Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +88 -0
- checkpoint-116/config.json +29 -0
- checkpoint-116/generation_config.json +8 -0
- checkpoint-116/model.safetensors +3 -0
- checkpoint-116/optimizer.pt +3 -0
- checkpoint-116/rng_state.pth +3 -0
- checkpoint-116/scheduler.pt +3 -0
- checkpoint-116/special_tokens_map.json +30 -0
- checkpoint-116/tokenizer.model +3 -0
- checkpoint-116/tokenizer_config.json +46 -0
- checkpoint-116/trainer_state.json +846 -0
- checkpoint-116/training_args.bin +3 -0
- checkpoint-29/config.json +29 -0
- checkpoint-29/generation_config.json +8 -0
- checkpoint-29/model.safetensors +3 -0
- checkpoint-29/optimizer.pt +3 -0
- checkpoint-29/rng_state.pth +3 -0
- checkpoint-29/scheduler.pt +3 -0
- checkpoint-29/special_tokens_map.json +30 -0
- checkpoint-29/tokenizer.model +3 -0
- checkpoint-29/tokenizer_config.json +46 -0
- checkpoint-29/trainer_state.json +237 -0
- checkpoint-29/training_args.bin +3 -0
- checkpoint-58/config.json +29 -0
- checkpoint-58/generation_config.json +8 -0
- checkpoint-58/model.safetensors +3 -0
- checkpoint-58/optimizer.pt +3 -0
- checkpoint-58/rng_state.pth +3 -0
- checkpoint-58/scheduler.pt +3 -0
- checkpoint-58/special_tokens_map.json +30 -0
- checkpoint-58/tokenizer.model +3 -0
- checkpoint-58/tokenizer_config.json +46 -0
- checkpoint-58/trainer_state.json +440 -0
- checkpoint-58/training_args.bin +3 -0
- checkpoint-87/config.json +29 -0
- checkpoint-87/generation_config.json +8 -0
- checkpoint-87/model.safetensors +3 -0
- checkpoint-87/optimizer.pt +3 -0
- checkpoint-87/rng_state.pth +3 -0
- checkpoint-87/scheduler.pt +3 -0
- checkpoint-87/special_tokens_map.json +30 -0
- checkpoint-87/tokenizer.model +3 -0
- checkpoint-87/tokenizer_config.json +46 -0
- checkpoint-87/trainer_state.json +643 -0
- checkpoint-87/training_args.bin +3 -0
- config.json +29 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- jaydenccc/AI_Storyteller_Dataset
|
| 9 |
+
model-index:
|
| 10 |
+
- name: models/Tiny_Llama_Storyteller
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
| 18 |
+
<details><summary>See axolotl config</summary>
|
| 19 |
+
|
| 20 |
+
axolotl version: `0.9.1.post1`
|
| 21 |
+
```yaml
|
| 22 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
| 23 |
+
batch_size: 4
|
| 24 |
+
bf16: auto
|
| 25 |
+
datasets:
|
| 26 |
+
- path: jaydenccc/AI_Storyteller_Dataset
|
| 27 |
+
type:
|
| 28 |
+
field_instruction: synopsis
|
| 29 |
+
field_output: short_story
|
| 30 |
+
field_system: system
|
| 31 |
+
format: <|user|> {instruction} </s> <|assistant|>
|
| 32 |
+
no_input_format: <|user|> {instruction} </s> <|assistant|>
|
| 33 |
+
system_prompt: ''
|
| 34 |
+
learning_rate: 0.0002
|
| 35 |
+
logging_steps: 1
|
| 36 |
+
micro_batch_size: 2
|
| 37 |
+
model_type: LlamaForCausalLM
|
| 38 |
+
num_epochs: 4
|
| 39 |
+
optimizer: adamw_bnb_8bit
|
| 40 |
+
output_dir: ./models/Tiny_Llama_Storyteller
|
| 41 |
+
sequence_length: 1024
|
| 42 |
+
tf32: false
|
| 43 |
+
tokenizer_type: LlamaTokenizer
|
| 44 |
+
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
</details><br>
|
| 48 |
+
|
| 49 |
+
# models/Tiny_Llama_Storyteller
|
| 50 |
+
|
| 51 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the jaydenccc/AI_Storyteller_Dataset dataset.
|
| 52 |
+
|
| 53 |
+
## Model description
|
| 54 |
+
|
| 55 |
+
More information needed
|
| 56 |
+
|
| 57 |
+
## Intended uses & limitations
|
| 58 |
+
|
| 59 |
+
More information needed
|
| 60 |
+
|
| 61 |
+
## Training and evaluation data
|
| 62 |
+
|
| 63 |
+
More information needed
|
| 64 |
+
|
| 65 |
+
## Training procedure
|
| 66 |
+
|
| 67 |
+
### Training hyperparameters
|
| 68 |
+
|
| 69 |
+
The following hyperparameters were used during training:
|
| 70 |
+
- learning_rate: 0.0002
|
| 71 |
+
- train_batch_size: 2
|
| 72 |
+
- eval_batch_size: 2
|
| 73 |
+
- seed: 42
|
| 74 |
+
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 75 |
+
- lr_scheduler_type: cosine
|
| 76 |
+
- lr_scheduler_warmup_steps: 2
|
| 77 |
+
- num_epochs: 4.0
|
| 78 |
+
|
| 79 |
+
### Training results
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- Transformers 4.51.3
|
| 86 |
+
- Pytorch 2.6.0+cu124
|
| 87 |
+
- Datasets 3.5.1
|
| 88 |
+
- Tokenizers 0.21.1
|
checkpoint-116/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 22,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.51.3",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"vocab_size": 32000
|
| 29 |
+
}
|
checkpoint-116/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 2048,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.51.3"
|
| 8 |
+
}
|
checkpoint-116/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3525b8067453b58e2e2d8d85bc2c4424e5ebe2faa1986639929f887d1b174ef6
|
| 3 |
+
size 2462448120
|
checkpoint-116/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49312bc9741faa19e93f8082f12e9aea90360fd8f9788e93a0e3a3627048075a
|
| 3 |
+
size 2235234810
|
checkpoint-116/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f37c40ce327861a7ca13b719d3aa37510a143368b6e74358bdb14becb3899e1e
|
| 3 |
+
size 14244
|
checkpoint-116/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68424c30349bda77a4657d1902f52c5a348248ab657a58e4aee2ebfc370c25ab
|
| 3 |
+
size 1064
|
checkpoint-116/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-116/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-116/tokenizer_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"extra_special_tokens": {},
|
| 36 |
+
"legacy": false,
|
| 37 |
+
"model_max_length": 2048,
|
| 38 |
+
"pad_token": "</s>",
|
| 39 |
+
"padding_side": "right",
|
| 40 |
+
"sp_model_kwargs": {},
|
| 41 |
+
"spaces_between_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false,
|
| 45 |
+
"use_fast": true
|
| 46 |
+
}
|
checkpoint-116/trainer_state.json
ADDED
|
@@ -0,0 +1,846 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 116,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.034482758620689655,
|
| 14 |
+
"grad_norm": 8.82559871673584,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.4554,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06896551724137931,
|
| 21 |
+
"grad_norm": 8.80897045135498,
|
| 22 |
+
"learning_rate": 0.0001,
|
| 23 |
+
"loss": 1.4394,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.10344827586206896,
|
| 28 |
+
"grad_norm": 22.349563598632812,
|
| 29 |
+
"learning_rate": 0.0002,
|
| 30 |
+
"loss": 1.9964,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.13793103448275862,
|
| 35 |
+
"grad_norm": 15.264303207397461,
|
| 36 |
+
"learning_rate": 0.00019996203070249516,
|
| 37 |
+
"loss": 2.232,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1724137931034483,
|
| 42 |
+
"grad_norm": 15.116658210754395,
|
| 43 |
+
"learning_rate": 0.00019984815164333163,
|
| 44 |
+
"loss": 2.1566,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.20689655172413793,
|
| 49 |
+
"grad_norm": 17.68694496154785,
|
| 50 |
+
"learning_rate": 0.000199658449300667,
|
| 51 |
+
"loss": 2.4215,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.2413793103448276,
|
| 56 |
+
"grad_norm": 8.640372276306152,
|
| 57 |
+
"learning_rate": 0.00019939306773179497,
|
| 58 |
+
"loss": 2.5103,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.27586206896551724,
|
| 63 |
+
"grad_norm": 51.94161605834961,
|
| 64 |
+
"learning_rate": 0.00019905220846375032,
|
| 65 |
+
"loss": 2.3878,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3103448275862069,
|
| 70 |
+
"grad_norm": 18.504257202148438,
|
| 71 |
+
"learning_rate": 0.00019863613034027224,
|
| 72 |
+
"loss": 2.6341,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3448275862068966,
|
| 77 |
+
"grad_norm": 10.244020462036133,
|
| 78 |
+
"learning_rate": 0.0001981451493252418,
|
| 79 |
+
"loss": 2.0863,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3793103448275862,
|
| 84 |
+
"grad_norm": 11.557518005371094,
|
| 85 |
+
"learning_rate": 0.00019757963826274357,
|
| 86 |
+
"loss": 2.8311,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.41379310344827586,
|
| 91 |
+
"grad_norm": 8.212669372558594,
|
| 92 |
+
"learning_rate": 0.00019694002659393305,
|
| 93 |
+
"loss": 2.3483,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.4482758620689655,
|
| 98 |
+
"grad_norm": 10.473441123962402,
|
| 99 |
+
"learning_rate": 0.00019622680003092503,
|
| 100 |
+
"loss": 2.4525,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.4827586206896552,
|
| 105 |
+
"grad_norm": 11.449350357055664,
|
| 106 |
+
"learning_rate": 0.00019544050018795075,
|
| 107 |
+
"loss": 2.4496,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.5172413793103449,
|
| 112 |
+
"grad_norm": 9.899384498596191,
|
| 113 |
+
"learning_rate": 0.00019458172417006347,
|
| 114 |
+
"loss": 2.3027,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.5517241379310345,
|
| 119 |
+
"grad_norm": 14.207268714904785,
|
| 120 |
+
"learning_rate": 0.0001936511241197055,
