End of training
Browse files- README.md +58 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +4 -0
- logs/events.out.tfevents.1726084170.ANUVATHAN-IO.25620.0 +3 -0
- merges.txt +0 -0
- special_tokens_map.json +49 -0
- tokenizer_config.json +87 -0
- trainer_state.json +1775 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: led-large-annual-report-QLoRA-fine-tuned-v0.9-merged
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: led-large-annual-report-QLoRA-fine-tuned-v0.9.7-openai
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# led-large-annual-report-QLoRA-fine-tuned-v0.9.7-openai
|
| 15 |
+
|
| 16 |
+
This model was trained from scratch on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- eval_loss: 1.5254
|
| 19 |
+
- eval_runtime: 168.5711
|
| 20 |
+
- eval_samples_per_second: 0.308
|
| 21 |
+
- eval_steps_per_second: 0.154
|
| 22 |
+
- epoch: 2.028
|
| 23 |
+
- step: 1014
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 2
|
| 44 |
+
- eval_batch_size: 2
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 2
|
| 49 |
+
- num_epochs: 3
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Framework versions
|
| 53 |
+
|
| 54 |
+
- PEFT 0.10.0
|
| 55 |
+
- Transformers 4.44.2
|
| 56 |
+
- Pytorch 2.4.1+cu124
|
| 57 |
+
- Datasets 2.14.5
|
| 58 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "led-large-annual-report-QLoRA-fine-tuned-v0.9-merged",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 128,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 256,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"dense"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "SEQ_2_SEQ_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32550fb50b1c5fab82c2886a4bbf30da70fde235986865bb1ab1caa8222ed14f
|
| 3 |
+
size 151015600
|
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|im_end|>": 50266,
|
| 3 |
+
"<|im_start|>": 50265
|
| 4 |
+
}
|
logs/events.out.tfevents.1726084170.ANUVATHAN-IO.25620.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a8909d585741a2da9ca9a530cf1b2ce4338fc40d4cd2185dd11c26beff30314
|
| 3 |
+
size 60177
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<|im_start|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"cls_token": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"mask_token": {
|
| 28 |
+
"content": "<mask>",
|
| 29 |
+
"lstrip": true,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
},
|
| 34 |
+
"pad_token": "<|im_end|>",
|
| 35 |
+
"sep_token": {
|
| 36 |
+
"content": "</s>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false
|
| 41 |
+
},
|
| 42 |
+
"unk_token": {
|
| 43 |
+
"content": "<unk>",
|
| 44 |
+
"lstrip": false,
|
| 45 |
+
"normalized": true,
|
| 46 |
+
"rstrip": false,
|
| 47 |
+
"single_word": false
|
| 48 |
+
}
|
| 49 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": true,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<s>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<pad>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"3": {
|
| 31 |
+
"content": "<unk>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"50264": {
|
| 39 |
+
"content": "<mask>",
|
| 40 |
+
"lstrip": true,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"50265": {
|
| 47 |
+
"content": "<|im_start|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"50266": {
|
| 55 |
+
"content": "<|im_end|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
}
|
| 62 |
+
},
|
| 63 |
+
"additional_special_tokens": [
|
| 64 |
+
"<|im_start|>",
|
| 65 |
+
"<|im_end|>"
|
| 66 |
+
],
|
| 67 |
+
"bos_token": "<|im_start|>",
|
| 68 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 69 |
+
"clean_up_tokenization_spaces": true,
|
| 70 |
+
"cls_token": "<s>",
|
| 71 |
+
"eos_token": "<|im_end|>",
|
| 72 |
+
"errors": "replace",
|
| 73 |
+
"mask_token": "<mask>",
|
| 74 |
+
"max_length": 1024,
|
| 75 |
+
"model_max_length": 16384,
|
| 76 |
+
"pad_to_multiple_of": null,
|
| 77 |
+
"pad_token": "<|im_end|>",
|
| 78 |
+
"pad_token_type_id": 0,
|
| 79 |
+
"padding_side": "right",
|
| 80 |
+
"sep_token": "</s>",
|
| 81 |
+
"stride": 0,
|
| 82 |
+
"tokenizer_class": "LEDTokenizer",
|
| 83 |
+
"trim_offsets": true,
|
| 84 |
+
"truncation_side": "right",
|
| 85 |
+
"truncation_strategy": "longest_first",
|
| 86 |
+
"unk_token": "<unk>"
|
| 87 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1775 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.5205299854278564,
|
| 3 |
+
"best_model_checkpoint": "led-large-annual-report-QLoRA-fine-tuned-v0.9.5-openai\\checkpoint-975",
|
| 4 |
+
"epoch": 2.028,
|
| 5 |
+
"eval_steps": 25,
|
| 6 |
+
"global_step": 1014,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 0.5776566863059998,
|
| 14 |
+
"learning_rate": 0.00019959946595460615,
|
| 15 |
+
"loss": 2.9761,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 0.7108611464500427,
|
| 21 |
+
"learning_rate": 0.00019893190921228305,
|
| 22 |
+
"loss": 2.5028,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"grad_norm": 0.6665928959846497,
|
| 28 |
+
"learning_rate": 0.0001983978638184246,
|
| 29 |
+
"loss": 2.7385,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04,
|
| 34 |
+
"grad_norm": 0.6933648586273193,
|
| 35 |
+
"learning_rate": 0.00019773030707610146,
|
| 36 |
+
"loss": 2.5519,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05,
|
| 41 |
+
"grad_norm": 0.6314701437950134,
|
| 42 |
+
"learning_rate": 0.0001970627503337784,
|
| 43 |
+
"loss": 2.2413,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.05,
|
| 48 |
+
"eval_loss": 2.0085484981536865,
|
| 49 |
+
"eval_runtime": 157.7525,
|
| 50 |
+
"eval_samples_per_second": 0.33,
|
| 51 |
+
"eval_steps_per_second": 0.165,
|
| 52 |
+
"step": 25
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06,
|
| 56 |
+
"grad_norm": 2.063861131668091,
|
| 57 |
+
"learning_rate": 0.0001963951935914553,
|
| 58 |
+
"loss": 2.6807,
|
| 59 |
+
"step": 30
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.07,
|
| 63 |
+
"grad_norm": 0.7584943175315857,
|
| 64 |
+
"learning_rate": 0.0001957276368491322,
|
| 65 |
+
"loss": 2.1435,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.08,
|
| 70 |
+
"grad_norm": 0.650688886642456,
|
| 71 |
+
"learning_rate": 0.0001950600801068091,
|
| 72 |
+
"loss": 2.0311,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.09,
|
| 77 |
+
"grad_norm": 0.6848713159561157,
|
| 78 |
+
"learning_rate": 0.000194392523364486,
|
| 79 |
+
"loss": 2.0928,
|
| 80 |
+
"step": 45
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1,
|
| 84 |
+
"grad_norm": 0.915006697177887,
|
| 85 |
+
"learning_rate": 0.0001937249666221629,
|
| 86 |
+
"loss": 2.2454,
|
| 87 |
+
"step": 50
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1,
|
| 91 |
+
"eval_loss": 1.8175970315933228,
|
| 92 |
+
"eval_runtime": 160.1948,
|
| 93 |
+
"eval_samples_per_second": 0.325,
|
| 94 |
+
"eval_steps_per_second": 0.162,
|
| 95 |
+
"step": 50
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.11,
|
| 99 |
+
"grad_norm": 0.63294917345047,
|
| 100 |
+
"learning_rate": 0.0001930574098798398,
|
| 101 |
+
"loss": 1.8694,
|
| 102 |
+
"step": 55
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.12,
|
| 106 |
+
"grad_norm": 0.6055558323860168,
|
| 107 |
+
"learning_rate": 0.0001923898531375167,
|
| 108 |
+
"loss": 2.0452,
