010737967914438503,
|
| 1549 |
+
"loss": 23.0374,
|
| 1550 |
+
"step": 438
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.4064,
|
| 1554 |
+
"grad_norm": 0.9895943999290466,
|
| 1555 |
+
"learning_rate": 0.0010695187165775401,
|
| 1556 |
+
"loss": 23.6018,
|
| 1557 |
+
"step": 440
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.4128,
|
| 1561 |
+
"grad_norm": 0.9779914617538452,
|
| 1562 |
+
"learning_rate": 0.00106524064171123,
|
| 1563 |
+
"loss": 23.4881,
|
| 1564 |
+
"step": 442
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.4192,
|
| 1568 |
+
"grad_norm": 0.9720066785812378,
|
| 1569 |
+
"learning_rate": 0.0010609625668449199,
|
| 1570 |
+
"loss": 23.7365,
|
| 1571 |
+
"step": 444
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.4256,
|
| 1575 |
+
"grad_norm": 0.9314095973968506,
|
| 1576 |
+
"learning_rate": 0.0010566844919786096,
|
| 1577 |
+
"loss": 23.6696,
|
| 1578 |
+
"step": 446
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.432,
|
| 1582 |
+
"grad_norm": 0.9558563232421875,
|
| 1583 |
+
"learning_rate": 0.0010524064171122996,
|
| 1584 |
+
"loss": 23.5277,
|
| 1585 |
+
"step": 448
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.4384000000000001,
|
| 1589 |
+
"grad_norm": 0.9274935722351074,
|
| 1590 |
+
"learning_rate": 0.0010481283422459893,
|
| 1591 |
+
"loss": 23.8089,
|
| 1592 |
+
"step": 450
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.4447999999999999,
|
| 1596 |
+
"grad_norm": 0.8989819884300232,
|
| 1597 |
+
"learning_rate": 0.0010438502673796792,
|
| 1598 |
+
"loss": 23.4861,
|
| 1599 |
+
"step": 452
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.4512,
|
| 1603 |
+
"grad_norm": 0.8949527144432068,
|
| 1604 |
+
"learning_rate": 0.001039572192513369,
|
| 1605 |
+
"loss": 23.8258,
|
| 1606 |
+
"step": 454
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.4576,
|
| 1610 |
+
"grad_norm": 1.0032631158828735,
|
| 1611 |
+
"learning_rate": 0.001035294117647059,
|
| 1612 |
+
"loss": 23.6332,
|
| 1613 |
+
"step": 456
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.464,
|
| 1617 |
+
"grad_norm": 0.8726269006729126,
|
| 1618 |
+
"learning_rate": 0.0010310160427807486,
|
| 1619 |
+
"loss": 23.852,
|
| 1620 |
+
"step": 458
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.4704,
|
| 1624 |
+
"grad_norm": 1.013187289237976,
|
| 1625 |
+
"learning_rate": 0.0010267379679144387,
|
| 1626 |
+
"loss": 23.6731,
|
| 1627 |
+
"step": 460
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.4768,
|
| 1631 |
+
"grad_norm": 0.9792904853820801,
|
| 1632 |
+
"learning_rate": 0.0010224598930481284,
|
| 1633 |
+
"loss": 23.4724,
|
| 1634 |
+
"step": 462
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.4832,
|
| 1638 |
+
"grad_norm": 0.9881017804145813,
|
| 1639 |
+
"learning_rate": 0.001018181818181818,
|
| 1640 |
+
"loss": 23.6523,
|
| 1641 |
+
"step": 464
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.4896,
|
| 1645 |
+
"grad_norm": 1.0167256593704224,
|
| 1646 |
+
"learning_rate": 0.0010139037433155081,
|
| 1647 |
+
"loss": 23.7077,
|
| 1648 |
+
"step": 466
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.496,
|
| 1652 |
+
"grad_norm": 1.028531551361084,
|
| 1653 |
+
"learning_rate": 0.0010096256684491978,
|
| 1654 |
+
"loss": 24.1109,
|
| 1655 |
+
"step": 468
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.5024,
|
| 1659 |
+
"grad_norm": 0.9525850415229797,
|
| 1660 |
+
"learning_rate": 0.0010053475935828877,
|
| 1661 |
+
"loss": 23.9823,
|
| 1662 |
+
"step": 470
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.5088,
|
| 1666 |
+
"grad_norm": 1.1063846349716187,
|
| 1667 |
+
"learning_rate": 0.0010010695187165776,
|
| 1668 |
+
"loss": 23.6939,
|
| 1669 |
+
"step": 472
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.5152,
|
| 1673 |
+
"grad_norm": 1.023152232170105,
|
| 1674 |
+
"learning_rate": 0.0009967914438502674,
|
| 1675 |
+
"loss": 23.5762,
|
| 1676 |
+
"step": 474
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.5215999999999998,
|
| 1680 |
+
"grad_norm": 0.9533156752586365,
|
| 1681 |
+
"learning_rate": 0.0009925133689839573,
|
| 1682 |
+
"loss": 23.8931,
|
| 1683 |
+
"step": 476
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.528,
|
| 1687 |
+
"grad_norm": 1.01291823387146,
|
| 1688 |
+
"learning_rate": 0.0009882352941176472,
|
| 1689 |
+
"loss": 23.7593,
|
| 1690 |
+
"step": 478
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.5344,
|
| 1694 |
+
"grad_norm": 0.967445969581604,
|
| 1695 |
+
"learning_rate": 0.000983957219251337,
|
| 1696 |
+
"loss": 23.5105,
|
| 1697 |
+
"step": 480
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.5408,
|
| 1701 |
+
"grad_norm": 0.8999999165534973,
|
| 1702 |
+
"learning_rate": 0.0009796791443850267,
|
| 1703 |
+
"loss": 23.9054,
|
| 1704 |
+
"step": 482
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.5472000000000001,
|
| 1708 |
+
"grad_norm": 1.0055955648422241,
|
| 1709 |
+
"learning_rate": 0.0009754010695187165,
|
| 1710 |
+
"loss": 23.6609,
|
| 1711 |
+
"step": 484
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.5535999999999999,
|
| 1715 |
+
"grad_norm": 0.9917962551116943,
|
| 1716 |
+
"learning_rate": 0.0009711229946524064,
|
| 1717 |
+
"loss": 23.664,
|
| 1718 |
+
"step": 486
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.56,
|
| 1722 |
+
"grad_norm": 1.0509769916534424,
|
| 1723 |
+
"learning_rate": 0.0009668449197860963,
|
| 1724 |
+
"loss": 23.5889,
|
| 1725 |
+
"step": 488
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.5664,
|
| 1729 |
+
"grad_norm": 0.9780173301696777,
|
| 1730 |
+
"learning_rate": 0.000962566844919786,
|
| 1731 |
+
"loss": 23.3563,
|
| 1732 |
+
"step": 490
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.5728,
|
| 1736 |
+
"grad_norm": 1.0623761415481567,
|
| 1737 |
+
"learning_rate": 0.0009582887700534759,
|
| 1738 |
+
"loss": 23.7324,
|
| 1739 |
+
"step": 492
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.5792000000000002,
|
| 1743 |
+
"grad_norm": 0.9415885806083679,
|
| 1744 |
+
"learning_rate": 0.0009540106951871658,
|
| 1745 |
+
"loss": 23.6075,
|
| 1746 |
+
"step": 494
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.5856,
|
| 1750 |
+
"grad_norm": 1.0558156967163086,
|
| 1751 |
+
"learning_rate": 0.0009497326203208556,
|
| 1752 |
+
"loss": 23.9617,
|
| 1753 |
+
"step": 496
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.592,
|
| 1757 |
+
"grad_norm": 1.2639505863189697,
|
| 1758 |
+
"learning_rate": 0.0009454545454545454,
|
| 1759 |
+
"loss": 23.7581,
|
| 1760 |
+
"step": 498
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.5984,
|
| 1764 |
+
"grad_norm": 0.9966816902160645,
|
| 1765 |
+
"learning_rate": 0.0009411764705882353,
|
| 1766 |
+
"loss": 23.4159,
|
| 1767 |
+
"step": 500
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.6048,
|
| 1771 |
+
"grad_norm": 1.1803079843521118,
|
| 1772 |
+
"learning_rate": 0.0009368983957219251,
|
| 1773 |
+
"loss": 23.6882,
|
| 1774 |
+
"step": 502