|
| 121 |
+
"loss": 2.3949,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5862068965517241,
|
| 126 |
+
"grad_norm": 8.849273681640625,
|
| 127 |
+
"learning_rate": 0.00019264940672148018,
|
| 128 |
+
"loss": 2.5911,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6206896551724138,
|
| 133 |
+
"grad_norm": 8.518115043640137,
|
| 134 |
+
"learning_rate": 0.00019157733266550575,
|
| 135 |
+
"loss": 2.4848,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6551724137931034,
|
| 140 |
+
"grad_norm": 8.173165321350098,
|
| 141 |
+
"learning_rate": 0.00019043571606975777,
|
| 142 |
+
"loss": 2.3583,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6896551724137931,
|
| 147 |
+
"grad_norm": 12.429973602294922,
|
| 148 |
+
"learning_rate": 0.0001892254238618394,
|
| 149 |
+
"loss": 2.5529,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.7241379310344828,
|
| 154 |
+
"grad_norm": 7.970499515533447,
|
| 155 |
+
"learning_rate": 0.0001879473751206489,
|
| 156 |
+
"loss": 2.3048,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.7586206896551724,
|
| 161 |
+
"grad_norm": 10.235267639160156,
|
| 162 |
+
"learning_rate": 0.00018660254037844388,
|
| 163 |
+
"loss": 2.5431,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.7931034482758621,
|
| 168 |
+
"grad_norm": 9.780701637268066,
|
| 169 |
+
"learning_rate": 0.00018519194088383273,
|
| 170 |
+
"loss": 2.4017,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.8275862068965517,
|
| 175 |
+
"grad_norm": 8.484028816223145,
|
| 176 |
+
"learning_rate": 0.00018371664782625287,
|
| 177 |
+
"loss": 2.3989,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.8620689655172413,
|
| 182 |
+
"grad_norm": 8.875442504882812,
|
| 183 |
+
"learning_rate": 0.0001821777815225245,
|
| 184 |
+
"loss": 2.3733,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.896551724137931,
|
| 189 |
+
"grad_norm": 7.790247440338135,
|
| 190 |
+
"learning_rate": 0.00018057651056609784,
|
| 191 |
+
"loss": 2.4949,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.9310344827586207,
|
| 196 |
+
"grad_norm": 9.66124439239502,
|
| 197 |
+
"learning_rate": 0.00017891405093963938,
|
| 198 |
+
"loss": 2.6426,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.9655172413793104,
|
| 203 |
+
"grad_norm": 10.793170928955078,
|
| 204 |
+
"learning_rate": 0.0001771916650916321,
|
| 205 |
+
"loss": 2.4486,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.0,
|
| 210 |
+
"grad_norm": 11.640007019042969,
|
| 211 |
+
"learning_rate": 0.00017541066097768963,
|
| 212 |
+
"loss": 2.5085,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.0344827586206897,
|
| 217 |
+
"grad_norm": 7.754225254058838,
|
| 218 |
+
"learning_rate": 0.00017357239106731317,
|
| 219 |
+
"loss": 1.2804,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.0689655172413792,
|
| 224 |
+
"grad_norm": 6.376781463623047,
|
| 225 |
+
"learning_rate": 0.00017167825131684513,
|
| 226 |
+
"loss": 0.914,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.103448275862069,
|
| 231 |
+
"grad_norm": 7.635883808135986,
|
| 232 |
+
"learning_rate": 0.00016972968010939954,
|
| 233 |
+
"loss": 0.9803,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.1379310344827587,
|
| 238 |
+
"grad_norm": 8.3922119140625,
|
| 239 |
+
"learning_rate": 0.00016772815716257412,
|
| 240 |
+
"loss": 1.1827,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.1724137931034484,
|
| 245 |
+
"grad_norm": 40.731563568115234,
|
| 246 |
+
"learning_rate": 0.00016567520240477344,
|
| 247 |
+
"loss": 1.0468,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.206896551724138,
|
| 252 |
+
"grad_norm": 8.111652374267578,
|
| 253 |
+
"learning_rate": 0.00016357237482099684,
|
| 254 |
+
"loss": 0.9133,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.2413793103448276,
|
| 259 |
+
"grad_norm": 11.691572189331055,
|
| 260 |
+
"learning_rate": 0.0001614212712689668,
|
| 261 |
+
"loss": 1.3907,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.2758620689655173,
|
| 266 |
+
"grad_norm": 13.854535102844238,
|
| 267 |
+
"learning_rate": 0.00015922352526649803,
|
| 268 |
+
"loss": 1.1896,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.3103448275862069,
|
| 273 |
+
"grad_norm": 13.816670417785645,
|
| 274 |
+
"learning_rate": 0.00015698080575102661,
|
| 275 |
+
"loss": 1.4907,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.3448275862068966,
|
| 280 |
+
"grad_norm": 9.702868461608887,
|
| 281 |
+
"learning_rate": 0.00015469481581224272,
|
| 282 |
+
"loss": 1.4863,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.3793103448275863,
|
| 287 |
+
"grad_norm": 6.986519813537598,
|
| 288 |
+
"learning_rate": 0.00015236729139878782,
|
| 289 |
+
"loss": 1.0933,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.4137931034482758,
|
| 294 |
+
"grad_norm": 5.615776538848877,
|
| 295 |
+
"learning_rate": 0.00015000000000000001,
|
| 296 |
+
"loss": 0.6781,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.4482758620689655,
|
| 301 |
+
"grad_norm": 10.113770484924316,
|
| 302 |
+
"learning_rate": 0.00014759473930370736,
|
| 303 |
+
"loss": 1.2472,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.4827586206896552,
|
| 308 |
+
"grad_norm": 6.870434284210205,
|
| 309 |
+
"learning_rate": 0.00014515333583108896,
|
| 310 |
+
"loss": 1.0049,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.5172413793103448,
|
| 315 |
+
"grad_norm": 8.070581436157227,
|
| 316 |
+
"learning_rate": 0.00014267764354964038,
|
| 317 |
+
"loss": 0.7818,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.5517241379310345,
|
| 322 |
+
"grad_norm": 5.975027084350586,
|
| 323 |
+
"learning_rate": 0.00014016954246529696,
|
| 324 |
+
"loss": 0.7797,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.5862068965517242,
|
| 329 |
+
"grad_norm": 6.494412899017334,
|
| 330 |
+
"learning_rate": 0.00013763093719478358,
|
| 331 |
+
"loss": 0.7939,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.6206896551724137,
|
| 336 |
+
"grad_norm": 7.849338054656982,
|
| 337 |
+
"learning_rate": 0.00013506375551927547,
|
| 338 |
+
"loss": 0.9905,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6551724137931034,
|
| 343 |
+
"grad_norm": 5.65253210067749,
|
| 344 |
+
"learning_rate": 0.00013246994692046836,
|
| 345 |
+
"loss": 0.6874,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.6896551724137931,
|
| 350 |
+
"grad_norm": 7.488522529602051,
|
| 351 |
+
"learning_rate": 0.00012985148110016947,
|
| 352 |
+
"loss": 0.7825,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.7241379310344827,
|
| 357 |
+
"grad_norm": 7.643749237060547,
|
| 358 |
+
"learning_rate": 0.00012721034648453353,
|
| 359 |
+
"loss": 0.748,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.7586206896551724,
|
| 364 |
+
"grad_norm": 9.57530403137207,
|
| 365 |
+
"learning_rate": 0.00012454854871407994,
|
| 366 |
+
"loss": 1.1548,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.793103448275862,
|
| 371 |
+
"grad_norm": 6.273963928222656,
|
| 372 |
+
"learning_rate": 0.0001218681091206376,
|
| 373 |
+
"loss": 0.8975,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.8275862068965516,
|
| 378 |
+
"grad_norm": 5.229036808013916,
|
| 379 |
+
"learning_rate": 0.00011917106319237386,
|
| 380 |
+
"loss": 0.761,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.8620689655172413,
|
| 385 |
+
"grad_norm": 7.955849647521973,
|
| 386 |
+
"learning_rate": 0.00011645945902807341,
|
| 387 |
+
"loss": 0.969,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.896551724137931,
|
| 392 |
+
"grad_norm": 5.826790809631348,
|
| 393 |
+
"learning_rate": 0.00011373535578184082,
|
| 394 |
+
"loss": 0.8425,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.9310344827586206,
|
| 399 |
+
"grad_norm": 7.660434246063232,
|
| 400 |
+
"learning_rate": 0.00011100082209940795,
|
| 401 |
+
"loss": 0.9966,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.9655172413793105,
|
| 406 |
+
"grad_norm": 8.542122840881348,
|
| 407 |
+
"learning_rate": 0.00010825793454723325,
|
| 408 |
+
"loss": 0.9864,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.0,
|
| 413 |
+
"grad_norm": 7.020619869232178,
|
| 414 |
+
"learning_rate": 0.00010550877603558655,
|
| 415 |
+
"loss": 0.8995,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.0344827586206895,
|
| 420 |
+
"grad_norm": 3.594993829727173,
|
| 421 |
+
"learning_rate": 0.00010275543423681621,
|
| 422 |
+
"loss": 0.3373,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.0689655172413794,
|
| 427 |
+
"grad_norm": 4.07737398147583,
|
| 428 |
+
"learning_rate": 0.0001,
|
| 429 |
+
"loss": 0.2722,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.103448275862069,
|
| 434 |
+
"grad_norm": 8.188806533813477,
|
| 435 |
+
"learning_rate": 9.724456576318381e-05,
|
| 436 |
+
"loss": 0.3745,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.1379310344827585,
|
| 441 |