|
| 109 |
+
"step": 60
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.13,
|
| 113 |
+
"grad_norm": 0.7194655537605286,
|
| 114 |
+
"learning_rate": 0.0001917222963951936,
|
| 115 |
+
"loss": 1.9801,
|
| 116 |
+
"step": 65
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.14,
|
| 120 |
+
"grad_norm": 0.7426390051841736,
|
| 121 |
+
"learning_rate": 0.00019105473965287052,
|
| 122 |
+
"loss": 1.9021,
|
| 123 |
+
"step": 70
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.15,
|
| 127 |
+
"grad_norm": 1.0124174356460571,
|
| 128 |
+
"learning_rate": 0.0001903871829105474,
|
| 129 |
+
"loss": 1.8887,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.15,
|
| 134 |
+
"eval_loss": 1.7658432722091675,
|
| 135 |
+
"eval_runtime": 157.6865,
|
| 136 |
+
"eval_samples_per_second": 0.33,
|
| 137 |
+
"eval_steps_per_second": 0.165,
|
| 138 |
+
"step": 75
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.16,
|
| 142 |
+
"grad_norm": 0.6850053071975708,
|
| 143 |
+
"learning_rate": 0.00018971962616822432,
|
| 144 |
+
"loss": 1.9158,
|
| 145 |
+
"step": 80
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.17,
|
| 149 |
+
"grad_norm": 0.9443833827972412,
|
| 150 |
+
"learning_rate": 0.00018905206942590122,
|
| 151 |
+
"loss": 1.9566,
|
| 152 |
+
"step": 85
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.18,
|
| 156 |
+
"grad_norm": 0.9081319570541382,
|
| 157 |
+
"learning_rate": 0.00018838451268357812,
|
| 158 |
+
"loss": 1.6911,
|
| 159 |
+
"step": 90
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.19,
|
| 163 |
+
"grad_norm": 1.0233992338180542,
|
| 164 |
+
"learning_rate": 0.00018771695594125502,
|
| 165 |
+
"loss": 1.9792,
|
| 166 |
+
"step": 95
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.2,
|
| 170 |
+
"grad_norm": 0.8909695148468018,
|
| 171 |
+
"learning_rate": 0.00018704939919893192,
|
| 172 |
+
"loss": 2.096,
|
| 173 |
+
"step": 100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.2,
|
| 177 |
+
"eval_loss": 1.723463773727417,
|
| 178 |
+
"eval_runtime": 155.3531,
|
| 179 |
+
"eval_samples_per_second": 0.335,
|
| 180 |
+
"eval_steps_per_second": 0.167,
|
| 181 |
+
"step": 100
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.21,
|
| 185 |
+
"grad_norm": 0.6819004416465759,
|
| 186 |
+
"learning_rate": 0.00018638184245660882,
|
| 187 |
+
"loss": 1.9699,
|
| 188 |
+
"step": 105
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.22,
|
| 192 |
+
"grad_norm": 1.0499932765960693,
|
| 193 |
+
"learning_rate": 0.00018571428571428572,
|
| 194 |
+
"loss": 1.4622,
|
| 195 |
+
"step": 110
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.23,
|
| 199 |
+
"grad_norm": 1.1806385517120361,
|
| 200 |
+
"learning_rate": 0.00018504672897196262,
|
| 201 |
+
"loss": 2.0254,
|
| 202 |
+
"step": 115
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.24,
|
| 206 |
+
"grad_norm": 0.8019367456436157,
|
| 207 |
+
"learning_rate": 0.00018437917222963952,
|
| 208 |
+
"loss": 1.7028,
|
| 209 |
+
"step": 120
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.25,
|
| 213 |
+
"grad_norm": 0.5862939953804016,
|
| 214 |
+
"learning_rate": 0.00018371161548731644,
|
| 215 |
+
"loss": 1.8961,
|
| 216 |
+
"step": 125
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.25,
|
| 220 |
+
"eval_loss": 1.6857578754425049,
|
| 221 |
+
"eval_runtime": 155.2512,
|
| 222 |
+
"eval_samples_per_second": 0.335,
|
| 223 |
+
"eval_steps_per_second": 0.167,
|
| 224 |
+
"step": 125
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.26,
|
| 228 |
+
"grad_norm": 0.8203465342521667,
|
| 229 |
+
"learning_rate": 0.00018304405874499332,
|
| 230 |
+
"loss": 1.695,
|
| 231 |
+
"step": 130
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.27,
|
| 235 |
+
"grad_norm": 0.9199301600456238,
|
| 236 |
+
"learning_rate": 0.00018237650200267024,
|
| 237 |
+
"loss": 1.6875,
|
| 238 |
+
"step": 135
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.28,
|
| 242 |
+
"grad_norm": 1.0262317657470703,
|
| 243 |
+
"learning_rate": 0.00018170894526034714,
|
| 244 |
+
"loss": 1.9771,
|
| 245 |
+
"step": 140
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.29,
|
| 249 |
+
"grad_norm": 0.6566195487976074,
|
| 250 |
+
"learning_rate": 0.00018104138851802404,
|
| 251 |
+
"loss": 1.794,
|
| 252 |
+
"step": 145
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.3,
|
| 256 |
+
"grad_norm": 0.6329429745674133,
|
| 257 |
+
"learning_rate": 0.00018037383177570094,
|
| 258 |
+
"loss": 1.4936,
|
| 259 |
+
"step": 150
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.3,
|
| 263 |
+
"eval_loss": 1.6933786869049072,
|
| 264 |
+
"eval_runtime": 154.938,
|
| 265 |
+
"eval_samples_per_second": 0.336,
|
| 266 |
+
"eval_steps_per_second": 0.168,
|
| 267 |
+
"step": 150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.31,
|
| 271 |
+
"grad_norm": 1.1340160369873047,
|
| 272 |
+
"learning_rate": 0.00017970627503337784,
|
| 273 |
+
"loss": 1.9533,
|
| 274 |
+
"step": 155
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.32,
|
| 278 |
+
"grad_norm": 0.8708927631378174,
|
| 279 |
+
"learning_rate": 0.00017903871829105474,
|
| 280 |
+
"loss": 1.8068,
|
| 281 |
+
"step": 160
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.33,
|
| 285 |
+
"grad_norm": 0.7619530558586121,
|
| 286 |
+
"learning_rate": 0.00017837116154873167,
|
| 287 |
+
"loss": 1.6662,
|
| 288 |
+
"step": 165
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.34,
|
| 292 |
+
"grad_norm": 0.6751542687416077,
|
| 293 |
+
"learning_rate": 0.00017770360480640854,
|
| 294 |
+
"loss": 1.7322,
|
| 295 |
+
"step": 170
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.35,
|
| 299 |
+
"grad_norm": 1.106812596321106,
|
| 300 |
+
"learning_rate": 0.00017703604806408544,
|
| 301 |
+
"loss": 1.9186,
|
| 302 |
+
"step": 175
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.35,
|
| 306 |
+
"eval_loss": 1.7012258768081665,
|
| 307 |
+
"eval_runtime": 155.0194,
|
| 308 |
+
"eval_samples_per_second": 0.335,
|
| 309 |
+
"eval_steps_per_second": 0.168,
|
| 310 |
+
"step": 175
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.36,
|
| 314 |
+
"grad_norm": 0.7777801752090454,
|
| 315 |
+
"learning_rate": 0.00017636849132176237,
|
| 316 |
+
"loss": 1.7517,
|
| 317 |
+
"step": 180
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.37,
|
| 321 |
+
"grad_norm": 2.1003479957580566,
|
| 322 |
+
"learning_rate": 0.00017570093457943927,
|
| 323 |
+
"loss": 1.8307,
|
| 324 |
+
"step": 185
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.38,
|
| 328 |
+
"grad_norm": 0.6046275496482849,
|
| 329 |
+
"learning_rate": 0.00017503337783711614,
|
| 330 |
+
"loss": 1.5722,
|
| 331 |
+
"step": 190
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.39,
|
| 335 |
+
"grad_norm": 0.6874721050262451,
|
| 336 |
+
"learning_rate": 0.00017436582109479307,
|
| 337 |
+
"loss": 1.5634,
|
| 338 |
+
"step": 195
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.4,
|
| 342 |
+
"grad_norm": 0.6428207159042358,
|
| 343 |
+
"learning_rate": 0.00017369826435246997,
|
| 344 |
+
"loss": 1.8532,
|
| 345 |
+
"step": 200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.4,
|
| 349 |
+
"eval_loss": 1.669812560081482,
|
| 350 |
+
"eval_runtime": 154.6164,
|
| 351 |
+
"eval_samples_per_second": 0.336,
|
| 352 |
+
