ptsv/olmo-7b-lora_tinystories_baseline
Browse files- README.md +61 -0
- adapter_config.json +38 -0
- adapter_model.safetensors +3 -0
- trainer_state.json +1367 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_baseline
|
| 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/84suv6on)
|
| 16 |
+
# tinystories_baseline
|
| 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: 2.2266
|
| 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: 0.001
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 44 |
+
- total_train_batch_size: 128
|
| 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 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- PEFT 0.14.0
|
| 58 |
+
- Transformers 4.47.0
|
| 59 |
+
- Pytorch 2.4.1+cu121
|
| 60 |
+
- Datasets 3.2.0
|
| 61 |
+
- 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": 32,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.05,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 32,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"lm_head",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"v_proj",
|
| 32 |
+
"q_proj",
|
| 33 |
+
"k_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 sha256:6779fb767ecd6aeedd8633755a220532b5fc1064f0ac22dde0c008ca28c9924c
|
| 3 |
+
size 1151021048
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1367 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 400,
|
| 6 |
+
"global_step": 375,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016,
|
| 13 |
+
"grad_norm": 0.5721463561058044,
|
| 14 |
+
"learning_rate": 0.000997326203208556,
|
| 15 |
+
"loss": 22.6723,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.032,
|
| 20 |
+
"grad_norm": 1.5221903324127197,
|
| 21 |
+
"learning_rate": 0.0009919786096256684,
|
| 22 |
+
"loss": 22.7502,
|
| 23 |
+
"step": 4
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.048,
|
| 27 |
+
"grad_norm": 3.269012212753296,
|
| 28 |
+
"learning_rate": 0.0009866310160427808,
|
| 29 |
+
"loss": 22.2706,
|
| 30 |
+
"step": 6
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.064,
|
| 34 |
+
"grad_norm": 4.567020416259766,
|
| 35 |
+
"learning_rate": 0.0009812834224598931,
|
| 36 |
+
"loss": 21.3625,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08,
|
| 41 |
+
"grad_norm": 7.019204139709473,
|
| 42 |
+
"learning_rate": 0.0009759358288770054,
|
| 43 |
+
"loss": 20.7279,
|
| 44 |
+
"step": 10
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.096,
|
| 48 |
+
"grad_norm": 8.498096466064453,
|
| 49 |
+
"learning_rate": 0.0009705882352941176,
|
| 50 |
+
"loss": 20.8221,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.112,
|
| 55 |
+
"grad_norm": 7.8151397705078125,
|
| 56 |
+
"learning_rate": 0.00096524064171123,
|
| 57 |
+
"loss": 20.4136,
|
| 58 |
+
"step": 14
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.128,
|
| 62 |
+
"grad_norm": 8.028499603271484,
|
| 63 |
+
"learning_rate": 0.0009598930481283422,
|
| 64 |
+
"loss": 20.2719,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.144,
|
| 69 |
+
"grad_norm": 8.516434669494629,
|
| 70 |
+
"learning_rate": 0.0009545454545454546,
|
| 71 |
+
"loss": 20.1681,
|
| 72 |
+
"step": 18
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16,
|
| 76 |
+
"grad_norm": 8.52490520477295,
|
| 77 |
+
"learning_rate": 0.0009491978609625669,
|
| 78 |
+
"loss": 19.8895,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.176,
|
| 83 |
+
"grad_norm": 6.709629058837891,
|
| 84 |
+
"learning_rate": 0.0009438502673796791,
|
| 85 |
+
"loss": 19.93,
|
| 86 |
+
"step": 22
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.192,
|
| 90 |
+
"grad_norm": 6.038687705993652,
|
| 91 |
+
"learning_rate": 0.0009385026737967914,
|
| 92 |
+
"loss": 19.6312,
|
| 93 |
+
"step": 24
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.208,
|
| 97 |
+
"grad_norm": 5.785665512084961,
|
| 98 |
+
"learning_rate": 0.0009331550802139037,
|
| 99 |
+
"loss": 19.7683,
|
| 100 |
+
"step": 26
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.224,
|
| 104 |
+
"grad_norm": 5.79067850112915,
|
| 105 |
+
"learning_rate": 0.0009278074866310161,
|
| 106 |
+
"loss": 19.6965,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.24,
|
| 111 |
+
"grad_norm": 5.166928291320801,
|
| 112 |
+
"learning_rate": 0.0009224598930481284,
|
| 113 |
+
"loss": 19.4005,
|
| 114 |
+
"step": 30
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.256,
|
| 118 |
+
"grad_norm": 4.578023433685303,
|
| 119 |
+
"learning_rate": 0.0009171122994652407,
|
| 120 |
+
"loss": 19.3963,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.272,
|
| 125 |
+
"grad_norm": 4.7540693283081055,
|
| 126 |
+
"learning_rate": 0.0009117647058823529,
|
| 127 |
+
"loss": 19.4129,
|
| 128 |
+
"step": 34
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.288,
|
| 132 |
+
"grad_norm": 5.394408226013184,
|
| 133 |
+
"learning_rate": 0.0009064171122994653,
|
| 134 |
+
"loss": 19.5821,
|
| 135 |
+
"step": 36
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.304,
|
| 139 |
+
"grad_norm": 4.4902753829956055,
|
| 140 |
+
"learning_rate": 0.0009010695187165776,
|
| 141 |
+
"loss": 19.6562,
|
| 142 |
+
"step": 38
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.32,
|
| 146 |
+
"grad_norm": 5.49019193649292,
|
| 147 |
+
"learning_rate": 0.0008957219251336899,
