thangvip/vwen-0.5
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: thangvip/vwen-0.5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-23 12:21:09 +08:00
commit 746289923f
85 changed files with 2728578 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View 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
View File

@@ -0,0 +1,61 @@
---
license: apache-2.0
base_model: sail/Sailor-0.5B
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: vwen-0.5
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. -->
# vwen-0.5
This model is a fine-tuned version of [sail/Sailor-0.5B](https://huggingface.co/sail/Sailor-0.5B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8915
## 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.8915 | 0.11 | 7644 | 1.8915 |
### Framework versions
- Transformers 4.39.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2

5
added_tokens.json Normal file
View File

@@ -0,0 +1,5 @@
{
"<|endoftext|>": 151643,
"<|im_end|>": 151645,
"<|im_start|>": 151644
}

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 0.11,
"train_loss": 1.9877741447859942,
"train_runtime": 107245.5846,
"train_samples": 1156437,
"train_samples_per_second": 10.783,
"train_steps_per_second": 0.674
}

5
checkpoint-7568/added_tokens.json Normal file
View File

@@ -0,0 +1,5 @@
{
"<|endoftext|>": 151643,
"<|im_end|>": 151645,
"<|im_start|>": 151644
}

28
checkpoint-7568/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "sail/Sailor-0.5B",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.39.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

6
checkpoint-7568/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token_id": 151643,
"eos_token_id": 151643,
"max_new_tokens": 2048,
"transformers_version": "4.39.0"
}

151388
checkpoint-7568/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-7568/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:79cb7261ef90180a443055a42335fb04910cbfffc2a1809d29714b212885a60f
size 2478313760

3
checkpoint-7568/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ebbfa38aec018143e0c1a8d7a237b9b60036764720fe274b572ee6104bb54485
size 4956808758

3
checkpoint-7568/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:755e14817720c41543c1a422a0b78e32e590221dc68b88ed0640eed88bd5f198
size 14180

3
checkpoint-7568/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0a380d5509102fb4ef8afb72ca9d9ebb750c25f01d982a83babdee4dab74265b
size 1064

20
checkpoint-7568/special_tokens_map.json Normal file
View File

@@ -0,0 +1,20 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

303111
checkpoint-7568/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

43
checkpoint-7568/tokenizer_config.json Normal file
View File

@@ -0,0 +1,43 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": null,
"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 %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

126
checkpoint-7568/trainer_state.json Normal file
View File

@@ -0,0 +1,126 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.1047078223889412,
"eval_steps": 500,
"global_step": 7568,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"grad_norm": 1.4067256450653076,
"learning_rate": 9.930821699849192e-05,
"loss": 2.2227,
"step": 500
},
{
"epoch": 0.01,
"grad_norm": 2.9092910289764404,
"learning_rate": 9.861643399698382e-05,
"loss": 2.1156,
"step": 1000
},
{
"epoch": 0.02,
"grad_norm": 1.1342206001281738,
"learning_rate": 9.792465099547574e-05,
"loss": 2.0774,
"step": 1500
},
{
"epoch": 0.03,
"grad_norm": 3.928356409072876,
"learning_rate": 9.723286799396766e-05,
"loss": 2.0468,
"step": 2000
},
{
"epoch": 0.03,
"grad_norm": 0.9985896944999695,
"learning_rate": 9.654108499245957e-05,
"loss": 2.0288,
"step": 2500
},
{
"epoch": 0.04,
"grad_norm": 1.6732710599899292,
"learning_rate": 9.584930199095148e-05,
"loss": 1.9954,
"step": 3000
},
{
"epoch": 0.05,
"grad_norm": 0.9810203313827515,
"learning_rate": 9.515751898944339e-05,
"loss": 1.9757,
"step": 3500
},
{
"epoch": 0.06,
"grad_norm": 0.8682870864868164,
"learning_rate": 9.446573598793531e-05,
"loss": 1.9651,
"step": 4000
},
{
"epoch": 0.06,
"grad_norm": 0.9405160546302795,
"learning_rate": 9.377395298642722e-05,
"loss": 1.9498,
"step": 4500
},
{
"epoch": 0.07,
"grad_norm": 0.8670147061347961,
"learning_rate": 9.308216998491913e-05,
"loss": 1.935,
"step": 5000
},
{
"epoch": 0.08,
"grad_norm": 0.9158061146736145,
"learning_rate": 9.239038698341104e-05,
"loss": 1.9252,
"step": 5500
},
{
"epoch": 0.08,
"grad_norm": 0.8484827280044556,
"learning_rate": 9.169860398190296e-05,
"loss": 1.9001,
"step": 6000
},
{
"epoch": 0.09,
"grad_norm": 0.8079173564910889,
"learning_rate": 9.100682098039488e-05,
"loss": 1.9174,
"step": 6500
},
{
"epoch": 0.1,
"grad_norm": 0.8451229929924011,
"learning_rate": 9.031503797888679e-05,
"loss": 1.8939,
"step": 7000
},
{
"epoch": 0.1,
"grad_norm": 0.7751355171203613,
"learning_rate": 8.962325497737871e-05,
"loss": 1.8915,
"step": 7500
}
],
"logging_steps": 500,
"max_steps": 72277,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 16,
"total_flos": 6.903809319402209e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
checkpoint-7568/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:619d9e843dd7d8cff288742698e1be890ea7a8be9d70f15a760162e676357fa4
size 4920