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.6112,
|
| 1778 |
+
"grad_norm": 1.068477749824524,
|
| 1779 |
+
"learning_rate": 0.000932620320855615,
|
| 1780 |
+
"loss": 23.3086,
|
| 1781 |
+
"step": 504
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.6176,
|
| 1785 |
+
"grad_norm": 1.0496388673782349,
|
| 1786 |
+
"learning_rate": 0.0009283422459893048,
|
| 1787 |
+
"loss": 23.5714,
|
| 1788 |
+
"step": 506
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.624,
|
| 1792 |
+
"grad_norm": 0.9868847727775574,
|
| 1793 |
+
"learning_rate": 0.0009240641711229947,
|
| 1794 |
+
"loss": 23.3231,
|
| 1795 |
+
"step": 508
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.6303999999999998,
|
| 1799 |
+
"grad_norm": 1.0146859884262085,
|
| 1800 |
+
"learning_rate": 0.0009197860962566845,
|
| 1801 |
+
"loss": 23.474,
|
| 1802 |
+
"step": 510
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.6368,
|
| 1806 |
+
"grad_norm": 1.3640587329864502,
|
| 1807 |
+
"learning_rate": 0.0009155080213903744,
|
| 1808 |
+
"loss": 23.728,
|
| 1809 |
+
"step": 512
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.6432,
|
| 1813 |
+
"grad_norm": 1.0222820043563843,
|
| 1814 |
+
"learning_rate": 0.0009112299465240643,
|
| 1815 |
+
"loss": 23.8034,
|
| 1816 |
+
"step": 514
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.6496,
|
| 1820 |
+
"grad_norm": 0.9659361243247986,
|
| 1821 |
+
"learning_rate": 0.000906951871657754,
|
| 1822 |
+
"loss": 23.454,
|
| 1823 |
+
"step": 516
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.6560000000000001,
|
| 1827 |
+
"grad_norm": 1.0694700479507446,
|
| 1828 |
+
"learning_rate": 0.0009026737967914439,
|
| 1829 |
+
"loss": 23.7977,
|
| 1830 |
+
"step": 518
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.6623999999999999,
|
| 1834 |
+
"grad_norm": 0.9259259700775146,
|
| 1835 |
+
"learning_rate": 0.0008983957219251338,
|
| 1836 |
+
"loss": 23.5328,
|
| 1837 |
+
"step": 520
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.6688,
|
| 1841 |
+
"grad_norm": 1.1431095600128174,
|
| 1842 |
+
"learning_rate": 0.0008941176470588236,
|
| 1843 |
+
"loss": 23.5061,
|
| 1844 |
+
"step": 522
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.6752,
|
| 1848 |
+
"grad_norm": 1.0091369152069092,
|
| 1849 |
+
"learning_rate": 0.0008898395721925134,
|
| 1850 |
+
"loss": 23.414,
|
| 1851 |
+
"step": 524
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.6816,
|
| 1855 |
+
"grad_norm": 1.0047186613082886,
|
| 1856 |
+
"learning_rate": 0.0008855614973262033,
|
| 1857 |
+
"loss": 23.7231,
|
| 1858 |
+
"step": 526
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.688,
|
| 1862 |
+
"grad_norm": 1.020326018333435,
|
| 1863 |
+
"learning_rate": 0.000881283422459893,
|
| 1864 |
+
"loss": 23.5656,
|
| 1865 |
+
"step": 528
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.6944,
|
| 1869 |
+
"grad_norm": 1.2622140645980835,
|
| 1870 |
+
"learning_rate": 0.0008770053475935829,
|
| 1871 |
+
"loss": 23.1935,
|
| 1872 |
+
"step": 530
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.7008,
|
| 1876 |
+
"grad_norm": 0.9633255004882812,
|
| 1877 |
+
"learning_rate": 0.0008727272727272727,
|
| 1878 |
+
"loss": 23.7261,
|
| 1879 |
+
"step": 532
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.7072,
|
| 1883 |
+
"grad_norm": 0.9747726321220398,
|
| 1884 |
+
"learning_rate": 0.0008684491978609625,
|
| 1885 |
+
"loss": 23.3123,
|
| 1886 |
+
"step": 534
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.7136,
|
| 1890 |
+
"grad_norm": 0.8444503545761108,
|
| 1891 |
+
"learning_rate": 0.0008641711229946524,
|
| 1892 |
+
"loss": 23.703,
|
| 1893 |
+
"step": 536
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.72,
|
| 1897 |
+
"grad_norm": 0.9087849855422974,
|
| 1898 |
+
"learning_rate": 0.0008598930481283423,
|
| 1899 |
+
"loss": 23.3917,
|
| 1900 |
+
"step": 538
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.7264,
|
| 1904 |
+
"grad_norm": 0.9356536269187927,
|
| 1905 |
+
"learning_rate": 0.000855614973262032,
|
| 1906 |
+
"loss": 23.6751,
|
| 1907 |
+
"step": 540
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 1.7328000000000001,
|
| 1911 |
+
"grad_norm": 0.9630663990974426,
|
| 1912 |
+
"learning_rate": 0.0008513368983957219,
|
| 1913 |
+
"loss": 23.4119,
|
| 1914 |
+
"step": 542
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.7391999999999999,
|
| 1918 |
+
"grad_norm": 1.0205367803573608,
|
| 1919 |
+
"learning_rate": 0.0008470588235294118,
|
| 1920 |
+
"loss": 23.2226,
|
| 1921 |
+
"step": 544
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.7456,
|
| 1925 |
+
"grad_norm": 1.0030864477157593,
|
| 1926 |
+
"learning_rate": 0.0008427807486631016,
|
| 1927 |
+
"loss": 23.6982,
|
| 1928 |
+
"step": 546
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.752,
|
| 1932 |
+
"grad_norm": 0.9470692276954651,
|
| 1933 |
+
"learning_rate": 0.0008385026737967914,
|
| 1934 |
+
"loss": 23.6646,
|
| 1935 |
+
"step": 548
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.7584,
|
| 1939 |
+
"grad_norm": 0.9366554617881775,
|
| 1940 |
+
"learning_rate": 0.0008342245989304813,
|
| 1941 |
+
"loss": 23.7817,
|
| 1942 |
+
"step": 550
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.7648000000000001,
|
| 1946 |
+
"grad_norm": 0.9047606587409973,
|
| 1947 |
+
"learning_rate": 0.0008299465240641711,
|
| 1948 |
+
"loss": 23.5856,
|
| 1949 |
+
"step": 552
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.7711999999999999,
|
| 1953 |
+
"grad_norm": 0.9083183407783508,
|
| 1954 |
+
"learning_rate": 0.000825668449197861,
|
| 1955 |
+
"loss": 23.694,
|
| 1956 |
+
"step": 554
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.7776,
|
| 1960 |
+
"grad_norm": 0.9529908895492554,
|
| 1961 |
+
"learning_rate": 0.0008213903743315509,
|
| 1962 |
+
"loss": 23.9012,
|
| 1963 |
+
"step": 556
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 1.784,
|
| 1967 |
+
"grad_norm": 0.9241888523101807,
|
| 1968 |
+
"learning_rate": 0.0008171122994652406,
|
| 1969 |
+
"loss": 23.6046,
|
| 1970 |
+
"step": 558
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.7904,
|
| 1974 |
+
"grad_norm": 0.869388997554779,
|
| 1975 |
+
"learning_rate": 0.0008128342245989305,
|
| 1976 |
+
"loss": 23.4944,
|
| 1977 |
+
"step": 560
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.7968,
|
| 1981 |
+
"grad_norm": 0.8648447394371033,
|
| 1982 |
+
"learning_rate": 0.0008085561497326204,
|
| 1983 |
+
"loss": 23.2361,
|
| 1984 |
+
"step": 562
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 1.8032,
|
| 1988 |
+
"grad_norm": 1.0052869319915771,
|
| 1989 |
+
"learning_rate": 0.0008042780748663103,
|
| 1990 |
+
"loss": 23.2241,
|
| 1991 |
+
"step": 564
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.8096,
|
| 1995 |
+
"grad_norm": 0.9710979461669922,
|
| 1996 |
+
"learning_rate": 0.0008,
|
| 1997 |
+
"loss": 23.3083,
|
| 1998 |
+
"step": 566
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 1.8159999999999998,
|
| 2002 |
+
"grad_norm": 0.9305456280708313,