+
"grad_norm": 3.8479177951812744,
|
| 442 |
+
"learning_rate": 9.449122396441345e-05,
|
| 443 |
+
"loss": 0.3211,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.1724137931034484,
|
| 448 |
+
"grad_norm": 4.40678596496582,
|
| 449 |
+
"learning_rate": 9.174206545276677e-05,
|
| 450 |
+
"loss": 0.4105,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.206896551724138,
|
| 455 |
+
"grad_norm": 4.841770648956299,
|
| 456 |
+
"learning_rate": 8.899917790059208e-05,
|
| 457 |
+
"loss": 0.4105,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.2413793103448274,
|
| 462 |
+
"grad_norm": 4.570344924926758,
|
| 463 |
+
"learning_rate": 8.626464421815919e-05,
|
| 464 |
+
"loss": 0.4432,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.2758620689655173,
|
| 469 |
+
"grad_norm": 3.0861401557922363,
|
| 470 |
+
"learning_rate": 8.35405409719266e-05,
|
| 471 |
+
"loss": 0.166,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.310344827586207,
|
| 476 |
+
"grad_norm": 3.652515411376953,
|
| 477 |
+
"learning_rate": 8.082893680762619e-05,
|
| 478 |
+
"loss": 0.3771,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.344827586206897,
|
| 483 |
+
"grad_norm": 5.078272342681885,
|
| 484 |
+
"learning_rate": 7.813189087936243e-05,
|
| 485 |
+
"loss": 0.3866,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.3793103448275863,
|
| 490 |
+
"grad_norm": 4.019447326660156,
|
| 491 |
+
"learning_rate": 7.54514512859201e-05,
|
| 492 |
+
"loss": 0.308,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.413793103448276,
|
| 497 |
+
"grad_norm": 3.4118640422821045,
|
| 498 |
+
"learning_rate": 7.278965351546648e-05,
|
| 499 |
+
"loss": 0.279,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.4482758620689653,
|
| 504 |
+
"grad_norm": 4.8846306800842285,
|
| 505 |
+
"learning_rate": 7.014851889983057e-05,
|
| 506 |
+
"loss": 0.3636,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.4827586206896552,
|
| 511 |
+
"grad_norm": 4.6204681396484375,
|
| 512 |
+
"learning_rate": 6.753005307953167e-05,
|
| 513 |
+
"loss": 0.4715,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.5172413793103448,
|
| 518 |
+
"grad_norm": 5.812495231628418,
|
| 519 |
+
"learning_rate": 6.493624448072457e-05,
|
| 520 |
+
"loss": 0.4816,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.5517241379310347,
|
| 525 |
+
"grad_norm": 4.512807369232178,
|
| 526 |
+
"learning_rate": 6.236906280521646e-05,
|
| 527 |
+
"loss": 0.1682,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.586206896551724,
|
| 532 |
+
"grad_norm": 4.009202003479004,
|
| 533 |
+
"learning_rate": 5.983045753470308e-05,
|
| 534 |
+
"loss": 0.2126,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.6206896551724137,
|
| 539 |
+
"grad_norm": 3.059624671936035,
|
| 540 |
+
"learning_rate": 5.732235645035964e-05,
|
| 541 |
+
"loss": 0.2485,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.655172413793103,
|
| 546 |
+
"grad_norm": 3.4690215587615967,
|
| 547 |
+
"learning_rate": 5.484666416891109e-05,
|
| 548 |
+
"loss": 0.2998,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.689655172413793,
|
| 553 |
+
"grad_norm": 5.230517387390137,
|
| 554 |
+
"learning_rate": 5.240526069629265e-05,
|
| 555 |
+
"loss": 0.34,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.7241379310344827,
|
| 560 |
+
"grad_norm": 4.850966930389404,
|
| 561 |
+
"learning_rate": 5.000000000000002e-05,
|
| 562 |
+
"loss": 0.5199,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.7586206896551726,
|
| 567 |
+
"grad_norm": 8.064337730407715,
|
| 568 |
+
"learning_rate": 4.763270860121222e-05,
|
| 569 |
+
"loss": 0.5783,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.793103448275862,
|
| 574 |
+
"grad_norm": 5.194494724273682,
|
| 575 |
+
"learning_rate": 4.530518418775733e-05,
|
| 576 |
+
"loss": 0.391,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.8275862068965516,
|
| 581 |
+
"grad_norm": 3.3784008026123047,
|
| 582 |
+
"learning_rate": 4.301919424897338e-05,
|
| 583 |
+
"loss": 0.2587,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.862068965517241,
|
| 588 |
+
"grad_norm": 3.8429758548736572,
|
| 589 |
+
"learning_rate": 4.077647473350201e-05,
|
| 590 |
+
"loss": 0.3064,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.896551724137931,
|
| 595 |
+
"grad_norm": 3.0566534996032715,
|
| 596 |
+
"learning_rate": 3.857872873103322e-05,
|
| 597 |
+
"loss": 0.2252,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.9310344827586206,
|
| 602 |
+
"grad_norm": 3.1600985527038574,
|
| 603 |
+
"learning_rate": 3.642762517900322e-05,
|
| 604 |
+
"loss": 0.1679,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.9655172413793105,
|
| 609 |
+
"grad_norm": 2.677255392074585,
|
| 610 |
+
"learning_rate": 3.4324797595226565e-05,
|
| 611 |
+
"loss": 0.2209,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 3.0,
|
| 616 |
+
"grad_norm": 4.203759670257568,
|
| 617 |
+
"learning_rate": 3.227184283742591e-05,
|
| 618 |
+
"loss": 0.3377,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 3.0344827586206895,
|
| 623 |
+
"grad_norm": 0.7876600027084351,
|
| 624 |
+
"learning_rate": 3.0270319890600462e-05,
|
| 625 |
+
"loss": 0.0367,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.0689655172413794,
|
| 630 |
+
"grad_norm": 1.69692063331604,
|
| 631 |
+
"learning_rate": 2.8321748683154893e-05,
|
| 632 |
+
"loss": 0.0885,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 3.103448275862069,
|
| 637 |
+
"grad_norm": 2.4697933197021484,
|
| 638 |
+
"learning_rate": 2.6427608932686843e-05,
|
| 639 |
+
"loss": 0.1183,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 3.1379310344827585,
|
| 644 |
+
"grad_norm": 2.506588935852051,
|
| 645 |
+
"learning_rate": 2.4589339022310386e-05,
|
| 646 |
+
"loss": 0.1693,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 3.1724137931034484,
|
| 651 |
+
"grad_norm": 0.990247368812561,
|
| 652 |
+
"learning_rate": 2.2808334908367914e-05,
|
| 653 |
+
"loss": 0.0484,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 3.206896551724138,
|
| 658 |
+
"grad_norm": 1.8859916925430298,
|
| 659 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 660 |
+
"loss": 0.0861,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 3.2413793103448274,
|
| 665 |
+
"grad_norm": 1.646560788154602,
|
| 666 |
+
"learning_rate": 1.9423489433902186e-05,
|
| 667 |
+
"loss": 0.0755,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.2758620689655173,
|
| 672 |
+
"grad_norm": 1.6290369033813477,
|
| 673 |
+
"learning_rate": 1.7822218477475494e-05,
|
| 674 |
+
"loss": 0.0965,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 3.310344827586207,
|
| 679 |
+
"grad_norm": 2.4385271072387695,
|
| 680 |
+
"learning_rate": 1.6283352173747145e-05,
|
| 681 |
+
"loss": 0.2077,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 3.344827586206897,
|
| 686 |
+
"grad_norm": 1.2653759717941284,
|
| 687 |
+
"learning_rate": 1.4808059116167305e-05,
|
| 688 |
+
"loss": 0.0557,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.3793103448275863,
|
| 693 |
+
"grad_norm": 1.5845226049423218,
|
| 694 |
+
"learning_rate": 1.339745962155613e-05,
|
| 695 |
+
"loss": 0.0838,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 3.413793103448276,
|
| 700 |
+
"grad_norm": 1.3302026987075806,
|
| 701 |
+
"learning_rate": 1.2052624879351104e-05,
|
| 702 |
+
"loss": 0.0677,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 3.4482758620689653,
|
| 707 |
+
"grad_norm": 1.1394819021224976,
|
| 708 |
+
"learning_rate": 1.0774576138160597e-05,
|
| 709 |
+
"loss": 0.0487,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 3.4827586206896552,
|
| 714 |
+
"grad_norm": 1.806217908859253,
|
| 715 |
+
"learning_rate": 9.564283930242257e-06,
|
| 716 |
+
"loss": 0.0852,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 3.5172413793103448,
|
| 721 |
+
"grad_norm": 1.6319350004196167,
|
| 722 |
+
"learning_rate": 8.422667334494249e-06,
|
| 723 |
+
"loss": 0.0778,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 3.5517241379310347,
|
| 728 |
+
"grad_norm": 1.4830849170684814,
|
| 729 |
+
"learning_rate": 7.350593278519824e-06,
|
| 730 |
+
"loss": 0.0893,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 3.586206896551724,
|
| 735 |
+
"grad_norm": 2.3866922855377197,
|
| 736 |
+
"learning_rate": 6.3488758802945354e-06,
|
| 737 |
+
"loss": 0.0795,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 3.6206896551724137,
|
| 742 |
+
"grad_norm": 3.7470719814300537,
|
| 743 |
+
"learning_rate": 5.418275829936537e-06,
|
| 744 |
+
"loss": 0.1359,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 3.655172413793103,
|
| 749 |
+
"grad_norm": 0.9075297713279724,
|
| 750 |
+
"learning_rate": 4.559499812049251e-06,
|
| 751 |
+
"loss": 0.0427,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 3.689655172413793,
|
| 756 |
+
"grad_norm": 1.1853052377700806,
|
| 757 |
+
