初始化项目，由ModelHub XC社区提供模型
Model: tzchen07/g2_X9e Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
checkpoint-498/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
58
README.md
Normal file
58
README.md
Normal file
@@ -0,0 +1,58 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: other
|
||||||
|
base_model: unsloth/gemma-2-2b-it
|
||||||
|
tags:
|
||||||
|
- llama-factory
|
||||||
|
- full
|
||||||
|
- generated_from_trainer
|
||||||
|
model-index:
|
||||||
|
- name: x9e
|
||||||
|
results: []
|
||||||
|
---
|
||||||
|
|
||||||
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||||
|
should probably proofread and complete it, then remove this comment. -->
|
||||||
|
|
||||||
|
# x9e
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [unsloth/gemma-2-2b-it](https://huggingface.co/unsloth/gemma-2-2b-it) on the v1.6, the v1.6b, the v1.6c, the v1.6d and the v1.6e datasets.
|
||||||
|
|
||||||
|
## Model description
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Intended uses & limitations
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training and evaluation data
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
### Training hyperparameters
|
||||||
|
|
||||||
|
The following hyperparameters were used during training:
|
||||||
|
- learning_rate: 5e-06
|
||||||
|
- train_batch_size: 4
|
||||||
|
- eval_batch_size: 8
|
||||||
|
- seed: 42
|
||||||
|
- gradient_accumulation_steps: 16
|
||||||
|
- total_train_batch_size: 64
|
||||||
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||||
|
- lr_scheduler_type: cosine
|
||||||
|
- lr_scheduler_warmup_ratio: 0.1
|
||||||
|
- num_epochs: 2.0
|
||||||
|
|
||||||
|
### Training results
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- Transformers 4.57.1
|
||||||
|
- Pytorch 2.10.0+cu129
|
||||||
|
- Datasets 4.0.0
|
||||||
|
- Tokenizers 0.22.2
|
||||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 2.0,
|
||||||
|
"total_flos": 1.28494219771102e+18,
|
||||||
|
"train_loss": 0.03479443759803312,
|
||||||
|
"train_runtime": 6147.788,
|
||||||
|
"train_samples_per_second": 5.179,
|
||||||
|
"train_steps_per_second": 0.081
|
||||||
|
}
|
||||||
4
chat_template.jinja
Normal file
4
chat_template.jinja
Normal file
@@ -0,0 +1,4 @@
|
|||||||
|
{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '
|
||||||
|
' + message['content'] | trim + '<end_of_turn>
|
||||||
|
' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
|
||||||
|
'}}{% endif %}
|
||||||
4
checkpoint-498/chat_template.jinja
Normal file
4
checkpoint-498/chat_template.jinja
Normal file
@@ -0,0 +1,4 @@
|
|||||||
|
{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '
|
||||||
|
' + message['content'] | trim + '<end_of_turn>
|
||||||
|
' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
|
||||||
|
'}}{% endif %}
|
||||||
61
checkpoint-498/config.json
Normal file
61
checkpoint-498/config.json
Normal file
@@ -0,0 +1,61 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Gemma2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"attn_logit_softcapping": 50.0,
|
||||||
|
"bos_token_id": 2,
|
||||||
|
"cache_implementation": "hybrid",
|
||||||
|
"dtype": "float32",
|
||||||
|
"eos_token_id": 107,
|
||||||
|
"final_logit_softcapping": 30.0,
|
||||||
|
"head_dim": 256,
|
||||||
|
"hidden_act": "gelu_pytorch_tanh",
|
||||||
|
"hidden_activation": "gelu_pytorch_tanh",
|
||||||
|
"hidden_size": 2304,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 9216,
|
||||||
|
"layer_types": [
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 8192,
|
||||||
|
"model_type": "gemma2",
|
||||||
|
"num_attention_heads": 8,
|
||||||
|
"num_hidden_layers": 26,
|
||||||
|
"num_key_value_heads": 4,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"query_pre_attn_scalar": 256,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_theta": 10000.0,
|
||||||
|
"sliding_window": 4096,
|
||||||
|
"transformers_version": "4.57.1",
|
||||||
|
"unsloth_version": "2024.9",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 256000
|
||||||
|
}
|
||||||
13
checkpoint-498/generation_config.json
Normal file
13
checkpoint-498/generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 2,
|
||||||
|
"cache_implementation": "hybrid",
|
||||||
|
"eos_token_id": [
|
||||||
|
107,
|
||||||
|
1,
|
||||||
|
107
|
||||||
|
],
|
||||||
|
"max_length": 8192,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"transformers_version": "4.57.1"
|
||||||
|
}
|
||||||
3
checkpoint-498/model-00001-of-00003.safetensors
Normal file
3
checkpoint-498/model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:883757107ed628ac68adfc4776742299a9f4152a51109595cf5c4447d889d856
|
||||||
|
size 4992576136
|
||||||
3
checkpoint-498/model-00002-of-00003.safetensors
Normal file
3
checkpoint-498/model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cbfeb36073f11805e2660ec76cc0b38985887e07581fcf923570b5a89d78c536
|
||||||
|
size 4983443424
|
||||||
3
checkpoint-498/model-00003-of-00003.safetensors
Normal file
3
checkpoint-498/model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8e04f476d50568d217d30f29db34ce1a63951758fede234cafef5b20b72af7d3
|
||||||
|
size 481381384
|
||||||
296
checkpoint-498/model.safetensors.index.json
Normal file
296
checkpoint-498/model.safetensors.index.json
Normal file
@@ -0,0 +1,296 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_parameters": 2614341888,
|
||||||
|
"total_size": 10457367552
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
3
checkpoint-498/optimizer.pt
Normal file
3
checkpoint-498/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ec9b92be30bc1d929984a3428f1bb2ec8980159209b8f286ad73c39e778d9f9d
|
||||||
|
size 20914991879
|
||||||
3
checkpoint-498/rng_state.pth
Normal file
3
checkpoint-498/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
|
||||||
|
size 14645
|
||||||
3
checkpoint-498/scheduler.pt
Normal file
3
checkpoint-498/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a1dab4ab977132a8fa31885c15cbac51ab780724467e4072a01a4b087b2d0314
|
||||||
|
size 1465
|
||||||
34
checkpoint-498/special_tokens_map.json
Normal file
34
checkpoint-498/special_tokens_map.json
Normal file
@@ -0,0 +1,34 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<start_of_turn>",
|
||||||
|
"<end_of_turn>"
|
||||||
|
],
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<bos>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<end_of_turn>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<pad>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
checkpoint-498/tokenizer.json
Normal file
3
checkpoint-498/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
|
||||||
|
size 34362873
|
||||||
3
checkpoint-498/tokenizer.model
Normal file
3
checkpoint-498/tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
||||||
|
size 4241003
|
||||||
2015
checkpoint-498/tokenizer_config.json
Normal file
2015
checkpoint-498/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
727
checkpoint-498/trainer_state.json
Normal file
727
checkpoint-498/trainer_state.json
Normal file
@@ -0,0 +1,727 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 2.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 498,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.02009545340366742,
|
||||||
|
"grad_norm": 101.4629135131836,
|
||||||
|
"learning_rate": 4.0000000000000003e-07,
|
||||||
|
"loss": 2.9256,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.04019090680733484,
|
||||||
|
"grad_norm": 83.51904296875,
|
||||||
|
"learning_rate": 9.000000000000001e-07,
|
||||||
|
"loss": 2.7459,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06028636021100226,
|
||||||
|
"grad_norm": 25.10388946533203,
|
||||||
|
"learning_rate": 1.4000000000000001e-06,
|
||||||
|
"loss": 1.637,
|
||||||
|
"step": 15
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.08038181361466969,
|
||||||
|
"grad_norm": 13.024300575256348,
|
||||||
|
"learning_rate": 1.9000000000000002e-06,
|
||||||
|
"loss": 1.1459,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1004772670183371,
|
||||||
|
"grad_norm": 8.315956115722656,
|
||||||
|
"learning_rate": 2.4000000000000003e-06,
|
||||||
|
"loss": 0.7456,
|
||||||
|
"step": 25
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.12057272042200452,
