初始化项目，由ModelHub XC社区提供模型
Model: pre-to-post-olmo/math-1b-sft-numinamath-bs512-from-step30000 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: other
|
||||||
|
base_model: pre-to-post-olmo/math-1b-anneal-from-step30000
|
||||||
|
tags:
|
||||||
|
- llama-factory
|
||||||
|
- full
|
||||||
|
- generated_from_trainer
|
||||||
|
model-index:
|
||||||
|
- name: math-1b-sft-numinamath-bs512-from-step30000
|
||||||
|
results: []
|
||||||
|
---
|
||||||
|
|
||||||
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||||
|
should probably proofread and complete it, then remove this comment. -->
|
||||||
|
|
||||||
|
# math-1b-sft-numinamath-bs512-from-step30000
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [pre-to-post-olmo/math-1b-anneal-from-step30000](https://huggingface.co/pre-to-post-olmo/math-1b-anneal-from-step30000) on the numinamath_cot dataset.
|
||||||
|
|
||||||
|
## Model description
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Intended uses & limitations
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training and evaluation data
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
### Training hyperparameters
|
||||||
|
|
||||||
|
The following hyperparameters were used during training:
|
||||||
|
- learning_rate: 1e-05
|
||||||
|
- train_batch_size: 32
|
||||||
|
- eval_batch_size: 8
|
||||||
|
- seed: 42
|
||||||
|
- distributed_type: multi-GPU
|
||||||
|
- num_devices: 8
|
||||||
|
- gradient_accumulation_steps: 2
|
||||||
|
- total_train_batch_size: 512
|
||||||
|
- total_eval_batch_size: 64
|
||||||
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||||
|
- lr_scheduler_type: cosine
|
||||||
|
- lr_scheduler_warmup_ratio: 0.03
|
||||||
|
- num_epochs: 1.0
|
||||||
|
|
||||||
|
### Training results
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- Transformers 4.57.1
|
||||||
|
- Pytorch 2.12.1+cu130
|
||||||
|
- Datasets 4.0.0
|
||||||
|
- Tokenizers 0.22.2
|
||||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"total_flos": 9.42165996526266e+18,
|
||||||
|
"train_loss": 0.5865233610470143,
|
||||||
|
"train_runtime": 4862.2389,
|
||||||
|
"train_samples_per_second": 176.769,
|
||||||
|
"train_steps_per_second": 0.345
|
||||||
|
}
|
||||||
4
chat_template.jinja
Normal file
4
chat_template.jinja
Normal file
@@ -0,0 +1,4 @@
|
|||||||
|
{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
||||||
|
' + message['content'] + '<|im_end|>' + '
|
||||||
|
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
||||||
|
' }}{% endif %}
|
||||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Olmo2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 100257,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2048,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 8192,
|
||||||
|
"max_position_embeddings": 8192,
|
||||||
|
"model_type": "olmo2",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 16,
|
||||||
|
"num_key_value_heads": 16,
|
||||||
|
"pad_token_id": 100277,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_parameters": {
|
||||||
|
"rope_theta": 500000,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 10000.0,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "4.57.1",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 100278
|
||||||
|
}
|
||||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
100265,
|
||||||
|
100257
|
||||||
|
],
|
||||||
|
"pad_token_id": 100277,
|
||||||
|
"transformers_version": "4.57.1"
|
||||||
|
}
|
||||||
100001
merges.txt
Normal file
100001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3644668e877ffb98aabd660389fb1d3fff4d495809db1159833bf6622f301ffd
|
||||||
|
size 2969248016
|
||||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
{
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
500536
tokenizer.json
Normal file
500536
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
195
tokenizer_config.json
Normal file
195
tokenizer_config.json
Normal file
@@ -0,0 +1,195 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"100256": {
|
||||||
|
"content": "<|extra_id_0|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100257": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100258": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100259": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100260": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100261": {
|
||||||
|
"content": "|||PHONE_NUMBER|||",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100262": {
|
||||||
|
"content": "|||EMAIL_ADDRESS|||",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100263": {
|
||||||
|
"content": "|||IP_ADDRESS|||",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100264": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100265": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100266": {
|
||||||
|
"content": "<|extra_id_1|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100267": {
|
||||||
|
"content": "<|extra_id_2|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100268": {
|
||||||
|
"content": "<|extra_id_3|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100269": {
|
||||||
|
"content": "<|extra_id_4|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100270": {
|
||||||
|
"content": "<|extra_id_5|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100271": {
|
||||||
|