|
| 148 |
+
"loss": 19.3588,
|
| 149 |
+
"step": 40
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.336,
|
| 153 |
+
"grad_norm": 4.184142589569092,
|
| 154 |
+
"learning_rate": 0.0008903743315508022,
|
| 155 |
+
"loss": 18.9032,
|
| 156 |
+
"step": 42
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.352,
|
| 160 |
+
"grad_norm": 3.98618483543396,
|
| 161 |
+
"learning_rate": 0.0008850267379679144,
|
| 162 |
+
"loss": 19.1882,
|
| 163 |
+
"step": 44
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.368,
|
| 167 |
+
"grad_norm": 4.851687908172607,
|
| 168 |
+
"learning_rate": 0.0008796791443850267,
|
| 169 |
+
"loss": 19.4565,
|
| 170 |
+
"step": 46
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.384,
|
| 174 |
+
"grad_norm": 4.108444690704346,
|
| 175 |
+
"learning_rate": 0.0008743315508021391,
|
| 176 |
+
"loss": 19.6149,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4,
|
| 181 |
+
"grad_norm": 3.7055838108062744,
|
| 182 |
+
"learning_rate": 0.0008689839572192514,
|
| 183 |
+
"loss": 18.9573,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.416,
|
| 188 |
+
"grad_norm": 4.930137634277344,
|
| 189 |
+
"learning_rate": 0.0008636363636363636,
|
| 190 |
+
"loss": 19.4389,
|
| 191 |
+
"step": 52
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.432,
|
| 195 |
+
"grad_norm": 3.910098075866699,
|
| 196 |
+
"learning_rate": 0.000858288770053476,
|
| 197 |
+
"loss": 19.1465,
|
| 198 |
+
"step": 54
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.448,
|
| 202 |
+
"grad_norm": 4.0127716064453125,
|
| 203 |
+
"learning_rate": 0.0008529411764705882,
|
| 204 |
+
"loss": 19.5038,
|
| 205 |
+
"step": 56
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.464,
|
| 209 |
+
"grad_norm": 4.495028018951416,
|
| 210 |
+
"learning_rate": 0.0008475935828877005,
|
| 211 |
+
"loss": 19.3252,
|
| 212 |
+
"step": 58
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.48,
|
| 216 |
+
"grad_norm": 3.7703821659088135,
|
| 217 |
+
"learning_rate": 0.0008422459893048129,
|
| 218 |
+
"loss": 19.0238,
|
| 219 |
+
"step": 60
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.496,
|
| 223 |
+
"grad_norm": 3.6335291862487793,
|
| 224 |
+
"learning_rate": 0.0008368983957219252,
|
| 225 |
+
"loss": 19.1296,
|
| 226 |
+
"step": 62
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.512,
|
| 230 |
+
"grad_norm": 3.819183588027954,
|
| 231 |
+
"learning_rate": 0.0008315508021390374,
|
| 232 |
+
"loss": 18.4946,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.528,
|
| 237 |
+
"grad_norm": 3.3171255588531494,
|
| 238 |
+
"learning_rate": 0.0008262032085561497,
|
| 239 |
+
"loss": 18.8054,
|
| 240 |
+
"step": 66
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.544,
|
| 244 |
+
"grad_norm": 4.316566467285156,
|
| 245 |
+
"learning_rate": 0.000820855614973262,
|
| 246 |
+
"loss": 19.162,
|
| 247 |
+
"step": 68
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.56,
|
| 251 |
+
"grad_norm": 3.39648175239563,
|
| 252 |
+
"learning_rate": 0.0008155080213903744,
|
| 253 |
+
"loss": 18.5671,
|
| 254 |
+
"step": 70
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.576,
|
| 258 |
+
"grad_norm": 3.7200136184692383,
|
| 259 |
+
"learning_rate": 0.0008101604278074867,
|
| 260 |
+
"loss": 18.9179,
|
| 261 |
+
"step": 72
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.592,
|
| 265 |
+
"grad_norm": 3.6730430126190186,
|
| 266 |
+
"learning_rate": 0.0008048128342245989,
|
| 267 |
+
"loss": 18.7162,
|
| 268 |
+
"step": 74
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.608,
|
| 272 |
+
"grad_norm": 3.5580945014953613,
|
| 273 |
+
"learning_rate": 0.0007994652406417113,
|
| 274 |
+
"loss": 19.0574,
|
| 275 |
+
"step": 76
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.624,
|
| 279 |
+
"grad_norm": 3.4793589115142822,
|
| 280 |
+
"learning_rate": 0.0007941176470588235,
|
| 281 |
+
"loss": 18.8649,
|
| 282 |
+
"step": 78
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.64,
|
| 286 |
+
"grad_norm": 4.074679374694824,
|
| 287 |
+
"learning_rate": 0.0007887700534759359,
|
| 288 |
+
"loss": 18.5553,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.656,
|
| 293 |
+
"grad_norm": 3.315810441970825,
|
| 294 |
+
"learning_rate": 0.0007834224598930482,
|
| 295 |
+
"loss": 18.2136,
|
| 296 |
+
"step": 82
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.672,
|
| 300 |
+
"grad_norm": 4.288172721862793,
|
| 301 |
+
"learning_rate": 0.0007780748663101605,
|
| 302 |
+
"loss": 18.6089,
|
| 303 |
+
"step": 84
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.688,
|
| 307 |
+
"grad_norm": 3.5749149322509766,
|
| 308 |
+
"learning_rate": 0.0007727272727272727,
|
| 309 |
+
"loss": 18.8697,
|
| 310 |
+
"step": 86
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.704,
|
| 314 |
+
"grad_norm": 3.608825206756592,
|
| 315 |
+
"learning_rate": 0.000767379679144385,
|
| 316 |
+
"loss": 18.4129,
|
| 317 |
+
"step": 88
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.72,
|
| 321 |
+
"grad_norm": 3.5199592113494873,
|
| 322 |
+
"learning_rate": 0.0007620320855614974,
|
| 323 |
+
"loss": 18.1619,
|
| 324 |
+
"step": 90
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.736,
|
| 328 |
+
"grad_norm": 3.5022549629211426,
|
| 329 |
+
"learning_rate": 0.0007566844919786096,