|
||||||
|
"grad_norm": 8.930346488952637,
|
||||||
|
"learning_rate": 2.9e-06,
|
||||||
|
"loss": 0.5717,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.14066817382567195,
|
||||||
|
"grad_norm": 7.356456756591797,
|
||||||
|
"learning_rate": 3.4000000000000005e-06,
|
||||||
|
"loss": 0.414,
|
||||||
|
"step": 35
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.16076362722933937,
|
||||||
|
"grad_norm": 5.648008346557617,
|
||||||
|
"learning_rate": 3.900000000000001e-06,
|
||||||
|
"loss": 0.2577,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1808590806330068,
|
||||||
|
"grad_norm": 6.329988956451416,
|
||||||
|
"learning_rate": 4.4e-06,
|
||||||
|
"loss": 0.2394,
|
||||||
|
"step": 45
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2009545340366742,
|
||||||
|
"grad_norm": 5.1738080978393555,
|
||||||
|
"learning_rate": 4.9000000000000005e-06,
|
||||||
|
"loss": 0.1848,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.22104998744034163,
|
||||||
|
"grad_norm": 4.86478853225708,
|
||||||
|
"learning_rate": 4.999016565957633e-06,
|
||||||
|
"loss": 0.2195,
|
||||||
|
"step": 55
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24114544084400905,
|
||||||
|
"grad_norm": 4.442976474761963,
|
||||||
|
"learning_rate": 4.995022691166621e-06,
|
||||||
|
"loss": 0.1582,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.26124089424767644,
|
||||||
|
"grad_norm": 3.704345941543579,
|
||||||
|
"learning_rate": 4.987961816680493e-06,
|
||||||
|
"loss": 0.183,
|
||||||
|
"step": 65
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2813363476513439,
|
||||||
|
"grad_norm": 3.772160768508911,
|
||||||
|
"learning_rate": 4.977842622059546e-06,
|
||||||
|
"loss": 0.164,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.30143180105501133,
|
||||||
|
"grad_norm": 3.2532081604003906,
|
||||||
|
"learning_rate": 4.96467754629559e-06,
|
||||||
|
"loss": 0.1781,
|
||||||
|
"step": 75
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.32152725445867875,
|
||||||
|
"grad_norm": 2.893615484237671,
|
||||||
|
"learning_rate": 4.948482772521346e-06,
|
||||||
|
"loss": 0.1288,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.34162270786234616,
|
||||||
|
"grad_norm": 4.654979705810547,
|
||||||
|
"learning_rate": 4.929278208117378e-06,
|
||||||
|
"loss": 0.1444,
|
||||||
|
"step": 85
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3617181612660136,
|
||||||
|
"grad_norm": 2.8989882469177246,
|
||||||
|
"learning_rate": 4.907087460240999e-06,
|
||||||
|
"loss": 0.1151,
|
||||||
|
"step": 90
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.381813614669681,
|
||||||
|
"grad_norm": 3.7547988891601562,
|
||||||
|
"learning_rate": 4.881937806807241e-06,
|
||||||
|
"loss": 0.1197,
|
||||||
|
"step": 95
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4019090680733484,
|
||||||
|
"grad_norm": 2.273831605911255,
|
||||||
|
"learning_rate": 4.8538601629575525e-06,
|
||||||
|
"loss": 0.0966,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.42200452147701584,
|
||||||
|
"grad_norm": 2.4642996788024902,
|
||||||
|
"learning_rate": 4.822889043057446e-06,
|
||||||
|
"loss": 0.1088,
|
||||||
|
"step": 105
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.44209997488068326,
|
||||||
|
"grad_norm": 3.29301381111145,
|
||||||
|
"learning_rate": 4.789062518269812e-06,
|
||||||
|
"loss": 0.1163,
|
||||||
|
"step": 110
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4621954282843507,
|
||||||
|
"grad_norm": 2.45603084564209,
|
||||||
|
"learning_rate": 4.752422169756048e-06,
|
||||||
|
"loss": 0.1151,
|
||||||
|
"step": 115
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4822908816880181,
|
||||||
|
"grad_norm": 3.199894666671753,
|
||||||
|
"learning_rate": 4.713013037562531e-06,
|
||||||
|
"loss": 0.098,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5023863350916855,
|
||||||
|
"grad_norm": 1.7128061056137085,
|
||||||
|
"learning_rate": 4.670883565255264e-06,
|
||||||
|
"loss": 0.0968,
|
||||||
|
"step": 125
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5224817884953529,
|
||||||
|
"grad_norm": 2.645235776901245,
|
||||||
|
"learning_rate": 4.6260855403707625e-06,
|
||||||
|
"loss": 0.1068,
|
||||||
|
"step": 130
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5425772418990203,
|
||||||
|
"grad_norm": 2.3140530586242676,
|
||||||
|
"learning_rate": 4.578674030756364e-06,
|
||||||
|
"loss": 0.0914,
|
||||||
|
"step": 135
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5626726953026878,
|
||||||
|
"grad_norm": 1.8588067293167114,
|
||||||
|
"learning_rate": 4.528707316878233e-06,
|
||||||
|
"loss": 0.0995,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5827681487063552,
|
||||||
|
"grad_norm": 1.9172967672348022,
|
||||||
|
"learning_rate": 4.476246820180259e-06,
|
||||||
|
"loss": 0.08,
|
||||||
|
"step": 145
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6028636021100227,
|
||||||
|
"grad_norm": 2.9082584381103516,
|
||||||
|
"learning_rate": 4.421357027581921e-06,
|
||||||
|
"loss": 0.1066,
|
||||||
|
"step": 150
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.62295905551369,
|
||||||
|
"grad_norm": 3.6944031715393066,
|
||||||
|
"learning_rate": 4.364105412207914e-06,
|
||||||
|
"loss": 0.1124,
|
||||||
|
"step": 155
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6430545089173575,
|
||||||
|
"grad_norm": 1.5622600317001343,
|
||||||
|
"learning_rate": 4.304562350447008e-06,
|
||||||
|
"loss": 0.0856,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6631499623210249,
|
||||||
|
"grad_norm": 2.388239860534668,
|
||||||
|
"learning_rate": 4.242801035442059e-06,
|
||||||
|
"loss": 0.0766,
|
||||||
|
"step": 165
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6832454157246923,
|
||||||
|
"grad_norm": 1.7182718515396118,
|
||||||
|
"learning_rate": 4.178897387117547e-06,
|
||||||
|
"loss": 0.104,
|
||||||
|
"step": 170
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7033408691283597,
|
||||||
|
"grad_norm": 2.2367119789123535,
|
||||||
|
"learning_rate": 4.11292995885522e-06,
|
||||||
|
"loss": 0.0737,
|
||||||
|
"step": 175
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7234363225320272,
|
||||||
|
"grad_norm": 2.007200241088867,
|
||||||
|
"learning_rate": 4.044979840932567e-06,
|
||||||
|
"loss": 0.0893,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7435317759356945,
|
||||||
|
"grad_norm": 2.6910905838012695,
|
||||||
|
"learning_rate": 3.975130560842821e-06,
|
||||||
|
"loss": 0.0944,
|
||||||
|
"step": 185
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.763627229339362,
|
||||||
|
"grad_norm": 2.042320489883423,
|
||||||
|
"learning_rate": 3.9034679806190204e-06,
|
||||||
|
"loss": 0.0843,
|
||||||
|
"step": 190
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7837226827430294,
|
||||||
|
"grad_norm": 2.700977087020874,
|
||||||
|
"learning_rate": 3.830080191288342e-06,
|
||||||
|
"loss": 0.0669,
|
||||||
|
"step": 195
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8038181361466968,
|
||||||
|
"grad_norm": 3.0307390689849854,
|
||||||
|
"learning_rate": 3.755057404586455e-06,
|
||||||
|
"loss": 0.0955,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8239135895503642,
|
||||||
|
"grad_norm": 1.0048880577087402,
|
||||||
|
"learning_rate": 3.6784918420649952e-06,
|
||||||
|
"loss": 0.0977,
|
||||||
|
"step": 205
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8440090429540317,
|
||||||
|
"grad_norm": 1.3049492835998535,
|
||||||
|
"learning_rate": 3.600477621728473e-06,
|
||||||
|
"loss": 0.0731,
|
||||||
|
"step": 210
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.864104496357699,
|
||||||
|
"grad_norm": 2.020117998123169,
|
||||||
|
"learning_rate": 3.521110642339991e-06,
|
||||||
|
"loss": 0.0939,
|
||||||
|
"step": 215
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8841999497613665,
|
||||||
|
"grad_norm": 2.2311348915100098,
|
||||||
|
"learning_rate": 3.4404884655379433e-06,
|
||||||
|
"loss": 0.0747,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9042954031650339,
|
||||||
|
"grad_norm": 2.1661417484283447,
|
||||||
|
"learning_rate": 3.358710195908653e-06,
|