"content": "<|extra_id_6|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100272": {
|
||||||
|
"content": "<|extra_id_7|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100273": {
|
||||||
|
"content": "<|extra_id_8|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100274": {
|
||||||
|
"content": "<|extra_id_9|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100275": {
|
||||||
|
"content": "<|extra_id_10|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"100276": {
|
||||||
|
"content": "<|endofprompt|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"100277": {
|
||||||
|
"content": "<|pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"backend": "tokenizers",
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"is_local": false,
|
||||||
|
"local_files_only": false,
|
||||||
|
"model_max_length": 8192,
|
||||||
|
"pad_token": "<|pad|>",
|
||||||
|
"padding_side": "right",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "GPT2Tokenizer",
|
||||||
|
"unk_token": "<|endoftext|>"
|
||||||
|
}
|
||||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"total_flos": 9.42165996526266e+18,
|
||||||
|
"train_loss": 0.5865233610470143,
|
||||||
|
"train_runtime": 4862.2389,
|
||||||
|
"train_samples_per_second": 176.769,
|
||||||
|
"train_steps_per_second": 0.345
|
||||||
|
}
|
||||||
84
trainer_log.jsonl
Normal file
84
trainer_log.jsonl
Normal file
@@ -0,0 +1,84 @@
|
|||||||
|
{"current_steps": 20, "total_steps": 1679, "loss": 1.6734, "lr": 3.7254901960784316e-06, "epoch": 0.011911852293031567, "percentage": 1.19, "elapsed_time": "0:01:04", "remaining_time": "1:29:19"}
|
||||||
|
{"current_steps": 40, "total_steps": 1679, "loss": 1.1925, "lr": 7.647058823529411e-06, "epoch": 0.023823704586063133, "percentage": 2.38, "elapsed_time": "0:02:02", "remaining_time": "1:23:33"}
|
||||||
|
{"current_steps": 60, "total_steps": 1679, "loss": 0.798, "lr": 9.999404197526844e-06, "epoch": 0.0357355568790947, "percentage": 3.57, "elapsed_time": "0:03:00", "remaining_time": "1:21:03"}
|
||||||
|
{"current_steps": 80, "total_steps": 1679, "loss": 0.6976, "lr": 9.99270305028903e-06, "epoch": 0.047647409172126266, "percentage": 4.76, "elapsed_time": "0:03:59", "remaining_time": "1:19:52"}
|
||||||
|
{"current_steps": 100, "total_steps": 1679, "loss": 0.663, "lr": 9.978566016361393e-06, "epoch": 0.05955926146515783, "percentage": 5.96, "elapsed_time": "0:05:04", "remaining_time": "1:20:15"}
|
||||||
|
{"current_steps": 120, "total_steps": 1679, "loss": 0.6451, "lr": 9.95701415074788e-06, "epoch": 0.0714711137581894, "percentage": 7.15, "elapsed_time": "0:06:04", "remaining_time": "1:18:55"}
|
||||||
|
{"current_steps": 140, "total_steps": 1679, "loss": 0.6341, "lr": 9.928079551738542e-06, "epoch": 0.08338296605122096, "percentage": 8.34, "elapsed_time": "0:07:05", "remaining_time": "1:17:52"}
|
||||||
|
{"current_steps": 160, "total_steps": 1679, "loss": 0.6293, "lr": 9.891805313103928e-06, "epoch": 0.09529481834425253, "percentage": 9.53, "elapsed_time": "0:08:01", "remaining_time": "1:16:07"}
|
||||||
|
{"current_steps": 180, "total_steps": 1679, "loss": 0.6142, "lr": 9.848245459913323e-06, "epoch": 0.1072066706372841, "percentage": 10.72, "elapsed_time": "0:08:59", "remaining_time": "1:14:52"}
|
||||||
|
{"current_steps": 200, "total_steps": 1679, "loss": 0.6166, "lr": 9.797464868072489e-06, "epoch": 0.11911852293031566, "percentage": 11.91, "elapsed_time": "0:09:57", "remaining_time": "1:13:36"}
|
||||||
|
{"current_steps": 220, "total_steps": 1679, "loss": 0.6094, "lr": 9.739539167700649e-06, "epoch": 0.13103037522334723, "percentage": 13.1, "elapsed_time": "0:10:58", "remaining_time": "1:12:46"}
|
||||||
|
{"current_steps": 240, "total_steps": 1679, "loss": 0.5995, "lr": 9.674554630490727e-06, "epoch": 0.1429422275163788, "percentage": 14.29, "elapsed_time": "0:12:01", "remaining_time": "1:12:06"}
|
||||||
|
{"current_steps": 260, "total_steps": 1679, "loss": 0.5949, "lr": 9.60260804122051e-06, "epoch": 0.15485407980941035, "percentage": 15.49, "elapsed_time": "0:12:57", "remaining_time": "1:10:43"}
|
||||||
|
{"current_steps": 280, "total_steps": 1679, "loss": 0.5945, "lr": 9.523806553606157e-06, "epoch": 0.16676593210244192, "percentage": 16.68, "elapsed_time": "0:14:00", "remaining_time": "1:09:57"}
|
||||||
|
{"current_steps": 300, "total_steps": 1679, "loss": 0.5944, "lr": 9.438267530712727e-06, "epoch": 0.1786777843954735, "percentage": 17.87, "elapsed_time": "0:14:58", "remaining_time": "1:08:50"}
|
||||||
|
{"current_steps": 320, "total_steps": 1679, "loss": 0.59, "lr": 9.34611837015938e-06, "epoch": 0.19058963668850507, "percentage": 19.06, "elapsed_time": "0:15:56", "remaining_time": "1:07:40"}
|
||||||
|
{"current_steps": 340, "total_steps": 1679, "loss": 0.5876, "lr": 9.247496314379634e-06, "epoch": 0.20250148898153664, "percentage": 20.25, "elapsed_time": "0:16:53", "remaining_time": "1:06:31"}
|
||||||
|
{"current_steps": 360, "total_steps": 1679, "loss": 0.5788, "lr": 9.142548246219212e-06, "epoch": 0.2144133412745682, "percentage": 21.44, "elapsed_time": "0:17:50", "remaining_time": "1:05:21"}
|
||||||
|
{"current_steps": 380, "total_steps": 1679, "loss": 0.5799, "lr": 9.031430470175958e-06, "epoch": 0.22632519356759975, "percentage": 22.63, "elapsed_time": "0:18:49", "remaining_time": "1:04:22"}