1
checkpoint-7568/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

5
checkpoint-7584/added_tokens.json Normal file
View File

@@ -0,0 +1,5 @@
{
"<|endoftext|>": 151643,
"<|im_end|>": 151645,
"<|im_start|>": 151644
}

28
checkpoint-7584/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "sail/Sailor-0.5B",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.39.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

6
checkpoint-7584/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token_id": 151643,
"eos_token_id": 151643,
"max_new_tokens": 2048,
"transformers_version": "4.39.0"
}

151388
checkpoint-7584/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-7584/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:04de49ef60a0904c181f094cd6444f7392b179c603bb3925c6ce25c9c4774201
size 2478313760

3
checkpoint-7584/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:89ccc150c02002f22f424fe60728d31d250a93657ef0c319b190794d4035bb92
size 4956808758

3
checkpoint-7584/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:755e14817720c41543c1a422a0b78e32e590221dc68b88ed0640eed88bd5f198
size 14180

3
checkpoint-7584/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:886fd42484078d6089ab68e7e094b4076189120859f226490410821eaefbfe39
size 1064

20
checkpoint-7584/special_tokens_map.json Normal file
View File

@@ -0,0 +1,20 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

303111
checkpoint-7584/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

43
checkpoint-7584/tokenizer_config.json Normal file
View File

@@ -0,0 +1,43 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": null,
"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 %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