|
| 2003 |
+
"learning_rate": 0.0007957219251336899,
|
| 2004 |
+
"loss": 23.5668,
|
| 2005 |
+
"step": 568
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 1.8224,
|
| 2009 |
+
"grad_norm": 0.9786150455474854,
|
| 2010 |
+
"learning_rate": 0.0007914438502673798,
|
| 2011 |
+
"loss": 23.576,
|
| 2012 |
+
"step": 570
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.8288,
|
| 2016 |
+
"grad_norm": 0.9177144169807434,
|
| 2017 |
+
"learning_rate": 0.0007871657754010695,
|
| 2018 |
+
"loss": 23.8692,
|
| 2019 |
+
"step": 572
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.8352,
|
| 2023 |
+
"grad_norm": 0.8715292811393738,
|
| 2024 |
+
"learning_rate": 0.0007828877005347593,
|
| 2025 |
+
"loss": 23.5924,
|
| 2026 |
+
"step": 574
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.8416000000000001,
|
| 2030 |
+
"grad_norm": 0.9923094511032104,
|
| 2031 |
+
"learning_rate": 0.0007786096256684492,
|
| 2032 |
+
"loss": 23.4065,
|
| 2033 |
+
"step": 576
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.8479999999999999,
|
| 2037 |
+
"grad_norm": 0.931535542011261,
|
| 2038 |
+
"learning_rate": 0.000774331550802139,
|
| 2039 |
+
"loss": 23.6056,
|
| 2040 |
+
"step": 578
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.8544,
|
| 2044 |
+
"grad_norm": 0.8508500456809998,
|
| 2045 |
+
"learning_rate": 0.0007700534759358289,
|
| 2046 |
+
"loss": 23.4128,
|
| 2047 |
+
"step": 580
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.8608,
|
| 2051 |
+
"grad_norm": 0.916963517665863,
|
| 2052 |
+
"learning_rate": 0.0007657754010695187,
|
| 2053 |
+
"loss": 23.6378,
|
| 2054 |
+
"step": 582
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 1.8672,
|
| 2058 |
+
"grad_norm": 0.8805645108222961,
|
| 2059 |
+
"learning_rate": 0.0007614973262032085,
|
| 2060 |
+
"loss": 23.2751,
|
| 2061 |
+
"step": 584
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.8736000000000002,
|
| 2065 |
+
"grad_norm": 0.9679768085479736,
|
| 2066 |
+
"learning_rate": 0.0007572192513368984,
|
| 2067 |
+
"loss": 23.496,
|
| 2068 |
+
"step": 586
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 1.88,
|
| 2072 |
+
"grad_norm": 0.9578665494918823,
|
| 2073 |
+
"learning_rate": 0.0007529411764705883,
|
| 2074 |
+
"loss": 23.5754,
|
| 2075 |
+
"step": 588
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 1.8864,
|
| 2079 |
+
"grad_norm": 0.9930956959724426,
|
| 2080 |
+
"learning_rate": 0.000748663101604278,
|
| 2081 |
+
"loss": 23.3563,
|
| 2082 |
+
"step": 590
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.8928,
|
| 2086 |
+
"grad_norm": 0.8266828656196594,
|
| 2087 |
+
"learning_rate": 0.0007443850267379679,
|
| 2088 |
+
"loss": 23.7507,
|
| 2089 |
+
"step": 592
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.8992,
|
| 2093 |
+
"grad_norm": 0.9037677049636841,
|
| 2094 |
+
"learning_rate": 0.0007401069518716578,
|
| 2095 |
+
"loss": 23.3083,
|
| 2096 |
+
"step": 594
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.9056,
|
| 2100 |
+
"grad_norm": 0.9325649738311768,
|
| 2101 |
+
"learning_rate": 0.0007358288770053476,
|
| 2102 |
+
"loss": 23.4873,
|
| 2103 |
+
"step": 596
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.912,
|
| 2107 |
+
"grad_norm": 0.8425143957138062,
|
| 2108 |
+
"learning_rate": 0.0007315508021390375,
|
| 2109 |
+
"loss": 23.2706,
|
| 2110 |
+
"step": 598
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 1.9184,
|
| 2114 |
+
"grad_norm": 0.9997607469558716,
|
| 2115 |
+
"learning_rate": 0.0007272727272727273,
|
| 2116 |
+
"loss": 23.4578,
|
| 2117 |
+
"step": 600
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.9247999999999998,
|
| 2121 |
+
"grad_norm": 0.9266635775566101,
|
| 2122 |
+
"learning_rate": 0.0007229946524064171,
|
| 2123 |
+
"loss": 23.3936,
|
| 2124 |
+
"step": 602
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.9312,
|
| 2128 |
+
"grad_norm": 0.9372814893722534,
|
| 2129 |
+
"learning_rate": 0.000718716577540107,
|
| 2130 |
+
"loss": 23.7373,
|
| 2131 |
+
"step": 604
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 1.9376,
|
| 2135 |
+
"grad_norm": 1.0302927494049072,
|
| 2136 |
+
"learning_rate": 0.0007144385026737969,
|
| 2137 |
+
"loss": 23.3622,
|
| 2138 |
+
"step": 606
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.944,
|
| 2142 |
+
"grad_norm": 0.8410359025001526,
|
| 2143 |
+
"learning_rate": 0.0007101604278074866,
|
| 2144 |
+
"loss": 23.6175,
|
| 2145 |
+
"step": 608
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 1.9504000000000001,
|
| 2149 |
+
"grad_norm": 1.002364993095398,
|
| 2150 |
+
"learning_rate": 0.0007058823529411765,
|
| 2151 |
+
"loss": 23.7065,
|
| 2152 |
+
"step": 610
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 1.9567999999999999,
|
| 2156 |
+
"grad_norm": 0.8989892601966858,
|
| 2157 |
+
"learning_rate": 0.0007016042780748664,
|
| 2158 |
+
"loss": 23.1151,
|
| 2159 |
+
"step": 612
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.9632,
|
| 2163 |
+
"grad_norm": 0.9592454433441162,
|
| 2164 |
+
"learning_rate": 0.0006973262032085561,
|
| 2165 |
+
"loss": 23.6266,
|
| 2166 |
+
"step": 614
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.9696,
|
| 2170 |
+
"grad_norm": 0.9210177063941956,
|
| 2171 |
+
"learning_rate": 0.0006930481283422459,
|
| 2172 |
+
"loss": 23.2886,
|
| 2173 |
+
"step": 616
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.976,
|
| 2177 |
+
"grad_norm": 1.1872823238372803,
|
| 2178 |
+
"learning_rate": 0.0006887700534759358,
|
| 2179 |
+
"loss": 23.495,
|
| 2180 |
+
"step": 618
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.9824000000000002,
|
| 2184 |
+
"grad_norm": 0.9874787330627441,
|
| 2185 |
+
"learning_rate": 0.0006844919786096256,
|
| 2186 |
+
"loss": 23.6608,
|
| 2187 |
+
"step": 620
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.9888,
|
| 2191 |
+
"grad_norm": 1.1812684535980225,
|
| 2192 |
+
"learning_rate": 0.0006802139037433155,
|
| 2193 |
+
"loss": 23.5925,
|
| 2194 |
+
"step": 622
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.9952,
|
| 2198 |
+
"grad_norm": 1.0033948421478271,
|
| 2199 |
+
"learning_rate": 0.0006759358288770053,
|
| 2200 |
+
"loss": 23.4883,
|
| 2201 |
+
"step": 624
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 2.0,
|
| 2205 |
+
"grad_norm": 0.7030152082443237,
|
| 2206 |
+
"learning_rate": 0.0006716577540106952,
|
| 2207 |
+
"loss": 17.5334,
|
| 2208 |
+
"step": 626
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 2.0064,
|
| 2212 |
+
"grad_norm": 1.017948865890503,
|
| 2213 |
+
"learning_rate": 0.000667379679144385,
|
| 2214 |
+
"loss": 23.2155,
|
| 2215 |
+
"step": 628
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 2.0128,
|
| 2219 |
+
"grad_norm": 0.9184821248054504,
|
| 2220 |
+
"learning_rate": 0.0006631016042780749,
|
| 2221 |
+
"loss": 23.2131,
|
| 2222 |
+
"step": 630
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 2.0192,
|
| 2226 |
+
"grad_norm": 1.0140761137008667,
|
| 2227 |
+
"learning_rate": 0.0006588235294117648,
