初始化项目，由ModelHub XC社区提供模型
Model: argilla/zephyr-7b-spin-iter3-v0 Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
||||
*.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
|
||||
model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
100
README.md
Normal file
100
README.md
Normal file
@@ -0,0 +1,100 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: argilla/zephyr-7b-spin-iter2-v0
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: zephyr-7b-spin-iter3-v0
|
||||
results: []
|
||||
datasets:
|
||||
- argilla/10k_prompts_SPIN_iter3_zephyr_top
|
||||
- argilla/10k_prompts_SPIN_iter2_zephyr_top
|
||||
- DIBT/10k_prompts_ranked
|
||||
---
|
||||
|
||||
<!-- 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. -->
|
||||
|
||||
# zephyr-7b-spin-iter3-v0
|
||||
|
||||
> A model matching the results of SPIN with very little data (30x less), carefully curated by the amazing [Data Is Better Together community](https://huggingface.co/DIBT)
|
||||
|
||||
<div>
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/60420dccc15e823a685f2b03/aEzpD6gvn0xOrN2rNzpZI.webp">
|
||||
</div>
|
||||
|
||||
|
||||
<p align="center">
|
||||
<a href="https://github.com/argilla-io/distilabel">
|
||||
<img src="https://raw.githubusercontent.com/argilla-io/distilabel/main/docs/assets/distilabel-badge-light.png" alt="Built with Distilabel" width="200" height="32"/>
|
||||
</a>
|
||||
</p>
|
||||
|
||||
This model is a fine-tuned version of [argilla/zephyr-7b-spin-iter2-v0](https://huggingface.co/argilla/zephyr-7b-spin-iter2-v0) on the
|
||||
[argilla/10k_prompts_SPIN_iter3_zephyr_top](https://huggingface.co/datasets/argilla/10k_prompts_SPIN_iter3_zephyr_top) and the
|
||||
[argilla/10k_prompts_SPIN_iter2_zephyr_top](https://huggingface.co/datasets/argilla/10k_prompts_SPIN_iter2_zephyr_top) dataset.
|
||||
|
||||
Check [this repo](https://github.com/argilla-io/distilabel-spin-dibt) for full reproducible code using the original SPIN implementation and distilabel.
|
||||
|
||||
If you want to contribute to high quality datasets like this, contribute to the [DIBT prompt collective initiative](https://huggingface.co/spaces/DIBT/prompt-collective-dashboard).
|
||||
|
||||
|
||||
## MT-Bench results
|
||||
|
||||
| Model | 1st Turn Score | 2nd Turn Score | Average Score | SPIN paper Score |
|
||||
|-------------------------|----------------|----------------|---------------|------------------|
|
||||
| zephyr-7b-sft-full | 6.6625 | 6.0250 | 6.34375 | 5.94 |
|
||||
| zephyr-7b-spin-iter0-v0 | 6.64375 | 6.1750 | 6.409375 | 6.46 |
|
||||
| zephyr-7b-spin-iter1-v0 | 6.90625 | 6.3000 | 6.603125 | 6.65 |
|
||||
| zephyr-7b-spin-iter2-v0 | **7.1375** | 6.3125 | 6.725000 | 6.78 |
|
||||
| zephyr-7b-spin-iter3-v0 | 7.09375 | **6.4500** | **6.771875** | - |
|
||||
|
||||
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 1e-07
|
||||
- train_batch_size: 8
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 4
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 64
|
||||
- total_eval_batch_size: 32
|
||||
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
||||
- lr_scheduler_type: linear
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 2.0
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss | Rewards/real | Rewards/generated | Rewards/accuracies | Rewards/margins | Logps/generated | Logps/real | Logits/generated | Logits/real |
|
||||
|:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------------:|:------------------:|:---------------:|:---------------:|:----------:|:----------------:|:-----------:|
|
||||
| 0.2928 | 0.49 | 25 | 0.3951 | -2.6212 | -20.3268 | 0.9062 | 17.7056 | -700.5638 | -278.0876 | -2.8098 | -2.8090 |
|
||||
| 0.1487 | 0.97 | 50 | 0.1319 | -2.9077 | -29.1459 | 0.9375 | 26.2382 | -702.3276 | -278.1449 | -2.8218 | -2.8066 |
|
||||
| 0.006 | 1.46 | 75 | 0.1269 | -2.6037 | -29.1519 | 0.9583 | 26.5482 | -702.3289 | -278.0841 | -2.8175 | -2.8037 |
|
||||
| 0.0086 | 1.94 | 100 | 0.1099 | -2.9181 | -29.6970 | 0.9271 | 26.7789 | -702.4378 | -278.1470 | -2.8177 | -2.8051 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.37.0
|
||||
- Pytorch 2.1.2+cu121
|
||||
- Datasets 2.14.6
|
||||
- Tokenizers 0.15.2
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.98,
|
||||
"train_loss": 0.1742458962578573,
|
||||
"train_runtime": 2590.1164,
|
||||
"train_samples": 3296,
|
||||
"train_samples_per_second": 2.545,
|
||||
"train_steps_per_second": 0.039
|
||||
}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "plaguss/zephyr-7b-spin-iter2-v0",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.37.0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.37.0"
|
||||
}
|
||||
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:d7ff4ce11c67e15a74bdced2857f247219f6d717c7a745efdf77cb2c5e0b5bfd