126
checkpoint-7584/trainer_state.json Normal file
View File

@@ -0,0 +1,126 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.10492919199230048,
"eval_steps": 500,
"global_step": 7584,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"grad_norm": 1.4067256450653076,
"learning_rate": 9.930821699849192e-05,
"loss": 2.2227,
"step": 500
},
{
"epoch": 0.01,
"grad_norm": 2.9092910289764404,
"learning_rate": 9.861643399698382e-05,
"loss": 2.1156,
"step": 1000
},
{
"epoch": 0.02,
"grad_norm": 1.1342206001281738,
"learning_rate": 9.792465099547574e-05,
"loss": 2.0774,
"step": 1500
},
{
"epoch": 0.03,
"grad_norm": 3.928356409072876,
"learning_rate": 9.723286799396766e-05,
"loss": 2.0468,
"step": 2000
},
{
"epoch": 0.03,
"grad_norm": 0.9985896944999695,
"learning_rate": 9.654108499245957e-05,
"loss": 2.0288,
"step": 2500
},
{
"epoch": 0.04,
"grad_norm": 1.6732710599899292,
"learning_rate": 9.584930199095148e-05,
"loss": 1.9954,
"step": 3000
},
{
"epoch": 0.05,
"grad_norm": 0.9810203313827515,
"learning_rate": 9.515751898944339e-05,
"loss": 1.9757,
"step": 3500
},
{
"epoch": 0.06,
"grad_norm": 0.8682870864868164,
"learning_rate": 9.446573598793531e-05,
"loss": 1.9651,
"step": 4000
},
{
"epoch": 0.06,
"grad_norm": 0.9405160546302795,
"learning_rate": 9.377395298642722e-05,
"loss": 1.9498,
"step": 4500
},
{
"epoch": 0.07,
"grad_norm": 0.8670147061347961,
"learning_rate": 9.308216998491913e-05,
"loss": 1.935,
"step": 5000
},
{
"epoch": 0.08,
"grad_norm": 0.9158061146736145,
"learning_rate": 9.239038698341104e-05,
"loss": 1.9252,
"step": 5500
},
{
"epoch": 0.08,
"grad_norm": 0.8484827280044556,
"learning_rate": 9.169860398190296e-05,
"loss": 1.9001,
"step": 6000
},
{
"epoch": 0.09,
"grad_norm": 0.8079173564910889,
"learning_rate": 9.100682098039488e-05,
"loss": 1.9174,
"step": 6500
},
{
"epoch": 0.1,
"grad_norm": 0.8451229929924011,
"learning_rate": 9.031503797888679e-05,
"loss": 1.8939,
"step": 7000
},
{
"epoch": 0.1,
"grad_norm": 0.7751355171203613,
"learning_rate": 8.962325497737871e-05,
"loss": 1.8915,
"step": 7500
}
],
"logging_steps": 500,
"max_steps": 72277,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 16,
"total_flos": 6.918405110775153e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
checkpoint-7584/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:619d9e843dd7d8cff288742698e1be890ea7a8be9d70f15a760162e676357fa4
size 4920

1
checkpoint-7584/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

5
checkpoint-7600/added_tokens.json Normal file
View File

@@ -0,0 +1,5 @@
{
"<|endoftext|>": 151643,
"<|im_end|>": 151645,
"<|im_start|>": 151644
}

28
checkpoint-7600/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "sail/Sailor-0.5B",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.39.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

6
checkpoint-7600/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token_id": 151643,
"eos_token_id": 151643,
"max_new_tokens": 2048,
"transformers_version": "4.39.0"
}

151388
checkpoint-7600/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-7600/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:11146d20de778d3cd004f0fb0fd9a9b35b43eeda4d30329a8ec6859c867f380c
size 2478313760

3
checkpoint-7600/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5c9bc20ea9a5f27c524b6c3aa458b2685618ce1dc14cc8eab8564ff0095e52fc
size 4956808758

3
checkpoint-7600/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a41ab52e23892da54d70091e14df8f1b6941c11a68eef43ba6478fda827b6f4
size 14244

3
checkpoint-7600/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4763ef45d4c6c771b85175f8a79b7d11b80434eb92b755c683851b559cf22273
size 1064

20
checkpoint-7600/special_tokens_map.json Normal file
View File

@@ -0,0 +1,20 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

303111
checkpoint-7600/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

43
checkpoint-7600/tokenizer_config.json Normal file
View File

@@ -0,0 +1,43 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": null,
"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 %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