"eval_steps_per_second": 0.168,
|
| 353 |
+
"step": 200
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.41,
|
| 357 |
+
"grad_norm": 0.7773897051811218,
|
| 358 |
+
"learning_rate": 0.00017303070761014687,
|
| 359 |
+
"loss": 1.591,
|
| 360 |
+
"step": 205
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.42,
|
| 364 |
+
"grad_norm": 0.6522992849349976,
|
| 365 |
+
"learning_rate": 0.00017236315086782377,
|
| 366 |
+
"loss": 1.6156,
|
| 367 |
+
"step": 210
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.43,
|
| 371 |
+
"grad_norm": 0.6386374831199646,
|
| 372 |
+
"learning_rate": 0.00017169559412550067,
|
| 373 |
+
"loss": 1.5089,
|
| 374 |
+
"step": 215
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.44,
|
| 378 |
+
"grad_norm": 0.5616068840026855,
|
| 379 |
+
"learning_rate": 0.0001710280373831776,
|
| 380 |
+
"loss": 1.3961,
|
| 381 |
+
"step": 220
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.45,
|
| 385 |
+
"grad_norm": 0.6595784425735474,
|
| 386 |
+
"learning_rate": 0.00017036048064085447,
|
| 387 |
+
"loss": 1.6172,
|
| 388 |
+
"step": 225
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.45,
|
| 392 |
+
"eval_loss": 1.6555695533752441,
|
| 393 |
+
"eval_runtime": 154.8952,
|
| 394 |
+
"eval_samples_per_second": 0.336,
|
| 395 |
+
"eval_steps_per_second": 0.168,
|
| 396 |
+
"step": 225
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.46,
|
| 400 |
+
"grad_norm": 0.5686245560646057,
|
| 401 |
+
"learning_rate": 0.00016969292389853137,
|
| 402 |
+
"loss": 1.7398,
|
| 403 |
+
"step": 230
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.47,
|
| 407 |
+
"grad_norm": 0.5429339408874512,
|
| 408 |
+
"learning_rate": 0.0001690253671562083,
|
| 409 |
+
"loss": 1.7083,
|
| 410 |
+
"step": 235
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.48,
|
| 414 |
+
"grad_norm": 0.5100717544555664,
|
| 415 |
+
"learning_rate": 0.0001683578104138852,
|
| 416 |
+
"loss": 1.803,
|
| 417 |
+
"step": 240
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.49,
|
| 421 |
+
"grad_norm": 0.8772192597389221,
|
| 422 |
+
"learning_rate": 0.00016769025367156207,
|
| 423 |
+
"loss": 1.7454,
|
| 424 |
+
"step": 245
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.5,
|
| 428 |
+
"grad_norm": 0.696287989616394,
|
| 429 |
+
"learning_rate": 0.000167022696929239,
|
| 430 |
+
"loss": 1.7838,
|
| 431 |
+
"step": 250
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.5,
|
| 435 |
+
"eval_loss": 1.6382060050964355,
|
| 436 |
+
"eval_runtime": 154.9708,
|
| 437 |
+
"eval_samples_per_second": 0.336,
|
| 438 |
+
"eval_steps_per_second": 0.168,
|
| 439 |
+
"step": 250
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.51,
|
| 443 |
+
"grad_norm": 0.7773283123970032,
|
| 444 |
+
"learning_rate": 0.0001663551401869159,
|
| 445 |
+
"loss": 1.7747,
|
| 446 |
+
"step": 255
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.52,
|
| 450 |
+
"grad_norm": 0.6426253318786621,
|
| 451 |
+
"learning_rate": 0.0001656875834445928,
|
| 452 |
+
"loss": 1.6671,
|
| 453 |
+
"step": 260
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.53,
|
| 457 |
+
"grad_norm": 0.5842812061309814,
|
| 458 |
+
"learning_rate": 0.0001650200267022697,
|
| 459 |
+
"loss": 1.8503,
|
| 460 |
+
"step": 265
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.54,
|
| 464 |
+
"grad_norm": 0.5060431361198425,
|
| 465 |
+
"learning_rate": 0.0001643524699599466,
|
| 466 |
+
"loss": 1.9078,
|
| 467 |
+
"step": 270
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.55,
|
| 471 |
+
"grad_norm": 0.7145740985870361,
|
| 472 |
+
"learning_rate": 0.00016368491321762352,
|
| 473 |
+
"loss": 2.0422,
|
| 474 |
+
"step": 275
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.55,
|
| 478 |
+
"eval_loss": 1.6412526369094849,
|
| 479 |
+
"eval_runtime": 154.8473,
|
| 480 |
+
"eval_samples_per_second": 0.336,
|
| 481 |
+
"eval_steps_per_second": 0.168,
|
| 482 |
+
"step": 275
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.56,
|
| 486 |
+
"grad_norm": 0.6752652525901794,
|
| 487 |
+
"learning_rate": 0.0001630173564753004,
|
| 488 |
+
"loss": 1.6336,
|
| 489 |
+
"step": 280
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.57,
|
| 493 |
+
"grad_norm": 0.7111806869506836,
|
| 494 |
+
"learning_rate": 0.0001623497997329773,
|
| 495 |
+
"loss": 1.6739,
|
| 496 |
+
"step": 285
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.58,
|
| 500 |
+
"grad_norm": 0.6902967691421509,
|
| 501 |
+
"learning_rate": 0.00016168224299065422,
|
| 502 |
+
"loss": 1.7994,
|
| 503 |
+
"step": 290
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.59,
|
| 507 |
+
"grad_norm": 0.5196375250816345,
|
| 508 |
+
"learning_rate": 0.00016101468624833112,
|
| 509 |
+
"loss": 1.5847,
|
| 510 |
+
"step": 295
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.6,
|
| 514 |
+
"grad_norm": 0.9794080853462219,
|
| 515 |
+
"learning_rate": 0.000160347129506008,
|
| 516 |
+
"loss": 1.8875,
|
| 517 |
+
"step": 300
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.6,
|
| 521 |
+
"eval_loss": 1.6254016160964966,
|
| 522 |
+
"eval_runtime": 154.7578,
|
| 523 |
+
"eval_samples_per_second": 0.336,
|
| 524 |
+
"eval_steps_per_second": 0.168,
|
| 525 |
+
"step": 300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.61,
|
| 529 |
+
"grad_norm": 0.5826653242111206,
|
| 530 |
+
"learning_rate": 0.00015967957276368492,
|
| 531 |
+
"loss": 1.6773,
|
| 532 |
+
"step": 305
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.62,
|
| 536 |
+
"grad_norm": 0.5551023483276367,
|
| 537 |
+
"learning_rate": 0.00015901201602136182,
|
| 538 |
+
"loss": 1.685,
|
| 539 |
+
"step": 310
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.63,
|
| 543 |
+
"grad_norm": 0.6069286465644836,
|
| 544 |
+
"learning_rate": 0.00015834445927903872,
|
| 545 |
+
"loss": 1.7293,
|
| 546 |
+
"step": 315
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.64,
|
| 550 |
+
"grad_norm": 0.8002230525016785,
|
| 551 |
+
"learning_rate": 0.00015767690253671562,
|
| 552 |
+
"loss": 1.8484,
|
| 553 |
+
"step": 320
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.65,
|
| 557 |
+
"grad_norm": 0.7304033041000366,
|
| 558 |
+
"learning_rate": 0.00015700934579439252,
|
| 559 |
+
"loss": 1.687,
|
| 560 |
+
"step": 325
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.65,
|
| 564 |
+
"eval_loss": 1.605177402496338,
|
| 565 |
+
"eval_runtime": 154.868,
|
| 566 |
+
"eval_samples_per_second": 0.336,
|
| 567 |
+
"eval_steps_per_second": 0.168,
|
| 568 |
+
"step": 325
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.66,
|
| 572 |
+
"grad_norm": 0.46438586711883545,
|
| 573 |
+
"learning_rate": 0.00015634178905206945,
|
| 574 |
+
"loss": 1.5457,
|
| 575 |
+
"step": 330
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.67,
|
| 579 |
+
"grad_norm": 1.024244785308838,
|
| 580 |
+
"learning_rate": 0.00015567423230974635,
|
| 581 |
+
"loss": 1.6972,
|
| 582 |
+
"step": 335
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.68,
|
| 586 |
+
"grad_norm": 0.506373941898346,
|
| 587 |
+
"learning_rate": 0.00015500667556742322,
|
| 588 |
+
"loss": 1.4549,
|
| 589 |
+
"step": 340
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.69,
|
| 593 |
+
"grad_norm": 0.7029207944869995,
|
| 594 |
+
"learning_rate": 0.00015433911882510015,