|
||||||
|
{"current_steps": 400, "total_steps": 1679, "loss": 0.5722, "lr": 8.914308479607592e-06, "epoch": 0.23823704586063132, "percentage": 23.82, "elapsed_time": "0:19:46", "remaining_time": "1:03:15"}
|
||||||
|
{"current_steps": 420, "total_steps": 1679, "loss": 0.5715, "lr": 8.791356710254026e-06, "epoch": 0.25014889815366287, "percentage": 25.01, "elapsed_time": "0:20:45", "remaining_time": "1:02:12"}
|
||||||
|
{"current_steps": 440, "total_steps": 1679, "loss": 0.5735, "lr": 8.662758280441353e-06, "epoch": 0.26206075044669447, "percentage": 26.21, "elapsed_time": "0:21:40", "remaining_time": "1:01:01"}
|
||||||
|
{"current_steps": 460, "total_steps": 1679, "loss": 0.5728, "lr": 8.528704718354392e-06, "epoch": 0.273972602739726, "percentage": 27.4, "elapsed_time": "0:22:37", "remaining_time": "0:59:57"}
|
||||||
|
{"current_steps": 480, "total_steps": 1679, "loss": 0.5702, "lr": 8.389395676784025e-06, "epoch": 0.2858844550327576, "percentage": 28.59, "elapsed_time": "0:23:39", "remaining_time": "0:59:05"}
|
||||||
|
{"current_steps": 500, "total_steps": 1679, "loss": 0.5677, "lr": 8.245038635774144e-06, "epoch": 0.29779630732578916, "percentage": 29.78, "elapsed_time": "0:24:36", "remaining_time": "0:58:00"}
|
||||||
|
{"current_steps": 520, "total_steps": 1679, "loss": 0.5643, "lr": 8.095848593611045e-06, "epoch": 0.3097081596188207, "percentage": 30.97, "elapsed_time": "0:25:33", "remaining_time": "0:56:57"}
|
||||||
|
{"current_steps": 540, "total_steps": 1679, "loss": 0.5648, "lr": 7.942047746615561e-06, "epoch": 0.3216200119118523, "percentage": 32.16, "elapsed_time": "0:26:29", "remaining_time": "0:55:53"}
|
||||||
|
{"current_steps": 560, "total_steps": 1679, "loss": 0.5623, "lr": 7.783865158214768e-06, "epoch": 0.33353186420488384, "percentage": 33.35, "elapsed_time": "0:27:32", "remaining_time": "0:55:01"}
|
||||||
|
{"current_steps": 580, "total_steps": 1679, "loss": 0.5576, "lr": 7.621536417786159e-06, "epoch": 0.34544371649791544, "percentage": 34.54, "elapsed_time": "0:28:29", "remaining_time": "0:53:58"}
|
||||||
|
{"current_steps": 600, "total_steps": 1679, "loss": 0.5664, "lr": 7.455303289782414e-06, "epoch": 0.357355568790947, "percentage": 35.74, "elapsed_time": "0:29:23", "remaining_time": "0:52:52"}
|
||||||
|
{"current_steps": 620, "total_steps": 1679, "loss": 0.562, "lr": 7.285413353659285e-06, "epoch": 0.36926742108397853, "percentage": 36.93, "elapsed_time": "0:30:20", "remaining_time": "0:51:48"}
|
||||||
|
{"current_steps": 640, "total_steps": 1679, "loss": 0.5631, "lr": 7.1121196351429235e-06, "epoch": 0.38117927337701013, "percentage": 38.12, "elapsed_time": "0:31:17", "remaining_time": "0:50:47"}
|
||||||
|
{"current_steps": 660, "total_steps": 1679, "loss": 0.5567, "lr": 6.935680229385788e-06, "epoch": 0.3930911256700417, "percentage": 39.31, "elapsed_time": "0:32:10", "remaining_time": "0:49:40"}
|
||||||
|
{"current_steps": 680, "total_steps": 1679, "loss": 0.5618, "lr": 6.7563579165724e-06, "epoch": 0.4050029779630733, "percentage": 40.5, "elapsed_time": "0:33:08", "remaining_time": "0:48:40"}
|
||||||
|
{"current_steps": 700, "total_steps": 1679, "loss": 0.5539, "lr": 6.574419770547455e-06, "epoch": 0.4169148302561048, "percentage": 41.69, "elapsed_time": "0:34:05", "remaining_time": "0:47:40"}
|
||||||
|
{"current_steps": 720, "total_steps": 1679, "loss": 0.5528, "lr": 6.390136761049138e-06, "epoch": 0.4288266825491364, "percentage": 42.88, "elapsed_time": "0:35:00", "remaining_time": "0:46:38"}
|
||||||
|
{"current_steps": 740, "total_steps": 1679, "loss": 0.5567, "lr": 6.2037833501401236e-06, "epoch": 0.44073853484216796, "percentage": 44.07, "elapsed_time": "0:35:56", "remaining_time": "0:45:36"}
|
||||||
|
{"current_steps": 760, "total_steps": 1679, "loss": 0.5541, "lr": 6.015637083437249e-06, "epoch": 0.4526503871351995, "percentage": 45.27, "elapsed_time": "0:36:53", "remaining_time": "0:44:36"}
|
||||||
|
{"current_steps": 780, "total_steps": 1679, "loss": 0.5551, "lr": 5.825978176748709e-06, "epoch": 0.4645622394282311, "percentage": 46.46, "elapsed_time": "0:37:50", "remaining_time": "0:43:36"}
|
||||||
|
{"current_steps": 800, "total_steps": 1679, "loss": 0.5533, "lr": 5.635089098734394e-06, "epoch": 0.47647409172126265, "percentage": 47.65, "elapsed_time": "0:38:54", "remaining_time": "0:42:45"}
|
||||||
|
{"current_steps": 820, "total_steps": 1679, "loss": 0.5579, "lr": 5.443254150210946e-06, "epoch": 0.48838594401429425, "percentage": 48.84, "elapsed_time": "0:39:53", "remaining_time": "0:41:47"}
|
||||||
|
{"current_steps": 840, "total_steps": 1679, "loss": 0.5511, "lr": 5.250759040728082e-06, "epoch": 0.5002977963073257, "percentage": 50.03, "elapsed_time": "0:40:49", "remaining_time": "0:40:46"}
|
||||||
|
{"current_steps": 860, "total_steps": 1679, "loss": 0.5536, "lr": 5.057890463046825e-06, "epoch": 0.5122096486003573, "percentage": 51.22, "elapsed_time": "0:41:45", "remaining_time": "0:39:45"}
|
||||||
|
{"current_steps": 880, "total_steps": 1679, "loss": 0.5532, "lr": 4.864935666153388e-06, "epoch": 0.5241215008933889, "percentage": 52.41, "elapsed_time": "0:42:43", "remaining_time": "0:38:47"}
|
||||||
|
{"current_steps": 900, "total_steps": 1679, "loss": 0.5465, "lr": 4.672182027444649e-06, "epoch": 0.5360333531864205, "percentage": 53.6, "elapsed_time": "0:43:40", "remaining_time": "0:37:48"}