126
checkpoint-7600/trainer_state.json Normal file
View File

@@ -0,0 +1,126 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.10515056159565978,
"eval_steps": 500,
"global_step": 7600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"grad_norm": 1.4067256450653076,
"learning_rate": 9.930821699849192e-05,
"loss": 2.2227,
"step": 500
},
{
"epoch": 0.01,
"grad_norm": 2.9092910289764404,
"learning_rate": 9.861643399698382e-05,
"loss": 2.1156,
"step": 1000
},
{
"epoch": 0.02,
"grad_norm": 1.1342206001281738,
"learning_rate": 9.792465099547574e-05,
"loss": 2.0774,
"step": 1500
},
{
"epoch": 0.03,
"grad_norm": 3.928356409072876,
"learning_rate": 9.723286799396766e-05,
"loss": 2.0468,
"step": 2000
},
{
"epoch": 0.03,
"grad_norm": 0.9985896944999695,
"learning_rate": 9.654108499245957e-05,
"loss": 2.0288,
"step": 2500
},
{
"epoch": 0.04,
"grad_norm": 1.6732710599899292,
"learning_rate": 9.584930199095148e-05,
"loss": 1.9954,
"step": 3000
},
{
"epoch": 0.05,
"grad_norm": 0.9810203313827515,
"learning_rate": 9.515751898944339e-05,
"loss": 1.9757,
"step": 3500
},
{
"epoch": 0.06,
"grad_norm": 0.8682870864868164,
"learning_rate": 9.446573598793531e-05,
"loss": 1.9651,
"step": 4000
},
{
"epoch": 0.06,
"grad_norm": 0.9405160546302795,
"learning_rate": 9.377395298642722e-05,
"loss": 1.9498,
"step": 4500
},
{
"epoch": 0.07,
"grad_norm": 0.8670147061347961,
"learning_rate": 9.308216998491913e-05,
"loss": 1.935,
"step": 5000
},
{
"epoch": 0.08,
"grad_norm": 0.9158061146736145,
"learning_rate": 9.239038698341104e-05,
"loss": 1.9252,
"step": 5500
},
{
"epoch": 0.08,
"grad_norm": 0.8484827280044556,
"learning_rate": 9.169860398190296e-05,
"loss": 1.9001,
"step": 6000
},
{
"epoch": 0.09,
"grad_norm": 0.8079173564910889,
"learning_rate": 9.100682098039488e-05,
"loss": 1.9174,
"step": 6500
},
{
"epoch": 0.1,
"grad_norm": 0.8451229929924011,
"learning_rate": 9.031503797888679e-05,
"loss": 1.8939,
"step": 7000
},
{
"epoch": 0.1,
"grad_norm": 0.7751355171203613,
"learning_rate": 8.962325497737871e-05,
"loss": 1.8915,
"step": 7500
}
],
"logging_steps": 500,
"max_steps": 72277,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 16,
"total_flos": 6.933000902148096e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
checkpoint-7600/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:619d9e843dd7d8cff288742698e1be890ea7a8be9d70f15a760162e676357fa4
size 4920

1
checkpoint-7600/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

5
checkpoint-7616/added_tokens.json Normal file
View File

@@ -0,0 +1,5 @@
{
"<|endoftext|>": 151643,
"<|im_end|>": 151645,
"<|im_start|>": 151644
}

28
checkpoint-7616/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "sail/Sailor-0.5B",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.39.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

6
checkpoint-7616/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token_id": 151643,
"eos_token_id": 151643,
"max_new_tokens": 2048,
"transformers_version": "4.39.0"
}

151388
checkpoint-7616/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-7616/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:937917280f9f64041d30fe11a7882da25ed0ecdee59fb7b1843952ded485414b
size 2478313760

3
checkpoint-7616/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e6fd4ddabc9c03beb3494446cb2704f5c995906496f4c3eaf614062fee6548bf
size 4956808758

3
checkpoint-7616/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a41ab52e23892da54d70091e14df8f1b6941c11a68eef43ba6478fda827b6f4
size 14244

3
checkpoint-7616/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6db315f6419291857886405428837bb956fc0854d21f21f3886d387347d4629d
size 1064

20
checkpoint-7616/special_tokens_map.json Normal file
View File

@@ -0,0 +1,20 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

303111
checkpoint-7616/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

43
checkpoint-7616/tokenizer_config.json Normal file
View File

@@ -0,0 +1,43 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": null,
"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 %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