|
| 595 |
+
"loss": 1.6963,
|
| 596 |
+
"step": 345
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.7,
|
| 600 |
+
"grad_norm": 0.5588846802711487,
|
| 601 |
+
"learning_rate": 0.00015367156208277705,
|
| 602 |
+
"loss": 1.6778,
|
| 603 |
+
"step": 350
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.7,
|
| 607 |
+
"eval_loss": 1.6053338050842285,
|
| 608 |
+
"eval_runtime": 154.828,
|
| 609 |
+
"eval_samples_per_second": 0.336,
|
| 610 |
+
"eval_steps_per_second": 0.168,
|
| 611 |
+
"step": 350
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.71,
|
| 615 |
+
"grad_norm": 0.5997027158737183,
|
| 616 |
+
"learning_rate": 0.00015300400534045395,
|
| 617 |
+
"loss": 1.5144,
|
| 618 |
+
"step": 355
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.72,
|
| 622 |
+
"grad_norm": 0.5491402745246887,
|
| 623 |
+
"learning_rate": 0.00015233644859813085,
|
| 624 |
+
"loss": 1.6086,
|
| 625 |
+
"step": 360
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.73,
|
| 629 |
+
"grad_norm": 0.6617192625999451,
|
| 630 |
+
"learning_rate": 0.00015166889185580775,
|
| 631 |
+
"loss": 1.5582,
|
| 632 |
+
"step": 365
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.74,
|
| 636 |
+
"grad_norm": 0.6810077428817749,
|
| 637 |
+
"learning_rate": 0.00015100133511348465,
|
| 638 |
+
"loss": 1.7498,
|
| 639 |
+
"step": 370
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.75,
|
| 643 |
+
"grad_norm": 0.6304115653038025,
|
| 644 |
+
"learning_rate": 0.00015033377837116155,
|
| 645 |
+
"loss": 1.5276,
|
| 646 |
+
"step": 375
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.75,
|
| 650 |
+
"eval_loss": 1.5960314273834229,
|
| 651 |
+
"eval_runtime": 154.8615,
|
| 652 |
+
"eval_samples_per_second": 0.336,
|
| 653 |
+
"eval_steps_per_second": 0.168,
|
| 654 |
+
"step": 375
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.76,
|
| 658 |
+
"grad_norm": 0.6610834002494812,
|
| 659 |
+
"learning_rate": 0.00014966622162883845,
|
| 660 |
+
"loss": 1.5969,
|
| 661 |
+
"step": 380
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.77,
|
| 665 |
+
"grad_norm": 0.8158746957778931,
|
| 666 |
+
"learning_rate": 0.00014899866488651538,
|
| 667 |
+
"loss": 1.5529,
|
| 668 |
+
"step": 385
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.78,
|
| 672 |
+
"grad_norm": 0.519496500492096,
|
| 673 |
+
"learning_rate": 0.00014833110814419228,
|
| 674 |
+
"loss": 1.6754,
|
| 675 |
+
"step": 390
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.79,
|
| 679 |
+
"grad_norm": 0.6644089221954346,
|
| 680 |
+
"learning_rate": 0.00014766355140186915,
|
| 681 |
+
"loss": 1.7254,
|
| 682 |
+
"step": 395
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.8,
|
| 686 |
+
"grad_norm": 0.7224368453025818,
|
| 687 |
+
"learning_rate": 0.00014699599465954608,
|
| 688 |
+
"loss": 1.4391,
|
| 689 |
+
"step": 400
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.8,
|
| 693 |
+
"eval_loss": 1.5978156328201294,
|
| 694 |
+
"eval_runtime": 153.9476,
|
| 695 |
+
"eval_samples_per_second": 0.338,
|
| 696 |
+
"eval_steps_per_second": 0.169,
|
| 697 |
+
"step": 400
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.81,
|
| 701 |
+
"grad_norm": 0.6566179394721985,
|
| 702 |
+
"learning_rate": 0.00014632843791722298,
|
| 703 |
+
"loss": 1.5994,
|
| 704 |
+
"step": 405
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.82,
|
| 708 |
+
"grad_norm": 1.0222816467285156,
|
| 709 |
+
"learning_rate": 0.00014566088117489988,
|
| 710 |
+
"loss": 1.4374,
|
| 711 |
+
"step": 410
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.83,
|
| 715 |
+
"grad_norm": 0.5965130925178528,
|
| 716 |
+
"learning_rate": 0.00014499332443257678,
|
| 717 |
+
"loss": 1.5863,
|
| 718 |
+
"step": 415
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.84,
|
| 722 |
+
"grad_norm": 0.5560926795005798,
|
| 723 |
+
"learning_rate": 0.00014432576769025368,
|
| 724 |
+
"loss": 1.5581,
|
| 725 |
+
"step": 420
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.85,
|
| 729 |
+
"grad_norm": 0.7057550549507141,
|
| 730 |
+
"learning_rate": 0.00014365821094793058,
|
| 731 |
+
"loss": 1.7263,
|
| 732 |
+
"step": 425
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.85,
|
| 736 |
+
"eval_loss": 1.6051459312438965,
|
| 737 |
+
"eval_runtime": 153.7143,
|
| 738 |
+
"eval_samples_per_second": 0.338,
|
| 739 |
+
"eval_steps_per_second": 0.169,
|
| 740 |
+
"step": 425
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.86,
|
| 744 |
+
"grad_norm": 1.132186770439148,
|
| 745 |
+
"learning_rate": 0.00014299065420560748,
|
| 746 |
+
"loss": 1.6684,
|
| 747 |
+
"step": 430
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.87,
|
| 751 |
+
"grad_norm": 0.5418440103530884,
|
| 752 |
+
"learning_rate": 0.00014232309746328438,
|
| 753 |
+
"loss": 1.6537,
|
| 754 |
+
"step": 435
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.88,
|
| 758 |
+
"grad_norm": 0.7945486903190613,
|
| 759 |
+
"learning_rate": 0.0001416555407209613,
|
| 760 |
+
"loss": 1.5685,
|
| 761 |
+
"step": 440
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.89,
|
| 765 |
+
"grad_norm": 0.6951822638511658,
|
| 766 |
+
"learning_rate": 0.0001409879839786382,
|
| 767 |
+
"loss": 1.2469,
|
| 768 |
+
"step": 445
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.9,
|
| 772 |
+
"grad_norm": 0.6232516765594482,
|
| 773 |
+
"learning_rate": 0.00014032042723631508,
|
| 774 |
+
"loss": 1.6128,
|
| 775 |
+
"step": 450
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.9,
|
| 779 |
+
"eval_loss": 1.5824800729751587,
|
| 780 |
+
"eval_runtime": 153.4919,
|
| 781 |
+
"eval_samples_per_second": 0.339,
|
| 782 |
+
"eval_steps_per_second": 0.169,
|
| 783 |
+
"step": 450
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.91,
|
| 787 |
+
"grad_norm": 0.5635793209075928,
|
| 788 |
+
"learning_rate": 0.000139652870493992,
|
| 789 |
+
"loss": 1.4892,
|
| 790 |
+
"step": 455
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.92,
|
| 794 |
+
"grad_norm": 0.7134138941764832,
|
| 795 |
+
"learning_rate": 0.0001389853137516689,
|
| 796 |
+
"loss": 1.6564,
|
| 797 |
+
"step": 460
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.93,
|
| 801 |
+
"grad_norm": 1.0067154169082642,
|
| 802 |
+
"learning_rate": 0.0001383177570093458,
|
| 803 |
+
"loss": 1.8738,
|
| 804 |
+
"step": 465
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.94,
|
| 808 |
+
"grad_norm": 0.7665852904319763,
|
| 809 |
+
"learning_rate": 0.0001376502002670227,
|
| 810 |
+
"loss": 1.7151,
|
| 811 |
+
"step": 470
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.95,
|
| 815 |
+
"grad_norm": 0.5606282949447632,
|
| 816 |
+
"learning_rate": 0.0001369826435246996,
|
| 817 |
+
"loss": 1.7477,
|
| 818 |
+
"step": 475
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.95,
|
| 822 |
+
"eval_loss": 1.5813050270080566,
|
| 823 |
+
"eval_runtime": 153.7414,
|
| 824 |
+
"eval_samples_per_second": 0.338,
|
| 825 |
+
"eval_steps_per_second": 0.169,
|
| 826 |
+
"step": 475
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.96,
|
| 830 |
+
"grad_norm": 0.48252391815185547,
|
| 831 |
+
"learning_rate": 0.0001363150867823765,
|
| 832 |
+
"loss": 1.6785,
|
| 833 |
+
"step": 480
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.97,
|
| 837 |
+