|
||||||
|
{"current_steps": 920, "total_steps": 1679, "loss": 0.5477, "lr": 4.4799166247223576e-06, "epoch": 0.547945205479452, "percentage": 54.79, "elapsed_time": "0:44:39", "remaining_time": "0:36:50"}
|
||||||
|
{"current_steps": 940, "total_steps": 1679, "loss": 0.5471, "lr": 4.2884258086335755e-06, "epoch": 0.5598570577724836, "percentage": 55.99, "elapsed_time": "0:45:37", "remaining_time": "0:35:52"}
|
||||||
|
{"current_steps": 960, "total_steps": 1679, "loss": 0.5487, "lr": 4.09799477619407e-06, "epoch": 0.5717689100655152, "percentage": 57.18, "elapsed_time": "0:46:37", "remaining_time": "0:34:55"}
|
||||||
|
{"current_steps": 980, "total_steps": 1679, "loss": 0.5433, "lr": 3.908907146029905e-06, "epoch": 0.5836807623585467, "percentage": 58.37, "elapsed_time": "0:47:35", "remaining_time": "0:33:56"}
|
||||||
|
{"current_steps": 1000, "total_steps": 1679, "loss": 0.5508, "lr": 3.721444535969774e-06, "epoch": 0.5955926146515783, "percentage": 59.56, "elapsed_time": "0:48:32", "remaining_time": "0:32:57"}
|
||||||
|
{"current_steps": 1020, "total_steps": 1679, "loss": 0.5464, "lr": 3.5358861436172487e-06, "epoch": 0.6075044669446099, "percentage": 60.75, "elapsed_time": "0:49:25", "remaining_time": "0:31:55"}
|
||||||
|
{"current_steps": 1040, "total_steps": 1679, "loss": 0.5416, "lr": 3.352508330527581e-06, "epoch": 0.6194163192376414, "percentage": 61.94, "elapsed_time": "0:50:22", "remaining_time": "0:30:56"}
|
||||||
|
{"current_steps": 1060, "total_steps": 1679, "loss": 0.5468, "lr": 3.1715842106083704e-06, "epoch": 0.631328171530673, "percentage": 63.13, "elapsed_time": "0:51:19", "remaining_time": "0:29:58"}
|
||||||
|
{"current_steps": 1080, "total_steps": 1679, "loss": 0.5456, "lr": 2.993383243357134e-06, "epoch": 0.6432400238237046, "percentage": 64.32, "elapsed_time": "0:52:16", "remaining_time": "0:28:59"}
|
||||||
|
{"current_steps": 1100, "total_steps": 1679, "loss": 0.5446, "lr": 2.8181708325415603e-06, "epoch": 0.6551518761167362, "percentage": 65.52, "elapsed_time": "0:53:15", "remaining_time": "0:28:01"}
|
||||||
|
{"current_steps": 1120, "total_steps": 1679, "loss": 0.5463, "lr": 2.646207930920175e-06, "epoch": 0.6670637284097677, "percentage": 66.71, "elapsed_time": "0:54:13", "remaining_time": "0:27:03"}
|
||||||
|
{"current_steps": 1140, "total_steps": 1679, "loss": 0.548, "lr": 2.4777506515921222e-06, "epoch": 0.6789755807027993, "percentage": 67.9, "elapsed_time": "0:55:09", "remaining_time": "0:26:04"}
|
||||||
|
{"current_steps": 1160, "total_steps": 1679, "loss": 0.5421, "lr": 2.31304988655489e-06, "epoch": 0.6908874329958309, "percentage": 69.09, "elapsed_time": "0:56:03", "remaining_time": "0:25:05"}
|
||||||
|
{"current_steps": 1180, "total_steps": 1679, "loss": 0.538, "lr": 2.152350933038097e-06, "epoch": 0.7027992852888624, "percentage": 70.28, "elapsed_time": "0:57:02", "remaining_time": "0:24:07"}
|
||||||
|
{"current_steps": 1200, "total_steps": 1679, "loss": 0.5417, "lr": 1.995893128169846e-06, "epoch": 0.714711137581894, "percentage": 71.47, "elapsed_time": "0:57:59", "remaining_time": "0:23:08"}
|
||||||
|
{"current_steps": 1220, "total_steps": 1679, "loss": 0.5396, "lr": 1.8439094925197593e-06, "epoch": 0.7266229898749256, "percentage": 72.66, "elapsed_time": "0:58:55", "remaining_time": "0:22:10"}
|
||||||
|
{"current_steps": 1240, "total_steps": 1679, "loss": 0.5455, "lr": 1.6966263830495939e-06, "epoch": 0.7385348421679571, "percentage": 73.85, "elapsed_time": "0:59:53", "remaining_time": "0:21:12"}
|
||||||
|
{"current_steps": 1260, "total_steps": 1679, "loss": 0.5472, "lr": 1.554263155988287e-06, "epoch": 0.7504466944609887, "percentage": 75.04, "elapsed_time": "1:00:49", "remaining_time": "0:20:13"}
|
||||||
|
{"current_steps": 1280, "total_steps": 1679, "loss": 0.5386, "lr": 1.4170318401335858e-06, "epoch": 0.7623585467540203, "percentage": 76.24, "elapsed_time": "1:01:48", "remaining_time": "0:19:16"}
|
||||||
|
{"current_steps": 1300, "total_steps": 1679, "loss": 0.5424, "lr": 1.2851368210667426e-06, "epoch": 0.7742703990470519, "percentage": 77.43, "elapsed_time": "1:02:47", "remaining_time": "0:18:18"}
|
||||||
|
{"current_steps": 1320, "total_steps": 1679, "loss": 0.5412, "lr": 1.158774536750698e-06, "epoch": 0.7861822513400833, "percentage": 78.62, "elapsed_time": "1:03:44", "remaining_time": "0:17:20"}
|
||||||
|
{"current_steps": 1340, "total_steps": 1679, "loss": 0.5388, "lr": 1.038133184965001e-06, "epoch": 0.798094103633115, "percentage": 79.81, "elapsed_time": "1:04:42", "remaining_time": "0:16:22"}
|
||||||
|
{"current_steps": 1360, "total_steps": 1679, "loss": 0.5485, "lr": 9.233924430133024e-07, "epoch": 0.8100059559261465, "percentage": 81.0, "elapsed_time": "1:05:41", "remaining_time": "0:15:24"}
|
||||||
|
{"current_steps": 1380, "total_steps": 1679, "loss": 0.5469, "lr": 8.147232001207894e-07, "epoch": 0.821917808219178, "percentage": 82.19, "elapsed_time": "1:06:38", "remaining_time": "0:14:26"}
|
||||||
|
{"current_steps": 1400, "total_steps": 1679, "loss": 0.5403, "lr": 7.122873029201732e-07, "epoch": 0.8338296605122096, "percentage": 83.38, "elapsed_time": "1:07:37", "remaining_time": "0:13:28"}
|
||||||
|