||||||
|
"loss": 0.0625,
|
||||||
|
"step": 225
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9243908565687013,
|
||||||
|
"grad_norm": 2.463257074356079,
|
||||||
|
"learning_rate": 3.27587635916233e-06,
|
||||||
|
"loss": 0.1004,
|
||||||
|
"step": 230
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9444863099723687,
|
||||||
|
"grad_norm": 1.5093741416931152,
|
||||||
|
"learning_rate": 3.1920887785621233e-06,
|
||||||
|
"loss": 0.1034,
|
||||||
|
"step": 235
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9645817633760362,
|
||||||
|
"grad_norm": 2.1394777297973633,
|
||||||
|
"learning_rate": 3.10745044975816e-06,
|
||||||
|
"loss": 0.0815,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9846772167797035,
|
||||||
|
"grad_norm": 1.6689902544021606,
|
||||||
|
"learning_rate": 3.022065414180425e-06,
|
||||||
|
"loss": 0.0887,
|
||||||
|
"step": 245
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0040190906807336,
|
||||||
|
"grad_norm": 1.9693433046340942,
|
||||||
|
"learning_rate": 2.9360386311461276e-06,
|
||||||
|
"loss": 0.0972,
|
||||||
|
"step": 250
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0241145440844008,
|
||||||
|
"grad_norm": 0.750286340713501,
|
||||||
|
"learning_rate": 2.849475848838749e-06,
|
||||||
|
"loss": 0.0546,
|
||||||
|
"step": 255
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0442099974880683,
|
||||||
|
"grad_norm": 3.802541732788086,
|
||||||
|
"learning_rate": 2.762483474317387e-06,
|
||||||
|
"loss": 0.0601,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0643054508917358,
|
||||||
|
"grad_norm": 1.3461735248565674,
|
||||||
|
"learning_rate": 2.6751684427161684e-06,
|
||||||
|
"loss": 0.0596,
|
||||||
|
"step": 265
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0844009042954033,
|
||||||
|
"grad_norm": 2.324124813079834,
|
||||||
|
"learning_rate": 2.587638085794541e-06,
|
||||||
|
"loss": 0.0577,
|
||||||
|
"step": 270
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1044963576990705,
|
||||||
|
"grad_norm": 1.4222259521484375,
|
||||||
|
"learning_rate": 2.5e-06,
|
||||||
|
"loss": 0.0527,
|
||||||
|
"step": 275
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.124591811102738,
|
||||||
|
"grad_norm": 0.48392441868782043,
|
||||||
|
"learning_rate": 2.41236191420546e-06,
|
||||||
|
"loss": 0.0592,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1446872645064055,
|
||||||
|
"grad_norm": 1.6113179922103882,
|
||||||
|
"learning_rate": 2.3248315572838316e-06,
|
||||||
|
"loss": 0.0552,
|
||||||
|
"step": 285
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.164782717910073,
|
||||||
|
"grad_norm": 2.1131763458251953,
|
||||||
|
"learning_rate": 2.237516525682614e-06,
|
||||||
|
"loss": 0.0601,
|
||||||
|
"step": 290
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1848781713137402,
|
||||||
|
"grad_norm": 1.010076880455017,
|
||||||
|
"learning_rate": 2.1505241511612522e-06,
|
||||||
|
"loss": 0.0601,
|
||||||
|
"step": 295
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2049736247174077,
|
||||||
|
"grad_norm": 1.5603766441345215,
|
||||||
|
"learning_rate": 2.0639613688538733e-06,
|
||||||
|
"loss": 0.0626,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2250690781210751,
|
||||||
|
"grad_norm": 0.9277430176734924,
|
||||||
|
"learning_rate": 1.9779345858195757e-06,
|
||||||
|
"loss": 0.049,
|
||||||
|
"step": 305
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2451645315247426,
|
||||||
|
"grad_norm": 1.768437147140503,
|
||||||
|
"learning_rate": 1.8925495502418407e-06,
|
||||||
|
"loss": 0.055,
|
||||||
|
"step": 310
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2652599849284099,
|
||||||
|
"grad_norm": 1.4469853639602661,
|
||||||
|
"learning_rate": 1.8079112214378769e-06,
|
||||||
|
"loss": 0.0608,
|
||||||
|
"step": 315
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2853554383320773,
|
||||||
|
"grad_norm": 1.503761649131775,
|
||||||
|
"learning_rate": 1.7241236408376702e-06,
|
||||||
|
"loss": 0.0526,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3054508917357448,
|
||||||
|
"grad_norm": 1.1352767944335938,
|
||||||
|
"learning_rate": 1.6412898040913471e-06,
|
||||||
|
"loss": 0.0509,
|
||||||
|
"step": 325
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3255463451394123,
|
||||||
|
"grad_norm": 2.6707780361175537,
|
||||||
|
"learning_rate": 1.5595115344620575e-06,
|
||||||
|
"loss": 0.0631,
|
||||||
|
"step": 330
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3456417985430797,
|
||||||
|
"grad_norm": 1.1756007671356201,
|
||||||
|
"learning_rate": 1.47888935766001e-06,
|
||||||
|
"loss": 0.0524,
|
||||||
|
"step": 335
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.365737251946747,
|
||||||
|
"grad_norm": 1.0455981492996216,
|
||||||
|
"learning_rate": 1.399522378271527e-06,
|
||||||
|
"loss": 0.0507,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3858327053504145,
|
||||||
|
"grad_norm": 0.7072739601135254,
|
||||||
|
"learning_rate": 1.3215081579350058e-06,
|
||||||
|
"loss": 0.0487,
|
||||||
|
"step": 345
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.405928158754082,
|
||||||
|
"grad_norm": 1.145075798034668,
|
||||||
|
"learning_rate": 1.2449425954135452e-06,
|
||||||
|
"loss": 0.0544,
|
||||||
|
"step": 350
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4260236121577492,
|
||||||
|
"grad_norm": 1.4399057626724243,
|
||||||
|
"learning_rate": 1.169919808711659e-06,
|
||||||
|
"loss": 0.0606,
|
||||||
|
"step": 355
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4461190655614167,
|
||||||
|
"grad_norm": 1.0342814922332764,
|
||||||
|
"learning_rate": 1.0965320193809808e-06,
|
||||||
|
"loss": 0.0547,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4662145189650841,
|
||||||
|
"grad_norm": 0.5163133144378662,
|
||||||
|
"learning_rate": 1.02486943915718e-06,
|
||||||
|
"loss": 0.0534,
|
||||||
|
"step": 365
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4863099723687516,
|
||||||
|
"grad_norm": 1.0042380094528198,
|
||||||
|
"learning_rate": 9.550201590674343e-07,
|
||||||
|
"loss": 0.0541,
|
||||||
|
"step": 370
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.506405425772419,
|
||||||
|
"grad_norm": 1.1944531202316284,
|
||||||
|
"learning_rate": 8.870700411447817e-07,
|
||||||
|
"loss": 0.0501,
|
||||||
|
"step": 375
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5265008791760866,
|
||||||
|
"grad_norm": 1.3594350814819336,
|
||||||
|
"learning_rate": 8.21102612882454e-07,
|
||||||
|
"loss": 0.0611,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5465963325797538,
|
||||||
|
"grad_norm": 1.2450895309448242,
|
||||||
|
"learning_rate": 7.57198964557942e-07,
|
||||||
|
"loss": 0.0505,
|
||||||
|
"step": 385
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5666917859834213,
|
||||||
|
"grad_norm": 1.6389065980911255,
|
||||||
|
"learning_rate": 6.954376495529927e-07,
|
||||||
|
"loss": 0.0473,
|
||||||
|
"step": 390
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5867872393870885,
|
||||||
|
"grad_norm": 2.077847719192505,
|
||||||
|
"learning_rate": 6.358945877920861e-07,
|
||||||
|
"loss": 0.0519,
|
||||||
|
"step": 395
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.606882692790756,
|
||||||
|
"grad_norm": 1.5446641445159912,
|
||||||
|
"learning_rate": 5.786429724180801e-07,
|
||||||
|
"loss": 0.0491,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6269781461944235,
|
||||||
|
"grad_norm": 1.4639307260513306,
|
||||||
|
"learning_rate": 5.237531798197415e-07,
|
||||||
|
"loss": 0.0441,
|
||||||
|
"step": 405
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.647073599598091,
|
||||||
|
"grad_norm": 1.4568461179733276,
|
||||||
|
"learning_rate": 4.712926831217685e-07,
|
||||||
|
"loss": 0.054,
|
||||||
|
"step": 410
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6671690530017584,
|
||||||
|
"grad_norm": 1.6878377199172974,
|
||||||
|
"learning_rate": 4.2132596924363666e-07,
|
||||||
|
"loss": 0.047,
|
||||||
|
"step": 415
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.687264506405426,
|
||||||
|
"grad_norm": 0.9864447116851807,
|
||||||
|
"learning_rate": 3.7391445962923824e-07,
|
||||||
|