"grad_norm": 0.7147005200386047,
|
| 838 |
+
"learning_rate": 0.0001356475300400534,
|
| 839 |
+
"loss": 1.5719,
|
| 840 |
+
"step": 485
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.98,
|
| 844 |
+
"grad_norm": 0.5606821775436401,
|
| 845 |
+
"learning_rate": 0.0001349799732977303,
|
| 846 |
+
"loss": 1.6884,
|
| 847 |
+
"step": 490
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.99,
|
| 851 |
+
"grad_norm": 0.6102766394615173,
|
| 852 |
+
"learning_rate": 0.0001343124165554072,
|
| 853 |
+
"loss": 1.5512,
|
| 854 |
+
"step": 495
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.0,
|
| 858 |
+
"grad_norm": 0.7451562285423279,
|
| 859 |
+
"learning_rate": 0.00013364485981308413,
|
| 860 |
+
"loss": 1.5853,
|
| 861 |
+
"step": 500
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.0,
|
| 865 |
+
"eval_loss": 1.5768074989318848,
|
| 866 |
+
"eval_runtime": 153.3623,
|
| 867 |
+
"eval_samples_per_second": 0.339,
|
| 868 |
+
"eval_steps_per_second": 0.17,
|
| 869 |
+
"step": 500
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 1.01,
|
| 873 |
+
"grad_norm": 0.6127219200134277,
|
| 874 |
+
"learning_rate": 0.000132977303070761,
|
| 875 |
+
"loss": 1.5375,
|
| 876 |
+
"step": 505
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.02,
|
| 880 |
+
"grad_norm": 0.6121686100959778,
|
| 881 |
+
"learning_rate": 0.00013230974632843793,
|
| 882 |
+
"loss": 1.4151,
|
| 883 |
+
"step": 510
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.03,
|
| 887 |
+
"grad_norm": 0.8484262824058533,
|
| 888 |
+
"learning_rate": 0.00013164218958611483,
|
| 889 |
+
"loss": 1.6334,
|
| 890 |
+
"step": 515
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.04,
|
| 894 |
+
"grad_norm": 1.115262508392334,
|
| 895 |
+
"learning_rate": 0.00013097463284379173,
|
| 896 |
+
"loss": 1.5492,
|
| 897 |
+
"step": 520
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.05,
|
| 901 |
+
"grad_norm": 0.6433502435684204,
|
| 902 |
+
"learning_rate": 0.00013030707610146863,
|
| 903 |
+
"loss": 1.54,
|
| 904 |
+
"step": 525
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.05,
|
| 908 |
+
"eval_loss": 1.5698615312576294,
|
| 909 |
+
"eval_runtime": 154.4611,
|
| 910 |
+
"eval_samples_per_second": 0.337,
|
| 911 |
+
"eval_steps_per_second": 0.168,
|
| 912 |
+
"step": 525
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.06,
|
| 916 |
+
"grad_norm": 0.6583875417709351,
|
| 917 |
+
"learning_rate": 0.00012963951935914553,
|
| 918 |
+
"loss": 1.5267,
|
| 919 |
+
"step": 530
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 1.07,
|
| 923 |
+
"grad_norm": 0.7508483529090881,
|
| 924 |
+
"learning_rate": 0.00012897196261682243,
|
| 925 |
+
"loss": 1.7802,
|
| 926 |
+
"step": 535
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 1.08,
|
| 930 |
+
"grad_norm": 0.9875255227088928,
|
| 931 |
+
"learning_rate": 0.00012830440587449936,
|
| 932 |
+
"loss": 1.4288,
|
| 933 |
+
"step": 540
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.09,
|
| 937 |
+
"grad_norm": 0.5857439637184143,
|
| 938 |
+
"learning_rate": 0.00012763684913217623,
|
| 939 |
+
"loss": 1.4952,
|
| 940 |
+
"step": 545
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.1,
|
| 944 |
+
"grad_norm": 0.4867228865623474,
|
| 945 |
+
"learning_rate": 0.00012696929238985313,
|
| 946 |
+
"loss": 1.3511,
|
| 947 |
+
"step": 550
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.1,
|
| 951 |
+
"eval_loss": 1.5703368186950684,
|
| 952 |
+
"eval_runtime": 155.0663,
|
| 953 |
+
"eval_samples_per_second": 0.335,
|
| 954 |
+
"eval_steps_per_second": 0.168,
|
| 955 |
+
"step": 550
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.11,
|
| 959 |
+
"grad_norm": 1.0664533376693726,
|
| 960 |
+
"learning_rate": 0.00012630173564753006,
|
| 961 |
+
"loss": 1.5299,
|
| 962 |
+
"step": 555
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.12,
|
| 966 |
+
"grad_norm": 0.5459120869636536,
|
| 967 |
+
"learning_rate": 0.00012563417890520696,
|
| 968 |
+
"loss": 1.6358,
|
| 969 |
+
"step": 560
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.13,
|
| 973 |
+
"grad_norm": 0.7361356616020203,
|
| 974 |
+
"learning_rate": 0.00012496662216288386,
|
| 975 |
+
"loss": 1.1664,
|
| 976 |
+
"step": 565
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.1400000000000001,
|
| 980 |
+
"grad_norm": 0.6312634348869324,
|
| 981 |
+
"learning_rate": 0.00012429906542056076,
|
| 982 |
+
"loss": 1.4422,
|
| 983 |
+
"step": 570
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.15,
|
| 987 |
+
"grad_norm": 0.6251769065856934,
|
| 988 |
+
"learning_rate": 0.00012363150867823766,
|
| 989 |
+
"loss": 1.4539,
|
| 990 |
+
"step": 575
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.15,
|
| 994 |
+
"eval_loss": 1.582599401473999,
|
| 995 |
+
"eval_runtime": 161.8119,
|
| 996 |
+
"eval_samples_per_second": 0.321,
|
| 997 |
+
"eval_steps_per_second": 0.161,
|
| 998 |
+
"step": 575
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.16,
|
| 1002 |
+
"grad_norm": 0.7663933634757996,
|
| 1003 |
+
"learning_rate": 0.00012296395193591456,
|
| 1004 |
+
"loss": 1.4286,
|
| 1005 |
+
"step": 580
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.17,
|
| 1009 |
+
"grad_norm": 0.5115808844566345,
|
| 1010 |
+
"learning_rate": 0.00012229639519359146,
|
| 1011 |
+
"loss": 1.5661,
|
| 1012 |
+
"step": 585
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.18,
|
| 1016 |
+
"grad_norm": 0.5785268545150757,
|
| 1017 |
+
"learning_rate": 0.00012162883845126836,
|
| 1018 |
+
"loss": 1.6004,
|
| 1019 |
+
"step": 590
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.19,
|
| 1023 |
+
"grad_norm": 1.1874048709869385,
|
| 1024 |
+
"learning_rate": 0.00012096128170894527,
|
| 1025 |
+
"loss": 1.4923,
|
| 1026 |
+
"step": 595
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.2,
|
| 1030 |
+
"grad_norm": 0.708734393119812,
|
| 1031 |
+
"learning_rate": 0.00012029372496662217,
|
| 1032 |
+
"loss": 1.6751,
|
| 1033 |
+
"step": 600
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.2,
|
| 1037 |
+
"eval_loss": 1.568034291267395,
|
| 1038 |
+
"eval_runtime": 157.401,
|
| 1039 |
+
"eval_samples_per_second": 0.33,
|
| 1040 |
+
"eval_steps_per_second": 0.165,
|
| 1041 |
+
"step": 600
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.21,
|
| 1045 |
+
"grad_norm": 0.9826223850250244,
|
| 1046 |
+
"learning_rate": 0.00011962616822429906,
|
| 1047 |
+
"loss": 1.5187,
|
| 1048 |
+
"step": 605
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.22,
|
| 1052 |
+
"grad_norm": 0.5815021991729736,
|
| 1053 |
+
"learning_rate": 0.00011895861148197598,
|
| 1054 |
+
"loss": 1.3991,
|
| 1055 |
+
"step": 610
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.23,
|
| 1059 |
+
"grad_norm": 0.7048662304878235,
|
| 1060 |
+
"learning_rate": 0.00011829105473965287,
|
| 1061 |
+
"loss": 1.316,
|
| 1062 |
+
"step": 615
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.24,
|
| 1066 |
+
"grad_norm": 0.667458176612854,
|
| 1067 |
+
"learning_rate": 0.00011762349799732977,
|
| 1068 |
+
"loss": 1.6166,
|
| 1069 |
+
"step": 620
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 1.25,
|
| 1073 |
+
"grad_norm": 0.7350333333015442,
|
| 1074 |
+
"learning_rate": 0.00011695594125500668,
|
| 1075 |
+
"loss": 1.5397,
|
| 1076 |
+
"step": 625