{"current_steps": 1420, "total_steps": 1679, "loss": 0.5465, "lr": 6.162373144052636e-07, "epoch": 0.8457415128052412, "percentage": 84.57, "elapsed_time": "1:08:35", "remaining_time": "0:12:30"}
|
||||||
|
{"current_steps": 1440, "total_steps": 1679, "loss": 0.5446, "lr": 5.267162867111387e-07, "epoch": 0.8576533650982728, "percentage": 85.77, "elapsed_time": "1:09:33", "remaining_time": "0:11:32"}
|
||||||
|
{"current_steps": 1460, "total_steps": 1679, "loss": 0.538, "lr": 4.43857548059321e-07, "epoch": 0.8695652173913043, "percentage": 86.96, "elapsed_time": "1:10:34", "remaining_time": "0:10:35"}
|
||||||
|
{"current_steps": 1480, "total_steps": 1679, "loss": 0.5484, "lr": 3.6778450418527735e-07, "epoch": 0.8814770696843359, "percentage": 88.15, "elapsed_time": "1:11:30", "remaining_time": "0:09:36"}
|
||||||
|
{"current_steps": 1500, "total_steps": 1679, "loss": 0.5447, "lr": 2.9861045454396943e-07, "epoch": 0.8933889219773675, "percentage": 89.34, "elapsed_time": "1:12:25", "remaining_time": "0:08:38"}
|
||||||
|
{"current_steps": 1520, "total_steps": 1679, "loss": 0.5516, "lr": 2.3643842356722124e-07, "epoch": 0.905300774270399, "percentage": 90.53, "elapsed_time": "1:13:21", "remaining_time": "0:07:40"}
|
||||||
|
{"current_steps": 1540, "total_steps": 1679, "loss": 0.5365, "lr": 1.8136100722418003e-07, "epoch": 0.9172126265634306, "percentage": 91.72, "elapsed_time": "1:14:16", "remaining_time": "0:06:42"}
|
||||||
|
{"current_steps": 1560, "total_steps": 1679, "loss": 0.5422, "lr": 1.3346023511343842e-07, "epoch": 0.9291244788564622, "percentage": 92.91, "elapsed_time": "1:15:13", "remaining_time": "0:05:44"}
|
||||||
|
{"current_steps": 1580, "total_steps": 1679, "loss": 0.5502, "lr": 9.280744829216982e-08, "epoch": 0.9410363311494937, "percentage": 94.1, "elapsed_time": "1:16:09", "remaining_time": "0:04:46"}
|
||||||
|
{"current_steps": 1600, "total_steps": 1679, "loss": 0.5405, "lr": 5.9463193024269505e-08, "epoch": 0.9529481834425253, "percentage": 95.29, "elapsed_time": "1:17:09", "remaining_time": "0:03:48"}
|
||||||
|
{"current_steps": 1620, "total_steps": 1679, "loss": 0.5444, "lr": 3.347713060571855e-08, "epoch": 0.9648600357355569, "percentage": 96.49, "elapsed_time": "1:18:05", "remaining_time": "0:02:50"}
|
||||||
|
{"current_steps": 1640, "total_steps": 1679, "loss": 0.5426, "lr": 1.4887963401492011e-08, "epoch": 0.9767718880285885, "percentage": 97.68, "elapsed_time": "1:19:01", "remaining_time": "0:01:52"}
|
||||||
|
{"current_steps": 1660, "total_steps": 1679, "loss": 0.5434, "lr": 3.7233772041533888e-09, "epoch": 0.98868374032162, "percentage": 98.87, "elapsed_time": "1:19:57", "remaining_time": "0:00:54"}
|
||||||
|
{"current_steps": 1679, "total_steps": 1679, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:21:00", "remaining_time": "0:00:00"}
|
||||||
624
trainer_state.json
Normal file
624
trainer_state.json
Normal file
@@ -0,0 +1,624 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 1.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 1679,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.011911852293031567,
|
||||||
|
"grad_norm": 2.319519281387329,
|
||||||
|
"learning_rate": 3.7254901960784316e-06,
|
||||||
|
"loss": 1.6734,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.023823704586063133,
|
||||||
|
"grad_norm": 0.5233764052391052,
|
||||||
|
"learning_rate": 7.647058823529411e-06,
|
||||||
|
"loss": 1.1925,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.0357355568790947,
|
||||||
|
"grad_norm": 0.19094516336917877,
|
||||||
|
"learning_rate": 9.999404197526844e-06,
|
||||||
|
"loss": 0.798,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.047647409172126266,
|
||||||
|
"grad_norm": 0.12445113062858582,
|
||||||
|
"learning_rate": 9.99270305028903e-06,
|
||||||
|
"loss": 0.6976,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.05955926146515783,
|
||||||
|
"grad_norm": 0.11021372675895691,
|
||||||
|
"learning_rate": 9.978566016361393e-06,
|
||||||
|
"loss": 0.663,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.0714711137581894,
|
||||||
|
"grad_norm": 0.10500118881464005,
|
||||||
|
"learning_rate": 9.95701415074788e-06,
|
||||||
|
"loss": 0.6451,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.08338296605122096,
|
||||||
|
"grad_norm": 0.09714240580797195,
|
||||||
|
"learning_rate": 9.928079551738542e-06,
|
||||||
|
"loss": 0.6341,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.09529481834425253,
|
||||||
|
"grad_norm": 0.10310710966587067,
|
||||||
|
"learning_rate": 9.891805313103928e-06,
|
||||||
|
"loss": 0.6293,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1072066706372841,
|
||||||
|
"grad_norm": 0.09910018742084503,
|
||||||
|
"learning_rate": 9.848245459913323e-06,
|
||||||
|
"loss": 0.6142,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.11911852293031566,
|
||||||
|
"grad_norm": 0.09675974398851395,
|
||||||
|
"learning_rate": 9.797464868072489e-06,
|
||||||
|
"loss": 0.6166,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.13103037522334723,
|
||||||
|
"grad_norm": 0.09194370359182358,
|
||||||
|
"learning_rate": 9.739539167700649e-06,
|
||||||
|
"loss": 0.6094,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1429422275163788,
|
||||||
|
"grad_norm": 0.09696715325117111,
|
||||||
|
"learning_rate": 9.674554630490727e-06,
|
||||||
|
"loss": 0.5995,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.15485407980941035,