|
| 2228 |
+
"loss": 23.0792,
|
| 2229 |
+
"step": 632
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 2.0256,
|
| 2233 |
+
"grad_norm": 0.9820951223373413,
|
| 2234 |
+
"learning_rate": 0.0006545454545454545,
|
| 2235 |
+
"loss": 23.2678,
|
| 2236 |
+
"step": 634
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 2.032,
|
| 2240 |
+
"grad_norm": 0.9167227745056152,
|
| 2241 |
+
"learning_rate": 0.0006502673796791444,
|
| 2242 |
+
"loss": 23.7916,
|
| 2243 |
+
"step": 636
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 2.0384,
|
| 2247 |
+
"grad_norm": 0.935867428779602,
|
| 2248 |
+
"learning_rate": 0.0006459893048128343,
|
| 2249 |
+
"loss": 23.5265,
|
| 2250 |
+
"step": 638
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 2.0448,
|
| 2254 |
+
"grad_norm": 0.871694803237915,
|
| 2255 |
+
"learning_rate": 0.0006417112299465241,
|
| 2256 |
+
"loss": 23.2606,
|
| 2257 |
+
"step": 640
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.0512,
|
| 2261 |
+
"grad_norm": 0.9383721947669983,
|
| 2262 |
+
"learning_rate": 0.0006374331550802139,
|
| 2263 |
+
"loss": 23.4792,
|
| 2264 |
+
"step": 642
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 2.0576,
|
| 2268 |
+
"grad_norm": 0.9656952023506165,
|
| 2269 |
+
"learning_rate": 0.0006331550802139038,
|
| 2270 |
+
"loss": 23.1145,
|
| 2271 |
+
"step": 644
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.064,
|
| 2275 |
+
"grad_norm": 0.8393946886062622,
|
| 2276 |
+
"learning_rate": 0.0006288770053475936,
|
| 2277 |
+
"loss": 23.2965,
|
| 2278 |
+
"step": 646
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.0704,
|
| 2282 |
+
"grad_norm": 0.8161150217056274,
|
| 2283 |
+
"learning_rate": 0.0006245989304812835,
|
| 2284 |
+
"loss": 23.4888,
|
| 2285 |
+
"step": 648
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.0768,
|
| 2289 |
+
"grad_norm": 0.8854630589485168,
|
| 2290 |
+
"learning_rate": 0.0006203208556149733,
|
| 2291 |
+
"loss": 23.4233,
|
| 2292 |
+
"step": 650
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.0832,
|
| 2296 |
+
"grad_norm": 0.9034832119941711,
|
| 2297 |
+
"learning_rate": 0.0006160427807486631,
|
| 2298 |
+
"loss": 23.1208,
|
| 2299 |
+
"step": 652
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.0896,
|
| 2303 |
+
"grad_norm": 0.9552251696586609,
|
| 2304 |
+
"learning_rate": 0.000611764705882353,
|
| 2305 |
+
"loss": 23.2775,
|
| 2306 |
+
"step": 654
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 2.096,
|
| 2310 |
+
"grad_norm": 0.9383313059806824,
|
| 2311 |
+
"learning_rate": 0.0006074866310160429,
|
| 2312 |
+
"loss": 23.096,
|
| 2313 |
+
"step": 656
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 2.1024,
|
| 2317 |
+
"grad_norm": 0.9303053021430969,
|
| 2318 |
+
"learning_rate": 0.0006032085561497325,
|
| 2319 |
+
"loss": 23.6542,
|
| 2320 |
+
"step": 658
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 2.1088,
|
| 2324 |
+
"grad_norm": 0.9048749804496765,
|
| 2325 |
+
"learning_rate": 0.0005989304812834224,
|
| 2326 |
+
"loss": 23.3699,
|
| 2327 |
+
"step": 660
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 2.1152,
|
| 2331 |
+
"grad_norm": 0.9803421497344971,
|
| 2332 |
+
"learning_rate": 0.0005946524064171123,
|
| 2333 |
+
"loss": 23.3341,
|
| 2334 |
+
"step": 662
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 2.1216,
|
| 2338 |
+
"grad_norm": 0.8741451501846313,
|
| 2339 |
+
"learning_rate": 0.0005903743315508021,
|
| 2340 |
+
"loss": 23.2353,
|
| 2341 |
+
"step": 664
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 2.128,
|
| 2345 |
+
"grad_norm": 0.9050042629241943,
|
| 2346 |
+
"learning_rate": 0.000586096256684492,
|
| 2347 |
+
"loss": 23.7765,
|
| 2348 |
+
"step": 666
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.1344,
|
| 2352 |
+
"grad_norm": 0.8833932280540466,
|
| 2353 |
+
"learning_rate": 0.0005818181818181818,
|
| 2354 |
+
"loss": 23.154,
|
| 2355 |
+
"step": 668
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 2.1408,
|
| 2359 |
+
"grad_norm": 0.872748851776123,
|
| 2360 |
+
"learning_rate": 0.0005775401069518716,
|
| 2361 |
+
"loss": 23.5524,
|
| 2362 |
+
"step": 670
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 2.1471999999999998,
|
| 2366 |
+
"grad_norm": 0.9564759731292725,
|
| 2367 |
+
"learning_rate": 0.0005732620320855615,
|
| 2368 |
+
"loss": 23.3869,
|
| 2369 |
+
"step": 672
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 2.1536,
|
| 2373 |
+
"grad_norm": 0.9444039463996887,
|
| 2374 |
+
"learning_rate": 0.0005689839572192514,
|
| 2375 |
+
"loss": 23.5905,
|
| 2376 |
+
"step": 674
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 2.16,
|
| 2380 |
+
"grad_norm": 1.1383410692214966,
|
| 2381 |
+
"learning_rate": 0.0005647058823529411,
|
| 2382 |
+
"loss": 23.1071,
|
| 2383 |
+
"step": 676
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 2.1664,
|
| 2387 |
+
"grad_norm": 0.8750917911529541,
|
| 2388 |
+
"learning_rate": 0.000560427807486631,
|
| 2389 |
+
"loss": 23.5244,
|
| 2390 |
+
"step": 678
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 2.1728,
|
| 2394 |
+
"grad_norm": 0.8726853132247925,
|
| 2395 |
+
"learning_rate": 0.0005561497326203209,
|
| 2396 |
+
"loss": 23.0605,
|
| 2397 |
+
"step": 680
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 2.1792,
|
| 2401 |
+
"grad_norm": 0.9074258208274841,
|
| 2402 |
+
"learning_rate": 0.0005518716577540108,
|
| 2403 |
+
"loss": 23.243,
|
| 2404 |
+
"step": 682
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 2.1856,
|
| 2408 |
+
"grad_norm": 0.9091795086860657,
|
| 2409 |
+
"learning_rate": 0.0005475935828877005,
|
| 2410 |
+
"loss": 23.3617,
|
| 2411 |
+
"step": 684
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 2.192,
|
| 2415 |
+
"grad_norm": 0.909899115562439,
|
| 2416 |
+
"learning_rate": 0.0005433155080213904,
|
| 2417 |
+
"loss": 23.1892,
|
| 2418 |
+
"step": 686
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 2.1984,
|
| 2422 |
+
"grad_norm": 0.9476255774497986,
|
| 2423 |
+
"learning_rate": 0.0005390374331550803,
|
| 2424 |
+
"loss": 23.3369,
|
| 2425 |
+
"step": 688
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 2.2048,
|
| 2429 |
+
"grad_norm": 0.9601420760154724,
|
| 2430 |
+
"learning_rate": 0.0005347593582887701,
|
| 2431 |
+
"loss": 23.5679,
|
| 2432 |
+
"step": 690
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 2.2112,
|
| 2436 |
+
"grad_norm": 0.9360019564628601,
|
| 2437 |
+
"learning_rate": 0.0005304812834224599,
|
| 2438 |
+
"loss": 23.007,
|
| 2439 |
+
"step": 692
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 2.2176,
|
| 2443 |
+
"grad_norm": 0.9346802830696106,
|
| 2444 |
+
"learning_rate": 0.0005262032085561498,
|
| 2445 |
+
"loss": 23.0159,
|
| 2446 |
+
"step": 694
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 2.224,
|
| 2450 |
+
"grad_norm": 0.9711213111877441,
|
| 2451 |
+
"learning_rate": 0.0005219251336898396,
|
| 2452 |
+
"loss": 23.3363,
|
| 2453 |
+
"step": 696
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 2.2304,