126
checkpoint-7616/trainer_state.json Normal file
View File

@@ -0,0 +1,126 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.10537193119901905,
"eval_steps": 500,
"global_step": 7616,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"grad_norm": 1.4067256450653076,
"learning_rate": 9.930821699849192e-05,
"loss": 2.2227,
"step": 500
},
{
"epoch": 0.01,
"grad_norm": 2.9092910289764404,
"learning_rate": 9.861643399698382e-05,
"loss": 2.1156,
"step": 1000
},
{
"epoch": 0.02,
"grad_norm": 1.1342206001281738,
"learning_rate": 9.792465099547574e-05,
"loss": 2.0774,
"step": 1500
},
{
"epoch": 0.03,
"grad_norm": 3.928356409072876,
"learning_rate": 9.723286799396766e-05,
"loss": 2.0468,
"step": 2000
},
{
"epoch": 0.03,
"grad_norm": 0.9985896944999695,
"learning_rate": 9.654108499245957e-05,
"loss": 2.0288,
"step": 2500
},
{
"epoch": 0.04,
"grad_norm": 1.6732710599899292,
"learning_rate": 9.584930199095148e-05,
"loss": 1.9954,
"step": 3000
},
{
"epoch": 0.05,
"grad_norm": 0.9810203313827515,
"learning_rate": 9.515751898944339e-05,
"loss": 1.9757,
"step": 3500
},
{
"epoch": 0.06,
"grad_norm": 0.8682870864868164,
"learning_rate": 9.446573598793531e-05,
"loss": 1.9651,
"step": 4000
},
{
"epoch": 0.06,
"grad_norm": 0.9405160546302795,
"learning_rate": 9.377395298642722e-05,
"loss": 1.9498,
"step": 4500
},
{
"epoch": 0.07,
"grad_norm": 0.8670147061347961,
"learning_rate": 9.308216998491913e-05,
"loss": 1.935,
"step": 5000
},
{
"epoch": 0.08,
"grad_norm": 0.9158061146736145,
"learning_rate": 9.239038698341104e-05,
"loss": 1.9252,
"step": 5500
},
{
"epoch": 0.08,
"grad_norm": 0.8484827280044556,
"learning_rate": 9.169860398190296e-05,
"loss": 1.9001,
"step": 6000
},
{
"epoch": 0.09,
"grad_norm": 0.8079173564910889,
"learning_rate": 9.100682098039488e-05,
"loss": 1.9174,
"step": 6500
},
{
"epoch": 0.1,
"grad_norm": 0.8451229929924011,
"learning_rate": 9.031503797888679e-05,
"loss": 1.8939,
"step": 7000
},
{
"epoch": 0.1,
"grad_norm": 0.7751355171203613,
"learning_rate": 8.962325497737871e-05,
"loss": 1.8915,
"step": 7500
}
],
"logging_steps": 500,
"max_steps": 72277,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 16,
"total_flos": 6.94759669352104e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
checkpoint-7616/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:619d9e843dd7d8cff288742698e1be890ea7a8be9d70f15a760162e676357fa4
size 4920

1
checkpoint-7616/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

5
checkpoint-7632/added_tokens.json Normal file
View File

@@ -0,0 +1,5 @@
{
"<|endoftext|>": 151643,
"<|im_end|>": 151645,
"<|im_start|>": 151644
}

28
checkpoint-7632/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "sail/Sailor-0.5B",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.39.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

6
checkpoint-7632/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token_id": 151643,
"eos_token_id": 151643,
"max_new_tokens": 2048,
"transformers_version": "4.39.0"
}

151388
checkpoint-7632/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-7632/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cb4503af528d7aba85a043254a1ee8c13c5450baec0e22718e58f29fb84e3ffe
size 2478313760

3
checkpoint-7632/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:31b4b3525a5146bca752f31a08070e48e584832ff7af56ff49921fa26188ae63
size 4956808758