"learning_rate": 3.7731999690749585e-06,
|
| 758 |
+
"loss": 0.0473,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 3.7241379310344827,
|
| 763 |
+
"grad_norm": 1.2385241985321045,
|
| 764 |
+
"learning_rate": 3.059973406066963e-06,
|
| 765 |
+
"loss": 0.0429,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 3.7586206896551726,
|
| 770 |
+
"grad_norm": 2.042271375656128,
|
| 771 |
+
"learning_rate": 2.420361737256438e-06,
|
| 772 |
+
"loss": 0.0869,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 3.793103448275862,
|
| 777 |
+
"grad_norm": 1.42056143283844,
|
| 778 |
+
"learning_rate": 1.8548506747582129e-06,
|
| 779 |
+
"loss": 0.0498,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 3.8275862068965516,
|
| 784 |
+
"grad_norm": 2.0945870876312256,
|
| 785 |
+
"learning_rate": 1.3638696597277679e-06,
|
| 786 |
+
"loss": 0.0909,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 3.862068965517241,
|
| 791 |
+
"grad_norm": 0.9981832504272461,
|
| 792 |
+
"learning_rate": 9.477915362496758e-07,
|
| 793 |
+
"loss": 0.044,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 3.896551724137931,
|
| 798 |
+
"grad_norm": 1.049004316329956,
|
| 799 |
+
"learning_rate": 6.069322682050516e-07,
|
| 800 |
+
"loss": 0.0589,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 3.9310344827586206,
|
| 805 |
+
"grad_norm": 1.8079121112823486,
|
| 806 |
+
"learning_rate": 3.415506993330153e-07,
|
| 807 |
+
"loss": 0.0937,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 3.9655172413793105,
|
| 812 |
+
"grad_norm": 10.492709159851074,
|
| 813 |
+
"learning_rate": 1.518483566683826e-07,
|
| 814 |
+
"loss": 0.0785,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 4.0,
|
| 819 |
+
"grad_norm": 2.368055820465088,
|
| 820 |
+
"learning_rate": 3.796929750485845e-08,
|
| 821 |
+
"loss": 0.1359,
|
| 822 |
+
"step": 116
|
| 823 |
+
}
|
| 824 |
+
],
|
| 825 |
+
"logging_steps": 1,
|
| 826 |
+
"max_steps": 116,
|
| 827 |
+
"num_input_tokens_seen": 0,
|
| 828 |
+
"num_train_epochs": 4,
|
| 829 |
+
"save_steps": 500,
|
| 830 |
+
"stateful_callbacks": {
|
| 831 |
+
"TrainerControl": {
|
| 832 |
+
"args": {
|
| 833 |
+
"should_epoch_stop": false,
|
| 834 |
+
"should_evaluate": false,
|
| 835 |
+
"should_log": false,
|
| 836 |
+
"should_save": true,
|
| 837 |
+
"should_training_stop": true
|
| 838 |
+
},
|
| 839 |
+
"attributes": {}
|
| 840 |
+
}
|
| 841 |
+
},
|
| 842 |
+
"total_flos": 714260454309888.0,
|
| 843 |
+
"train_batch_size": 2,
|
| 844 |
+
"trial_name": null,
|
| 845 |
+
"trial_params": null
|
| 846 |
+
}
|
checkpoint-116/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5850f18486da32f4c0d93fa9a10324134011ad7d40e79f7ce9366d71ef9b2851
|
| 3 |
+
size 6584
|
checkpoint-29/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 22,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.51.3",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"vocab_size": 32000
|
| 29 |
+
}
|
checkpoint-29/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 2048,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.51.3"
|
| 8 |
+
}
|
checkpoint-29/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e915352612b5e66431cdbcf464d8e42ca12a7d8d91344679dd4268a05e9c42f4
|
| 3 |
+
size 2462448120
|
checkpoint-29/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46ff7ed03f88f764c6941e78c0d58de48dd4ec0f1ceef9eefe4751f6b5ed1284
|
| 3 |
+
size 2235234810
|
checkpoint-29/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
|
| 3 |
+
size 14244
|
checkpoint-29/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15d6d9e74debfe880377b66f63e3170bc92084f30f82e06ca9657a93d4b3a63b
|
| 3 |
+
size 1064
|
checkpoint-29/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-29/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-29/tokenizer_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"extra_special_tokens": {},
|
| 36 |
+
"legacy": false,
|
| 37 |
+
"model_max_length": 2048,
|
| 38 |
+
"pad_token": "</s>",
|
| 39 |
+
"padding_side": "right",
|
| 40 |
+
"sp_model_kwargs": {},
|
| 41 |
+
"spaces_between_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false,
|
| 45 |
+
"use_fast": true
|
| 46 |
+
}
|
checkpoint-29/trainer_state.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 29,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.034482758620689655,
|
| 14 |
+
"grad_norm": 8.82559871673584,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.4554,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06896551724137931,
|
| 21 |
+
"grad_norm": 8.80897045135498,
|
| 22 |
+
"learning_rate": 0.0001,
|
| 23 |
+
"loss": 1.4394,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.10344827586206896,
|
| 28 |
+
"grad_norm": 22.349563598632812,
|
| 29 |
+
"learning_rate": 0.0002,
|
| 30 |
+
"loss": 1.9964,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.13793103448275862,
|
| 35 |
+
"grad_norm": 15.264303207397461,
|
| 36 |
+
"learning_rate": 0.00019996203070249516,
|
| 37 |
+
"loss": 2.232,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1724137931034483,
|
| 42 |
+
"grad_norm": 15.116658210754395,
|
| 43 |
+
"learning_rate": 0.00019984815164333163,
|
| 44 |
+
"loss": 2.1566,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.20689655172413793,
|
| 49 |
+
"grad_norm": 17.68694496154785,
|
| 50 |
+
"learning_rate": 0.000199658449300667,
|
| 51 |
+
"loss": 2.4215,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.2413793103448276,
|
| 56 |
+
"grad_norm": 8.640372276306152,
|
| 57 |
+
"learning_rate": 0.00019939306773179497,
|
| 58 |
+
"loss": 2.5103,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.27586206896551724,
|
| 63 |
+
"grad_norm": 51.94161605834961,
|
| 64 |
+
"learning_rate": 0.00019905220846375032,
|
| 65 |
+
"loss": 2.3878,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3103448275862069,
|
| 70 |
+
"grad_norm": 18.504257202148438,
|
| 71 |
+
"learning_rate": 0.00019863613034027224,
|
| 72 |
+
"loss": 2.6341,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3448275862068966,
|
| 77 |
+
"grad_norm": 10.244020462036133,
|
| 78 |
+
"learning_rate": 0.0001981451493252418,
|
| 79 |
+
"loss": 2.0863,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3793103448275862,
|
| 84 |
+
"grad_norm": 11.557518005371094,
|
| 85 |
+
"learning_rate": 0.00019757963826274357,
|
| 86 |
+
"loss": 2.8311,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.41379310344827586,
|
| 91 |
+
"grad_norm": 8.212669372558594,
|
| 92 |
+
"learning_rate": 0.00019694002659393305,
|
| 93 |
+
"loss": 2.3483,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.4482758620689655,
|
| 98 |
+
"grad_norm": 10.473441123962402,
|
| 99 |
+
"learning_rate": 0.00019622680003092503,
|
| 100 |
+
"loss": 2.4525,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.4827586206896552,
|
| 105 |
+
"grad_norm": 11.449350357055664,
|
| 106 |
+
"learning_rate": 0.00019544050018795075,
|
| 107 |
+
"loss": 2.4496,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.5172413793103449,
|
| 112 |
+
"grad_norm": 9.899384498596191,
|
| 113 |
+
"learning_rate": 0.00019458172417006347,
|
| 114 |
+
"loss": 2.3027,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.5517241379310345,
|
| 119 |
+
"grad_norm": 14.207268714904785,
|
| 120 |
+
"learning_rate": 0.0001936511241197055,
|
| 121 |
+
"loss": 2.3949,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5862068965517241,
|
| 126 |
+
"grad_norm": 8.849273681640625,
|
| 127 |
+
"learning_rate": 0.00019264940672148018,
|
| 128 |
+
"loss": 2.5911,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6206896551724138,
|
| 133 |
+
"grad_norm": 8.518115043640137,
|
| 134 |
+
"learning_rate": 0.00019157733266550575,
|
| 135 |
+
"loss": 2.4848,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6551724137931034,
|
| 140 |
+
"grad_norm": 8.173165321350098,
|
| 141 |
+
"learning_rate": 0.00019043571606975777,
|
| 142 |
+
"loss": 2.3583,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6896551724137931,
|
| 147 |
+
"grad_norm": 12.429973602294922,
|
| 148 |
+
"learning_rate": 0.0001892254238618394,
|
| 149 |
+
"loss": 2.5529,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.7241379310344828,
|
| 154 |
+
"grad_norm": 7.970499515533447,
|
| 155 |
+
"learning_rate": 0.0001879473751206489,
|
| 156 |
+
"loss": 2.3048,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.7586206896551724,
|
| 161 |
+
"grad_norm": 10.235267639160156,
|
| 162 |
+
"learning_rate": 0.00018660254037844388,
|
| 163 |
+
"loss": 2.5431,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.7931034482758621,
|
| 168 |
+
"grad_norm": 9.780701637268066,
|
| 169 |
+
"learning_rate": 0.00018519194088383273,
|
| 170 |
+
"loss": 2.4017,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.8275862068965517,
|
| 175 |
+
"grad_norm": 8.484028816223145,
|
| 176 |
+
"learning_rate": 0.00018371664782625287,
|
| 177 |
+