|
| 330 |
+
"loss": 18.7368,
|
| 331 |
+
"step": 92
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.752,
|
| 335 |
+
"grad_norm": 3.6002230644226074,
|
| 336 |
+
"learning_rate": 0.000751336898395722,
|
| 337 |
+
"loss": 18.7792,
|
| 338 |
+
"step": 94
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.768,
|
| 342 |
+
"grad_norm": 4.682362079620361,
|
| 343 |
+
"learning_rate": 0.0007459893048128342,
|
| 344 |
+
"loss": 18.5495,
|
| 345 |
+
"step": 96
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.784,
|
| 349 |
+
"grad_norm": 3.6108767986297607,
|
| 350 |
+
"learning_rate": 0.0007406417112299465,
|
| 351 |
+
"loss": 18.7077,
|
| 352 |
+
"step": 98
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8,
|
| 356 |
+
"grad_norm": 3.4719815254211426,
|
| 357 |
+
"learning_rate": 0.0007352941176470589,
|
| 358 |
+
"loss": 18.3262,
|
| 359 |
+
"step": 100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.816,
|
| 363 |
+
"grad_norm": 4.4115986824035645,
|
| 364 |
+
"learning_rate": 0.0007299465240641712,
|
| 365 |
+
"loss": 18.3416,
|
| 366 |
+
"step": 102
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.832,
|
| 370 |
+
"grad_norm": 3.324169158935547,
|
| 371 |
+
"learning_rate": 0.0007245989304812834,
|
| 372 |
+
"loss": 18.7297,
|
| 373 |
+
"step": 104
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.848,
|
| 377 |
+
"grad_norm": 3.4287421703338623,
|
| 378 |
+
"learning_rate": 0.0007192513368983958,
|
| 379 |
+
"loss": 18.4499,
|
| 380 |
+
"step": 106
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.864,
|
| 384 |
+
"grad_norm": 3.9451239109039307,
|
| 385 |
+
"learning_rate": 0.000713903743315508,
|
| 386 |
+
"loss": 18.2669,
|
| 387 |
+
"step": 108
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.88,
|
| 391 |
+
"grad_norm": 3.5031988620758057,
|
| 392 |
+
"learning_rate": 0.0007085561497326202,
|
| 393 |
+
"loss": 18.8895,
|
| 394 |
+
"step": 110
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.896,
|
| 398 |
+
"grad_norm": 3.5174903869628906,
|
| 399 |
+
"learning_rate": 0.0007032085561497327,
|
| 400 |
+
"loss": 18.2961,
|
| 401 |
+
"step": 112
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.912,
|
| 405 |
+
"grad_norm": 4.080729961395264,
|
| 406 |
+
"learning_rate": 0.0006978609625668449,
|
| 407 |
+
"loss": 18.5613,
|
| 408 |
+
"step": 114
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.928,
|
| 412 |
+
"grad_norm": 3.7523930072784424,
|
| 413 |
+
"learning_rate": 0.0006925133689839572,
|
| 414 |
+
"loss": 18.5538,
|
| 415 |
+
"step": 116
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.944,
|
| 419 |
+
"grad_norm": 3.066669225692749,
|
| 420 |
+
"learning_rate": 0.0006871657754010695,
|
| 421 |
+
"loss": 18.6904,
|
| 422 |
+
"step": 118
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.96,
|
| 426 |
+
"grad_norm": 4.274256706237793,
|
| 427 |
+
"learning_rate": 0.0006818181818181818,
|
| 428 |
+
"loss": 18.6147,
|
| 429 |
+
"step": 120
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.976,
|
| 433 |
+
"grad_norm": 3.690139055252075,
|
| 434 |
+
"learning_rate": 0.0006764705882352942,
|
| 435 |
+
"loss": 18.1693,
|
| 436 |
+
"step": 122
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.992,
|
| 440 |
+
"grad_norm": 3.6681807041168213,
|
| 441 |
+
"learning_rate": 0.0006711229946524065,
|
| 442 |
+
"loss": 18.2498,
|
| 443 |
+
"step": 124
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.008,
|
| 447 |
+
"grad_norm": 3.5203354358673096,
|
| 448 |
+
"learning_rate": 0.0006657754010695187,
|
| 449 |
+
"loss": 18.4522,
|
| 450 |
+
"step": 126
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.024,
|
| 454 |
+
"grad_norm": 4.650991439819336,
|
| 455 |
+
"learning_rate": 0.000660427807486631,
|
| 456 |
+
"loss": 18.2839,
|
| 457 |
+
"step": 128
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 1.04,
|
| 461 |
+
"grad_norm": 3.7944228649139404,
|
| 462 |
+
"learning_rate": 0.0006550802139037433,
|
| 463 |
+
"loss": 18.051,
|
| 464 |
+
"step": 130
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.056,
|
| 468 |
+
"grad_norm": 3.2437500953674316,
|
| 469 |
+
"learning_rate": 0.0006497326203208556,
|
| 470 |
+
"loss": 18.1842,
|
| 471 |
+
"step": 132
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.072,
|
| 475 |
+
"grad_norm": 3.2863543033599854,
|
| 476 |
+
"learning_rate": 0.000644385026737968,
|
| 477 |
+
"loss": 18.2304,
|
| 478 |
+
"step": 134
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.088,
|
| 482 |
+
"grad_norm": 3.553260326385498,
|
| 483 |
+
"learning_rate": 0.0006390374331550802,
|
| 484 |
+
"loss": 18.1385,
|
| 485 |
+
"step": 136
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.104,
|
| 489 |
+
"grad_norm": 3.4277195930480957,
|
| 490 |
+
"learning_rate": 0.0006336898395721925,
|
| 491 |
+
"loss": 18.1337,
|
| 492 |
+
"step": 138
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.12,
|
| 496 |
+
"grad_norm": 3.974073886871338,
|
| 497 |
+
"learning_rate": 0.0006283422459893048,
|
| 498 |
+
"loss": 18.0326,
|
| 499 |
+
"step": 140
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 1.1360000000000001,
|
| 503 |
+
"grad_norm": 3.3450510501861572,
|
| 504 |
+
"learning_rate": 0.0006229946524064172,
|
| 505 |
+
"loss": 18.2695,
|