|
||||||
|
"grad_norm": 0.08973082154989243,
|
||||||
|
"learning_rate": 9.60260804122051e-06,
|
||||||
|
"loss": 0.5949,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.16676593210244192,
|
||||||
|
"grad_norm": 0.09478715062141418,
|
||||||
|
"learning_rate": 9.523806553606157e-06,
|
||||||
|
"loss": 0.5945,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1786777843954735,
|
||||||
|
"grad_norm": 0.09915424883365631,
|
||||||
|
"learning_rate": 9.438267530712727e-06,
|
||||||
|
"loss": 0.5944,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.19058963668850507,
|
||||||
|
"grad_norm": 0.09569481760263443,
|
||||||
|
"learning_rate": 9.34611837015938e-06,
|
||||||
|
"loss": 0.59,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20250148898153664,
|
||||||
|
"grad_norm": 0.09609861671924591,
|
||||||
|
"learning_rate": 9.247496314379634e-06,
|
||||||
|
"loss": 0.5876,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2144133412745682,
|
||||||
|
"grad_norm": 0.09400948882102966,
|
||||||
|
"learning_rate": 9.142548246219212e-06,
|
||||||
|
"loss": 0.5788,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.22632519356759975,
|
||||||
|
"grad_norm": 0.08953362703323364,
|
||||||
|
"learning_rate": 9.031430470175958e-06,
|
||||||
|
"loss": 0.5799,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.23823704586063132,
|
||||||
|
"grad_norm": 0.09138830751180649,
|
||||||
|
"learning_rate": 8.914308479607592e-06,
|
||||||
|
"loss": 0.5722,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.25014889815366287,
|
||||||
|
"grad_norm": 0.09195993840694427,
|
||||||
|
"learning_rate": 8.791356710254026e-06,
|
||||||
|
"loss": 0.5715,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.26206075044669447,
|
||||||
|
"grad_norm": 0.0933992937207222,
|
||||||
|
"learning_rate": 8.662758280441353e-06,
|
||||||
|
"loss": 0.5735,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.273972602739726,
|
||||||
|
"grad_norm": 0.09093426913022995,
|
||||||
|
"learning_rate": 8.528704718354392e-06,
|
||||||
|
"loss": 0.5728,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2858844550327576,
|
||||||
|
"grad_norm": 0.09080294519662857,
|
||||||
|
"learning_rate": 8.389395676784025e-06,
|
||||||
|
"loss": 0.5702,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.29779630732578916,
|
||||||
|
"grad_norm": 0.09120159596204758,
|
||||||
|
"learning_rate": 8.245038635774144e-06,
|
||||||
|
"loss": 0.5677,
|
||||||
|
"step": 500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3097081596188207,
|
||||||
|
"grad_norm": 0.09126840531826019,
|
||||||
|
"learning_rate": 8.095848593611045e-06,
|
||||||
|
"loss": 0.5643,
|
||||||
|
"step": 520
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3216200119118523,
|
||||||
|
"grad_norm": 0.09190158545970917,
|
||||||
|
"learning_rate": 7.942047746615561e-06,
|
||||||
|
"loss": 0.5648,
|
||||||
|
"step": 540
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.33353186420488384,
|
||||||
|
"grad_norm": 0.09290704131126404,
|
||||||
|
"learning_rate": 7.783865158214768e-06,
|
||||||
|
"loss": 0.5623,
|
||||||
|
"step": 560
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.34544371649791544,
|
||||||
|
"grad_norm": 0.09177636355161667,
|
||||||
|
"learning_rate": 7.621536417786159e-06,
|
||||||
|
"loss": 0.5576,
|
||||||
|
"step": 580
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.357355568790947,
|
||||||
|
"grad_norm": 0.09153669327497482,
|
||||||
|
"learning_rate": 7.455303289782414e-06,
|
||||||
|
"loss": 0.5664,
|
||||||
|
"step": 600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.36926742108397853,
|
||||||
|
"grad_norm": 0.08856385946273804,
|
||||||
|
"learning_rate": 7.285413353659285e-06,
|
||||||
|
"loss": 0.562,
|
||||||
|
"step": 620
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.38117927337701013,
|
||||||
|
"grad_norm": 0.08958728611469269,
|
||||||
|
"learning_rate": 7.1121196351429235e-06,
|
||||||
|
"loss": 0.5631,
|
||||||
|
"step": 640
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3930911256700417,
|
||||||
|
"grad_norm": 0.08628527820110321,
|
||||||
|
"learning_rate": 6.935680229385788e-06,
|
||||||
|
"loss": 0.5567,
|
||||||
|
"step": 660
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4050029779630733,
|
||||||
|
"grad_norm": 0.09060859680175781,
|
||||||
|
"learning_rate": 6.7563579165724e-06,
|
||||||
|
"loss": 0.5618,
|
||||||
|
"step": 680
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4169148302561048,
|
||||||
|
"grad_norm": 0.0899747982621193,
|
||||||
|
"learning_rate": 6.574419770547455e-06,
|
||||||
|
"loss": 0.5539,
|
||||||
|
"step": 700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4288266825491364,
|
||||||
|
"grad_norm": 0.08697455376386642,
|
||||||
|
"learning_rate": 6.390136761049138e-06,
|
||||||
|
"loss": 0.5528,
|
||||||
|
"step": 720
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.44073853484216796,
|
||||||
|
"grad_norm": 0.08819800615310669,
|
||||||
|
"learning_rate": 6.2037833501401236e-06,
|
||||||
|
"loss": 0.5567,
|
||||||
|
"step": 740
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4526503871351995,
|
||||||
|
"grad_norm": 0.09015385061502457,
|
||||||
|
"learning_rate": 6.015637083437249e-06,
|
||||||
|
"loss": 0.5541,
|
||||||