3
checkpoint-7632/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a41ab52e23892da54d70091e14df8f1b6941c11a68eef43ba6478fda827b6f4
size 14244

3
checkpoint-7632/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e37df2bec45d85e56362eb8965fc251719de706529a5ea55b0e2fdd3da763e9b
size 1064

20
checkpoint-7632/special_tokens_map.json Normal file
View File

@@ -0,0 +1,20 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

303111
checkpoint-7632/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

43
checkpoint-7632/tokenizer_config.json Normal file
View File

@@ -0,0 +1,43 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": null,
"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 %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

126
checkpoint-7632/trainer_state.json Normal file
View File

@@ -0,0 +1,126 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.10559330080237835,
"eval_steps": 500,
"global_step": 7632,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"grad_norm": 1.4067256450653076,
"learning_rate": 9.930821699849192e-05,
"loss": 2.2227,
"step": 500
},
{
"epoch": 0.01,
"grad_norm": 2.9092910289764404,
"learning_rate": 9.861643399698382e-05,
"loss": 2.1156,
"step": 1000
},
{
"epoch": 0.02,
"grad_norm": 1.1342206001281738,
"learning_rate": 9.792465099547574e-05,
"loss": 2.0774,
"step": 1500
},
{
"epoch": 0.03,
"grad_norm": 3.928356409072876,
"learning_rate": 9.723286799396766e-05,
"loss": 2.0468,
"step": 2000
},
{
"epoch": 0.03,
"grad_norm": 0.9985896944999695,
"learning_rate": 9.654108499245957e-05,
"loss": 2.0288,
"step": 2500
},
{
"epoch": 0.04,
"grad_norm": 1.6732710599899292,
"learning_rate": 9.584930199095148e-05,
"loss": 1.9954,
"step": 3000
},
{
"epoch": 0.05,
"grad_norm": 0.9810203313827515,
"learning_rate": 9.515751898944339e-05,
"loss": 1.9757,
"step": 3500
},
{
"epoch": 0.06,
"grad_norm": 0.8682870864868164,
"learning_rate": 9.446573598793531e-05,
"loss": 1.9651,
"step": 4000
},
{
"epoch": 0.06,
"grad_norm": 0.9405160546302795,
"learning_rate": 9.377395298642722e-05,
"loss": 1.9498,
"step": 4500
},
{
"epoch": 0.07,
"grad_norm": 0.8670147061347961,
"learning_rate": 9.308216998491913e-05,
"loss": 1.935,
"step": 5000
},
{
"epoch": 0.08,
"grad_norm": 0.9158061146736145,
"learning_rate": 9.239038698341104e-05,
"loss": 1.9252,
"step": 5500
},
{
"epoch": 0.08,
"grad_norm": 0.8484827280044556,
"learning_rate": 9.169860398190296e-05,
"loss": 1.9001,
"step": 6000
},
{
"epoch": 0.09,
"grad_norm": 0.8079173564910889,
"learning_rate": 9.100682098039488e-05,
"loss": 1.9174,
"step": 6500
},
{
"epoch": 0.1,
"grad_norm": 0.8451229929924011,
"learning_rate": 9.031503797888679e-05,
"loss": 1.8939,
"step": 7000
},
{
"epoch": 0.1,
"grad_norm": 0.7751355171203613,
"learning_rate": 8.962325497737871e-05,
"loss": 1.8915,
"step": 7500
}
],
"logging_steps": 500,
"max_steps": 72277,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 16,
"total_flos": 6.962192484893983e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
checkpoint-7632/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:619d9e843dd7d8cff288742698e1be890ea7a8be9d70f15a760162e676357fa4
size 4920

1
checkpoint-7632/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

28
config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "sail/Sailor-0.5B",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.39.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token_id": 151643,
"eos_token_id": 151643,
"max_new_tokens": 2048,
"transformers_version": "4.39.0"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e90dd087e7eddc1a9e072e16a439b2294dae3c022131ec7cde49b69558458373
size 2478313760