|
| 2457 |
+
"grad_norm": 0.9546957612037659,
|
| 2458 |
+
"learning_rate": 0.0005176470588235295,
|
| 2459 |
+
"loss": 23.1201,
|
| 2460 |
+
"step": 698
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 2.2368,
|
| 2464 |
+
"grad_norm": 0.916655957698822,
|
| 2465 |
+
"learning_rate": 0.0005133689839572194,
|
| 2466 |
+
"loss": 23.2946,
|
| 2467 |
+
"step": 700
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 2.2432,
|
| 2471 |
+
"grad_norm": 0.8734573125839233,
|
| 2472 |
+
"learning_rate": 0.000509090909090909,
|
| 2473 |
+
"loss": 23.2751,
|
| 2474 |
+
"step": 702
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 2.2496,
|
| 2478 |
+
"grad_norm": 0.9505683779716492,
|
| 2479 |
+
"learning_rate": 0.0005048128342245989,
|
| 2480 |
+
"loss": 23.3028,
|
| 2481 |
+
"step": 704
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 2.2560000000000002,
|
| 2485 |
+
"grad_norm": 0.934208333492279,
|
| 2486 |
+
"learning_rate": 0.0005005347593582888,
|
| 2487 |
+
"loss": 23.2606,
|
| 2488 |
+
"step": 706
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 2.2624,
|
| 2492 |
+
"grad_norm": 0.8738580942153931,
|
| 2493 |
+
"learning_rate": 0.0004962566844919787,
|
| 2494 |
+
"loss": 23.0636,
|
| 2495 |
+
"step": 708
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 2.2688,
|
| 2499 |
+
"grad_norm": 0.9497429132461548,
|
| 2500 |
+
"learning_rate": 0.0004919786096256685,
|
| 2501 |
+
"loss": 23.3791,
|
| 2502 |
+
"step": 710
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 2.2752,
|
| 2506 |
+
"grad_norm": 0.9983781576156616,
|
| 2507 |
+
"learning_rate": 0.00048770053475935825,
|
| 2508 |
+
"loss": 23.4518,
|
| 2509 |
+
"step": 712
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 2.2816,
|
| 2513 |
+
"grad_norm": 0.9503285884857178,
|
| 2514 |
+
"learning_rate": 0.00048342245989304813,
|
| 2515 |
+
"loss": 23.2358,
|
| 2516 |
+
"step": 714
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 2.288,
|
| 2520 |
+
"grad_norm": 0.9116323590278625,
|
| 2521 |
+
"learning_rate": 0.00047914438502673796,
|
| 2522 |
+
"loss": 23.0996,
|
| 2523 |
+
"step": 716
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 2.2944,
|
| 2527 |
+
"grad_norm": 0.8628079295158386,
|
| 2528 |
+
"learning_rate": 0.0004748663101604278,
|
| 2529 |
+
"loss": 23.5187,
|
| 2530 |
+
"step": 718
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 2.3008,
|
| 2534 |
+
"grad_norm": 0.9411908984184265,
|
| 2535 |
+
"learning_rate": 0.00047058823529411766,
|
| 2536 |
+
"loss": 23.5873,
|
| 2537 |
+
"step": 720
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 2.3072,
|
| 2541 |
+
"grad_norm": 0.9314679503440857,
|
| 2542 |
+
"learning_rate": 0.0004663101604278075,
|
| 2543 |
+
"loss": 23.3654,
|
| 2544 |
+
"step": 722
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 2.3136,
|
| 2548 |
+
"grad_norm": 0.9462237358093262,
|
| 2549 |
+
"learning_rate": 0.00046203208556149736,
|
| 2550 |
+
"loss": 23.0101,
|
| 2551 |
+
"step": 724
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 2.32,
|
| 2555 |
+
"grad_norm": 0.889033317565918,
|
| 2556 |
+
"learning_rate": 0.0004577540106951872,
|
| 2557 |
+
"loss": 23.4283,
|
| 2558 |
+
"step": 726
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 2.3264,
|
| 2562 |
+
"grad_norm": 0.9167575836181641,
|
| 2563 |
+
"learning_rate": 0.000453475935828877,
|
| 2564 |
+
"loss": 23.2583,
|
| 2565 |
+
"step": 728
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 2.3327999999999998,
|
| 2569 |
+
"grad_norm": 0.9349282383918762,
|
| 2570 |
+
"learning_rate": 0.0004491978609625669,
|
| 2571 |
+
"loss": 23.463,
|
| 2572 |
+
"step": 730
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 2.3392,
|
| 2576 |
+
"grad_norm": 1.114784836769104,
|
| 2577 |
+
"learning_rate": 0.0004449197860962567,
|
| 2578 |
+
"loss": 23.2864,
|
| 2579 |
+
"step": 732
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 2.3456,
|
| 2583 |
+
"grad_norm": 0.9500236511230469,
|
| 2584 |
+
"learning_rate": 0.0004406417112299465,
|
| 2585 |
+
"loss": 23.4031,
|
| 2586 |
+
"step": 734
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 2.352,
|
| 2590 |
+
"grad_norm": 1.0214568376541138,
|
| 2591 |
+
"learning_rate": 0.00043636363636363637,
|
| 2592 |
+
"loss": 23.2233,
|
| 2593 |
+
"step": 736
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 2.3584,
|
| 2597 |
+
"grad_norm": 1.118489146232605,
|
| 2598 |
+
"learning_rate": 0.0004320855614973262,
|
| 2599 |
+
"loss": 23.7254,
|
| 2600 |
+
"step": 738
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 2.3648,
|
| 2604 |
+
"grad_norm": 0.9648391008377075,
|
| 2605 |
+
"learning_rate": 0.000427807486631016,
|
| 2606 |
+
"loss": 23.3774,
|
| 2607 |
+
"step": 740
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 2.3712,
|
| 2611 |
+
"grad_norm": 0.9128082394599915,
|
| 2612 |
+
"learning_rate": 0.0004235294117647059,
|
| 2613 |
+
"loss": 23.5378,
|
| 2614 |
+
"step": 742
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 2.3776,
|
| 2618 |
+
"grad_norm": 0.9346900582313538,
|
| 2619 |
+
"learning_rate": 0.0004192513368983957,
|
| 2620 |
+
"loss": 23.6871,
|
| 2621 |
+
"step": 744
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 2.384,
|
| 2625 |
+
"grad_norm": 1.0307550430297852,
|
| 2626 |
+
"learning_rate": 0.00041497326203208555,
|
| 2627 |
+
"loss": 23.2258,
|
| 2628 |
+
"step": 746
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 2.3904,
|
| 2632 |
+
"grad_norm": 0.9579919576644897,
|
| 2633 |
+
"learning_rate": 0.00041069518716577543,
|
| 2634 |
+
"loss": 23.269,
|
| 2635 |
+
"step": 748
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 2.3968,
|
| 2639 |
+
"grad_norm": 0.9140896201133728,
|
| 2640 |
+
"learning_rate": 0.00040641711229946525,
|
| 2641 |
+
"loss": 23.3352,
|
| 2642 |
+
"step": 750
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 2.4032,
|
| 2646 |
+
"grad_norm": 0.9879317879676819,
|
| 2647 |
+
"learning_rate": 0.00040213903743315513,
|
| 2648 |
+
"loss": 23.2264,
|
| 2649 |
+
"step": 752
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 2.4096,
|
| 2653 |
+
"grad_norm": 1.1229231357574463,
|
| 2654 |
+
"learning_rate": 0.00039786096256684496,
|
| 2655 |
+
"loss": 23.5893,
|
| 2656 |
+
"step": 754
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 2.416,
|
| 2660 |
+
"grad_norm": 0.8806203007698059,
|
| 2661 |
+
"learning_rate": 0.00039358288770053473,
|
| 2662 |
+
"loss": 23.3295,
|
| 2663 |
+
"step": 756
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 2.4224,
|
| 2667 |
+
"grad_norm": 1.0155560970306396,
|
| 2668 |
+
"learning_rate": 0.0003893048128342246,
|
| 2669 |
+
"loss": 23.0444,
|
| 2670 |
+
"step": 758
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 2.4288,
|
| 2674 |
+
"grad_norm": 0.9045442342758179,
|
| 2675 |
+
"learning_rate": 0.00038502673796791443,
|
| 2676 |
+
"loss": 22.9648,
|
| 2677 |
+
"step": 760
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 2.4352,
|
| 2681 |
+
"grad_norm": 0.9359453320503235,