| 506 |
+
"step": 142
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.152,
|
| 510 |
+
"grad_norm": 3.2181997299194336,
|
| 511 |
+
"learning_rate": 0.0006176470588235294,
|
| 512 |
+
"loss": 18.0315,
|
| 513 |
+
"step": 144
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.168,
|
| 517 |
+
"grad_norm": 3.8346364498138428,
|
| 518 |
+
"learning_rate": 0.0006122994652406418,
|
| 519 |
+
"loss": 18.4272,
|
| 520 |
+
"step": 146
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.184,
|
| 524 |
+
"grad_norm": 3.2085418701171875,
|
| 525 |
+
"learning_rate": 0.000606951871657754,
|
| 526 |
+
"loss": 18.1768,
|
| 527 |
+
"step": 148
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.2,
|
| 531 |
+
"grad_norm": 3.462108850479126,
|
| 532 |
+
"learning_rate": 0.0006016042780748662,
|
| 533 |
+
"loss": 18.1731,
|
| 534 |
+
"step": 150
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.216,
|
| 538 |
+
"grad_norm": 3.444965362548828,
|
| 539 |
+
"learning_rate": 0.0005962566844919787,
|
| 540 |
+
"loss": 18.3599,
|
| 541 |
+
"step": 152
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.232,
|
| 545 |
+
"grad_norm": 3.3701171875,
|
| 546 |
+
"learning_rate": 0.0005909090909090909,
|
| 547 |
+
"loss": 18.1495,
|
| 548 |
+
"step": 154
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.248,
|
| 552 |
+
"grad_norm": 3.5145843029022217,
|
| 553 |
+
"learning_rate": 0.0005855614973262032,
|
| 554 |
+
"loss": 18.0835,
|
| 555 |
+
"step": 156
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.264,
|
| 559 |
+
"grad_norm": 3.4785313606262207,
|
| 560 |
+
"learning_rate": 0.0005802139037433155,
|
| 561 |
+
"loss": 17.8138,
|
| 562 |
+
"step": 158
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.28,
|
| 566 |
+
"grad_norm": 3.9735538959503174,
|
| 567 |
+
"learning_rate": 0.0005748663101604278,
|
| 568 |
+
"loss": 18.0071,
|
| 569 |
+
"step": 160
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.296,
|
| 573 |
+
"grad_norm": 3.650447368621826,
|
| 574 |
+
"learning_rate": 0.00056951871657754,
|
| 575 |
+
"loss": 18.0124,
|
| 576 |
+
"step": 162
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.312,
|
| 580 |
+
"grad_norm": 3.6459813117980957,
|
| 581 |
+
"learning_rate": 0.0005641711229946525,
|
| 582 |
+
"loss": 18.0059,
|
| 583 |
+
"step": 164
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.328,
|
| 587 |
+
"grad_norm": 3.2154831886291504,
|
| 588 |
+
"learning_rate": 0.0005588235294117647,
|
| 589 |
+
"loss": 17.9694,
|
| 590 |
+
"step": 166
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.3439999999999999,
|
| 594 |
+
"grad_norm": 3.367403507232666,
|
| 595 |
+
"learning_rate": 0.0005534759358288771,
|
| 596 |
+
"loss": 17.6557,
|
| 597 |
+
"step": 168
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.3599999999999999,
|
| 601 |
+
"grad_norm": 3.9948298931121826,
|
| 602 |
+
"learning_rate": 0.0005481283422459893,
|
| 603 |
+
"loss": 18.1942,
|
| 604 |
+
"step": 170
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.376,
|
| 608 |
+
"grad_norm": 3.3495073318481445,
|
| 609 |
+
"learning_rate": 0.0005427807486631015,
|
| 610 |
+
"loss": 18.2016,
|
| 611 |
+
"step": 172
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.392,
|
| 615 |
+
"grad_norm": 3.373162269592285,
|
| 616 |
+
"learning_rate": 0.000537433155080214,
|
| 617 |
+
"loss": 18.0422,
|
| 618 |
+
"step": 174
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.408,
|
| 622 |
+
"grad_norm": 4.063633441925049,
|
| 623 |
+
"learning_rate": 0.0005320855614973262,
|
| 624 |
+
"loss": 18.0809,
|
| 625 |
+
"step": 176
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.424,
|
| 629 |
+
"grad_norm": 3.4912514686584473,
|
| 630 |
+
"learning_rate": 0.0005267379679144385,
|
| 631 |
+
"loss": 18.0674,
|
| 632 |
+
"step": 178
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.44,
|
| 636 |
+
"grad_norm": 3.5900015830993652,
|
| 637 |
+
"learning_rate": 0.0005213903743315508,
|
| 638 |
+
"loss": 17.9285,
|
| 639 |
+
"step": 180
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.456,
|
| 643 |
+
"grad_norm": 4.066802024841309,
|
| 644 |
+
"learning_rate": 0.0005160427807486631,
|
| 645 |
+
"loss": 18.1551,
|
| 646 |
+
"step": 182
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.472,
|
| 650 |
+
"grad_norm": 3.9782357215881348,
|
| 651 |
+
"learning_rate": 0.0005106951871657754,
|
| 652 |
+
"loss": 18.0509,
|
| 653 |
+
"step": 184
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.488,
|
| 657 |
+
"grad_norm": 3.314682960510254,
|
| 658 |
+
"learning_rate": 0.0005053475935828878,
|
| 659 |
+
"loss": 17.7608,
|
| 660 |
+
"step": 186
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.504,
|
| 664 |
+
"grad_norm": 3.3548595905303955,
|
| 665 |
+
"learning_rate": 0.0005,
|
| 666 |
+
"loss": 17.8103,
|
| 667 |
+
"step": 188
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.52,
|
| 671 |
+
"grad_norm": 3.3475797176361084,
|
| 672 |
+
"learning_rate": 0.0004946524064171123,
|
| 673 |
+
"loss": 17.9465,
|
| 674 |
+
"step": 190
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.536,
|
| 678 |
+
"grad_norm": 3.4256432056427,
|
| 679 |
+
"learning_rate": 0.0004893048128342246,
|
| 680 |
+
"loss": 17.6619,
|
| 681 |
+
"step": 192
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.552,