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.25,
|
| 1080 |
+
"eval_loss": 1.5718026161193848,
|
| 1081 |
+
"eval_runtime": 156.5658,
|
| 1082 |
+
"eval_samples_per_second": 0.332,
|
| 1083 |
+
"eval_steps_per_second": 0.166,
|
| 1084 |
+
"step": 625
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.26,
|
| 1088 |
+
"grad_norm": 0.6255879402160645,
|
| 1089 |
+
"learning_rate": 0.00011628838451268358,
|
| 1090 |
+
"loss": 1.3613,
|
| 1091 |
+
"step": 630
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.27,
|
| 1095 |
+
"grad_norm": 0.6177966594696045,
|
| 1096 |
+
"learning_rate": 0.0001156208277703605,
|
| 1097 |
+
"loss": 1.2452,
|
| 1098 |
+
"step": 635
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.28,
|
| 1102 |
+
"grad_norm": 0.5699389576911926,
|
| 1103 |
+
"learning_rate": 0.0001149532710280374,
|
| 1104 |
+
"loss": 1.2252,
|
| 1105 |
+
"step": 640
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.29,
|
| 1109 |
+
"grad_norm": 0.8304943442344666,
|
| 1110 |
+
"learning_rate": 0.00011428571428571428,
|
| 1111 |
+
"loss": 1.371,
|
| 1112 |
+
"step": 645
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.3,
|
| 1116 |
+
"grad_norm": 0.8348840475082397,
|
| 1117 |
+
"learning_rate": 0.0001136181575433912,
|
| 1118 |
+
"loss": 1.5561,
|
| 1119 |
+
"step": 650
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.3,
|
| 1123 |
+
"eval_loss": 1.5528948307037354,
|
| 1124 |
+
"eval_runtime": 155.2207,
|
| 1125 |
+
"eval_samples_per_second": 0.335,
|
| 1126 |
+
"eval_steps_per_second": 0.168,
|
| 1127 |
+
"step": 650
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 1.31,
|
| 1131 |
+
"grad_norm": 0.6180741786956787,
|
| 1132 |
+
"learning_rate": 0.0001129506008010681,
|
| 1133 |
+
"loss": 1.3885,
|
| 1134 |
+
"step": 655
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 1.32,
|
| 1138 |
+
"grad_norm": 0.9591236114501953,
|
| 1139 |
+
"learning_rate": 0.000112283044058745,
|
| 1140 |
+
"loss": 1.8704,
|
| 1141 |
+
"step": 660
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 1.33,
|
| 1145 |
+
"grad_norm": 0.5324267148971558,
|
| 1146 |
+
"learning_rate": 0.00011161548731642191,
|
| 1147 |
+
"loss": 1.3346,
|
| 1148 |
+
"step": 665
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 1.34,
|
| 1152 |
+
"grad_norm": 0.519713819026947,
|
| 1153 |
+
"learning_rate": 0.0001109479305740988,
|
| 1154 |
+
"loss": 1.553,
|
| 1155 |
+
"step": 670
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 1.35,
|
| 1159 |
+
"grad_norm": 0.7792118191719055,
|
| 1160 |
+
"learning_rate": 0.0001102803738317757,
|
| 1161 |
+
"loss": 1.4646,
|
| 1162 |
+
"step": 675
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.35,
|
| 1166 |
+
"eval_loss": 1.5499815940856934,
|
| 1167 |
+
"eval_runtime": 157.3901,
|
| 1168 |
+
"eval_samples_per_second": 0.33,
|
| 1169 |
+
"eval_steps_per_second": 0.165,
|
| 1170 |
+
"step": 675
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.3599999999999999,
|
| 1174 |
+
"grad_norm": 0.7332251667976379,
|
| 1175 |
+
"learning_rate": 0.00010961281708945261,
|
| 1176 |
+
"loss": 1.5366,
|
| 1177 |
+
"step": 680
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.37,
|
| 1181 |
+
"grad_norm": 1.0482912063598633,
|
| 1182 |
+
"learning_rate": 0.00010894526034712951,
|
| 1183 |
+
"loss": 1.7866,
|
| 1184 |
+
"step": 685
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.38,
|
| 1188 |
+
"grad_norm": 0.6060436964035034,
|
| 1189 |
+
"learning_rate": 0.00010827770360480642,
|
| 1190 |
+
"loss": 1.3853,
|
| 1191 |
+
"step": 690
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.3900000000000001,
|
| 1195 |
+
"grad_norm": 0.6550512313842773,
|
| 1196 |
+
"learning_rate": 0.00010761014686248332,
|
| 1197 |
+
"loss": 1.765,
|
| 1198 |
+
"step": 695
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 1.4,
|
| 1202 |
+
"grad_norm": 0.8347830176353455,
|
| 1203 |
+
"learning_rate": 0.00010694259012016021,
|
| 1204 |
+
"loss": 1.4687,
|
| 1205 |
+
"step": 700
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.4,
|
| 1209 |
+
"eval_loss": 1.5612692832946777,
|
| 1210 |
+
"eval_runtime": 166.6597,
|
| 1211 |
+
"eval_samples_per_second": 0.312,
|
| 1212 |
+
"eval_steps_per_second": 0.156,
|
| 1213 |
+
"step": 700
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.41,
|
| 1217 |
+
"grad_norm": 0.6563287973403931,
|
| 1218 |
+
"learning_rate": 0.00010627503337783712,
|
| 1219 |
+
"loss": 1.3366,
|
| 1220 |
+
"step": 705
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.42,
|
| 1224 |
+
"grad_norm": 0.6529929637908936,
|
| 1225 |
+
"learning_rate": 0.00010560747663551402,
|
| 1226 |
+
"loss": 1.6132,
|
| 1227 |
+
"step": 710
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.43,
|
| 1231 |
+
"grad_norm": 0.504224956035614,
|
| 1232 |
+
"learning_rate": 0.00010493991989319092,
|
| 1233 |
+
"loss": 1.4062,
|
| 1234 |
+
"step": 715
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.44,
|
| 1238 |
+
"grad_norm": 0.5341633558273315,
|
| 1239 |
+
"learning_rate": 0.00010427236315086784,
|
| 1240 |
+
"loss": 1.3092,
|
| 1241 |
+
"step": 720
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.45,
|
| 1245 |
+
"grad_norm": 0.8322250843048096,
|
| 1246 |
+
"learning_rate": 0.00010360480640854472,
|
| 1247 |
+
"loss": 1.4273,
|
| 1248 |
+
"step": 725
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.45,
|
| 1252 |
+
"eval_loss": 1.5545457601547241,
|
| 1253 |
+
"eval_runtime": 161.785,
|
| 1254 |
+
"eval_samples_per_second": 0.321,
|
| 1255 |
+
"eval_steps_per_second": 0.161,
|
| 1256 |
+
"step": 725
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.46,
|
| 1260 |
+
"grad_norm": 0.694214940071106,
|
| 1261 |
+
"learning_rate": 0.00010293724966622162,
|
| 1262 |
+
"loss": 1.3338,
|
| 1263 |
+
"step": 730
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.47,
|
| 1267 |
+
"grad_norm": 0.83758944272995,
|
| 1268 |
+
"learning_rate": 0.00010226969292389854,
|
| 1269 |
+
"loss": 1.4813,
|
| 1270 |
+
"step": 735
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.48,
|
| 1274 |
+
"grad_norm": 0.7225409150123596,
|
| 1275 |
+
"learning_rate": 0.00010160213618157544,
|
| 1276 |
+
"loss": 1.4857,
|
| 1277 |
+
"step": 740
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.49,
|
| 1281 |
+
"grad_norm": 0.6755008697509766,
|
| 1282 |
+
"learning_rate": 0.00010093457943925234,
|
| 1283 |
+
"loss": 1.452,
|
| 1284 |
+
"step": 745
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.5,
|
| 1288 |
+
"grad_norm": 0.8779104351997375,
|
| 1289 |
+
"learning_rate": 0.00010026702269692925,
|
| 1290 |
+
"loss": 1.5225,
|
| 1291 |
+
"step": 750
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.5,
|
| 1295 |
+
"eval_loss": 1.5489907264709473,
|
| 1296 |
+
"eval_runtime": 157.1309,
|
| 1297 |
+
"eval_samples_per_second": 0.331,
|
| 1298 |
+
"eval_steps_per_second": 0.165,
|
| 1299 |
+
"step": 750
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.51,
|
| 1303 |
+
"grad_norm": 0.7593478560447693,
|
| 1304 |
+
"learning_rate": 9.959946595460614e-05,
|
| 1305 |
+
"loss": 1.7504,
|
| 1306 |
+
"step": 755
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.52,
|
| 1310 |
+
"grad_norm": 0.7336363792419434,
|
| 1311 |
+
"learning_rate": 9.893190921228305e-05,
|
| 1312 |
+
"loss": 1.7467,
|