"loss": 2.3989,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.8620689655172413,
|
| 182 |
+
"grad_norm": 8.875442504882812,
|
| 183 |
+
"learning_rate": 0.0001821777815225245,
|
| 184 |
+
"loss": 2.3733,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.896551724137931,
|
| 189 |
+
"grad_norm": 7.790247440338135,
|
| 190 |
+
"learning_rate": 0.00018057651056609784,
|
| 191 |
+
"loss": 2.4949,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.9310344827586207,
|
| 196 |
+
"grad_norm": 9.66124439239502,
|
| 197 |
+
"learning_rate": 0.00017891405093963938,
|
| 198 |
+
"loss": 2.6426,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.9655172413793104,
|
| 203 |
+
"grad_norm": 10.793170928955078,
|
| 204 |
+
"learning_rate": 0.0001771916650916321,
|
| 205 |
+
"loss": 2.4486,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.0,
|
| 210 |
+
"grad_norm": 11.640007019042969,
|
| 211 |
+
"learning_rate": 0.00017541066097768963,
|
| 212 |
+
"loss": 2.5085,
|
| 213 |
+
"step": 29
|
| 214 |
+
}
|
| 215 |
+
],
|
| 216 |
+
"logging_steps": 1,
|
| 217 |
+
"max_steps": 116,
|
| 218 |
+
"num_input_tokens_seen": 0,
|
| 219 |
+
"num_train_epochs": 4,
|
| 220 |
+
"save_steps": 500,
|
| 221 |
+
"stateful_callbacks": {
|
| 222 |
+
"TrainerControl": {
|
| 223 |
+
"args": {
|
| 224 |
+
"should_epoch_stop": false,
|
| 225 |
+
"should_evaluate": false,
|
| 226 |
+
"should_log": false,
|
| 227 |
+
"should_save": true,
|
| 228 |
+
"should_training_stop": false
|
| 229 |
+
},
|
| 230 |
+
"attributes": {}
|
| 231 |
+
}
|
| 232 |
+
},
|
| 233 |
+
"total_flos": 179558245466112.0,
|
| 234 |
+
"train_batch_size": 2,
|
| 235 |
+
"trial_name": null,
|
| 236 |
+
"trial_params": null
|
| 237 |
+
}
|
checkpoint-29/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5850f18486da32f4c0d93fa9a10324134011ad7d40e79f7ce9366d71ef9b2851
|
| 3 |
+
size 6584
|
checkpoint-58/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 22,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.51.3",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"vocab_size": 32000
|
| 29 |
+
}
|
checkpoint-58/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 2048,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.51.3"
|
| 8 |
+
}
|
checkpoint-58/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a030b988e404b42b40bbd9b1fddd6024671601ed79a2b718c01f65fd5bdb3fb6
|
| 3 |
+
size 2462448120
|
checkpoint-58/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4571c8919ce20242834ad867311c2e1677b312bd20e710ea0eab3a35816d35f
|
| 3 |
+
size 2235234810
|
checkpoint-58/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
|
| 3 |
+
size 14244
|
checkpoint-58/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99930521a0cdafb3ccc648c300427f95aabd7f836c72e4ba27c495e5ea995318
|
| 3 |
+
size 1064
|
checkpoint-58/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-58/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-58/tokenizer_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"extra_special_tokens": {},
|
| 36 |
+
"legacy": false,
|
| 37 |
+
"model_max_length": 2048,
|
| 38 |
+
"pad_token": "</s>",
|
| 39 |
+
"padding_side": "right",
|
| 40 |
+
"sp_model_kwargs": {},
|
| 41 |
+
"spaces_between_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false,
|
| 45 |
+
"use_fast": true
|
| 46 |
+
}
|
checkpoint-58/trainer_state.json
ADDED
|
@@ -0,0 +1,440 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 58,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.034482758620689655,
|
| 14 |
+
"grad_norm": 8.82559871673584,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.4554,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06896551724137931,
|
| 21 |
+
"grad_norm": 8.80897045135498,
|
| 22 |
+
"learning_rate": 0.0001,
|
| 23 |
+
"loss": 1.4394,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.10344827586206896,
|
| 28 |
+
"grad_norm": 22.349563598632812,
|
| 29 |
+
"learning_rate": 0.0002,
|
| 30 |
+
"loss": 1.9964,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.13793103448275862,
|
| 35 |
+
"grad_norm": 15.264303207397461,
|
| 36 |
+
"learning_rate": 0.00019996203070249516,
|
| 37 |
+
"loss": 2.232,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1724137931034483,
|
| 42 |
+
"grad_norm": 15.116658210754395,
|
| 43 |
+
"learning_rate": 0.00019984815164333163,
|
| 44 |
+
"loss": 2.1566,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.20689655172413793,
|
| 49 |
+
"grad_norm": 17.68694496154785,
|
| 50 |
+
"learning_rate": 0.000199658449300667,
|
| 51 |
+
"loss": 2.4215,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.2413793103448276,
|
| 56 |
+
"grad_norm": 8.640372276306152,
|
| 57 |
+
"learning_rate": 0.00019939306773179497,
|
| 58 |
+
"loss": 2.5103,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.27586206896551724,
|
| 63 |
+
"grad_norm": 51.94161605834961,
|
| 64 |
+
"learning_rate": 0.00019905220846375032,
|
| 65 |
+
"loss": 2.3878,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3103448275862069,
|
| 70 |
+
"grad_norm": 18.504257202148438,
|
| 71 |
+
"learning_rate": 0.00019863613034027224,
|
| 72 |
+
"loss": 2.6341,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3448275862068966,
|
| 77 |
+
"grad_norm": 10.244020462036133,
|
| 78 |
+
"learning_rate": 0.0001981451493252418,
|
| 79 |
+
"loss": 2.0863,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3793103448275862,
|
| 84 |
+
"grad_norm": 11.557518005371094,
|
| 85 |
+
"learning_rate": 0.00019757963826274357,
|
| 86 |
+
"loss": 2.8311,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.41379310344827586,
|
| 91 |
+
"grad_norm": 8.212669372558594,
|
| 92 |
+
"learning_rate": 0.00019694002659393305,
|
| 93 |
+
"loss": 2.3483,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.4482758620689655,
|
| 98 |
+
"grad_norm": 10.473441123962402,
|
| 99 |
+
"learning_rate": 0.00019622680003092503,
|
| 100 |
+
"loss": 2.4525,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.4827586206896552,
|
| 105 |
+
"grad_norm": 11.449350357055664,
|
| 106 |
+
"learning_rate": 0.00019544050018795075,
|
| 107 |
+
"loss": 2.4496,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.5172413793103449,
|
| 112 |
+
"grad_norm": 9.899384498596191,
|
| 113 |
+
"learning_rate": 0.00019458172417006347,
|
| 114 |
+
"loss": 2.3027,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.5517241379310345,
|
| 119 |
+
"grad_norm": 14.207268714904785,
|
| 120 |
+
"learning_rate": 0.0001936511241197055,
|
| 121 |
+
"loss": 2.3949,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5862068965517241,
|
| 126 |
+
"grad_norm": 8.849273681640625,
|
| 127 |
+
"learning_rate": 0.00019264940672148018,
|
| 128 |
+
"loss": 2.5911,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6206896551724138,
|
| 133 |
+
"grad_norm": 8.518115043640137,
|
| 134 |
+
"learning_rate": 0.00019157733266550575,
|
| 135 |
+
"loss": 2.4848,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6551724137931034,
|
| 140 |
+
"grad_norm": 8.173165321350098,
|
| 141 |
+
"learning_rate": 0.00019043571606975777,
|
| 142 |
+
"loss": 2.3583,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6896551724137931,
|
| 147 |
+
"grad_norm": 12.429973602294922,
|
| 148 |
+
"learning_rate": 0.0001892254238618394,
|
| 149 |
+
"loss": 2.5529,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.7241379310344828,
|
| 154 |
+
"grad_norm": 7.970499515533447,
|
| 155 |
+
"learning_rate": 0.0001879473751206489,
|
| 156 |
+
"loss": 2.3048,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.7586206896551724,
|
| 161 |
+
"grad_norm": 10.235267639160156,
|
| 162 |
+
"learning_rate": 0.00018660254037844388,
|
| 163 |
+
"loss": 2.5431,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.7931034482758621,
|
| 168 |
+
"grad_norm": 9.780701637268066,
|
| 169 |
+
"learning_rate": 0.00018519194088383273,
|
| 170 |
+
"loss": 2.4017,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.8275862068965517,
|
| 175 |
+
"grad_norm": 8.484028816223145,
|
| 176 |
+
"learning_rate": 0.00018371664782625287,
|
| 177 |
+
"loss": 2.3989,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.8620689655172413,
|
| 182 |
+
"grad_norm": 8.875442504882812,
|
| 183 |
+
"learning_rate": 0.0001821777815225245,
|
| 184 |
+
"loss": 2.3733,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.896551724137931,
|
| 189 |
+
"grad_norm": 7.790247440338135,
|
| 190 |
+
"learning_rate": 0.00018057651056609784,
|
| 191 |
+
"loss": 2.4949,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.9310344827586207,
|
| 196 |
+
"grad_norm": 9.66124439239502,
|
| 197 |
+
"learning_rate": 0.00017891405093963938,
|
| 198 |
+
"loss": 2.6426,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.9655172413793104,
|
| 203 |
+
"grad_norm": 10.793170928955078,
|
| 204 |
+
"learning_rate": 0.0001771916650916321,
|
| 205 |
+
"loss": 2.4486,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.0,
|
| 210 |
+
"grad_norm": 11.640007019042969,