|
"step": 760
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4645622394282311,
|
||||||
|
"grad_norm": 0.08507155627012253,
|
||||||
|
"learning_rate": 5.825978176748709e-06,
|
||||||
|
"loss": 0.5551,
|
||||||
|
"step": 780
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.47647409172126265,
|
||||||
|
"grad_norm": 0.08560214191675186,
|
||||||
|
"learning_rate": 5.635089098734394e-06,
|
||||||
|
"loss": 0.5533,
|
||||||
|
"step": 800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.48838594401429425,
|
||||||
|
"grad_norm": 0.08728593587875366,
|
||||||
|
"learning_rate": 5.443254150210946e-06,
|
||||||
|
"loss": 0.5579,
|
||||||
|
"step": 820
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5002977963073257,
|
||||||
|
"grad_norm": 0.09012866020202637,
|
||||||
|
"learning_rate": 5.250759040728082e-06,
|
||||||
|
"loss": 0.5511,
|
||||||
|
"step": 840
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5122096486003573,
|
||||||
|
"grad_norm": 0.08543788641691208,
|
||||||
|
"learning_rate": 5.057890463046825e-06,
|
||||||
|
"loss": 0.5536,
|
||||||
|
"step": 860
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5241215008933889,
|
||||||
|
"grad_norm": 0.08579913526773453,
|
||||||
|
"learning_rate": 4.864935666153388e-06,
|
||||||
|
"loss": 0.5532,
|
||||||
|
"step": 880
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5360333531864205,
|
||||||
|
"grad_norm": 0.09294642508029938,
|
||||||
|
"learning_rate": 4.672182027444649e-06,
|
||||||
|
"loss": 0.5465,
|
||||||
|
"step": 900
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.547945205479452,
|
||||||
|
"grad_norm": 0.0893787369132042,
|
||||||
|
"learning_rate": 4.4799166247223576e-06,
|
||||||
|
"loss": 0.5477,
|
||||||
|
"step": 920
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5598570577724836,
|
||||||
|
"grad_norm": 0.09061983972787857,
|
||||||
|
"learning_rate": 4.2884258086335755e-06,
|
||||||
|
"loss": 0.5471,
|
||||||
|
"step": 940
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5717689100655152,
|
||||||
|
"grad_norm": 0.08709097653627396,
|
||||||
|
"learning_rate": 4.09799477619407e-06,
|
||||||
|
"loss": 0.5487,
|
||||||
|
"step": 960
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5836807623585467,
|
||||||
|
"grad_norm": 0.09192101657390594,
|
||||||
|
"learning_rate": 3.908907146029905e-06,
|
||||||
|
"loss": 0.5433,
|
||||||
|
"step": 980
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5955926146515783,
|
||||||
|
"grad_norm": 0.08835067600011826,
|
||||||
|
"learning_rate": 3.721444535969774e-06,
|
||||||
|
"loss": 0.5508,
|
||||||
|
"step": 1000
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6075044669446099,
|
||||||
|
"grad_norm": 0.08473947644233704,
|
||||||
|
"learning_rate": 3.5358861436172487e-06,
|
||||||
|
"loss": 0.5464,
|
||||||
|
"step": 1020
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6194163192376414,
|
||||||
|
"grad_norm": 0.08449548482894897,
|
||||||
|
"learning_rate": 3.352508330527581e-06,
|
||||||
|
"loss": 0.5416,
|
||||||
|
"step": 1040
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.631328171530673,
|
||||||
|
"grad_norm": 0.08983448892831802,
|
||||||
|
"learning_rate": 3.1715842106083704e-06,
|
||||||
|
"loss": 0.5468,
|
||||||
|
"step": 1060
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6432400238237046,
|
||||||
|
"grad_norm": 0.08712620288133621,
|
||||||
|
"learning_rate": 2.993383243357134e-06,
|
||||||
|
"loss": 0.5456,
|
||||||
|
"step": 1080
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6551518761167362,
|
||||||
|
"grad_norm": 0.08562883734703064,
|
||||||
|
"learning_rate": 2.8181708325415603e-06,
|
||||||
|
"loss": 0.5446,
|
||||||
|
"step": 1100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6670637284097677,
|
||||||
|
"grad_norm": 0.08872649073600769,
|
||||||
|
"learning_rate": 2.646207930920175e-06,
|
||||||
|
"loss": 0.5463,
|
||||||
|
"step": 1120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6789755807027993,
|
||||||
|
"grad_norm": 0.08730657398700714,
|
||||||
|
"learning_rate": 2.4777506515921222e-06,
|
||||||
|
"loss": 0.548,
|
||||||
|
"step": 1140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6908874329958309,
|
||||||
|
"grad_norm": 0.08714567869901657,
|
||||||
|
"learning_rate": 2.31304988655489e-06,
|
||||||
|
"loss": 0.5421,
|
||||||
|
"step": 1160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7027992852888624,
|
||||||
|
"grad_norm": 0.0823967382311821,
|
||||||
|
"learning_rate": 2.152350933038097e-06,
|
||||||
|
"loss": 0.538,
|
||||||
|
"step": 1180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.714711137581894,
|
||||||
|
"grad_norm": 0.08490780740976334,
|
||||||
|
"learning_rate": 1.995893128169846e-06,
|
||||||
|
"loss": 0.5417,
|
||||||
|
"step": 1200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7266229898749256,
|
||||||
|
"grad_norm": 0.08957539498806,
|
||||||
|
"learning_rate": 1.8439094925197593e-06,
|
||||||
|
"loss": 0.5396,
|
||||||
|
"step": 1220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7385348421679571,
|
||||||
|
"grad_norm": 0.08784908056259155,
|
||||||
|
"learning_rate": 1.6966263830495939e-06,
|
||||||
|
"loss": 0.5455,
|
||||||
|
"step": 1240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7504466944609887,
|
||||||
|