"loss": 0.0503,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7073599598090932,
|
||||||
|
"grad_norm": 0.9351651668548584,
|
||||||
|
"learning_rate": 3.2911643474473647e-07,
|
||||||
|
"loss": 0.0456,
|
||||||
|
"step": 425
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7274554132127606,
|
||||||
|
"grad_norm": 0.9683827757835388,
|
||||||
|
"learning_rate": 2.869869624374699e-07,
|
||||||
|
"loss": 0.0535,
|
||||||
|
"step": 430
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.747550866616428,
|
||||||
|
"grad_norm": 1.0934531688690186,
|
||||||
|
"learning_rate": 2.4757783024395244e-07,
|
||||||
|
"loss": 0.0481,
|
||||||
|
"step": 435
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7676463200200954,
|
||||||
|
"grad_norm": 1.5016802549362183,
|
||||||
|
"learning_rate": 2.1093748173018846e-07,
|
||||||
|
"loss": 0.0519,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7877417734237628,
|
||||||
|
"grad_norm": 1.4125523567199707,
|
||||||
|
"learning_rate": 1.771109569425547e-07,
|
||||||
|
"loss": 0.0523,
|
||||||
|
"step": 445
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8078372268274303,
|
||||||
|
"grad_norm": 1.1559640169143677,
|
||||||
|
"learning_rate": 1.4613983704244826e-07,
|
||||||
|
"loss": 0.0454,
|
||||||
|
"step": 450
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8279326802310978,
|
||||||
|
"grad_norm": 1.0382763147354126,
|
||||||
|
"learning_rate": 1.1806219319275918e-07,
|
||||||
|
"loss": 0.046,
|
||||||
|
"step": 455
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8480281336347653,
|
||||||
|
"grad_norm": 1.4664262533187866,
|
||||||
|
"learning_rate": 9.291253975900138e-08,
|
||||||
|
"loss": 0.0529,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8681235870384325,
|
||||||
|
"grad_norm": 0.8224850296974182,
|
||||||
|
"learning_rate": 7.072179188262252e-08,
|
||||||
|
"loss": 0.0389,
|
||||||
|
"step": 465
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8882190404421,
|
||||||
|
"grad_norm": 0.5471680760383606,
|
||||||
|
"learning_rate": 5.151722747865434e-08,
|
||||||
|
"loss": 0.0489,
|
||||||
|
"step": 470
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9083144938457672,
|
||||||
|
"grad_norm": 0.9190619587898254,
|
||||||
|
"learning_rate": 3.5322453704410286e-08,
|
||||||
|
"loss": 0.0438,
|
||||||
|
"step": 475
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9284099472494347,
|
||||||
|
"grad_norm": 0.8270437121391296,
|
||||||
|
"learning_rate": 2.215737794045436e-08,
|
||||||
|
"loss": 0.0448,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9485054006531022,
|
||||||
|
"grad_norm": 0.6661733388900757,
|
||||||
|
"learning_rate": 1.2038183319507957e-08,
|
||||||
|
"loss": 0.0436,
|
||||||
|
"step": 485
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9686008540567697,
|
||||||
|
"grad_norm": 0.7018892168998718,
|
||||||
|
"learning_rate": 4.977308833379324e-09,
|
||||||
|
"loss": 0.0419,
|
||||||
|
"step": 490
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9886963074604371,
|
||||||
|
"grad_norm": 0.8652178645133972,
|
||||||
|
"learning_rate": 9.834340423678368e-10,
|
||||||
|
"loss": 0.048,
|
||||||
|
"step": 495
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 5,
|
||||||
|
"max_steps": 498,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 2,
|
||||||
|
"save_steps": 200,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 1.28494219771102e+18,
|
||||||
|
"train_batch_size": 4,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
checkpoint-498/training_args.bin
Normal file
3
checkpoint-498/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:62f0adb9f98878d5918d58cd798bf85ae88dd0ed2328bb63223e8143e2502520
|
||||||
|
size 6225
|
||||||
61
config.json
Normal file
61
config.json
Normal file
@@ -0,0 +1,61 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Gemma2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"attn_logit_softcapping": 50.0,
|
||||||
|
"bos_token_id": 2,
|
||||||
|
"cache_implementation": "hybrid",
|
||||||
|
"dtype": "float32",
|
||||||
|
"eos_token_id": 107,
|
||||||
|
"final_logit_softcapping": 30.0,
|
||||||
|
"head_dim": 256,
|
||||||
|
"hidden_act": "gelu_pytorch_tanh",
|
||||||
|
"hidden_activation": "gelu_pytorch_tanh",
|
||||||
|
"hidden_size": 2304,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 9216,
|
||||||
|
"layer_types": [
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention",
|
||||||
|
"sliding_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 8192,
|
||||||
|
"model_type": "gemma2",
|
||||||
|
"num_attention_heads": 8,
|
||||||
|
"num_hidden_layers": 26,
|
||||||
|
"num_key_value_heads": 4,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"query_pre_attn_scalar": 256,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_theta": 10000.0,
|
||||||
|
"sliding_window": 4096,
|
||||||
|
"transformers_version": "4.57.1",
|
||||||
|
"unsloth_version": "2024.9",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 256000
|
||||||
|
}
|
||||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 2,
|
||||||
|
"cache_implementation": "hybrid",
|
||||||
|
"eos_token_id": [
|
||||||
|
107,
|
||||||
|
1,
|
||||||
|
107
|
||||||
|
],
|
||||||
|
"max_length": 8192,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"transformers_version": "4.57.1"
|
||||||
|
}
|
||||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:883757107ed628ac68adfc4776742299a9f4152a51109595cf5c4447d889d856
|
||||||
|
size 4992576136
|
||||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cbfeb36073f11805e2660ec76cc0b38985887e07581fcf923570b5a89d78c536
|
||||||
|
size 4983443424
|
||||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8e04f476d50568d217d30f29db34ce1a63951758fede234cafef5b20b72af7d3
|
||||||
|
size 481381384
|
||||||
296
model.safetensors.index.json
Normal file
296
model.safetensors.index.json
Normal file
@@ -0,0 +1,296 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_parameters": 2614341888,
|
||||||
|
"total_size": 10457367552
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||||
|
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
34
special_tokens_map.json
Normal file
34
special_tokens_map.json
Normal file
@@ -0,0 +1,34 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<start_of_turn>",
|
||||||
|
"<end_of_turn>"
|
||||||
|
],
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<bos>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<end_of_turn>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<pad>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
|
||||||
|
size 34362873
|
||||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
||||||
|
size 4241003
|
||||||
2015
tokenizer_config.json
Normal file
2015
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 2.0,
|
||||||
|
"total_flos": 1.28494219771102e+18,
|
||||||
|
"train_loss": 0.03479443759803312,
|
||||||
|
"train_runtime": 6147.788,
|
||||||
|
"train_samples_per_second": 5.179,
|
||||||
|
"train_steps_per_second": 0.081
|
||||||
|
}
|
||||||
60
trainer_log.jsonl
Normal file
60
trainer_log.jsonl
Normal file
@@ -0,0 +1,60 @@
|
|||||||
|
{"current_steps": 205, "total_steps": 498, "loss": 0.0977, "lr": 3.6784918420649952e-06, "epoch": 0.8239135895503642, "percentage": 41.16, "elapsed_time": "0:01:41", "remaining_time": "0:02:24"}
|
||||||
|
{"current_steps": 210, "total_steps": 498, "loss": 0.0731, "lr": 3.600477621728473e-06, "epoch": 0.8440090429540317, "percentage": 42.17, "elapsed_time": "0:03:21", "remaining_time": "0:04:36"}
|
||||||
|
{"current_steps": 215, "total_steps": 498, "loss": 0.0939, "lr": 3.521110642339991e-06, "epoch": 0.864104496357699, "percentage": 43.17, "elapsed_time": "0:05:03", "remaining_time": "0:06:39"}
|
||||||
|
{"current_steps": 220, "total_steps": 498, "loss": 0.0747, "lr": 3.4404884655379433e-06, "epoch": 0.8841999497613665, "percentage": 44.18, "elapsed_time": "0:06:43", "remaining_time": "0:08:30"}
|
||||||
|
{"current_steps": 225, "total_steps": 498, "loss": 0.0625, "lr": 3.358710195908653e-06, "epoch": 0.9042954031650339, "percentage": 45.18, "elapsed_time": "0:08:26", "remaining_time": "0:10:15"}
|
||||||
|