| 1313 |
+
"step": 760
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.53,
|
| 1317 |
+
"grad_norm": 0.6226593852043152,
|
| 1318 |
+
"learning_rate": 9.826435246995995e-05,
|
| 1319 |
+
"loss": 1.2953,
|
| 1320 |
+
"step": 765
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 1.54,
|
| 1324 |
+
"grad_norm": 0.652702808380127,
|
| 1325 |
+
"learning_rate": 9.759679572763686e-05,
|
| 1326 |
+
"loss": 1.6913,
|
| 1327 |
+
"step": 770
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.55,
|
| 1331 |
+
"grad_norm": 0.6243285536766052,
|
| 1332 |
+
"learning_rate": 9.692923898531375e-05,
|
| 1333 |
+
"loss": 1.5129,
|
| 1334 |
+
"step": 775
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.55,
|
| 1338 |
+
"eval_loss": 1.5401288270950317,
|
| 1339 |
+
"eval_runtime": 159.6754,
|
| 1340 |
+
"eval_samples_per_second": 0.326,
|
| 1341 |
+
"eval_steps_per_second": 0.163,
|
| 1342 |
+
"step": 775
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 1.56,
|
| 1346 |
+
"grad_norm": 0.5181707739830017,
|
| 1347 |
+
"learning_rate": 9.626168224299066e-05,
|
| 1348 |
+
"loss": 1.4,
|
| 1349 |
+
"step": 780
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 1.5699999999999998,
|
| 1353 |
+
"grad_norm": 0.4900369346141815,
|
| 1354 |
+
"learning_rate": 9.559412550066756e-05,
|
| 1355 |
+
"loss": 1.4891,
|
| 1356 |
+
"step": 785
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 1.58,
|
| 1360 |
+
"grad_norm": 0.7415319085121155,
|
| 1361 |
+
"learning_rate": 9.492656875834446e-05,
|
| 1362 |
+
"loss": 1.2679,
|
| 1363 |
+
"step": 790
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 1.5899999999999999,
|
| 1367 |
+
"grad_norm": 0.6447709798812866,
|
| 1368 |
+
"learning_rate": 9.425901201602136e-05,
|
| 1369 |
+
"loss": 1.4957,
|
| 1370 |
+
"step": 795
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.6,
|
| 1374 |
+
"grad_norm": 0.6303768754005432,
|
| 1375 |
+
"learning_rate": 9.359145527369826e-05,
|
| 1376 |
+
"loss": 1.4617,
|
| 1377 |
+
"step": 800
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 1.6,
|
| 1381 |
+
"eval_loss": 1.5425684452056885,
|
| 1382 |
+
"eval_runtime": 157.5599,
|
| 1383 |
+
"eval_samples_per_second": 0.33,
|
| 1384 |
+
"eval_steps_per_second": 0.165,
|
| 1385 |
+
"step": 800
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.6099999999999999,
|
| 1389 |
+
"grad_norm": 0.6443194150924683,
|
| 1390 |
+
"learning_rate": 9.292389853137518e-05,
|
| 1391 |
+
"loss": 1.4427,
|
| 1392 |
+
"step": 805
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.62,
|
| 1396 |
+
"grad_norm": 0.6477059125900269,
|
| 1397 |
+
"learning_rate": 9.225634178905206e-05,
|
| 1398 |
+
"loss": 1.3323,
|
| 1399 |
+
"step": 810
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.63,
|
| 1403 |
+
"grad_norm": 1.2460426092147827,
|
| 1404 |
+
"learning_rate": 9.158878504672898e-05,
|
| 1405 |
+
"loss": 1.6938,
|
| 1406 |
+
"step": 815
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.6400000000000001,
|
| 1410 |
+
"grad_norm": 0.5094366073608398,
|
| 1411 |
+
"learning_rate": 9.092122830440588e-05,
|
| 1412 |
+
"loss": 1.3493,
|
| 1413 |
+
"step": 820
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.65,
|
| 1417 |
+
"grad_norm": 0.6189996004104614,
|
| 1418 |
+
"learning_rate": 9.025367156208279e-05,
|
| 1419 |
+
"loss": 1.5123,
|
| 1420 |
+
"step": 825
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.65,
|
| 1424 |
+
"eval_loss": 1.5375796556472778,
|
| 1425 |
+
"eval_runtime": 156.9638,
|
| 1426 |
+
"eval_samples_per_second": 0.331,
|
| 1427 |
+
"eval_steps_per_second": 0.166,
|
| 1428 |
+
"step": 825
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.6600000000000001,
|
| 1432 |
+
"grad_norm": 0.8235365748405457,
|
| 1433 |
+
"learning_rate": 8.958611481975968e-05,
|
| 1434 |
+
"loss": 1.3337,
|
| 1435 |
+
"step": 830
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 1.67,
|
| 1439 |
+
"grad_norm": 0.6116329431533813,
|
| 1440 |
+
"learning_rate": 8.891855807743659e-05,
|
| 1441 |
+
"loss": 1.2533,
|
| 1442 |
+
"step": 835
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.6800000000000002,
|
| 1446 |
+
"grad_norm": 0.597701370716095,
|
| 1447 |
+
"learning_rate": 8.825100133511349e-05,
|
| 1448 |
+
"loss": 1.4036,
|
| 1449 |
+
"step": 840
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.69,
|
| 1453 |
+
"grad_norm": 0.5337836742401123,
|
| 1454 |
+
"learning_rate": 8.758344459279039e-05,
|
| 1455 |
+
"loss": 1.2977,
|
| 1456 |
+
"step": 845
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.7,
|
| 1460 |
+
"grad_norm": 0.5650852918624878,
|
| 1461 |
+
"learning_rate": 8.691588785046729e-05,
|
| 1462 |
+
"loss": 1.4909,
|
| 1463 |
+
"step": 850
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.7,
|
| 1467 |
+
"eval_loss": 1.5355829000473022,
|
| 1468 |
+
"eval_runtime": 156.0274,
|
| 1469 |
+
"eval_samples_per_second": 0.333,
|
| 1470 |
+
"eval_steps_per_second": 0.167,
|
| 1471 |
+
"step": 850
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 1.71,
|
| 1475 |
+
"grad_norm": 0.7378519773483276,
|
| 1476 |
+
"learning_rate": 8.62483311081442e-05,
|
| 1477 |
+
"loss": 1.6229,
|
| 1478 |
+
"step": 855
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 1.72,
|
| 1482 |
+
"grad_norm": 0.6510607600212097,
|
| 1483 |
+
"learning_rate": 8.55807743658211e-05,
|
| 1484 |
+
"loss": 1.3392,
|
| 1485 |
+
"step": 860
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.73,
|
| 1489 |
+
"grad_norm": 0.6023868918418884,
|
| 1490 |
+
"learning_rate": 8.4913217623498e-05,
|
| 1491 |
+
"loss": 1.5289,
|
| 1492 |
+
"step": 865
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 1.74,
|
| 1496 |
+
"grad_norm": 0.7228203415870667,
|
| 1497 |
+
"learning_rate": 8.42456608811749e-05,
|
| 1498 |
+
"loss": 1.5144,
|
| 1499 |
+
"step": 870
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.75,
|
| 1503 |
+
"grad_norm": 0.7221407294273376,
|
| 1504 |
+
"learning_rate": 8.35781041388518e-05,
|
| 1505 |
+
"loss": 1.2201,
|
| 1506 |
+
"step": 875
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.75,
|
| 1510 |
+
"eval_loss": 1.5325042009353638,
|
| 1511 |
+
"eval_runtime": 157.2229,
|
| 1512 |
+
"eval_samples_per_second": 0.331,
|
| 1513 |
+
"eval_steps_per_second": 0.165,
|
| 1514 |
+
"step": 875
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.76,
|
| 1518 |
+
"grad_norm": 0.48412030935287476,
|
| 1519 |
+
"learning_rate": 8.29105473965287e-05,
|
| 1520 |
+
"loss": 1.5154,
|
| 1521 |
+
"step": 880
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.77,
|
| 1525 |
+
"grad_norm": 0.7840531468391418,
|
| 1526 |
+
"learning_rate": 8.22429906542056e-05,
|
| 1527 |
+
"loss": 1.7819,
|
| 1528 |
+
"step": 885
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 1.78,
|
| 1532 |
+
"grad_norm": 0.6077267527580261,
|
| 1533 |
+
"learning_rate": 8.157543391188252e-05,
|
| 1534 |
+
"loss": 1.4317,
|
| 1535 |
+
"step": 890
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.79,
|
| 1539 |
+
"grad_norm": 0.6933810114860535,
|
| 1540 |
+
"learning_rate": 8.090787716955942e-05,
|
| 1541 |
+
"loss": 1.7069,
|
| 1542 |
+
"step": 895
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.8,
|
| 1546 |
+
"grad_norm": 0.7501831650733948,
|
| 1547 |
+
"learning_rate": 8.024032042723632e-05,
|
| 1548 |