"grad_norm": 0.08189205080270767,
|
||||||
|
"learning_rate": 1.554263155988287e-06,
|
||||||
|
"loss": 0.5472,
|
||||||
|
"step": 1260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7623585467540203,
|
||||||
|
"grad_norm": 0.08474428951740265,
|
||||||
|
"learning_rate": 1.4170318401335858e-06,
|
||||||
|
"loss": 0.5386,
|
||||||
|
"step": 1280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7742703990470519,
|
||||||
|
"grad_norm": 0.08598953485488892,
|
||||||
|
"learning_rate": 1.2851368210667426e-06,
|
||||||
|
"loss": 0.5424,
|
||||||
|
"step": 1300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7861822513400833,
|
||||||
|
"grad_norm": 0.08535321056842804,
|
||||||
|
"learning_rate": 1.158774536750698e-06,
|
||||||
|
"loss": 0.5412,
|
||||||
|
"step": 1320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.798094103633115,
|
||||||
|
"grad_norm": 0.08556421101093292,
|
||||||
|
"learning_rate": 1.038133184965001e-06,
|
||||||
|
"loss": 0.5388,
|
||||||
|
"step": 1340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8100059559261465,
|
||||||
|
"grad_norm": 0.08341170847415924,
|
||||||
|
"learning_rate": 9.233924430133024e-07,
|
||||||
|
"loss": 0.5485,
|
||||||
|
"step": 1360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.821917808219178,
|
||||||
|
"grad_norm": 0.08838168531656265,
|
||||||
|
"learning_rate": 8.147232001207894e-07,
|
||||||
|
"loss": 0.5469,
|
||||||
|
"step": 1380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8338296605122096,
|
||||||
|
"grad_norm": 0.08617264032363892,
|
||||||
|
"learning_rate": 7.122873029201732e-07,
|
||||||
|
"loss": 0.5403,
|
||||||
|
"step": 1400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8457415128052412,
|
||||||
|
"grad_norm": 0.0815279632806778,
|
||||||
|
"learning_rate": 6.162373144052636e-07,
|
||||||
|
"loss": 0.5465,
|
||||||
|
"step": 1420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8576533650982728,
|
||||||
|
"grad_norm": 0.08794637769460678,
|
||||||
|
"learning_rate": 5.267162867111387e-07,
|
||||||
|
"loss": 0.5446,
|
||||||
|
"step": 1440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8695652173913043,
|
||||||
|
"grad_norm": 0.08446835726499557,
|
||||||
|
"learning_rate": 4.43857548059321e-07,
|
||||||
|
"loss": 0.538,
|
||||||
|
"step": 1460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8814770696843359,
|
||||||
|
"grad_norm": 0.0861380472779274,
|
||||||
|
"learning_rate": 3.6778450418527735e-07,
|
||||||
|
"loss": 0.5484,
|
||||||
|
"step": 1480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8933889219773675,
|
||||||
|
"grad_norm": 0.08714042603969574,
|
||||||
|
"learning_rate": 2.9861045454396943e-07,
|
||||||
|
"loss": 0.5447,
|
||||||
|
"step": 1500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.905300774270399,
|
||||||
|
"grad_norm": 0.08558403700590134,
|
||||||
|
"learning_rate": 2.3643842356722124e-07,
|
||||||
|
"loss": 0.5516,
|
||||||
|
"step": 1520
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9172126265634306,
|
||||||
|
"grad_norm": 0.08699293434619904,
|
||||||
|
"learning_rate": 1.8136100722418003e-07,
|
||||||
|
"loss": 0.5365,
|
||||||
|
"step": 1540
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9291244788564622,
|
||||||
|
"grad_norm": 0.0858757421374321,
|
||||||
|
"learning_rate": 1.3346023511343842e-07,
|
||||||
|
"loss": 0.5422,
|
||||||
|
"step": 1560
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9410363311494937,
|
||||||
|
"grad_norm": 0.08714671432971954,
|
||||||
|
"learning_rate": 9.280744829216982e-08,
|
||||||
|
"loss": 0.5502,
|
||||||
|
"step": 1580
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9529481834425253,
|
||||||
|
"grad_norm": 0.0844811275601387,
|
||||||
|
"learning_rate": 5.9463193024269505e-08,
|
||||||
|
"loss": 0.5405,
|
||||||
|
"step": 1600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9648600357355569,
|
||||||
|
"grad_norm": 0.08579962700605392,
|
||||||
|
"learning_rate": 3.347713060571855e-08,
|
||||||
|
"loss": 0.5444,
|
||||||
|
"step": 1620
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9767718880285885,
|
||||||
|
"grad_norm": 0.08677230775356293,
|
||||||
|
"learning_rate": 1.4887963401492011e-08,
|
||||||
|
"loss": 0.5426,
|
||||||
|
"step": 1640
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.98868374032162,
|
||||||
|
"grad_norm": 0.08511412888765335,
|
||||||
|
"learning_rate": 3.7233772041533888e-09,
|
||||||
|
"loss": 0.5434,
|
||||||
|
"step": 1660
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"step": 1679,
|
||||||
|
"total_flos": 9.42165996526266e+18,
|
||||||
|
"train_loss": 0.5865233610470143,
|
||||||
|
"train_runtime": 4862.2389,
|
||||||
|
"train_samples_per_second": 176.769,
|
||||||
|
"train_steps_per_second": 0.345
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 20,
|
||||||
|
"max_steps": 1679,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 1,
|
||||||
|
"save_steps": 500,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 9.42165996526266e+18,
|
||||||
|
"train_batch_size": 32,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a0b3df355e507d47c91b41c1d1064181f5952c46e95ed5fe51c6379d95b88f38
|
||||||
|
size 8017
|
||||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 34 KiB |
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user