{"current_steps": 230, "total_steps": 498, "loss": 0.1004, "lr": 3.27587635916233e-06, "epoch": 0.9243908565687013, "percentage": 46.18, "elapsed_time": "0:10:07", "remaining_time": "0:11:48"}
|
||||||
|
{"current_steps": 235, "total_steps": 498, "loss": 0.1034, "lr": 3.1920887785621233e-06, "epoch": 0.9444863099723687, "percentage": 47.19, "elapsed_time": "0:11:51", "remaining_time": "0:13:16"}
|
||||||
|
{"current_steps": 240, "total_steps": 498, "loss": 0.0815, "lr": 3.10745044975816e-06, "epoch": 0.9645817633760362, "percentage": 48.19, "elapsed_time": "0:13:33", "remaining_time": "0:14:34"}
|
||||||
|
{"current_steps": 245, "total_steps": 498, "loss": 0.0887, "lr": 3.022065414180425e-06, "epoch": 0.9846772167797035, "percentage": 49.2, "elapsed_time": "0:15:13", "remaining_time": "0:15:42"}
|
||||||
|
{"current_steps": 250, "total_steps": 498, "loss": 0.0972, "lr": 2.9360386311461276e-06, "epoch": 1.0040190906807336, "percentage": 50.2, "elapsed_time": "0:16:52", "remaining_time": "0:16:43"}
|
||||||
|
{"current_steps": 255, "total_steps": 498, "loss": 0.0546, "lr": 2.849475848838749e-06, "epoch": 1.0241145440844008, "percentage": 51.2, "elapsed_time": "0:18:30", "remaining_time": "0:17:38"}
|
||||||
|
{"current_steps": 260, "total_steps": 498, "loss": 0.0601, "lr": 2.762483474317387e-06, "epoch": 1.0442099974880683, "percentage": 52.21, "elapsed_time": "0:20:09", "remaining_time": "0:18:27"}
|
||||||
|
{"current_steps": 265, "total_steps": 498, "loss": 0.0596, "lr": 2.6751684427161684e-06, "epoch": 1.0643054508917358, "percentage": 53.21, "elapsed_time": "0:21:51", "remaining_time": "0:19:12"}
|
||||||
|
{"current_steps": 270, "total_steps": 498, "loss": 0.0577, "lr": 2.587638085794541e-06, "epoch": 1.0844009042954033, "percentage": 54.22, "elapsed_time": "0:23:31", "remaining_time": "0:19:52"}
|
||||||
|
{"current_steps": 275, "total_steps": 498, "loss": 0.0527, "lr": 2.5e-06, "epoch": 1.1044963576990705, "percentage": 55.22, "elapsed_time": "0:25:11", "remaining_time": "0:20:25"}
|
||||||
|
{"current_steps": 280, "total_steps": 498, "loss": 0.0592, "lr": 2.41236191420546e-06, "epoch": 1.124591811102738, "percentage": 56.22, "elapsed_time": "0:26:52", "remaining_time": "0:20:55"}
|
||||||
|
{"current_steps": 285, "total_steps": 498, "loss": 0.0552, "lr": 2.3248315572838316e-06, "epoch": 1.1446872645064055, "percentage": 57.23, "elapsed_time": "0:28:33", "remaining_time": "0:21:20"}
|
||||||
|
{"current_steps": 290, "total_steps": 498, "loss": 0.0601, "lr": 2.237516525682614e-06, "epoch": 1.164782717910073, "percentage": 58.23, "elapsed_time": "0:30:13", "remaining_time": "0:21:40"}
|
||||||
|
{"current_steps": 295, "total_steps": 498, "loss": 0.0601, "lr": 2.1505241511612522e-06, "epoch": 1.1848781713137402, "percentage": 59.24, "elapsed_time": "0:31:57", "remaining_time": "0:21:59"}
|
||||||
|
{"current_steps": 300, "total_steps": 498, "loss": 0.0626, "lr": 2.0639613688538733e-06, "epoch": 1.2049736247174077, "percentage": 60.24, "elapsed_time": "0:33:42", "remaining_time": "0:22:14"}
|
||||||
|
{"current_steps": 305, "total_steps": 498, "loss": 0.049, "lr": 1.9779345858195757e-06, "epoch": 1.2250690781210751, "percentage": 61.24, "elapsed_time": "0:35:25", "remaining_time": "0:22:24"}
|
||||||
|
{"current_steps": 310, "total_steps": 498, "loss": 0.055, "lr": 1.8925495502418407e-06, "epoch": 1.2451645315247426, "percentage": 62.25, "elapsed_time": "0:37:07", "remaining_time": "0:22:30"}
|
||||||
|
{"current_steps": 315, "total_steps": 498, "loss": 0.0608, "lr": 1.8079112214378769e-06, "epoch": 1.2652599849284099, "percentage": 63.25, "elapsed_time": "0:38:48", "remaining_time": "0:22:32"}
|
||||||
|
{"current_steps": 320, "total_steps": 498, "loss": 0.0526, "lr": 1.7241236408376702e-06, "epoch": 1.2853554383320773, "percentage": 64.26, "elapsed_time": "0:40:27", "remaining_time": "0:22:30"}
|
||||||
|
{"current_steps": 325, "total_steps": 498, "loss": 0.0509, "lr": 1.6412898040913471e-06, "epoch": 1.3054508917357448, "percentage": 65.26, "elapsed_time": "0:42:09", "remaining_time": "0:22:26"}
|
||||||
|
{"current_steps": 330, "total_steps": 498, "loss": 0.0631, "lr": 1.5595115344620575e-06, "epoch": 1.3255463451394123, "percentage": 66.27, "elapsed_time": "0:43:54", "remaining_time": "0:22:21"}
|
||||||
|
{"current_steps": 335, "total_steps": 498, "loss": 0.0524, "lr": 1.47888935766001e-06, "epoch": 1.3456417985430797, "percentage": 67.27, "elapsed_time": "0:45:37", "remaining_time": "0:22:11"}
|
||||||
|
{"current_steps": 340, "total_steps": 498, "loss": 0.0507, "lr": 1.399522378271527e-06, "epoch": 1.365737251946747, "percentage": 68.27, "elapsed_time": "0:47:16", "remaining_time": "0:21:58"}
|
||||||
|
{"current_steps": 345, "total_steps": 498, "loss": 0.0487, "lr": 1.3215081579350058e-06, "epoch": 1.3858327053504145, "percentage": 69.28, "elapsed_time": "0:48:58", "remaining_time": "0:21:43"}
|
||||||
|
{"current_steps": 350, "total_steps": 498, "loss": 0.0544, "lr": 1.2449425954135452e-06, "epoch": 1.405928158754082, "percentage": 70.28, "elapsed_time": "0:50:38", "remaining_time": "0:21:25"}
|
||||||
|
{"current_steps": 355, "total_steps": 498, "loss": 0.0606, "lr": 1.169919808711659e-06, "epoch": 1.4260236121577492, "percentage": 71.29, "elapsed_time": "0:52:20", "remaining_time": "0:21:05"}
|
||||||
|
{"current_steps": 360, "total_steps": 498, "loss": 0.0547, "lr": 1.0965320193809808e-06, "epoch": 1.4461190655614167, "percentage": 72.29, "elapsed_time": "0:54:03", "remaining_time": "0:20:43"}
|
||||||
|
{"current_steps": 365, "total_steps": 498, "loss": 0.0534, "lr": 1.02486943915718e-06, "epoch": 1.4662145189650841, "percentage": 73.29, "elapsed_time": "0:55:45", "remaining_time": "0:20:18"}
|
||||||
|
{"current_steps": 370, "total_steps": 498, "loss": 0.0541, "lr": 9.550201590674343e-07, "epoch": 1.4863099723687516, "percentage": 74.3, "elapsed_time": "0:57:29", "remaining_time": "0:19:53"}
|
||||||
|
{"current_steps": 375, "total_steps": 498, "loss": 0.0501, "lr": 8.870700411447817e-07, "epoch": 1.506405425772419, "percentage": 75.3, "elapsed_time": "0:59:15", "remaining_time": "0:19:26"}
|
||||||
|
{"current_steps": 380, "total_steps": 498, "loss": 0.0611, "lr": 8.21102612882454e-07, "epoch": 1.5265008791760866, "percentage": 76.31, "elapsed_time": "1:01:00", "remaining_time": "0:18:56"}
|
||||||
|
{"current_steps": 385, "total_steps": 498, "loss": 0.0505, "lr": 7.57198964557942e-07, "epoch": 1.5465963325797538, "percentage": 77.31, "elapsed_time": "1:02:43", "remaining_time": "0:18:24"}
|
||||||
|
{"current_steps": 390, "total_steps": 498, "loss": 0.0473, "lr": 6.954376495529927e-07, "epoch": 1.5666917859834213, "percentage": 78.31, "elapsed_time": "1:04:23", "remaining_time": "0:17:49"}
|
||||||
|
{"current_steps": 395, "total_steps": 498, "loss": 0.0519, "lr": 6.358945877920861e-07, "epoch": 1.5867872393870885, "percentage": 79.32, "elapsed_time": "1:06:04", "remaining_time": "0:17:13"}
|
||||||
|
{"current_steps": 400, "total_steps": 498, "loss": 0.0491, "lr": 5.786429724180801e-07, "epoch": 1.606882692790756, "percentage": 80.32, "elapsed_time": "1:07:48", "remaining_time": "0:16:36"}
|
||||||
|
{"current_steps": 405, "total_steps": 498, "loss": 0.0441, "lr": 5.237531798197415e-07, "epoch": 1.6269781461944235, "percentage": 81.33, "elapsed_time": "1:10:07", "remaining_time": "0:16:06"}
|
||||||
|
{"current_steps": 410, "total_steps": 498, "loss": 0.054, "lr": 4.712926831217685e-07, "epoch": 1.647073599598091, "percentage": 82.33, "elapsed_time": "1:11:47", "remaining_time": "0:15:24"}
|
||||||
|
{"current_steps": 415, "total_steps": 498, "loss": 0.047, "lr": 4.2132596924363666e-07, "epoch": 1.6671690530017584, "percentage": 83.33, "elapsed_time": "1:13:30", "remaining_time": "0:14:42"}
|
||||||
|
{"current_steps": 420, "total_steps": 498, "loss": 0.0503, "lr": 3.7391445962923824e-07, "epoch": 1.687264506405426, "percentage": 84.34, "elapsed_time": "1:15:14", "remaining_time": "0:13:58"}
|
||||||
|
{"current_steps": 425, "total_steps": 498, "loss": 0.0456, "lr": 3.2911643474473647e-07, "epoch": 1.7073599598090932, "percentage": 85.34, "elapsed_time": "1:16:56", "remaining_time": "0:13:12"}
|
||||||
|