|
| 2682 |
+
"learning_rate": 0.00038074866310160426,
|
| 2683 |
+
"loss": 23.6534,
|
| 2684 |
+
"step": 762
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 2.4416,
|
| 2688 |
+
"grad_norm": 0.9333987236022949,
|
| 2689 |
+
"learning_rate": 0.00037647058823529414,
|
| 2690 |
+
"loss": 23.3959,
|
| 2691 |
+
"step": 764
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 2.448,
|
| 2695 |
+
"grad_norm": 0.8483988046646118,
|
| 2696 |
+
"learning_rate": 0.00037219251336898396,
|
| 2697 |
+
"loss": 23.8575,
|
| 2698 |
+
"step": 766
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 2.4544,
|
| 2702 |
+
"grad_norm": 0.8853796720504761,
|
| 2703 |
+
"learning_rate": 0.0003679144385026738,
|
| 2704 |
+
"loss": 23.0032,
|
| 2705 |
+
"step": 768
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 2.4608,
|
| 2709 |
+
"grad_norm": 0.9364005327224731,
|
| 2710 |
+
"learning_rate": 0.00036363636363636367,
|
| 2711 |
+
"loss": 23.1803,
|
| 2712 |
+
"step": 770
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 2.4672,
|
| 2716 |
+
"grad_norm": 0.820959210395813,
|
| 2717 |
+
"learning_rate": 0.0003593582887700535,
|
| 2718 |
+
"loss": 23.4326,
|
| 2719 |
+
"step": 772
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 2.4736000000000002,
|
| 2723 |
+
"grad_norm": 0.927909255027771,
|
| 2724 |
+
"learning_rate": 0.0003550802139037433,
|
| 2725 |
+
"loss": 22.8314,
|
| 2726 |
+
"step": 774
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 2.48,
|
| 2730 |
+
"grad_norm": 0.9819096922874451,
|
| 2731 |
+
"learning_rate": 0.0003508021390374332,
|
| 2732 |
+
"loss": 23.3604,
|
| 2733 |
+
"step": 776
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 2.4864,
|
| 2737 |
+
"grad_norm": 0.8942359089851379,
|
| 2738 |
+
"learning_rate": 0.00034652406417112297,
|
| 2739 |
+
"loss": 23.3988,
|
| 2740 |
+
"step": 778
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 2.4928,
|
| 2744 |
+
"grad_norm": 0.9608676433563232,
|
| 2745 |
+
"learning_rate": 0.0003422459893048128,
|
| 2746 |
+
"loss": 23.2326,
|
| 2747 |
+
"step": 780
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 2.4992,
|
| 2751 |
+
"grad_norm": 0.8843042254447937,
|
| 2752 |
+
"learning_rate": 0.0003379679144385027,
|
| 2753 |
+
"loss": 23.3506,
|
| 2754 |
+
"step": 782
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 2.5056000000000003,
|
| 2758 |
+
"grad_norm": 0.8857446312904358,
|
| 2759 |
+
"learning_rate": 0.0003336898395721925,
|
| 2760 |
+
"loss": 23.1861,
|
| 2761 |
+
"step": 784
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 2.512,
|
| 2765 |
+
"grad_norm": 0.8458705544471741,
|
| 2766 |
+
"learning_rate": 0.0003294117647058824,
|
| 2767 |
+
"loss": 23.0167,
|
| 2768 |
+
"step": 786
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 2.5183999999999997,
|
| 2772 |
+
"grad_norm": 0.8760762214660645,
|
| 2773 |
+
"learning_rate": 0.0003251336898395722,
|
| 2774 |
+
"loss": 23.5173,
|
| 2775 |
+
"step": 788
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 2.5248,
|
| 2779 |
+
"grad_norm": 0.8493122458457947,
|
| 2780 |
+
"learning_rate": 0.00032085561497326203,
|
| 2781 |
+
"loss": 23.257,
|
| 2782 |
+
"step": 790
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 2.5312,
|
| 2786 |
+
"grad_norm": 0.8905952572822571,
|
| 2787 |
+
"learning_rate": 0.0003165775401069519,
|
| 2788 |
+
"loss": 23.1194,
|
| 2789 |
+
"step": 792
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 2.5376,
|
| 2793 |
+
"grad_norm": 0.9125280976295471,
|
| 2794 |
+
"learning_rate": 0.00031229946524064173,
|
| 2795 |
+
"loss": 23.0237,
|
| 2796 |
+
"step": 794
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 2.544,
|
| 2800 |
+
"grad_norm": 0.9156554341316223,
|
| 2801 |
+
"learning_rate": 0.00030802139037433156,
|
| 2802 |
+
"loss": 23.4626,
|
| 2803 |
+
"step": 796
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 2.5504,
|
| 2807 |
+
"grad_norm": 0.8901218771934509,
|
| 2808 |
+
"learning_rate": 0.00030374331550802144,
|
| 2809 |
+
"loss": 22.9936,
|
| 2810 |
+
"step": 798
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 2.5568,
|
| 2814 |
+
"grad_norm": 0.8714930415153503,
|
| 2815 |
+
"learning_rate": 0.0002994652406417112,
|
| 2816 |
+
"loss": 23.1742,
|
| 2817 |
+
"step": 800
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 2.5568,
|
| 2821 |
+
"eval_loss": 1.4636129140853882,
|
| 2822 |
+
"eval_runtime": 1115.7802,
|
| 2823 |
+
"eval_samples_per_second": 8.962,
|
| 2824 |
+
"eval_steps_per_second": 1.12,
|
| 2825 |
+
"step": 800
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 2.5632,
|
| 2829 |
+
"grad_norm": 0.8894703984260559,
|
| 2830 |
+
"learning_rate": 0.00029518716577540103,
|
| 2831 |
+
"loss": 23.6523,
|
| 2832 |
+
"step": 802
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 2.5696,
|
| 2836 |
+
"grad_norm": 0.8964853286743164,
|
| 2837 |
+
"learning_rate": 0.0002909090909090909,
|
| 2838 |
+
"loss": 22.9383,
|
| 2839 |
+
"step": 804
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 2.576,
|
| 2843 |
+
"grad_norm": 0.8526540398597717,
|
| 2844 |
+
"learning_rate": 0.00028663101604278074,
|
| 2845 |
+
"loss": 23.1684,
|
| 2846 |
+
"step": 806
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 2.5824,
|
| 2850 |
+
"grad_norm": 1.0182241201400757,
|
| 2851 |
+
"learning_rate": 0.00028235294117647056,
|
| 2852 |
+
"loss": 23.3383,
|
| 2853 |
+
"step": 808
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 2.5888,
|
| 2857 |
+
"grad_norm": 0.9509109854698181,
|
| 2858 |
+
"learning_rate": 0.00027807486631016044,
|
| 2859 |
+
"loss": 23.4199,
|
| 2860 |
+
"step": 810
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 2.5952,
|
| 2864 |
+
"grad_norm": 0.8805685639381409,
|
| 2865 |
+
"learning_rate": 0.00027379679144385027,
|
| 2866 |
+
"loss": 23.3654,
|
| 2867 |
+
"step": 812
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 2.6016,
|
| 2871 |
+
"grad_norm": 0.9017741680145264,
|
| 2872 |
+
"learning_rate": 0.00026951871657754015,
|
| 2873 |
+
"loss": 23.2814,
|
| 2874 |
+
"step": 814
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 2.608,
|
| 2878 |
+
"grad_norm": 0.844363808631897,
|
| 2879 |
+
"learning_rate": 0.00026524064171122997,
|
| 2880 |
+
"loss": 23.3663,
|
| 2881 |
+
"step": 816
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 2.6144,
|
| 2885 |
+
"grad_norm": 0.868501603603363,
|
| 2886 |
+
"learning_rate": 0.0002609625668449198,
|
| 2887 |
+
"loss": 23.3927,
|
| 2888 |
+
"step": 818
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 2.6208,
|
| 2892 |
+
"grad_norm": 0.965802788734436,
|
| 2893 |
+
"learning_rate": 0.0002566844919786097,
|
| 2894 |
+
"loss": 23.3886,
|
| 2895 |
+
"step": 820
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 2.6272,
|
| 2899 |
+
"grad_norm": 0.9137208461761475,
|
| 2900 |
+
"learning_rate": 0.00025240641711229945,
|
| 2901 |
+
"loss": 23.2161,
|
| 2902 |
+
"step": 822
|
| 2903 |
+
},
|
| 2904 |
+
{
|
| 2905 |
+
"epoch": 2.6336,
|
| 2906 |
+
"grad_norm": 0.8800885081291199,