20
special_tokens_map.json Normal file
View File

@@ -0,0 +1,20 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

303111
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

43
tokenizer_config.json Normal file
View File

@@ -0,0 +1,43 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>"
],
"bos_token": null,
"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 %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 0.11,
"train_loss": 1.9877741447859942,
"train_runtime": 107245.5846,
"train_samples": 1156437,
"train_samples_per_second": 10.783,
"train_steps_per_second": 0.674
}

143
trainer_state.json Normal file
View File

@@ -0,0 +1,143 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.1057593280048978,
"eval_steps": 500,
"global_step": 7644,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"grad_norm": 1.4067256450653076,
"learning_rate": 9.930821699849192e-05,
"loss": 2.2227,
"step": 500
},
{
"epoch": 0.01,
"grad_norm": 2.9092910289764404,
"learning_rate": 9.861643399698382e-05,
"loss": 2.1156,
"step": 1000
},
{
"epoch": 0.02,
"grad_norm": 1.1342206001281738,
"learning_rate": 9.792465099547574e-05,
"loss": 2.0774,
"step": 1500
},
{
"epoch": 0.03,
"grad_norm": 3.928356409072876,
"learning_rate": 9.723286799396766e-05,
"loss": 2.0468,
"step": 2000
},
{
"epoch": 0.03,
"grad_norm": 0.9985896944999695,
"learning_rate": 9.654108499245957e-05,
"loss": 2.0288,
"step": 2500
},
{
"epoch": 0.04,
"grad_norm": 1.6732710599899292,
"learning_rate": 9.584930199095148e-05,
"loss": 1.9954,
"step": 3000
},
{
"epoch": 0.05,
"grad_norm": 0.9810203313827515,
"learning_rate": 9.515751898944339e-05,
"loss": 1.9757,
"step": 3500
},
{
"epoch": 0.06,
"grad_norm": 0.8682870864868164,
"learning_rate": 9.446573598793531e-05,
"loss": 1.9651,
"step": 4000
},
{
"epoch": 0.06,
"grad_norm": 0.9405160546302795,
"learning_rate": 9.377395298642722e-05,
"loss": 1.9498,
"step": 4500
},
{
"epoch": 0.07,
"grad_norm": 0.8670147061347961,
"learning_rate": 9.308216998491913e-05,
"loss": 1.935,
"step": 5000
},
{
"epoch": 0.08,
"grad_norm": 0.9158061146736145,
"learning_rate": 9.239038698341104e-05,
"loss": 1.9252,
"step": 5500
},
{
"epoch": 0.08,
"grad_norm": 0.8484827280044556,
"learning_rate": 9.169860398190296e-05,
"loss": 1.9001,
"step": 6000
},
{
"epoch": 0.09,
"grad_norm": 0.8079173564910889,
"learning_rate": 9.100682098039488e-05,
"loss": 1.9174,
"step": 6500
},
{
"epoch": 0.1,
"grad_norm": 0.8451229929924011,
"learning_rate": 9.031503797888679e-05,
"loss": 1.8939,
"step": 7000
},
{
"epoch": 0.1,
"grad_norm": 0.7751355171203613,
"learning_rate": 8.962325497737871e-05,
"loss": 1.8915,
"step": 7500
},
{
"epoch": 0.11,
"eval_loss": 1.891456127166748,
"eval_runtime": 2795.0331,
"eval_samples_per_second": 45.972,
"eval_steps_per_second": 45.972,
"step": 7644
},
{
"epoch": 0.11,
"step": 7644,
"total_flos": 6.973880520954348e+17,
"train_loss": 1.9877741447859942,
"train_runtime": 107245.5846,
"train_samples_per_second": 10.783,
"train_steps_per_second": 0.674
}
],
"logging_steps": 500,
"max_steps": 72277,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 16,
"total_flos": 6.973880520954348e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:619d9e843dd7d8cff288742698e1be890ea7a8be9d70f15a760162e676357fa4
size 4920

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long