{"current_steps": 430, "total_steps": 498, "loss": 0.0535, "lr": 2.869869624374699e-07, "epoch": 1.7274554132127606, "percentage": 86.35, "elapsed_time": "1:18:36", "remaining_time": "0:12:25"}
|
||||||
|
{"current_steps": 435, "total_steps": 498, "loss": 0.0481, "lr": 2.4757783024395244e-07, "epoch": 1.747550866616428, "percentage": 87.35, "elapsed_time": "1:20:19", "remaining_time": "0:11:37"}
|
||||||
|
{"current_steps": 440, "total_steps": 498, "loss": 0.0519, "lr": 2.1093748173018846e-07, "epoch": 1.7676463200200954, "percentage": 88.35, "elapsed_time": "1:22:01", "remaining_time": "0:10:48"}
|
||||||
|
{"current_steps": 445, "total_steps": 498, "loss": 0.0523, "lr": 1.771109569425547e-07, "epoch": 1.7877417734237628, "percentage": 89.36, "elapsed_time": "1:23:43", "remaining_time": "0:09:58"}
|
||||||
|
{"current_steps": 450, "total_steps": 498, "loss": 0.0454, "lr": 1.4613983704244826e-07, "epoch": 1.8078372268274303, "percentage": 90.36, "elapsed_time": "1:25:25", "remaining_time": "0:09:06"}
|
||||||
|
{"current_steps": 455, "total_steps": 498, "loss": 0.046, "lr": 1.1806219319275918e-07, "epoch": 1.8279326802310978, "percentage": 91.37, "elapsed_time": "1:27:04", "remaining_time": "0:08:13"}
|
||||||
|
{"current_steps": 460, "total_steps": 498, "loss": 0.0529, "lr": 9.291253975900138e-08, "epoch": 1.8480281336347653, "percentage": 92.37, "elapsed_time": "1:28:51", "remaining_time": "0:07:20"}
|
||||||
|
{"current_steps": 465, "total_steps": 498, "loss": 0.0389, "lr": 7.072179188262252e-08, "epoch": 1.8681235870384325, "percentage": 93.37, "elapsed_time": "1:30:35", "remaining_time": "0:06:25"}
|
||||||
|
{"current_steps": 470, "total_steps": 498, "loss": 0.0489, "lr": 5.151722747865434e-08, "epoch": 1.8882190404421, "percentage": 94.38, "elapsed_time": "1:32:14", "remaining_time": "0:05:29"}
|
||||||
|
{"current_steps": 475, "total_steps": 498, "loss": 0.0438, "lr": 3.5322453704410286e-08, "epoch": 1.9083144938457672, "percentage": 95.38, "elapsed_time": "1:33:56", "remaining_time": "0:04:32"}
|
||||||
|
{"current_steps": 480, "total_steps": 498, "loss": 0.0448, "lr": 2.215737794045436e-08, "epoch": 1.9284099472494347, "percentage": 96.39, "elapsed_time": "1:35:43", "remaining_time": "0:03:35"}
|
||||||
|
{"current_steps": 485, "total_steps": 498, "loss": 0.0436, "lr": 1.2038183319507957e-08, "epoch": 1.9485054006531022, "percentage": 97.39, "elapsed_time": "1:37:25", "remaining_time": "0:02:36"}
|
||||||
|
{"current_steps": 490, "total_steps": 498, "loss": 0.0419, "lr": 4.977308833379324e-09, "epoch": 1.9686008540567697, "percentage": 98.39, "elapsed_time": "1:39:07", "remaining_time": "0:01:37"}
|
||||||
|
{"current_steps": 495, "total_steps": 498, "loss": 0.048, "lr": 9.834340423678368e-10, "epoch": 1.9886963074604371, "percentage": 99.4, "elapsed_time": "1:40:50", "remaining_time": "0:00:36"}
|
||||||
|
{"current_steps": 498, "total_steps": 498, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "1:42:27", "remaining_time": "0:00:00"}
|
||||||
736
trainer_state.json
Normal file
736
trainer_state.json
Normal file
@@ -0,0 +1,736 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 2.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 498,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.02009545340366742,
|
||||||
|
"grad_norm": 101.4629135131836,
|
||||||
|
"learning_rate": 4.0000000000000003e-07,
|
||||||
|
"loss": 2.9256,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.04019090680733484,
|
||||||
|
"grad_norm": 83.51904296875,
|
||||||
|
"learning_rate": 9.000000000000001e-07,
|
||||||
|
"loss": 2.7459,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06028636021100226,
|
||||||
|
"grad_norm": 25.10388946533203,
|
||||||
|
"learning_rate": 1.4000000000000001e-06,
|
||||||
|
"loss": 1.637,
|
||||||
|
"step": 15
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.08038181361466969,
|
||||||
|
"grad_norm": 13.024300575256348,
|
||||||
|
"learning_rate": 1.9000000000000002e-06,
|
||||||
|
"loss": 1.1459,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1004772670183371,
|
||||||
|
"grad_norm": 8.315956115722656,
|
||||||
|
"learning_rate": 2.4000000000000003e-06,
|
||||||
|
"loss": 0.7456,
|
||||||
|
"step": 25
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.12057272042200452,
|
||||||
|
"grad_norm": 8.930346488952637,
|
||||||
|
"learning_rate": 2.9e-06,
|
||||||
|
"loss": 0.5717,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.14066817382567195,
|
||||||
|
"grad_norm": 7.356456756591797,
|
||||||
|
"learning_rate": 3.4000000000000005e-06,
|
||||||
|
"loss": 0.414,
|
||||||
|
"step": 35
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.16076362722933937,
|
||||||
|
"grad_norm": 5.648008346557617,
|
||||||
|
"learning_rate": 3.900000000000001e-06,
|
||||||
|
"loss": 0.2577,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1808590806330068,
|
||||||
|
"grad_norm": 6.329988956451416,
|
||||||
|
"learning_rate": 4.4e-06,
|
||||||
|
"loss": 0.2394,
|
||||||
|
"step": 45
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2009545340366742,
|
||||||
|
"grad_norm": 5.1738080978393555,
|
||||||
|
"learning_rate": 4.9000000000000005e-06,
|
||||||
|
"loss": 0.1848,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.22104998744034163,
|
||||||
|
"grad_norm": 4.86478853225708,
|
||||||
|
"learning_rate": 4.999016565957633e-06,
|
||||||
|
"loss": 0.2195,
|
||||||
|
"step": 55
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24114544084400905,
|
||||||
|
"grad_norm": 4.442976474761963,
|
||||||
|
"learning_rate": 4.995022691166621e-06,
|
||||||
|
"loss": 0.1582,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.26124089424767644,
|
||||||
|
"grad_norm": 3.704345941543579,
|
||||||
|
"learning_rate": 4.987961816680493e-06,
|
||||||
|
"loss": 0.183,
|
||||||
|
"step": 65
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2813363476513439,
|
||||||
|
"grad_norm": 3.772160768508911,
|
||||||
|
"learning_rate": 4.977842622059546e-06,
|
||||||
|
"loss": 0.164,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.30143180105501133,
|
||||||
|
"grad_norm": 3.2532081604003906,
|
||||||
|
"learning_rate": 4.96467754629559e-06,
|
||||||
|
"loss": 0.1781,
|
||||||
|
"step": 75
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.32152725445867875,
|
||||||
|
"grad_norm": 2.893615484237671,
|
||||||
|
"learning_rate": 4.948482772521346e-06,
|
||||||
|
"loss": 0.1288,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.34162270786234616,
|
||||||
|
"grad_norm": 4.654979705810547,
|
||||||
|
"learning_rate": 4.929278208117378e-06,
|
||||||
|
"loss": 0.1444,
|
||||||
|
"step": 85
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3617181612660136,
|
||||||
|
"grad_norm": 2.8989882469177246,
|
||||||
|
"learning_rate": 4.907087460240999e-06,
|
||||||
|
"loss": 0.1151,
|
||||||
|
"step": 90
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.381813614669681,
|
||||||
|
"grad_norm": 3.7547988891601562,
|
||||||
|
"learning_rate": 4.881937806807241e-06,
|
||||||
|
"loss": 0.1197,
|
||||||
|
"step": 95
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4019090680733484,
|
||||||
|
"grad_norm": 2.273831605911255,
|
||||||
|
"learning_rate": 4.8538601629575525e-06,
|
||||||
|
"loss": 0.0966,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.42200452147701584,
|
||||||
|
"grad_norm": 2.4642996788024902,
|
||||||
|
"learning_rate": 4.822889043057446e-06,
|
||||||
|
"loss": 0.1088,
|
||||||
|
"step": 105
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.44209997488068326,
|
||||||
|
"grad_norm": 3.29301381111145,
|
||||||
|
"learning_rate": 4.789062518269812e-06,
|
||||||
|
"loss": 0.1163,
|
||||||
|
"step": 110
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4621954282843507,
|
||||||
|
"grad_norm": 2.45603084564209,
|
||||||
|
"learning_rate": 4.752422169756048e-06,
|
||||||
|
"loss": 0.1151,
|
||||||
|
"step": 115
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4822908816880181,
|
||||||
|
"grad_norm": 3.199894666671753,
|
||||||
|
"learning_rate": 4.713013037562531e-06,
|
||||||
|
"loss": 0.098,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5023863350916855,
|
||||||
|
"grad_norm": 1.7128061056137085,
|
||||||
|
"learning_rate": 4.670883565255264e-06,
|
||||||