|
| 685 |
+
"grad_norm": 3.390056848526001,
|
| 686 |
+
"learning_rate": 0.0004839572192513369,
|
| 687 |
+
"loss": 17.9681,
|
| 688 |
+
"step": 194
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.568,
|
| 692 |
+
"grad_norm": 3.4441208839416504,
|
| 693 |
+
"learning_rate": 0.00047860962566844924,
|
| 694 |
+
"loss": 17.9407,
|
| 695 |
+
"step": 196
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.584,
|
| 699 |
+
"grad_norm": 3.2374165058135986,
|
| 700 |
+
"learning_rate": 0.0004732620320855615,
|
| 701 |
+
"loss": 17.7235,
|
| 702 |
+
"step": 198
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.6,
|
| 706 |
+
"grad_norm": 3.5628514289855957,
|
| 707 |
+
"learning_rate": 0.0004679144385026738,
|
| 708 |
+
"loss": 18.1743,
|
| 709 |
+
"step": 200
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.616,
|
| 713 |
+
"grad_norm": 3.41139554977417,
|
| 714 |
+
"learning_rate": 0.00046256684491978613,
|
| 715 |
+
"loss": 17.8456,
|
| 716 |
+
"step": 202
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 1.6320000000000001,
|
| 720 |
+
"grad_norm": 3.423110008239746,
|
| 721 |
+
"learning_rate": 0.0004572192513368984,
|
| 722 |
+
"loss": 17.6656,
|
| 723 |
+
"step": 204
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.6480000000000001,
|
| 727 |
+
"grad_norm": 3.3344337940216064,
|
| 728 |
+
"learning_rate": 0.00045187165775401067,
|
| 729 |
+
"loss": 17.962,
|
| 730 |
+
"step": 206
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.6640000000000001,
|
| 734 |
+
"grad_norm": 3.5036981105804443,
|
| 735 |
+
"learning_rate": 0.000446524064171123,
|
| 736 |
+
"loss": 18.0875,
|
| 737 |
+
"step": 208
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 1.6800000000000002,
|
| 741 |
+
"grad_norm": 3.4953839778900146,
|
| 742 |
+
"learning_rate": 0.0004411764705882353,
|
| 743 |
+
"loss": 17.3435,
|
| 744 |
+
"step": 210
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.696,
|
| 748 |
+
"grad_norm": 3.6864068508148193,
|
| 749 |
+
"learning_rate": 0.0004358288770053476,
|
| 750 |
+
"loss": 17.9087,
|
| 751 |
+
"step": 212
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.712,
|
| 755 |
+
"grad_norm": 3.4755449295043945,
|
| 756 |
+
"learning_rate": 0.0004304812834224599,
|
| 757 |
+
"loss": 17.5076,
|
| 758 |
+
"step": 214
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.728,
|
| 762 |
+
"grad_norm": 3.8116891384124756,
|
| 763 |
+
"learning_rate": 0.0004251336898395722,
|
| 764 |
+
"loss": 17.9272,
|
| 765 |
+
"step": 216
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.744,
|
| 769 |
+
"grad_norm": 3.18284010887146,
|
| 770 |
+
"learning_rate": 0.0004197860962566845,
|
| 771 |
+
"loss": 17.7148,
|
| 772 |
+
"step": 218
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.76,
|
| 776 |
+
"grad_norm": 3.2884979248046875,
|
| 777 |
+
"learning_rate": 0.0004144385026737968,
|
| 778 |
+
"loss": 17.8813,
|
| 779 |
+
"step": 220
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.776,
|
| 783 |
+
"grad_norm": 3.3735768795013428,
|
| 784 |
+
"learning_rate": 0.00040909090909090913,
|
| 785 |
+
"loss": 18.0372,
|
| 786 |
+
"step": 222
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.792,
|
| 790 |
+
"grad_norm": 3.2611794471740723,
|
| 791 |
+
"learning_rate": 0.00040374331550802143,
|
| 792 |
+
"loss": 17.3771,
|
| 793 |
+
"step": 224
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 1.808,
|
| 797 |
+
"grad_norm": 3.3338570594787598,
|
| 798 |
+
"learning_rate": 0.00039839572192513367,
|
| 799 |
+
"loss": 18.4657,
|
| 800 |
+
"step": 226
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 1.8239999999999998,
|
| 804 |
+
"grad_norm": 3.405127763748169,
|
| 805 |
+
"learning_rate": 0.000393048128342246,
|
| 806 |
+
"loss": 17.9076,
|
| 807 |
+
"step": 228
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.8399999999999999,
|
| 811 |
+
"grad_norm": 3.561793565750122,
|
| 812 |
+
"learning_rate": 0.0003877005347593583,
|
| 813 |
+
"loss": 17.8996,
|
| 814 |
+
"step": 230
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.8559999999999999,
|
| 818 |
+
"grad_norm": 3.5615479946136475,
|
| 819 |
+
"learning_rate": 0.00038235294117647055,
|
| 820 |
+
"loss": 17.6746,
|
| 821 |
+
"step": 232
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.8719999999999999,
|
| 825 |
+
"grad_norm": 3.4306275844573975,
|
| 826 |
+
"learning_rate": 0.0003770053475935829,
|
| 827 |
+
"loss": 17.7182,
|
| 828 |
+
"step": 234
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.888,
|
| 832 |
+
"grad_norm": 3.5057003498077393,
|
| 833 |
+
"learning_rate": 0.0003716577540106952,
|
| 834 |
+
"loss": 17.8058,
|
| 835 |
+
"step": 236
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.904,
|
| 839 |
+
"grad_norm": 3.3117101192474365,
|
| 840 |
+
"learning_rate": 0.0003663101604278075,
|
| 841 |
+
"loss": 17.8643,
|
| 842 |
+
"step": 238
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 1.92,
|
| 846 |
+
"grad_norm": 3.6897945404052734,
|
| 847 |
+
"learning_rate": 0.0003609625668449198,
|
| 848 |
+
"loss": 17.8266,
|
| 849 |
+
"step": 240
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.936,
|
| 853 |
+
"grad_norm": 3.7577505111694336,
|
| 854 |
+
"learning_rate": 0.0003556149732620321,
|
| 855 |
+
"loss": 18.6381,
|