|
| 2907 |
+
"learning_rate": 0.00024812834224598933,
|
| 2908 |
+
"loss": 23.4479,
|
| 2909 |
+
"step": 824
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 2.64,
|
| 2913 |
+
"grad_norm": 0.8783839344978333,
|
| 2914 |
+
"learning_rate": 0.00024385026737967913,
|
| 2915 |
+
"loss": 23.1788,
|
| 2916 |
+
"step": 826
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"epoch": 2.6464,
|
| 2920 |
+
"grad_norm": 0.8877150416374207,
|
| 2921 |
+
"learning_rate": 0.00023957219251336898,
|
| 2922 |
+
"loss": 23.3931,
|
| 2923 |
+
"step": 828
|
| 2924 |
+
},
|
| 2925 |
+
{
|
| 2926 |
+
"epoch": 2.6528,
|
| 2927 |
+
"grad_norm": 0.8638187050819397,
|
| 2928 |
+
"learning_rate": 0.00023529411764705883,
|
| 2929 |
+
"loss": 23.1699,
|
| 2930 |
+
"step": 830
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 2.6592000000000002,
|
| 2934 |
+
"grad_norm": 0.8768156170845032,
|
| 2935 |
+
"learning_rate": 0.00023101604278074868,
|
| 2936 |
+
"loss": 23.2747,
|
| 2937 |
+
"step": 832
|
| 2938 |
+
},
|
| 2939 |
+
{
|
| 2940 |
+
"epoch": 2.6656,
|
| 2941 |
+
"grad_norm": 0.9169402718544006,
|
| 2942 |
+
"learning_rate": 0.0002267379679144385,
|
| 2943 |
+
"loss": 23.281,
|
| 2944 |
+
"step": 834
|
| 2945 |
+
},
|
| 2946 |
+
{
|
| 2947 |
+
"epoch": 2.672,
|
| 2948 |
+
"grad_norm": 0.978992223739624,
|
| 2949 |
+
"learning_rate": 0.00022245989304812836,
|
| 2950 |
+
"loss": 23.0263,
|
| 2951 |
+
"step": 836
|
| 2952 |
+
},
|
| 2953 |
+
{
|
| 2954 |
+
"epoch": 2.6784,
|
| 2955 |
+
"grad_norm": 0.9082220792770386,
|
| 2956 |
+
"learning_rate": 0.00021818181818181818,
|
| 2957 |
+
"loss": 23.1189,
|
| 2958 |
+
"step": 838
|
| 2959 |
+
},
|
| 2960 |
+
{
|
| 2961 |
+
"epoch": 2.6848,
|
| 2962 |
+
"grad_norm": 0.9290631413459778,
|
| 2963 |
+
"learning_rate": 0.000213903743315508,
|
| 2964 |
+
"loss": 23.6318,
|
| 2965 |
+
"step": 840
|
| 2966 |
+
},
|
| 2967 |
+
{
|
| 2968 |
+
"epoch": 2.6912000000000003,
|
| 2969 |
+
"grad_norm": 0.9007918834686279,
|
| 2970 |
+
"learning_rate": 0.00020962566844919786,
|
| 2971 |
+
"loss": 23.0228,
|
| 2972 |
+
"step": 842
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 2.6976,
|
| 2976 |
+
"grad_norm": 0.9045092463493347,
|
| 2977 |
+
"learning_rate": 0.00020534759358288771,
|
| 2978 |
+
"loss": 23.1173,
|
| 2979 |
+
"step": 844
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 2.7039999999999997,
|
| 2983 |
+
"grad_norm": 0.8459358215332031,
|
| 2984 |
+
"learning_rate": 0.00020106951871657757,
|
| 2985 |
+
"loss": 23.0842,
|
| 2986 |
+
"step": 846
|
| 2987 |
+
},
|
| 2988 |
+
{
|
| 2989 |
+
"epoch": 2.7104,
|
| 2990 |
+
"grad_norm": 0.8688234686851501,
|
| 2991 |
+
"learning_rate": 0.00019679144385026736,
|
| 2992 |
+
"loss": 23.1473,
|
| 2993 |
+
"step": 848
|
| 2994 |
+
},
|
| 2995 |
+
{
|
| 2996 |
+
"epoch": 2.7168,
|
| 2997 |
+
"grad_norm": 0.8705434203147888,
|
| 2998 |
+
"learning_rate": 0.00019251336898395722,
|
| 2999 |
+
"loss": 23.2901,
|
| 3000 |
+
"step": 850
|
| 3001 |
+
},
|
| 3002 |
+
{
|
| 3003 |
+
"epoch": 2.7232,
|
| 3004 |
+
"grad_norm": 0.9049879908561707,
|
| 3005 |
+
"learning_rate": 0.00018823529411764707,
|
| 3006 |
+
"loss": 23.2844,
|
| 3007 |
+
"step": 852
|
| 3008 |
+
},
|
| 3009 |
+
{
|
| 3010 |
+
"epoch": 2.7296,
|
| 3011 |
+
"grad_norm": 0.8677183985710144,
|
| 3012 |
+
"learning_rate": 0.0001839572192513369,
|
| 3013 |
+
"loss": 23.441,
|
| 3014 |
+
"step": 854
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 2.7359999999999998,
|
| 3018 |
+
"grad_norm": 0.8370922207832336,
|
| 3019 |
+
"learning_rate": 0.00017967914438502675,
|
| 3020 |
+
"loss": 23.3627,
|
| 3021 |
+
"step": 856
|
| 3022 |
+
},
|
| 3023 |
+
{
|
| 3024 |
+
"epoch": 2.7424,
|
| 3025 |
+
"grad_norm": 0.827491819858551,
|
| 3026 |
+
"learning_rate": 0.0001754010695187166,
|
| 3027 |
+
"loss": 23.3567,
|
| 3028 |
+
"step": 858
|
| 3029 |
+
},
|
| 3030 |
+
{
|
| 3031 |
+
"epoch": 2.7488,
|
| 3032 |
+
"grad_norm": 0.8676392436027527,
|
| 3033 |
+
"learning_rate": 0.0001711229946524064,
|
| 3034 |
+
"loss": 23.5228,
|
| 3035 |
+
"step": 860
|
| 3036 |
+
},
|
| 3037 |
+
{
|
| 3038 |
+
"epoch": 2.7552,
|
| 3039 |
+
"grad_norm": 0.916731059551239,
|
| 3040 |
+
"learning_rate": 0.00016684491978609625,
|
| 3041 |
+
"loss": 23.4274,
|
| 3042 |
+
"step": 862
|
| 3043 |
+
},
|
| 3044 |
+
{
|
| 3045 |
+
"epoch": 2.7616,
|
| 3046 |
+
"grad_norm": 0.8114993572235107,
|
| 3047 |
+
"learning_rate": 0.0001625668449197861,
|
| 3048 |
+
"loss": 23.0131,
|
| 3049 |
+
"step": 864
|
| 3050 |
+
},
|
| 3051 |
+
{
|
| 3052 |
+
"epoch": 2.768,
|
| 3053 |
+
"grad_norm": 0.821692705154419,
|
| 3054 |
+
"learning_rate": 0.00015828877005347595,
|
| 3055 |
+
"loss": 22.9853,
|
| 3056 |
+
"step": 866
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 2.7744,
|
| 3060 |
+
"grad_norm": 0.8291884064674377,
|
| 3061 |
+
"learning_rate": 0.00015401069518716578,
|
| 3062 |
+
"loss": 22.6708,
|
| 3063 |
+
"step": 868
|
| 3064 |
+
},
|
| 3065 |
+
{
|
| 3066 |
+
"epoch": 2.7808,
|
| 3067 |
+
"grad_norm": 0.8806215524673462,
|
| 3068 |
+
"learning_rate": 0.0001497326203208556,
|
| 3069 |
+
"loss": 23.079,
|
| 3070 |
+
"step": 870
|
| 3071 |
+
},
|
| 3072 |
+
{
|
| 3073 |
+
"epoch": 2.7872,
|
| 3074 |
+
"grad_norm": 0.8456304669380188,
|
| 3075 |
+
"learning_rate": 0.00014545454545454546,
|
| 3076 |
+
"loss": 23.3899,
|
| 3077 |
+
"step": 872
|
| 3078 |
+
},
|
| 3079 |
+
{
|
| 3080 |
+
"epoch": 2.7936,
|
| 3081 |
+
"grad_norm": 0.8849140405654907,
|
| 3082 |
+
"learning_rate": 0.00014117647058823528,
|
| 3083 |
+
"loss": 23.3624,
|
| 3084 |
+
"step": 874
|
| 3085 |
+
},
|
| 3086 |
+
{
|
| 3087 |
+
"epoch": 2.8,
|
| 3088 |
+
"grad_norm": 0.8567163944244385,
|
| 3089 |
+
"learning_rate": 0.00013689839572192513,
|
| 3090 |
+
"loss": 23.2244,
|
| 3091 |
+
"step": 876
|
| 3092 |
+
},
|
| 3093 |
+
{
|
| 3094 |
+
"epoch": 2.8064,
|
| 3095 |
+
"grad_norm": 0.886084258556366,
|
| 3096 |
+
"learning_rate": 0.00013262032085561499,
|
| 3097 |
+
"loss": 23.275,
|
| 3098 |
+
"step": 878
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 2.8128,
|
| 3102 |
+
"grad_norm": 0.8626444339752197,
|
| 3103 |
+
"learning_rate": 0.00012834224598930484,
|
| 3104 |
+
"loss": 23.3534,
|
| 3105 |
+
"step": 880
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"epoch": 2.8192,
|
| 3109 |
+
"grad_norm": 0.8719081282615662,
|
| 3110 |
+
"learning_rate": 0.00012406417112299466,
|
| 3111 |
+
"loss": 23.7974,
|
| 3112 |
+
"step": 882
|
| 3113 |
+
},
|
| 3114 |
+
{
|
| 3115 |
+
"epoch": 2.8256,
|
| 3116 |
+
"grad_norm": 0.8361597061157227,
|
| 3117 |
+
"learning_rate": 0.00011978609625668449,
|
| 3118 |
+
"loss": 23.2917,
|
| 3119 |
+
"step": 884
|
| 3120 |
+
},
|
| 3121 |
+
{
|
| 3122 |
+
"epoch": 2.832,
|
| 3123 |
+
"grad_norm": 0.9440580606460571,
|
| 3124 |
+
"learning_rate": 0.00011550802139037434,
|
| 3125 |
+
"loss": 23.2307,
|
| 3126 |
+
"step": 886
|
| 3127 |
+
},
|
| 3128 |
+
{
|
| 3129 |
+
"epoch": 2.8384,
|
| 3130 |
+
"grad_norm": 0.84004145860672,
|
| 3131 |
+