|
"loss": 0.0968,
|
||||||
|
"step": 125
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5224817884953529,
|
||||||
|
"grad_norm": 2.645235776901245,
|
||||||
|
"learning_rate": 4.6260855403707625e-06,
|
||||||
|
"loss": 0.1068,
|
||||||
|
"step": 130
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5425772418990203,
|
||||||
|
"grad_norm": 2.3140530586242676,
|
||||||
|
"learning_rate": 4.578674030756364e-06,
|
||||||
|
"loss": 0.0914,
|
||||||
|
"step": 135
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5626726953026878,
|
||||||
|
"grad_norm": 1.8588067293167114,
|
||||||
|
"learning_rate": 4.528707316878233e-06,
|
||||||
|
"loss": 0.0995,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5827681487063552,
|
||||||
|
"grad_norm": 1.9172967672348022,
|
||||||
|
"learning_rate": 4.476246820180259e-06,
|
||||||
|
"loss": 0.08,
|
||||||
|
"step": 145
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6028636021100227,
|
||||||
|
"grad_norm": 2.9082584381103516,
|
||||||
|
"learning_rate": 4.421357027581921e-06,
|
||||||
|
"loss": 0.1066,
|
||||||
|
"step": 150
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.62295905551369,
|
||||||
|
"grad_norm": 3.6944031715393066,
|
||||||
|
"learning_rate": 4.364105412207914e-06,
|
||||||
|
"loss": 0.1124,
|
||||||
|
"step": 155
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6430545089173575,
|
||||||
|
"grad_norm": 1.5622600317001343,
|
||||||
|
"learning_rate": 4.304562350447008e-06,
|
||||||
|
"loss": 0.0856,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6631499623210249,
|
||||||
|
"grad_norm": 2.388239860534668,
|
||||||
|
"learning_rate": 4.242801035442059e-06,
|
||||||
|
"loss": 0.0766,
|
||||||
|
"step": 165
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6832454157246923,
|
||||||
|
"grad_norm": 1.7182718515396118,
|
||||||
|
"learning_rate": 4.178897387117547e-06,
|
||||||
|
"loss": 0.104,
|
||||||
|
"step": 170
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7033408691283597,
|
||||||
|
"grad_norm": 2.2367119789123535,
|
||||||
|
"learning_rate": 4.11292995885522e-06,
|
||||||
|
"loss": 0.0737,
|
||||||
|
"step": 175
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7234363225320272,
|
||||||
|
"grad_norm": 2.007200241088867,
|
||||||
|
"learning_rate": 4.044979840932567e-06,
|
||||||
|
"loss": 0.0893,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7435317759356945,
|
||||||
|
"grad_norm": 2.6910905838012695,
|
||||||
|
"learning_rate": 3.975130560842821e-06,
|
||||||
|
"loss": 0.0944,
|
||||||
|
"step": 185
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.763627229339362,
|
||||||
|
"grad_norm": 2.042320489883423,
|
||||||
|
"learning_rate": 3.9034679806190204e-06,
|
||||||
|
"loss": 0.0843,
|
||||||
|
"step": 190
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7837226827430294,
|
||||||
|
"grad_norm": 2.700977087020874,
|
||||||
|
"learning_rate": 3.830080191288342e-06,
|
||||||
|
"loss": 0.0669,
|
||||||
|
"step": 195
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8038181361466968,
|
||||||
|
"grad_norm": 3.0307390689849854,
|
||||||
|
"learning_rate": 3.755057404586455e-06,
|
||||||
|
"loss": 0.0955,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8239135895503642,
|
||||||
|
"grad_norm": 1.0048880577087402,
|
||||||
|
"learning_rate": 3.6784918420649952e-06,
|
||||||
|
"loss": 0.0977,
|
||||||
|
"step": 205
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8440090429540317,
|
||||||
|
"grad_norm": 1.3049492835998535,
|
||||||
|
"learning_rate": 3.600477621728473e-06,
|
||||||
|
"loss": 0.0731,
|
||||||
|
"step": 210
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.864104496357699,
|
||||||
|
"grad_norm": 2.020117998123169,
|
||||||
|
"learning_rate": 3.521110642339991e-06,
|
||||||
|
"loss": 0.0939,
|
||||||
|
"step": 215
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8841999497613665,
|
||||||
|
"grad_norm": 2.2311348915100098,
|
||||||
|
"learning_rate": 3.4404884655379433e-06,
|
||||||
|
"loss": 0.0747,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9042954031650339,
|
||||||
|
"grad_norm": 2.1661417484283447,
|
||||||
|
"learning_rate": 3.358710195908653e-06,
|
||||||
|
"loss": 0.0625,
|
||||||
|
"step": 225
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9243908565687013,
|
||||||
|
"grad_norm": 2.463257074356079,
|
||||||
|
"learning_rate": 3.27587635916233e-06,
|
||||||
|
"loss": 0.1004,
|
||||||
|
"step": 230
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9444863099723687,
|
||||||
|
"grad_norm": 1.5093741416931152,
|
||||||
|
"learning_rate": 3.1920887785621233e-06,
|
||||||
|
"loss": 0.1034,
|
||||||
|
"step": 235
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9645817633760362,
|
||||||
|
"grad_norm": 2.1394777297973633,
|
||||||
|
"learning_rate": 3.10745044975816e-06,
|
||||||
|
"loss": 0.0815,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9846772167797035,
|
||||||
|
"grad_norm": 1.6689902544021606,
|
||||||
|
"learning_rate": 3.022065414180425e-06,
|
||||||
|
"loss": 0.0887,
|
||||||
|
"step": 245
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0040190906807336,
|
||||||
|
"grad_norm": 1.9693433046340942,
|
||||||
|
"learning_rate": 2.9360386311461276e-06,
|
||||||
|
"loss": 0.0972,
|
||||||
|
"step": 250
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0241145440844008,
|
||||||
|
"grad_norm": 0.750286340713501,
|
||||||
|
"learning_rate": 2.849475848838749e-06,
|
||||||
|
"loss": 0.0546,
|
||||||
|
"step": 255
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0442099974880683,
|
||||||
|
"grad_norm": 3.802541732788086,
|
||||||
|
"learning_rate": 2.762483474317387e-06,
|
||||||
|
"loss": 0.0601,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0643054508917358,
|
||||||
|
"grad_norm": 1.3461735248565674,
|
||||||
|
"learning_rate": 2.6751684427161684e-06,
|
||||||
|
"loss": 0.0596,
|
||||||
|
"step": 265
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0844009042954033,
|
||||||
|
"grad_norm": 2.324124813079834,
|
||||||
|
"learning_rate": 2.587638085794541e-06,
|
||||||
|
"loss": 0.0577,
|
||||||
|
"step": 270
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1044963576990705,
|
||||||
|
"grad_norm": 1.4222259521484375,
|
||||||
|
"learning_rate": 2.5e-06,
|
||||||
|
"loss": 0.0527,
|
||||||
|
"step": 275
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.124591811102738,
|
||||||
|
"grad_norm": 0.48392441868782043,
|
||||||
|
"learning_rate": 2.41236191420546e-06,
|
||||||
|
"loss": 0.0592,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1446872645064055,
|
||||||
|
"grad_norm": 1.6113179922103882,
|
||||||
|
"learning_rate": 2.3248315572838316e-06,
|
||||||
|
"loss": 0.0552,
|
||||||
|
"step": 285
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.164782717910073,
|
||||||
|
"grad_norm": 2.1131763458251953,
|
||||||
|
"learning_rate": 2.237516525682614e-06,
|
||||||
|
"loss": 0.0601,
|
||||||
|
"step": 290
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1848781713137402,
|
||||||
|
"grad_norm": 1.010076880455017,
|
||||||
|
"learning_rate": 2.1505241511612522e-06,
|
||||||
|
"loss": 0.0601,
|
||||||
|
"step": 295
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2049736247174077,
|
||||||
|
"grad_norm": 1.5603766441345215,
|
||||||
|
"learning_rate": 2.0639613688538733e-06,
|
||||||
|
"loss": 0.0626,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2250690781210751,
|
||||||
|
"grad_norm": 0.9277430176734924,
|
||||||
|
"learning_rate": 1.9779345858195757e-06,
|
||||||
|
"loss": 0.049,
|
||||||
|
"step": 305
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2451645315247426,
|
||||||
|
"grad_norm": 1.768437147140503,
|
||||||
|
"learning_rate": 1.8925495502418407e-06,
|
||||||
|
"loss": 0.055,
|
||||||
|
"step": 310
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2652599849284099,
|
||||||
|
"grad_norm": 1.4469853639602661,
|
||||||
|
"learning_rate": 1.8079112214378769e-06,
|
||||||
|
"loss": 0.0608,
|
||||||
|
"step": 315
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2853554383320773,
|
||||||
|
"grad_norm": 1.503761649131775,
|
||||||
|
"learning_rate": 1.7241236408376702e-06,
|
||||||
|