| 856 |
+
"step": 242
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.952,
|
| 860 |
+
"grad_norm": 3.2401480674743652,
|
| 861 |
+
"learning_rate": 0.0003502673796791444,
|
| 862 |
+
"loss": 17.6933,
|
| 863 |
+
"step": 244
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 1.968,
|
| 867 |
+
"grad_norm": 3.6619515419006348,
|
| 868 |
+
"learning_rate": 0.0003449197860962567,
|
| 869 |
+
"loss": 18.0547,
|
| 870 |
+
"step": 246
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.984,
|
| 874 |
+
"grad_norm": 3.8387668132781982,
|
| 875 |
+
"learning_rate": 0.000339572192513369,
|
| 876 |
+
"loss": 17.7932,
|
| 877 |
+
"step": 248
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.0,
|
| 881 |
+
"grad_norm": 3.390653371810913,
|
| 882 |
+
"learning_rate": 0.0003342245989304813,
|
| 883 |
+
"loss": 17.2655,
|
| 884 |
+
"step": 250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.016,
|
| 888 |
+
"grad_norm": 3.40058970451355,
|
| 889 |
+
"learning_rate": 0.00032887700534759356,
|
| 890 |
+
"loss": 17.703,
|
| 891 |
+
"step": 252
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.032,
|
| 895 |
+
"grad_norm": 3.568702220916748,
|
| 896 |
+
"learning_rate": 0.0003235294117647059,
|
| 897 |
+
"loss": 17.2042,
|
| 898 |
+
"step": 254
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.048,
|
| 902 |
+
"grad_norm": 3.529431104660034,
|
| 903 |
+
"learning_rate": 0.0003181818181818182,
|
| 904 |
+
"loss": 17.5732,
|
| 905 |
+
"step": 256
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.064,
|
| 909 |
+
"grad_norm": 3.3919003009796143,
|
| 910 |
+
"learning_rate": 0.00031283422459893044,
|
| 911 |
+
"loss": 17.6191,
|
| 912 |
+
"step": 258
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.08,
|
| 916 |
+
"grad_norm": 3.878042459487915,
|
| 917 |
+
"learning_rate": 0.0003074866310160428,
|
| 918 |
+
"loss": 17.4911,
|
| 919 |
+
"step": 260
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 2.096,
|
| 923 |
+
"grad_norm": 3.772318124771118,
|
| 924 |
+
"learning_rate": 0.0003021390374331551,
|
| 925 |
+
"loss": 17.7258,
|
| 926 |
+
"step": 262
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 2.112,
|
| 930 |
+
"grad_norm": 3.4453060626983643,
|
| 931 |
+
"learning_rate": 0.0002967914438502674,
|
| 932 |
+
"loss": 17.4906,
|
| 933 |
+
"step": 264
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.128,
|
| 937 |
+
"grad_norm": 3.4957454204559326,
|
| 938 |
+
"learning_rate": 0.0002914438502673797,
|
| 939 |
+
"loss": 17.5716,
|
| 940 |
+
"step": 266
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.144,
|
| 944 |
+
"grad_norm": 3.530831813812256,
|
| 945 |
+
"learning_rate": 0.000286096256684492,
|
| 946 |
+
"loss": 17.4089,
|
| 947 |
+
"step": 268
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 2.16,
|
| 951 |
+
"grad_norm": 3.7524755001068115,
|
| 952 |
+
"learning_rate": 0.0002807486631016043,
|
| 953 |
+
"loss": 17.7712,
|
| 954 |
+
"step": 270
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 2.176,
|
| 958 |
+
"grad_norm": 3.297961711883545,
|
| 959 |
+
"learning_rate": 0.00027540106951871656,
|
| 960 |
+
"loss": 17.4408,
|
| 961 |
+
"step": 272
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 2.192,
|
| 965 |
+
"grad_norm": 3.3661088943481445,
|
| 966 |
+
"learning_rate": 0.0002700534759358289,
|
| 967 |
+
"loss": 17.6753,
|
| 968 |
+
"step": 274
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.208,
|
| 972 |
+
"grad_norm": 3.646210193634033,
|
| 973 |
+
"learning_rate": 0.0002647058823529412,
|
| 974 |
+
"loss": 17.7821,
|
| 975 |
+
"step": 276
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.224,
|
| 979 |
+
"grad_norm": 3.475140333175659,
|
| 980 |
+
"learning_rate": 0.00025935828877005345,
|
| 981 |
+
"loss": 17.6129,
|
| 982 |
+
"step": 278
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 2.24,
|
| 986 |
+
"grad_norm": 3.4734578132629395,
|
| 987 |
+
"learning_rate": 0.0002540106951871658,
|
| 988 |
+
"loss": 17.6856,
|
| 989 |
+
"step": 280
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.2560000000000002,
|
| 993 |
+
"grad_norm": 3.491572380065918,
|
| 994 |
+
"learning_rate": 0.0002486631016042781,
|
| 995 |
+
"loss": 17.6071,
|
| 996 |
+
"step": 282
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.2720000000000002,
|
| 1000 |
+
"grad_norm": 3.4102542400360107,
|
| 1001 |
+
"learning_rate": 0.0002433155080213904,
|
| 1002 |
+
"loss": 17.352,
|
| 1003 |
+
"step": 284
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 2.288,
|
| 1007 |
+
"grad_norm": 3.393477439880371,
|
| 1008 |
+
"learning_rate": 0.00023796791443850268,
|
| 1009 |
+
"loss": 17.2612,
|
| 1010 |
+
"step": 286
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.304,
|
| 1014 |
+
"grad_norm": 3.112462282180786,
|
| 1015 |
+
"learning_rate": 0.000232620320855615,
|
| 1016 |
+
"loss": 17.3272,
|
| 1017 |
+
"step": 288
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 2.32,
|
| 1021 |
+
"grad_norm": 3.3398191928863525,
|
| 1022 |
+
"learning_rate": 0.00022727272727272727,
|
| 1023 |
+
"loss": 17.5815,
|
| 1024 |
+
"step": 290
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 2.336,
|
| 1028 |
+
"grad_norm": 3.5039889812469482,
|
| 1029 |
+
"learning_rate": 0.00022192513368983957,
|
| 1030 |
+
"loss": 17.7557,
|