|
| 211 |
+
"learning_rate": 0.00017541066097768963,
|
| 212 |
+
"loss": 2.5085,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.0344827586206897,
|
| 217 |
+
"grad_norm": 7.754225254058838,
|
| 218 |
+
"learning_rate": 0.00017357239106731317,
|
| 219 |
+
"loss": 1.2804,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.0689655172413792,
|
| 224 |
+
"grad_norm": 6.376781463623047,
|
| 225 |
+
"learning_rate": 0.00017167825131684513,
|
| 226 |
+
"loss": 0.914,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.103448275862069,
|
| 231 |
+
"grad_norm": 7.635883808135986,
|
| 232 |
+
"learning_rate": 0.00016972968010939954,
|
| 233 |
+
"loss": 0.9803,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.1379310344827587,
|
| 238 |
+
"grad_norm": 8.3922119140625,
|
| 239 |
+
"learning_rate": 0.00016772815716257412,
|
| 240 |
+
"loss": 1.1827,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.1724137931034484,
|
| 245 |
+
"grad_norm": 40.731563568115234,
|
| 246 |
+
"learning_rate": 0.00016567520240477344,
|
| 247 |
+
"loss": 1.0468,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.206896551724138,
|
| 252 |
+
"grad_norm": 8.111652374267578,
|
| 253 |
+
"learning_rate": 0.00016357237482099684,
|
| 254 |
+
"loss": 0.9133,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.2413793103448276,
|
| 259 |
+
"grad_norm": 11.691572189331055,
|
| 260 |
+
"learning_rate": 0.0001614212712689668,
|
| 261 |
+
"loss": 1.3907,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.2758620689655173,
|
| 266 |
+
"grad_norm": 13.854535102844238,
|
| 267 |
+
"learning_rate": 0.00015922352526649803,
|
| 268 |
+
"loss": 1.1896,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.3103448275862069,
|
| 273 |
+
"grad_norm": 13.816670417785645,
|
| 274 |
+
"learning_rate": 0.00015698080575102661,
|
| 275 |
+
"loss": 1.4907,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.3448275862068966,
|
| 280 |
+
"grad_norm": 9.702868461608887,
|
| 281 |
+
"learning_rate": 0.00015469481581224272,
|
| 282 |
+
"loss": 1.4863,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.3793103448275863,
|
| 287 |
+
"grad_norm": 6.986519813537598,
|
| 288 |
+
"learning_rate": 0.00015236729139878782,
|
| 289 |
+
"loss": 1.0933,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.4137931034482758,
|
| 294 |
+
"grad_norm": 5.615776538848877,
|
| 295 |
+
"learning_rate": 0.00015000000000000001,
|
| 296 |
+
"loss": 0.6781,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.4482758620689655,
|
| 301 |
+
"grad_norm": 10.113770484924316,
|
| 302 |
+
"learning_rate": 0.00014759473930370736,
|
| 303 |
+
"loss": 1.2472,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.4827586206896552,
|
| 308 |
+
"grad_norm": 6.870434284210205,
|
| 309 |
+
"learning_rate": 0.00014515333583108896,
|
| 310 |
+
"loss": 1.0049,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.5172413793103448,
|
| 315 |
+
"grad_norm": 8.070581436157227,
|
| 316 |
+
"learning_rate": 0.00014267764354964038,
|
| 317 |
+
"loss": 0.7818,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.5517241379310345,
|
| 322 |
+
"grad_norm": 5.975027084350586,
|
| 323 |
+
"learning_rate": 0.00014016954246529696,
|
| 324 |
+
"loss": 0.7797,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.5862068965517242,
|
| 329 |
+
"grad_norm": 6.494412899017334,
|
| 330 |
+
"learning_rate": 0.00013763093719478358,
|
| 331 |
+
"loss": 0.7939,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.6206896551724137,
|
| 336 |
+
"grad_norm": 7.849338054656982,
|
| 337 |
+
"learning_rate": 0.00013506375551927547,
|
| 338 |
+
"loss": 0.9905,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6551724137931034,
|
| 343 |
+
"grad_norm": 5.65253210067749,
|
| 344 |
+
"learning_rate": 0.00013246994692046836,
|
| 345 |
+
"loss": 0.6874,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.6896551724137931,
|
| 350 |
+
"grad_norm": 7.488522529602051,
|
| 351 |
+
"learning_rate": 0.00012985148110016947,
|
| 352 |
+
"loss": 0.7825,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.7241379310344827,
|
| 357 |
+
"grad_norm": 7.643749237060547,
|
| 358 |
+
"learning_rate": 0.00012721034648453353,
|
| 359 |
+
"loss": 0.748,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.7586206896551724,
|
| 364 |
+
"grad_norm": 9.57530403137207,
|
| 365 |
+
"learning_rate": 0.00012454854871407994,
|
| 366 |
+
"loss": 1.1548,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.793103448275862,
|
| 371 |
+
"grad_norm": 6.273963928222656,
|
| 372 |
+
"learning_rate": 0.0001218681091206376,
|
| 373 |
+
"loss": 0.8975,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.8275862068965516,
|
| 378 |
+
"grad_norm": 5.229036808013916,
|
| 379 |
+
"learning_rate": 0.00011917106319237386,
|
| 380 |
+
"loss": 0.761,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.8620689655172413,
|
| 385 |
+
"grad_norm": 7.955849647521973,
|
| 386 |
+
"learning_rate": 0.00011645945902807341,
|
| 387 |
+
"loss": 0.969,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.896551724137931,
|
| 392 |
+
"grad_norm": 5.826790809631348,
|
| 393 |
+
"learning_rate": 0.00011373535578184082,
|
| 394 |
+
"loss": 0.8425,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.9310344827586206,
|
| 399 |
+
"grad_norm": 7.660434246063232,
|
| 400 |
+
"learning_rate": 0.00011100082209940795,
|
| 401 |
+
"loss": 0.9966,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.9655172413793105,
|
| 406 |
+
"grad_norm": 8.542122840881348,
|
| 407 |
+
"learning_rate": 0.00010825793454723325,
|
| 408 |
+
"loss": 0.9864,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.0,
|
| 413 |
+
"grad_norm": 7.020619869232178,
|
| 414 |
+
"learning_rate": 0.00010550877603558655,
|
| 415 |
+
"loss": 0.8995,
|
| 416 |
+
"step": 58
|
| 417 |
+
}
|
| 418 |
+
],
|
| 419 |
+
"logging_steps": 1,
|
| 420 |
+
"max_steps": 116,
|
| 421 |
+
"num_input_tokens_seen": 0,
|
| 422 |
+
"num_train_epochs": 4,
|
| 423 |
+
"save_steps": 500,
|
| 424 |
+
"stateful_callbacks": {
|
| 425 |
+
"TrainerControl": {
|
| 426 |
+
"args": {
|
| 427 |
+
"should_epoch_stop": false,
|
| 428 |
+
"should_evaluate": false,
|
| 429 |
+
"should_log": false,
|
| 430 |
+
"should_save": true,
|
| 431 |
+
"should_training_stop": false
|
| 432 |
+
},
|
| 433 |
+
"attributes": {}
|
| 434 |
+
}
|
| 435 |
+
},
|
| 436 |
+
"total_flos": 357527479910400.0,
|
| 437 |
+
"train_batch_size": 2,
|
| 438 |
+
"trial_name": null,
|
| 439 |
+
"trial_params": null
|
| 440 |
+
}
|
checkpoint-58/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5850f18486da32f4c0d93fa9a10324134011ad7d40e79f7ce9366d71ef9b2851
|
| 3 |
+
size 6584
|
checkpoint-87/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 22,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.51.3",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"vocab_size": 32000
|
| 29 |
+
}
|
checkpoint-87/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 2048,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.51.3"
|
| 8 |
+
}
|
checkpoint-87/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6302a97c5e2565a75db76a9035acb403a8dbca06f1c97b0c5a2c66912b284ea
|
| 3 |
+
size 2462448120
|
checkpoint-87/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ef166aa5de33a84a27b7ba81ba1ab90aa41f5db983776548791d8556a520004
|
| 3 |
+
size 2235234810
|
checkpoint-87/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cf9097d4513154245c48236b6ec5137b7ee2a21c9f58f2cba798ea275c6026f
|
| 3 |
+
size 14244
|
checkpoint-87/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e90919b48f21e15928cee1610e5e17676dccd6de5774b8ab3db4f6f4363c37aa
|
| 3 |
+
size 1064
|
checkpoint-87/special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
checkpoint-87/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-87/tokenizer_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"extra_special_tokens": {},
|
| 36 |
+
"legacy": false,
|
| 37 |
+
"model_max_length": 2048,
|
| 38 |
+
"pad_token": "</s>",
|
| 39 |
+
"padding_side": "right",
|
| 40 |
+
"sp_model_kwargs": {},
|
| 41 |
+
"spaces_between_special_tokens": false,
|
| 42 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"unk_token": "<unk>",
|
| 44 |
+
"use_default_system_prompt": false,
|
| 45 |
+
"use_fast": true
|
| 46 |
+
}
|
checkpoint-87/trainer_state.json
ADDED
|
@@ -0,0 +1,643 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 87,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.034482758620689655,
|
| 14 |
+
"grad_norm": 8.82559871673584,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.4554,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06896551724137931,
|
| 21 |
+
"grad_norm": 8.80897045135498,
|
| 22 |
+
"learning_rate": 0.0001,
|
| 23 |
+
"loss": 1.4394,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.10344827586206896,
|
| 28 |
+
"grad_norm": 22.349563598632812,
|
| 29 |
+
"learning_rate": 0.0002,