"learning_rate": 0.00011122994652406418,
|
| 3132 |
+
"loss": 23.135,
|
| 3133 |
+
"step": 888
|
| 3134 |
+
},
|
| 3135 |
+
{
|
| 3136 |
+
"epoch": 2.8448,
|
| 3137 |
+
"grad_norm": 0.836331307888031,
|
| 3138 |
+
"learning_rate": 0.000106951871657754,
|
| 3139 |
+
"loss": 23.327,
|
| 3140 |
+
"step": 890
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 2.8512,
|
| 3144 |
+
"grad_norm": 0.9749852418899536,
|
| 3145 |
+
"learning_rate": 0.00010267379679144386,
|
| 3146 |
+
"loss": 23.0129,
|
| 3147 |
+
"step": 892
|
| 3148 |
+
},
|
| 3149 |
+
{
|
| 3150 |
+
"epoch": 2.8576,
|
| 3151 |
+
"grad_norm": 0.902911365032196,
|
| 3152 |
+
"learning_rate": 9.839572192513368e-05,
|
| 3153 |
+
"loss": 23.4656,
|
| 3154 |
+
"step": 894
|
| 3155 |
+
},
|
| 3156 |
+
{
|
| 3157 |
+
"epoch": 2.864,
|
| 3158 |
+
"grad_norm": 0.8584335446357727,
|
| 3159 |
+
"learning_rate": 9.411764705882353e-05,
|
| 3160 |
+
"loss": 22.9288,
|
| 3161 |
+
"step": 896
|
| 3162 |
+
},
|
| 3163 |
+
{
|
| 3164 |
+
"epoch": 2.8704,
|
| 3165 |
+
"grad_norm": 0.8301668167114258,
|
| 3166 |
+
"learning_rate": 8.983957219251337e-05,
|
| 3167 |
+
"loss": 23.4383,
|
| 3168 |
+
"step": 898
|
| 3169 |
+
},
|
| 3170 |
+
{
|
| 3171 |
+
"epoch": 2.8768000000000002,
|
| 3172 |
+
"grad_norm": 0.8426039814949036,
|
| 3173 |
+
"learning_rate": 8.55614973262032e-05,
|
| 3174 |
+
"loss": 23.2636,
|
| 3175 |
+
"step": 900
|
| 3176 |
+
},
|
| 3177 |
+
{
|
| 3178 |
+
"epoch": 2.8832,
|
| 3179 |
+
"grad_norm": 0.8241990208625793,
|
| 3180 |
+
"learning_rate": 8.128342245989305e-05,
|
| 3181 |
+
"loss": 23.4808,
|
| 3182 |
+
"step": 902
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 2.8895999999999997,
|
| 3186 |
+
"grad_norm": 0.8555430769920349,
|
| 3187 |
+
"learning_rate": 7.700534759358289e-05,
|
| 3188 |
+
"loss": 22.9983,
|
| 3189 |
+
"step": 904
|
| 3190 |
+
},
|
| 3191 |
+
{
|
| 3192 |
+
"epoch": 2.896,
|
| 3193 |
+
"grad_norm": 0.8600494265556335,
|
| 3194 |
+
"learning_rate": 7.272727272727273e-05,
|
| 3195 |
+
"loss": 23.2584,
|
| 3196 |
+
"step": 906
|
| 3197 |
+
},
|
| 3198 |
+
{
|
| 3199 |
+
"epoch": 2.9024,
|
| 3200 |
+
"grad_norm": 0.9131312966346741,
|
| 3201 |
+
"learning_rate": 6.844919786096257e-05,
|
| 3202 |
+
"loss": 23.4513,
|
| 3203 |
+
"step": 908
|
| 3204 |
+
},
|
| 3205 |
+
{
|
| 3206 |
+
"epoch": 2.9088000000000003,
|
| 3207 |
+
"grad_norm": 0.8168982267379761,
|
| 3208 |
+
"learning_rate": 6.417112299465242e-05,
|
| 3209 |
+
"loss": 23.4352,
|
| 3210 |
+
"step": 910
|
| 3211 |
+
},
|
| 3212 |
+
{
|
| 3213 |
+
"epoch": 2.9152,
|
| 3214 |
+
"grad_norm": 0.8447926640510559,
|
| 3215 |
+
"learning_rate": 5.9893048128342244e-05,
|
| 3216 |
+
"loss": 23.2975,
|
| 3217 |
+
"step": 912
|
| 3218 |
+
},
|
| 3219 |
+
{
|
| 3220 |
+
"epoch": 2.9215999999999998,
|
| 3221 |
+
"grad_norm": 0.8652685284614563,
|
| 3222 |
+
"learning_rate": 5.561497326203209e-05,
|
| 3223 |
+
"loss": 23.5172,
|
| 3224 |
+
"step": 914
|
| 3225 |
+
},
|
| 3226 |
+
{
|
| 3227 |
+
"epoch": 2.928,
|
| 3228 |
+
"grad_norm": 0.8298205733299255,
|
| 3229 |
+
"learning_rate": 5.133689839572193e-05,
|
| 3230 |
+
"loss": 23.5154,
|
| 3231 |
+
"step": 916
|
| 3232 |
+
},
|
| 3233 |
+
{
|
| 3234 |
+
"epoch": 2.9344,
|
| 3235 |
+
"grad_norm": 0.8782302141189575,
|
| 3236 |
+
"learning_rate": 4.705882352941177e-05,
|
| 3237 |
+
"loss": 23.3597,
|
| 3238 |
+
"step": 918
|
| 3239 |
+
},
|
| 3240 |
+
{
|
| 3241 |
+
"epoch": 2.9408,
|
| 3242 |
+
"grad_norm": 0.9018718004226685,
|
| 3243 |
+
"learning_rate": 4.27807486631016e-05,
|
| 3244 |
+
"loss": 23.601,
|
| 3245 |
+
"step": 920
|
| 3246 |
+
},
|
| 3247 |
+
{
|
| 3248 |
+
"epoch": 2.9472,
|
| 3249 |
+
"grad_norm": 0.912187933921814,
|
| 3250 |
+
"learning_rate": 3.8502673796791445e-05,
|
| 3251 |
+
"loss": 23.4442,
|
| 3252 |
+
"step": 922
|
| 3253 |
+
},
|
| 3254 |
+
{
|
| 3255 |
+
"epoch": 2.9536,
|
| 3256 |
+
"grad_norm": 0.8485115170478821,
|
| 3257 |
+
"learning_rate": 3.4224598930481284e-05,
|
| 3258 |
+
"loss": 23.0539,
|
| 3259 |
+
"step": 924
|
| 3260 |
+
},
|
| 3261 |
+
{
|
| 3262 |
+
"epoch": 2.96,
|
| 3263 |
+
"grad_norm": 0.880998432636261,
|
| 3264 |
+
"learning_rate": 2.9946524064171122e-05,
|
| 3265 |
+
"loss": 23.1452,
|
| 3266 |
+
"step": 926
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 2.9664,
|
| 3270 |
+
"grad_norm": 0.8453803658485413,
|
| 3271 |
+
"learning_rate": 2.5668449197860964e-05,
|
| 3272 |
+
"loss": 22.8998,
|
| 3273 |
+
"step": 928
|
| 3274 |
+
},
|
| 3275 |
+
{
|
| 3276 |
+
"epoch": 2.9728,
|
| 3277 |
+
"grad_norm": 0.8399450182914734,
|
| 3278 |
+
"learning_rate": 2.13903743315508e-05,
|
| 3279 |
+
"loss": 23.0928,
|
| 3280 |
+
"step": 930
|
| 3281 |
+
},
|
| 3282 |
+
{
|
| 3283 |
+
"epoch": 2.9792,
|
| 3284 |
+
"grad_norm": 0.8890286684036255,
|
| 3285 |
+
"learning_rate": 1.7112299465240642e-05,
|
| 3286 |
+
"loss": 23.0015,
|
| 3287 |
+
"step": 932
|
| 3288 |
+
},
|
| 3289 |
+
{
|
| 3290 |
+
"epoch": 2.9856,
|
| 3291 |
+
"grad_norm": 0.8455818295478821,
|
| 3292 |
+
"learning_rate": 1.2834224598930482e-05,
|
| 3293 |
+
"loss": 23.4294,
|
| 3294 |
+
"step": 934
|
| 3295 |
+
},
|
| 3296 |
+
{
|
| 3297 |
+
"epoch": 2.992,
|
| 3298 |
+
"grad_norm": 0.8911629915237427,
|
| 3299 |
+
"learning_rate": 8.556149732620321e-06,
|
| 3300 |
+
"loss": 23.0343,
|
| 3301 |
+
"step": 936
|
| 3302 |
+
},
|
| 3303 |
+
{
|
| 3304 |
+
"epoch": 2.992,
|
| 3305 |
+
"step": 936,
|
| 3306 |
+
"total_flos": 1.015865179865088e+19,
|
| 3307 |
+
"train_loss": 28.25554455243624,
|
| 3308 |
+
"train_runtime": 30178.7669,
|
| 3309 |
+
"train_samples_per_second": 7.953,
|
| 3310 |
+
"train_steps_per_second": 0.031
|
| 3311 |
+
},
|
| 3312 |
+
{
|
| 3313 |
+
"epoch": 2.992,
|
| 3314 |
+
"eval_loss": 1.4616048336029053,
|
| 3315 |
+
"eval_runtime": 1115.0715,
|
| 3316 |
+
"eval_samples_per_second": 8.968,
|
| 3317 |
+
"eval_steps_per_second": 1.121,
|
| 3318 |
+
"step": 936
|
| 3319 |
+
},
|
| 3320 |
+
{
|
| 3321 |
+
"epoch": 2.992,
|
| 3322 |
+
"eval_loss": 1.4569849967956543,
|
| 3323 |
+
"eval_runtime": 1130.2457,
|
| 3324 |
+
"eval_samples_per_second": 8.848,
|
| 3325 |
+
"eval_steps_per_second": 1.106,
|
| 3326 |
+
"step": 936
|
| 3327 |
+
}
|
| 3328 |
+
],
|
| 3329 |
+
"logging_steps": 2,
|
| 3330 |
+
"max_steps": 936,
|
| 3331 |
+
"num_input_tokens_seen": 0,
|
| 3332 |
+
"num_train_epochs": 3,
|
| 3333 |
+
"save_steps": 500,
|
| 3334 |
+
"stateful_callbacks": {
|
| 3335 |
+
"TrainerControl": {
|
| 3336 |
+
"args": {
|
| 3337 |
+
"should_epoch_stop": false,
|
| 3338 |
+
"should_evaluate": false,
|
| 3339 |
+
"should_log": false,
|
| 3340 |
+
"should_save": true,
|
| 3341 |
+
"should_training_stop": true
|
| 3342 |
+
},
|
| 3343 |
+
"attributes": {}
|
| 3344 |
+
}
|
| 3345 |
+
},
|
| 3346 |
+
"total_flos": 1.015865179865088e+19,
|
| 3347 |
+
"train_batch_size": 16,
|
| 3348 |
+
"trial_name": null,
|
| 3349 |
+
"trial_params": null
|
| 3350 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:308b76b99b3a1683d0897ca6d4a649b595a25f58fbeb8ebdc51a2e5bd9dd546c
|
| 3 |
+
size 5432
|