| 1031 |
+
"step": 292
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 2.352,
|
| 1035 |
+
"grad_norm": 3.532892942428589,
|
| 1036 |
+
"learning_rate": 0.0002165775401069519,
|
| 1037 |
+
"loss": 18.0523,
|
| 1038 |
+
"step": 294
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 2.368,
|
| 1042 |
+
"grad_norm": 3.2969062328338623,
|
| 1043 |
+
"learning_rate": 0.00021122994652406418,
|
| 1044 |
+
"loss": 17.7496,
|
| 1045 |
+
"step": 296
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 2.384,
|
| 1049 |
+
"grad_norm": 3.262855291366577,
|
| 1050 |
+
"learning_rate": 0.00020588235294117645,
|
| 1051 |
+
"loss": 17.793,
|
| 1052 |
+
"step": 298
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.4,
|
| 1056 |
+
"grad_norm": 3.459914445877075,
|
| 1057 |
+
"learning_rate": 0.00020053475935828877,
|
| 1058 |
+
"loss": 17.9245,
|
| 1059 |
+
"step": 300
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 2.416,
|
| 1063 |
+
"grad_norm": 3.6749696731567383,
|
| 1064 |
+
"learning_rate": 0.00019518716577540107,
|
| 1065 |
+
"loss": 17.7125,
|
| 1066 |
+
"step": 302
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.432,
|
| 1070 |
+
"grad_norm": 3.266754150390625,
|
| 1071 |
+
"learning_rate": 0.0001898395721925134,
|
| 1072 |
+
"loss": 17.5905,
|
| 1073 |
+
"step": 304
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.448,
|
| 1077 |
+
"grad_norm": 3.1848971843719482,
|
| 1078 |
+
"learning_rate": 0.00018449197860962566,
|
| 1079 |
+
"loss": 17.523,
|
| 1080 |
+
"step": 306
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.464,
|
| 1084 |
+
"grad_norm": 3.2962844371795654,
|
| 1085 |
+
"learning_rate": 0.00017914438502673795,
|
| 1086 |
+
"loss": 17.5297,
|
| 1087 |
+
"step": 308
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.48,
|
| 1091 |
+
"grad_norm": 3.4688000679016113,
|
| 1092 |
+
"learning_rate": 0.00017379679144385028,
|
| 1093 |
+
"loss": 17.6315,
|
| 1094 |
+
"step": 310
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.496,
|
| 1098 |
+
"grad_norm": 3.4146833419799805,
|
| 1099 |
+
"learning_rate": 0.00016844919786096257,
|
| 1100 |
+
"loss": 17.5776,
|
| 1101 |
+
"step": 312
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 2.512,
|
| 1105 |
+
"grad_norm": 3.3122944831848145,
|
| 1106 |
+
"learning_rate": 0.0001631016042780749,
|
| 1107 |
+
"loss": 17.7264,
|
| 1108 |
+
"step": 314
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.528,
|
| 1112 |
+
"grad_norm": 3.2939462661743164,
|
| 1113 |
+
"learning_rate": 0.00015775401069518716,
|
| 1114 |
+
"loss": 17.48,
|
| 1115 |
+
"step": 316
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 2.544,
|
| 1119 |
+
"grad_norm": 3.8504631519317627,
|
| 1120 |
+
"learning_rate": 0.00015240641711229946,
|
| 1121 |
+
"loss": 17.3854,
|
| 1122 |
+
"step": 318
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.56,
|
| 1126 |
+
"grad_norm": 4.062356948852539,
|
| 1127 |
+
"learning_rate": 0.00014705882352941178,
|
| 1128 |
+
"loss": 17.6811,
|
| 1129 |
+
"step": 320
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 2.576,
|
| 1133 |
+
"grad_norm": 3.741989850997925,
|
| 1134 |
+
"learning_rate": 0.00014171122994652407,
|
| 1135 |
+
"loss": 17.4078,
|
| 1136 |
+
"step": 322
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 2.592,
|
| 1140 |
+
"grad_norm": 3.7287967205047607,
|
| 1141 |
+
"learning_rate": 0.00013636363636363637,
|
| 1142 |
+
"loss": 17.3517,
|
| 1143 |
+
"step": 324
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.608,
|
| 1147 |
+
"grad_norm": 3.6224465370178223,
|
| 1148 |
+
"learning_rate": 0.00013101604278074866,
|
| 1149 |
+
"loss": 17.254,
|
| 1150 |
+
"step": 326
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 2.624,
|
| 1154 |
+
"grad_norm": 3.5674147605895996,
|
| 1155 |
+
"learning_rate": 0.00012566844919786096,
|
| 1156 |
+
"loss": 17.869,
|
| 1157 |
+
"step": 328
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 2.64,
|
| 1161 |
+
"grad_norm": 3.722736358642578,
|
| 1162 |
+
"learning_rate": 0.00012032085561497325,
|
| 1163 |
+
"loss": 17.7399,
|
| 1164 |
+
"step": 330
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.656,
|
| 1168 |
+
"grad_norm": 3.6463096141815186,
|
| 1169 |
+
"learning_rate": 0.00011497326203208556,
|
| 1170 |
+
"loss": 17.5016,
|
| 1171 |
+
"step": 332
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.672,
|
| 1175 |
+
"grad_norm": 3.5358524322509766,
|
| 1176 |
+
"learning_rate": 0.00010962566844919786,
|
| 1177 |
+
"loss": 17.0355,
|
| 1178 |
+
"step": 334
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.6879999999999997,
|
| 1182 |
+
"grad_norm": 3.5321309566497803,
|
| 1183 |
+
"learning_rate": 0.00010427807486631017,
|
| 1184 |
+
"loss": 17.5089,
|
| 1185 |
+
"step": 336
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 2.7039999999999997,
|
| 1189 |
+
"grad_norm": 3.4019291400909424,
|
| 1190 |
+
"learning_rate": 9.893048128342247e-05,
|
| 1191 |
+
"loss": 17.3768,
|
| 1192 |
+
"step": 338
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 2.7199999999999998,
|
| 1196 |
+
"grad_norm": 3.4486570358276367,
|
| 1197 |
+
"learning_rate": 9.358288770053476e-05,
|
| 1198 |
+
"loss": 17.488,
|
| 1199 |
+
"step": 340
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.7359999999999998,