|
| 30 |
+
"loss": 1.9964,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.13793103448275862,
|
| 35 |
+
"grad_norm": 15.264303207397461,
|
| 36 |
+
"learning_rate": 0.00019996203070249516,
|
| 37 |
+
"loss": 2.232,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1724137931034483,
|
| 42 |
+
"grad_norm": 15.116658210754395,
|
| 43 |
+
"learning_rate": 0.00019984815164333163,
|
| 44 |
+
"loss": 2.1566,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.20689655172413793,
|
| 49 |
+
"grad_norm": 17.68694496154785,
|
| 50 |
+
"learning_rate": 0.000199658449300667,
|
| 51 |
+
"loss": 2.4215,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.2413793103448276,
|
| 56 |
+
"grad_norm": 8.640372276306152,
|
| 57 |
+
"learning_rate": 0.00019939306773179497,
|
| 58 |
+
"loss": 2.5103,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.27586206896551724,
|
| 63 |
+
"grad_norm": 51.94161605834961,
|
| 64 |
+
"learning_rate": 0.00019905220846375032,
|
| 65 |
+
"loss": 2.3878,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3103448275862069,
|
| 70 |
+
"grad_norm": 18.504257202148438,
|
| 71 |
+
"learning_rate": 0.00019863613034027224,
|
| 72 |
+
"loss": 2.6341,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.3448275862068966,
|
| 77 |
+
"grad_norm": 10.244020462036133,
|
| 78 |
+
"learning_rate": 0.0001981451493252418,
|
| 79 |
+
"loss": 2.0863,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3793103448275862,
|
| 84 |
+
"grad_norm": 11.557518005371094,
|
| 85 |
+
"learning_rate": 0.00019757963826274357,
|
| 86 |
+
"loss": 2.8311,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.41379310344827586,
|
| 91 |
+
"grad_norm": 8.212669372558594,
|
| 92 |
+
"learning_rate": 0.00019694002659393305,
|
| 93 |
+
"loss": 2.3483,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.4482758620689655,
|
| 98 |
+
"grad_norm": 10.473441123962402,
|
| 99 |
+
"learning_rate": 0.00019622680003092503,
|
| 100 |
+
"loss": 2.4525,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.4827586206896552,
|
| 105 |
+
"grad_norm": 11.449350357055664,
|
| 106 |
+
"learning_rate": 0.00019544050018795075,
|
| 107 |
+
"loss": 2.4496,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.5172413793103449,
|
| 112 |
+
"grad_norm": 9.899384498596191,
|
| 113 |
+
"learning_rate": 0.00019458172417006347,
|
| 114 |
+
"loss": 2.3027,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.5517241379310345,
|
| 119 |
+
"grad_norm": 14.207268714904785,
|
| 120 |
+
"learning_rate": 0.0001936511241197055,
|
| 121 |
+
"loss": 2.3949,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5862068965517241,
|
| 126 |
+
"grad_norm": 8.849273681640625,
|
| 127 |
+
"learning_rate": 0.00019264940672148018,
|
| 128 |
+
"loss": 2.5911,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6206896551724138,
|
| 133 |
+
"grad_norm": 8.518115043640137,
|
| 134 |
+
"learning_rate": 0.00019157733266550575,
|
| 135 |
+
"loss": 2.4848,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6551724137931034,
|
| 140 |
+
"grad_norm": 8.173165321350098,
|
| 141 |
+
"learning_rate": 0.00019043571606975777,
|
| 142 |
+
"loss": 2.3583,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6896551724137931,
|
| 147 |
+
"grad_norm": 12.429973602294922,
|
| 148 |
+
"learning_rate": 0.0001892254238618394,
|
| 149 |
+
"loss": 2.5529,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.7241379310344828,
|
| 154 |
+
"grad_norm": 7.970499515533447,
|
| 155 |
+
"learning_rate": 0.0001879473751206489,
|
| 156 |
+
"loss": 2.3048,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.7586206896551724,
|
| 161 |
+
"grad_norm": 10.235267639160156,
|
| 162 |
+
"learning_rate": 0.00018660254037844388,
|
| 163 |
+
"loss": 2.5431,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.7931034482758621,
|
| 168 |
+
"grad_norm": 9.780701637268066,
|
| 169 |
+
"learning_rate": 0.00018519194088383273,
|
| 170 |
+
"loss": 2.4017,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.8275862068965517,
|
| 175 |
+
"grad_norm": 8.484028816223145,
|
| 176 |
+
"learning_rate": 0.00018371664782625287,
|
| 177 |
+
"loss": 2.3989,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.8620689655172413,
|
| 182 |
+
"grad_norm": 8.875442504882812,
|
| 183 |
+
"learning_rate": 0.0001821777815225245,
|
| 184 |
+
"loss": 2.3733,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.896551724137931,
|
| 189 |
+
"grad_norm": 7.790247440338135,
|
| 190 |
+
"learning_rate": 0.00018057651056609784,
|
| 191 |
+
"loss": 2.4949,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.9310344827586207,
|
| 196 |
+
"grad_norm": 9.66124439239502,
|
| 197 |
+
"learning_rate": 0.00017891405093963938,
|
| 198 |
+
"loss": 2.6426,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.9655172413793104,
|
| 203 |
+
"grad_norm": 10.793170928955078,
|
| 204 |
+
"learning_rate": 0.0001771916650916321,
|
| 205 |
+
"loss": 2.4486,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.0,
|
| 210 |
+
"grad_norm": 11.640007019042969,
|
| 211 |
+
"learning_rate": 0.00017541066097768963,
|
| 212 |
+
"loss": 2.5085,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.0344827586206897,
|
| 217 |
+
"grad_norm": 7.754225254058838,
|
| 218 |
+
"learning_rate": 0.00017357239106731317,
|
| 219 |
+
"loss": 1.2804,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.0689655172413792,
|
| 224 |
+
"grad_norm": 6.376781463623047,
|
| 225 |
+
"learning_rate": 0.00017167825131684513,
|
| 226 |
+
"loss": 0.914,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.103448275862069,
|
| 231 |
+
"grad_norm": 7.635883808135986,
|
| 232 |
+
"learning_rate": 0.00016972968010939954,
|
| 233 |
+
"loss": 0.9803,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.1379310344827587,
|
| 238 |
+
"grad_norm": 8.3922119140625,
|
| 239 |
+
"learning_rate": 0.00016772815716257412,
|
| 240 |
+
"loss": 1.1827,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.1724137931034484,
|
| 245 |
+
"grad_norm": 40.731563568115234,
|
| 246 |
+
"learning_rate": 0.00016567520240477344,
|
| 247 |
+
"loss": 1.0468,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.206896551724138,
|
| 252 |
+
"grad_norm": 8.111652374267578,
|
| 253 |
+
"learning_rate": 0.00016357237482099684,
|
| 254 |
+
"loss": 0.9133,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.2413793103448276,
|
| 259 |
+
"grad_norm": 11.691572189331055,
|
| 260 |
+
"learning_rate": 0.0001614212712689668,
|
| 261 |
+
"loss": 1.3907,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.2758620689655173,
|
| 266 |
+
"grad_norm": 13.854535102844238,
|
| 267 |
+
"learning_rate": 0.00015922352526649803,
|
| 268 |
+
"loss": 1.1896,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.3103448275862069,
|
| 273 |
+
"grad_norm": 13.816670417785645,
|
| 274 |
+
"learning_rate": 0.00015698080575102661,
|
| 275 |
+
"loss": 1.4907,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.3448275862068966,
|
| 280 |
+
"grad_norm": 9.702868461608887,
|
| 281 |
+
"learning_rate": 0.00015469481581224272,
|
| 282 |
+
"loss": 1.4863,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.3793103448275863,
|
| 287 |
+
"grad_norm": 6.986519813537598,
|
| 288 |
+
"learning_rate": 0.00015236729139878782,
|
| 289 |
+
"loss": 1.0933,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.4137931034482758,
|
| 294 |
+
"grad_norm": 5.615776538848877,
|
| 295 |
+
"learning_rate": 0.00015000000000000001,
|
| 296 |
+
"loss": 0.6781,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.4482758620689655,
|
| 301 |
+
"grad_norm": 10.113770484924316,
|
| 302 |
+
"learning_rate": 0.00014759473930370736,
|
| 303 |
+
"loss": 1.2472,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.4827586206896552,
|
| 308 |
+
"grad_norm": 6.870434284210205,
|
| 309 |
+
"learning_rate": 0.00014515333583108896,
|
| 310 |
+
"loss": 1.0049,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.5172413793103448,
|
| 315 |
+
"grad_norm": 8.070581436157227,
|
| 316 |
+
"learning_rate": 0.00014267764354964038,
|
| 317 |
+
"loss": 0.7818,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.5517241379310345,
|
| 322 |
+
"grad_norm": 5.975027084350586,
|
| 323 |
+
"learning_rate": 0.00014016954246529696,
|
| 324 |
+
"loss": 0.7797,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.5862068965517242,
|
| 329 |
+
"grad_norm": 6.494412899017334,
|
| 330 |
+
"learning_rate": 0.00013763093719478358,
|
| 331 |
+
"loss": 0.7939,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.6206896551724137,
|
| 336 |
+
"grad_norm": 7.849338054656982,
|
| 337 |
+
"learning_rate": 0.00013506375551927547,
|
| 338 |
+
"loss": 0.9905,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6551724137931034,
|
| 343 |
+
"grad_norm": 5.65253210067749,
|
| 344 |
+
"learning_rate": 0.00013246994692046836,
|
| 345 |
+
"loss": 0.6874,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.6896551724137931,