"loss": 0.0526,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3054508917357448,
|
||||||
|
"grad_norm": 1.1352767944335938,
|
||||||
|
"learning_rate": 1.6412898040913471e-06,
|
||||||
|
"loss": 0.0509,
|
||||||
|
"step": 325
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3255463451394123,
|
||||||
|
"grad_norm": 2.6707780361175537,
|
||||||
|
"learning_rate": 1.5595115344620575e-06,
|
||||||
|
"loss": 0.0631,
|
||||||
|
"step": 330
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3456417985430797,
|
||||||
|
"grad_norm": 1.1756007671356201,
|
||||||
|
"learning_rate": 1.47888935766001e-06,
|
||||||
|
"loss": 0.0524,
|
||||||
|
"step": 335
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.365737251946747,
|
||||||
|
"grad_norm": 1.0455981492996216,
|
||||||
|
"learning_rate": 1.399522378271527e-06,
|
||||||
|
"loss": 0.0507,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3858327053504145,
|
||||||
|
"grad_norm": 0.7072739601135254,
|
||||||
|
"learning_rate": 1.3215081579350058e-06,
|
||||||
|
"loss": 0.0487,
|
||||||
|
"step": 345
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.405928158754082,
|
||||||
|
"grad_norm": 1.145075798034668,
|
||||||
|
"learning_rate": 1.2449425954135452e-06,
|
||||||
|
"loss": 0.0544,
|
||||||
|
"step": 350
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4260236121577492,
|
||||||
|
"grad_norm": 1.4399057626724243,
|
||||||
|
"learning_rate": 1.169919808711659e-06,
|
||||||
|
"loss": 0.0606,
|
||||||
|
"step": 355
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4461190655614167,
|
||||||
|
"grad_norm": 1.0342814922332764,
|
||||||
|
"learning_rate": 1.0965320193809808e-06,
|
||||||
|
"loss": 0.0547,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4662145189650841,
|
||||||
|
"grad_norm": 0.5163133144378662,
|
||||||
|
"learning_rate": 1.02486943915718e-06,
|
||||||
|
"loss": 0.0534,
|
||||||
|
"step": 365
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4863099723687516,
|
||||||
|
"grad_norm": 1.0042380094528198,
|
||||||
|
"learning_rate": 9.550201590674343e-07,
|
||||||
|
"loss": 0.0541,
|
||||||
|
"step": 370
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.506405425772419,
|
||||||
|
"grad_norm": 1.1944531202316284,
|
||||||
|
"learning_rate": 8.870700411447817e-07,
|
||||||
|
"loss": 0.0501,
|
||||||
|
"step": 375
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5265008791760866,
|
||||||
|
"grad_norm": 1.3594350814819336,
|
||||||
|
"learning_rate": 8.21102612882454e-07,
|
||||||
|
"loss": 0.0611,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5465963325797538,
|
||||||
|
"grad_norm": 1.2450895309448242,
|
||||||
|
"learning_rate": 7.57198964557942e-07,
|
||||||
|
"loss": 0.0505,
|
||||||
|
"step": 385
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5666917859834213,
|
||||||
|
"grad_norm": 1.6389065980911255,
|
||||||
|
"learning_rate": 6.954376495529927e-07,
|
||||||
|
"loss": 0.0473,
|
||||||
|
"step": 390
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5867872393870885,
|
||||||
|
"grad_norm": 2.077847719192505,
|
||||||
|
"learning_rate": 6.358945877920861e-07,
|
||||||
|
"loss": 0.0519,
|
||||||
|
"step": 395
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.606882692790756,
|
||||||
|
"grad_norm": 1.5446641445159912,
|
||||||
|
"learning_rate": 5.786429724180801e-07,
|
||||||
|
"loss": 0.0491,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6269781461944235,
|
||||||
|
"grad_norm": 1.4639307260513306,
|
||||||
|
"learning_rate": 5.237531798197415e-07,
|
||||||
|
"loss": 0.0441,
|
||||||
|
"step": 405
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.647073599598091,
|
||||||
|
"grad_norm": 1.4568461179733276,
|
||||||
|
"learning_rate": 4.712926831217685e-07,
|
||||||
|
"loss": 0.054,
|
||||||
|
"step": 410
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6671690530017584,
|
||||||
|
"grad_norm": 1.6878377199172974,
|
||||||
|
"learning_rate": 4.2132596924363666e-07,
|
||||||
|
"loss": 0.047,
|
||||||
|
"step": 415
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.687264506405426,
|
||||||
|
"grad_norm": 0.9864447116851807,
|
||||||
|
"learning_rate": 3.7391445962923824e-07,
|
||||||
|
"loss": 0.0503,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7073599598090932,
|
||||||
|
"grad_norm": 0.9351651668548584,
|
||||||
|
"learning_rate": 3.2911643474473647e-07,
|
||||||
|
"loss": 0.0456,
|
||||||
|
"step": 425
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7274554132127606,
|
||||||
|
"grad_norm": 0.9683827757835388,
|
||||||
|
"learning_rate": 2.869869624374699e-07,
|
||||||
|
"loss": 0.0535,
|
||||||
|
"step": 430
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.747550866616428,
|
||||||
|
"grad_norm": 1.0934531688690186,
|
||||||
|
"learning_rate": 2.4757783024395244e-07,
|
||||||
|
"loss": 0.0481,
|
||||||
|
"step": 435
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7676463200200954,
|
||||||
|
"grad_norm": 1.5016802549362183,
|
||||||
|
"learning_rate": 2.1093748173018846e-07,
|
||||||
|
"loss": 0.0519,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7877417734237628,
|
||||||
|
"grad_norm": 1.4125523567199707,
|
||||||
|
"learning_rate": 1.771109569425547e-07,
|
||||||
|
"loss": 0.0523,
|
||||||
|
"step": 445
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8078372268274303,
|
||||||
|
"grad_norm": 1.1559640169143677,
|
||||||
|
"learning_rate": 1.4613983704244826e-07,
|
||||||
|
"loss": 0.0454,
|
||||||
|
"step": 450
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8279326802310978,
|
||||||
|
"grad_norm": 1.0382763147354126,
|
||||||
|
"learning_rate": 1.1806219319275918e-07,
|
||||||
|
"loss": 0.046,
|
||||||
|
"step": 455
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8480281336347653,
|
||||||
|
"grad_norm": 1.4664262533187866,
|
||||||
|
"learning_rate": 9.291253975900138e-08,
|
||||||
|
"loss": 0.0529,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8681235870384325,
|
||||||
|
"grad_norm": 0.8224850296974182,
|
||||||
|
"learning_rate": 7.072179188262252e-08,
|
||||||
|
"loss": 0.0389,
|
||||||
|
"step": 465
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8882190404421,
|
||||||
|
"grad_norm": 0.5471680760383606,
|
||||||
|
"learning_rate": 5.151722747865434e-08,
|
||||||
|
"loss": 0.0489,
|
||||||
|
"step": 470
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9083144938457672,
|
||||||
|
"grad_norm": 0.9190619587898254,
|
||||||
|
"learning_rate": 3.5322453704410286e-08,
|
||||||
|
"loss": 0.0438,
|
||||||
|
"step": 475
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9284099472494347,
|
||||||
|
"grad_norm": 0.8270437121391296,
|
||||||
|
"learning_rate": 2.215737794045436e-08,
|
||||||
|
"loss": 0.0448,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9485054006531022,
|
||||||
|
"grad_norm": 0.6661733388900757,
|
||||||
|
"learning_rate": 1.2038183319507957e-08,
|
||||||
|
"loss": 0.0436,
|
||||||
|
"step": 485
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9686008540567697,
|
||||||
|
"grad_norm": 0.7018892168998718,
|
||||||
|
"learning_rate": 4.977308833379324e-09,
|
||||||
|
"loss": 0.0419,
|
||||||
|
"step": 490
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9886963074604371,
|
||||||
|
"grad_norm": 0.8652178645133972,
|
||||||
|
"learning_rate": 9.834340423678368e-10,
|
||||||
|
"loss": 0.048,
|
||||||
|
"step": 495
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.0,
|
||||||
|
"step": 498,
|
||||||
|
"total_flos": 1.28494219771102e+18,
|
||||||
|
"train_loss": 0.03479443759803312,
|
||||||
|
"train_runtime": 6147.788,
|
||||||
|
"train_samples_per_second": 5.179,
|
||||||
|
"train_steps_per_second": 0.081
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 5,
|
||||||
|
"max_steps": 498,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 2,
|
||||||
|
"save_steps": 200,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 1.28494219771102e+18,
|
||||||
|
"train_batch_size": 4,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:62f0adb9f98878d5918d58cd798bf85ae88dd0ed2328bb63223e8143e2502520
|
||||||
|
size 6225
|
||||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 31 KiB |
Reference in New Issue
Block a user