|
| 1203 |
+
"grad_norm": 3.7740256786346436,
|
| 1204 |
+
"learning_rate": 8.823529411764706e-05,
|
| 1205 |
+
"loss": 17.5768,
|
| 1206 |
+
"step": 342
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.752,
|
| 1210 |
+
"grad_norm": 3.5659339427948,
|
| 1211 |
+
"learning_rate": 8.288770053475936e-05,
|
| 1212 |
+
"loss": 17.6865,
|
| 1213 |
+
"step": 344
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.768,
|
| 1217 |
+
"grad_norm": 3.3678972721099854,
|
| 1218 |
+
"learning_rate": 7.754010695187167e-05,
|
| 1219 |
+
"loss": 17.4687,
|
| 1220 |
+
"step": 346
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.784,
|
| 1224 |
+
"grad_norm": 3.585134506225586,
|
| 1225 |
+
"learning_rate": 7.219251336898395e-05,
|
| 1226 |
+
"loss": 17.536,
|
| 1227 |
+
"step": 348
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 2.8,
|
| 1231 |
+
"grad_norm": 3.6471846103668213,
|
| 1232 |
+
"learning_rate": 6.684491978609626e-05,
|
| 1233 |
+
"loss": 17.6269,
|
| 1234 |
+
"step": 350
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 2.816,
|
| 1238 |
+
"grad_norm": 3.533790111541748,
|
| 1239 |
+
"learning_rate": 6.149732620320857e-05,
|
| 1240 |
+
"loss": 17.5771,
|
| 1241 |
+
"step": 352
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 2.832,
|
| 1245 |
+
"grad_norm": 3.7971367835998535,
|
| 1246 |
+
"learning_rate": 5.614973262032086e-05,
|
| 1247 |
+
"loss": 17.874,
|
| 1248 |
+
"step": 354
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.848,
|
| 1252 |
+
"grad_norm": 3.391874074935913,
|
| 1253 |
+
"learning_rate": 5.080213903743316e-05,
|
| 1254 |
+
"loss": 17.2528,
|
| 1255 |
+
"step": 356
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.864,
|
| 1259 |
+
"grad_norm": 3.069033145904541,
|
| 1260 |
+
"learning_rate": 4.545454545454546e-05,
|
| 1261 |
+
"loss": 17.6175,
|
| 1262 |
+
"step": 358
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 2.88,
|
| 1266 |
+
"grad_norm": 3.780275821685791,
|
| 1267 |
+
"learning_rate": 4.0106951871657754e-05,
|
| 1268 |
+
"loss": 17.2663,
|
| 1269 |
+
"step": 360
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.896,
|
| 1273 |
+
"grad_norm": 3.3377978801727295,
|
| 1274 |
+
"learning_rate": 3.4759358288770055e-05,
|
| 1275 |
+
"loss": 17.3711,
|
| 1276 |
+
"step": 362
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 2.912,
|
| 1280 |
+
"grad_norm": 3.356203317642212,
|
| 1281 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 1282 |
+
"loss": 17.6077,
|
| 1283 |
+
"step": 364
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 2.928,
|
| 1287 |
+
"grad_norm": 3.302241563796997,
|
| 1288 |
+
"learning_rate": 2.4064171122994652e-05,
|
| 1289 |
+
"loss": 17.4777,
|
| 1290 |
+
"step": 366
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.944,
|
| 1294 |
+
"grad_norm": 3.73811411857605,
|
| 1295 |
+
"learning_rate": 1.871657754010695e-05,
|
| 1296 |
+
"loss": 17.3149,
|
| 1297 |
+
"step": 368
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.96,
|
| 1301 |
+
"grad_norm": 3.392902135848999,
|
| 1302 |
+
"learning_rate": 1.336898395721925e-05,
|
| 1303 |
+
"loss": 17.8118,
|
| 1304 |
+
"step": 370
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 2.976,
|
| 1308 |
+
"grad_norm": 3.8080010414123535,
|
| 1309 |
+
"learning_rate": 8.021390374331552e-06,
|
| 1310 |
+
"loss": 17.1875,
|
| 1311 |
+
"step": 372
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.992,
|
| 1315 |
+
"grad_norm": 3.5202646255493164,
|
| 1316 |
+
"learning_rate": 2.67379679144385e-06,
|
| 1317 |
+
"loss": 17.7556,
|
| 1318 |
+
"step": 374
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 3.0,
|
| 1322 |
+
"step": 375,
|
| 1323 |
+
"total_flos": 2.6461914289864704e+17,
|
| 1324 |
+
"train_loss": 18.264725362141927,
|
| 1325 |
+
"train_runtime": 1944.3243,
|
| 1326 |
+
"train_samples_per_second": 24.687,
|
| 1327 |
+
"train_steps_per_second": 0.193
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 3.0,
|
| 1331 |
+
"eval_loss": 2.2290163040161133,
|
| 1332 |
+
"eval_runtime": 83.3238,
|
| 1333 |
+
"eval_samples_per_second": 24.003,
|
| 1334 |
+
"eval_steps_per_second": 3.0,
|
| 1335 |
+
"step": 375
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 3.0,
|
| 1339 |
+
"eval_loss": 2.226619243621826,
|
| 1340 |
+
"eval_runtime": 83.9815,
|
| 1341 |
+
"eval_samples_per_second": 23.815,
|
| 1342 |
+
"eval_steps_per_second": 2.977,
|
| 1343 |
+
"step": 375
|
| 1344 |
+
}
|
| 1345 |
+
],
|
| 1346 |
+
"logging_steps": 2,
|
| 1347 |
+
"max_steps": 375,
|
| 1348 |
+
"num_input_tokens_seen": 0,
|
| 1349 |
+
"num_train_epochs": 3,
|
| 1350 |
+
"save_steps": 500,
|
| 1351 |
+
"stateful_callbacks": {
|
| 1352 |
+
"TrainerControl": {
|
| 1353 |
+
"args": {
|
| 1354 |
+
"should_epoch_stop": false,
|
| 1355 |
+
"should_evaluate": false,
|
| 1356 |
+
"should_log": false,
|
| 1357 |
+
"should_save": true,
|
| 1358 |
+
"should_training_stop": true
|
| 1359 |
+
},
|
| 1360 |
+
"attributes": {}
|
| 1361 |
+
}
|
| 1362 |
+
},
|
| 1363 |
+
"total_flos": 2.6461914289864704e+17,
|
| 1364 |
+
"train_batch_size": 16,
|
| 1365 |
+
"trial_name": null,
|
| 1366 |
+
"trial_params": null
|
| 1367 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02e08c5b7c7f54b1dd01657560b2b757c51c561ffc2a7ceb17a677da68fb107e
|
| 3 |
+
size 5368
|