|
| 350 |
+
"grad_norm": 7.488522529602051,
|
| 351 |
+
"learning_rate": 0.00012985148110016947,
|
| 352 |
+
"loss": 0.7825,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.7241379310344827,
|
| 357 |
+
"grad_norm": 7.643749237060547,
|
| 358 |
+
"learning_rate": 0.00012721034648453353,
|
| 359 |
+
"loss": 0.748,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.7586206896551724,
|
| 364 |
+
"grad_norm": 9.57530403137207,
|
| 365 |
+
"learning_rate": 0.00012454854871407994,
|
| 366 |
+
"loss": 1.1548,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.793103448275862,
|
| 371 |
+
"grad_norm": 6.273963928222656,
|
| 372 |
+
"learning_rate": 0.0001218681091206376,
|
| 373 |
+
"loss": 0.8975,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.8275862068965516,
|
| 378 |
+
"grad_norm": 5.229036808013916,
|
| 379 |
+
"learning_rate": 0.00011917106319237386,
|
| 380 |
+
"loss": 0.761,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.8620689655172413,
|
| 385 |
+
"grad_norm": 7.955849647521973,
|
| 386 |
+
"learning_rate": 0.00011645945902807341,
|
| 387 |
+
"loss": 0.969,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.896551724137931,
|
| 392 |
+
"grad_norm": 5.826790809631348,
|
| 393 |
+
"learning_rate": 0.00011373535578184082,
|
| 394 |
+
"loss": 0.8425,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.9310344827586206,
|
| 399 |
+
"grad_norm": 7.660434246063232,
|
| 400 |
+
"learning_rate": 0.00011100082209940795,
|
| 401 |
+
"loss": 0.9966,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.9655172413793105,
|
| 406 |
+
"grad_norm": 8.542122840881348,
|
| 407 |
+
"learning_rate": 0.00010825793454723325,
|
| 408 |
+
"loss": 0.9864,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 2.0,
|
| 413 |
+
"grad_norm": 7.020619869232178,
|
| 414 |
+
"learning_rate": 0.00010550877603558655,
|
| 415 |
+
"loss": 0.8995,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.0344827586206895,
|
| 420 |
+
"grad_norm": 3.594993829727173,
|
| 421 |
+
"learning_rate": 0.00010275543423681621,
|
| 422 |
+
"loss": 0.3373,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.0689655172413794,
|
| 427 |
+
"grad_norm": 4.07737398147583,
|
| 428 |
+
"learning_rate": 0.0001,
|
| 429 |
+
"loss": 0.2722,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.103448275862069,
|
| 434 |
+
"grad_norm": 8.188806533813477,
|
| 435 |
+
"learning_rate": 9.724456576318381e-05,
|
| 436 |
+
"loss": 0.3745,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.1379310344827585,
|
| 441 |
+
"grad_norm": 3.8479177951812744,
|
| 442 |
+
"learning_rate": 9.449122396441345e-05,
|
| 443 |
+
"loss": 0.3211,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.1724137931034484,
|
| 448 |
+
"grad_norm": 4.40678596496582,
|
| 449 |
+
"learning_rate": 9.174206545276677e-05,
|
| 450 |
+
"loss": 0.4105,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.206896551724138,
|
| 455 |
+
"grad_norm": 4.841770648956299,
|
| 456 |
+
"learning_rate": 8.899917790059208e-05,
|
| 457 |
+
"loss": 0.4105,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.2413793103448274,
|
| 462 |
+
"grad_norm": 4.570344924926758,
|
| 463 |
+
"learning_rate": 8.626464421815919e-05,
|
| 464 |
+
"loss": 0.4432,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.2758620689655173,
|
| 469 |
+
"grad_norm": 3.0861401557922363,
|
| 470 |
+
"learning_rate": 8.35405409719266e-05,
|
| 471 |
+
"loss": 0.166,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.310344827586207,
|
| 476 |
+
"grad_norm": 3.652515411376953,
|
| 477 |
+
"learning_rate": 8.082893680762619e-05,
|
| 478 |
+
"loss": 0.3771,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.344827586206897,
|
| 483 |
+
"grad_norm": 5.078272342681885,
|
| 484 |
+
"learning_rate": 7.813189087936243e-05,
|
| 485 |
+
"loss": 0.3866,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.3793103448275863,
|
| 490 |
+
"grad_norm": 4.019447326660156,
|
| 491 |
+
"learning_rate": 7.54514512859201e-05,
|
| 492 |
+
"loss": 0.308,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 2.413793103448276,
|
| 497 |
+
"grad_norm": 3.4118640422821045,
|
| 498 |
+
"learning_rate": 7.278965351546648e-05,
|
| 499 |
+
"loss": 0.279,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.4482758620689653,
|
| 504 |
+
"grad_norm": 4.8846306800842285,
|
| 505 |
+
"learning_rate": 7.014851889983057e-05,
|
| 506 |
+
"loss": 0.3636,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.4827586206896552,
|
| 511 |
+
"grad_norm": 4.6204681396484375,
|
| 512 |
+
"learning_rate": 6.753005307953167e-05,
|
| 513 |
+
"loss": 0.4715,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.5172413793103448,
|
| 518 |
+
"grad_norm": 5.812495231628418,
|
| 519 |
+
"learning_rate": 6.493624448072457e-05,
|
| 520 |
+
"loss": 0.4816,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.5517241379310347,
|
| 525 |
+
"grad_norm": 4.512807369232178,
|
| 526 |
+
"learning_rate": 6.236906280521646e-05,
|
| 527 |
+
"loss": 0.1682,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.586206896551724,
|
| 532 |
+
"grad_norm": 4.009202003479004,
|
| 533 |
+
"learning_rate": 5.983045753470308e-05,
|
| 534 |
+
"loss": 0.2126,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 2.6206896551724137,
|
| 539 |
+
"grad_norm": 3.059624671936035,
|
| 540 |
+
"learning_rate": 5.732235645035964e-05,
|
| 541 |
+
"loss": 0.2485,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.655172413793103,
|
| 546 |
+
"grad_norm": 3.4690215587615967,
|
| 547 |
+
"learning_rate": 5.484666416891109e-05,
|
| 548 |
+
"loss": 0.2998,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.689655172413793,
|
| 553 |
+
"grad_norm": 5.230517387390137,
|
| 554 |
+
"learning_rate": 5.240526069629265e-05,
|
| 555 |
+
"loss": 0.34,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.7241379310344827,
|
| 560 |
+
"grad_norm": 4.850966930389404,
|
| 561 |
+
"learning_rate": 5.000000000000002e-05,
|
| 562 |
+
"loss": 0.5199,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.7586206896551726,
|
| 567 |
+
"grad_norm": 8.064337730407715,
|
| 568 |
+
"learning_rate": 4.763270860121222e-05,
|
| 569 |
+
"loss": 0.5783,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.793103448275862,
|
| 574 |
+
"grad_norm": 5.194494724273682,
|
| 575 |
+
"learning_rate": 4.530518418775733e-05,
|
| 576 |
+
"loss": 0.391,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.8275862068965516,
|
| 581 |
+
"grad_norm": 3.3784008026123047,
|
| 582 |
+
"learning_rate": 4.301919424897338e-05,
|
| 583 |
+
"loss": 0.2587,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.862068965517241,
|
| 588 |
+
"grad_norm": 3.8429758548736572,
|
| 589 |
+
"learning_rate": 4.077647473350201e-05,
|
| 590 |
+
"loss": 0.3064,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.896551724137931,
|
| 595 |
+
"grad_norm": 3.0566534996032715,
|
| 596 |
+
"learning_rate": 3.857872873103322e-05,
|
| 597 |
+
"loss": 0.2252,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.9310344827586206,
|
| 602 |
+
"grad_norm": 3.1600985527038574,
|
| 603 |
+
"learning_rate": 3.642762517900322e-05,
|
| 604 |
+
"loss": 0.1679,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 2.9655172413793105,
|
| 609 |
+
"grad_norm": 2.677255392074585,
|
| 610 |
+
"learning_rate": 3.4324797595226565e-05,
|
| 611 |
+
"loss": 0.2209,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 3.0,
|
| 616 |
+
"grad_norm": 4.203759670257568,
|
| 617 |
+
"learning_rate": 3.227184283742591e-05,
|
| 618 |
+
"loss": 0.3377,
|
| 619 |
+
"step": 87
|
| 620 |
+
}
|
| 621 |
+
],
|
| 622 |
+
"logging_steps": 1,
|
| 623 |
+
"max_steps": 116,
|
| 624 |
+
"num_input_tokens_seen": 0,
|
| 625 |
+
"num_train_epochs": 4,
|
| 626 |
+
"save_steps": 500,
|
| 627 |
+
"stateful_callbacks": {
|
| 628 |
+
"TrainerControl": {
|
| 629 |
+
"args": {
|
| 630 |
+
"should_epoch_stop": false,
|
| 631 |
+
"should_evaluate": false,
|
| 632 |
+
"should_log": false,
|
| 633 |
+
"should_save": true,
|
| 634 |
+
"should_training_stop": false
|
| 635 |
+
},
|
| 636 |
+
"attributes": {}
|
| 637 |
+
}
|
| 638 |
+
},
|
| 639 |
+
"total_flos": 537085725376512.0,
|
| 640 |
+
"train_batch_size": 2,
|
| 641 |
+
"trial_name": null,
|
| 642 |
+
"trial_params": null
|
| 643 |
+
}
|
checkpoint-87/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5850f18486da32f4c0d93fa9a10324134011ad7d40e79f7ce9366d71ef9b2851
|
| 3 |
+
size 6584
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 22,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.51.3",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 32000
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 2048,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.51.3"
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3525b8067453b58e2e2d8d85bc2c4424e5ebe2faa1986639929f887d1b174ef6
|
| 3 |
+
size 2462448120
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|