+
"loss": 1.2877,
|
| 1549 |
+
"step": 900
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.8,
|
| 1553 |
+
"eval_loss": 1.5253818035125732,
|
| 1554 |
+
"eval_runtime": 156.1433,
|
| 1555 |
+
"eval_samples_per_second": 0.333,
|
| 1556 |
+
"eval_steps_per_second": 0.167,
|
| 1557 |
+
"step": 900
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.81,
|
| 1561 |
+
"grad_norm": 0.6081863045692444,
|
| 1562 |
+
"learning_rate": 7.957276368491322e-05,
|
| 1563 |
+
"loss": 1.2527,
|
| 1564 |
+
"step": 905
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.8199999999999998,
|
| 1568 |
+
"grad_norm": 0.6956006288528442,
|
| 1569 |
+
"learning_rate": 7.890520694259013e-05,
|
| 1570 |
+
"loss": 1.4184,
|
| 1571 |
+
"step": 910
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.83,
|
| 1575 |
+
"grad_norm": 0.5345895886421204,
|
| 1576 |
+
"learning_rate": 7.823765020026703e-05,
|
| 1577 |
+
"loss": 1.6186,
|
| 1578 |
+
"step": 915
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.8399999999999999,
|
| 1582 |
+
"grad_norm": 0.682368814945221,
|
| 1583 |
+
"learning_rate": 7.757009345794393e-05,
|
| 1584 |
+
"loss": 1.3062,
|
| 1585 |
+
"step": 920
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.85,
|
| 1589 |
+
"grad_norm": 0.7534874677658081,
|
| 1590 |
+
"learning_rate": 7.690253671562083e-05,
|
| 1591 |
+
"loss": 1.3955,
|
| 1592 |
+
"step": 925
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.85,
|
| 1596 |
+
"eval_loss": 1.5264804363250732,
|
| 1597 |
+
"eval_runtime": 157.3189,
|
| 1598 |
+
"eval_samples_per_second": 0.331,
|
| 1599 |
+
"eval_steps_per_second": 0.165,
|
| 1600 |
+
"step": 925
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.8599999999999999,
|
| 1604 |
+
"grad_norm": 0.8998626470565796,
|
| 1605 |
+
"learning_rate": 7.623497997329774e-05,
|
| 1606 |
+
"loss": 1.6625,
|
| 1607 |
+
"step": 930
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.87,
|
| 1611 |
+
"grad_norm": 0.5620250105857849,
|
| 1612 |
+
"learning_rate": 7.556742323097463e-05,
|
| 1613 |
+
"loss": 1.6022,
|
| 1614 |
+
"step": 935
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.88,
|
| 1618 |
+
"grad_norm": 0.656494677066803,
|
| 1619 |
+
"learning_rate": 7.489986648865154e-05,
|
| 1620 |
+
"loss": 1.3404,
|
| 1621 |
+
"step": 940
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.8900000000000001,
|
| 1625 |
+
"grad_norm": 1.0331978797912598,
|
| 1626 |
+
"learning_rate": 7.423230974632844e-05,
|
| 1627 |
+
"loss": 1.6219,
|
| 1628 |
+
"step": 945
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.9,
|
| 1632 |
+
"grad_norm": 0.7671311497688293,
|
| 1633 |
+
"learning_rate": 7.356475300400534e-05,
|
| 1634 |
+
"loss": 1.5102,
|
| 1635 |
+
"step": 950
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.9,
|
| 1639 |
+
"eval_loss": 1.5233145952224731,
|
| 1640 |
+
"eval_runtime": 156.2243,
|
| 1641 |
+
"eval_samples_per_second": 0.333,
|
| 1642 |
+
"eval_steps_per_second": 0.166,
|
| 1643 |
+
"step": 950
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 1.9100000000000001,
|
| 1647 |
+
"grad_norm": 0.514800488948822,
|
| 1648 |
+
"learning_rate": 7.289719626168224e-05,
|
| 1649 |
+
"loss": 1.4231,
|
| 1650 |
+
"step": 955
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.92,
|
| 1654 |
+
"grad_norm": 1.1229217052459717,
|
| 1655 |
+
"learning_rate": 7.222963951935914e-05,
|
| 1656 |
+
"loss": 1.3732,
|
| 1657 |
+
"step": 960
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 1.9300000000000002,
|
| 1661 |
+
"grad_norm": 0.7795677185058594,
|
| 1662 |
+
"learning_rate": 7.156208277703606e-05,
|
| 1663 |
+
"loss": 1.242,
|
| 1664 |
+
"step": 965
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 1.94,
|
| 1668 |
+
"grad_norm": 0.6444641351699829,
|
| 1669 |
+
"learning_rate": 7.089452603471294e-05,
|
| 1670 |
+
"loss": 1.437,
|
| 1671 |
+
"step": 970
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 1.95,
|
| 1675 |
+
"grad_norm": 0.698694109916687,
|
| 1676 |
+
"learning_rate": 7.022696929238986e-05,
|
| 1677 |
+
"loss": 1.4972,
|
| 1678 |
+
"step": 975
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 1.95,
|
| 1682 |
+
"eval_loss": 1.5205299854278564,
|
| 1683 |
+
"eval_runtime": 157.1769,
|
| 1684 |
+
"eval_samples_per_second": 0.331,
|
| 1685 |
+
"eval_steps_per_second": 0.165,
|
| 1686 |
+
"step": 975
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 1.96,
|
| 1690 |
+
"grad_norm": 0.7859231233596802,
|
| 1691 |
+
"learning_rate": 6.955941255006676e-05,
|
| 1692 |
+
"loss": 1.4448,
|
| 1693 |
+
"step": 980
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 1.97,
|
| 1697 |
+
"grad_norm": 0.6304051876068115,
|
| 1698 |
+
"learning_rate": 6.889185580774367e-05,
|
| 1699 |
+
"loss": 1.5132,
|
| 1700 |
+
"step": 985
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 1.98,
|
| 1704 |
+
"grad_norm": 0.6905663013458252,
|
| 1705 |
+
"learning_rate": 6.822429906542056e-05,
|
| 1706 |
+
"loss": 1.5612,
|
| 1707 |
+
"step": 990
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 1.99,
|
| 1711 |
+
"grad_norm": 0.6258041262626648,
|
| 1712 |
+
"learning_rate": 6.755674232309747e-05,
|
| 1713 |
+
"loss": 1.4587,
|
| 1714 |
+
"step": 995
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 2.0,
|
| 1718 |
+
"grad_norm": 0.7253485918045044,
|
| 1719 |
+
"learning_rate": 6.688918558077437e-05,
|
| 1720 |
+
"loss": 1.4498,
|
| 1721 |
+
"step": 1000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 2.0,
|
| 1725 |
+
"eval_loss": 1.5251318216323853,
|
| 1726 |
+
"eval_runtime": 156.2874,
|
| 1727 |
+
"eval_samples_per_second": 0.333,
|
| 1728 |
+
"eval_steps_per_second": 0.166,
|
| 1729 |
+
"step": 1000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 2.01,
|
| 1733 |
+
"grad_norm": 0.5841794013977051,
|
| 1734 |
+
"learning_rate": 6.622162883845127e-05,
|
| 1735 |
+
"loss": 1.5441,
|
| 1736 |
+
"step": 1005
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 2.02,
|
| 1740 |
+
"grad_norm": 0.7779578566551208,
|
| 1741 |
+
"learning_rate": 6.555407209612817e-05,
|
| 1742 |
+
"loss": 1.4619,
|
| 1743 |
+
"step": 1010
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 2.028,
|
| 1747 |
+
"eval_loss": 1.5253530740737915,
|
| 1748 |
+
"eval_runtime": 168.5711,
|
| 1749 |
+
"eval_samples_per_second": 0.308,
|
| 1750 |
+
"eval_steps_per_second": 0.154,
|
| 1751 |
+
"step": 1014
|
| 1752 |
+
}
|
| 1753 |
+
],
|
| 1754 |
+
"logging_steps": 5,
|
| 1755 |
+
"max_steps": 1500,
|
| 1756 |
+
"num_input_tokens_seen": 0,
|
| 1757 |
+
"num_train_epochs": 3,
|
| 1758 |
+
"save_steps": 25,
|
| 1759 |
+
"stateful_callbacks": {
|
| 1760 |
+
"TrainerControl": {
|
| 1761 |
+
"args": {
|
| 1762 |
+
"should_epoch_stop": false,
|
| 1763 |
+
"should_evaluate": false,
|
| 1764 |
+
"should_log": false,
|
| 1765 |
+
"should_save": true,
|
| 1766 |
+
"should_training_stop": false
|
| 1767 |
+
},
|
| 1768 |
+
"attributes": {}
|
| 1769 |
+
}
|
| 1770 |
+
},
|
| 1771 |
+
"total_flos": 8.503998201987072e+16,
|
| 1772 |
+
"train_batch_size": 2,
|
| 1773 |
+
"trial_name": null,
|
| 1774 |
+
"trial_params": null
|
| 1775 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efdf0602db8b813b15ad61fa70a59474f91c589cd332f4b34932102b391be55f
|
| 3 |
+
size 5432
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|