|
||||
size 4943162336
|
||||
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:f1b2e6888d9714ab406b70141affcde42af62ef635d809e9c047ec04d2a1fb5b
|
||||
size 4999819336
|
||||
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:fb0d66e326b5f6c239ab28b5feb6fefc38262e43e830c75fbb97179b361d3360
|
||||
size 4540516344
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14483464192
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors",
|
||||
"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.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.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-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-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.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.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.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.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.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.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.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.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.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.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.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.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-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-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-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-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-00003-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.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-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.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.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.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.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.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-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.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.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.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.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-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-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-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
43
tokenizer_config.json
Normal file
43
tokenizer_config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.98,
|
||||
"train_loss": 0.1742458962578573,
|
||||
"train_runtime": 2590.1164,
|
||||
"train_samples": 3296,
|
||||
"train_samples_per_second": 2.545,
|
||||
"train_steps_per_second": 0.039
|
||||
}
|
||||
248
trainer_state.json
Normal file
248
trainer_state.json
Normal file
@@ -0,0 +1,248 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.9805825242718447,
|
||||
"eval_steps": 25,
|
||||
"global_step": 102,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.02,
|
||||
"learning_rate": 9.09090909090909e-09,
|
||||
"logits/generated": -2.911376476287842,
|
||||
"logits/real": -2.89278507232666,
|
||||
"logps/generated": -668.016845703125,
|
||||
"logps/real": -324.0830383300781,
|
||||
"loss": 0.6931,
|
||||
"rewards/accuracies": 0.0,
|
||||
"rewards/generated": 0.0,
|
||||
"rewards/margins": 0.0,
|
||||
"rewards/real": 0.0,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.19,
|
||||
"learning_rate": 9.09090909090909e-08,
|
||||
"logits/generated": -2.848540782928467,
|
||||
"logits/real": -2.8350822925567627,
|
||||
"logps/generated": -617.5262451171875,
|
||||
"logps/real": -255.12559509277344,
|
||||
"loss": 0.8027,
|
||||
"rewards/accuracies": 0.6527777910232544,
|
||||
"rewards/generated": -6.766346454620361,
|
||||
"rewards/margins": 4.9929962158203125,
|
||||
"rewards/real": -1.7733497619628906,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.39,
|
||||
"learning_rate": 9.010989010989011e-08,
|
||||
"logits/generated": -2.8388895988464355,
|
||||
"logits/real": -2.8330814838409424,
|
||||
"logps/generated": -707.9961547851562,
|
||||
"logps/real": -283.4620056152344,
|
||||
"loss": 0.2928,
|
||||
"rewards/accuracies": 0.9125000238418579,
|
||||
"rewards/generated": -20.150367736816406,
|
||||
"rewards/margins": 17.525970458984375,
|
||||
"rewards/real": -2.6243953704833984,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.49,
|
||||
"eval_logits/generated": -2.8098323345184326,
|
||||
"eval_logits/real": -2.8089659214019775,
|
||||
"eval_logps/generated": -700.5637817382812,
|
||||
"eval_logps/real": -278.0876159667969,
|
||||
"eval_loss": 0.3950892686843872,
|
||||
"eval_rewards/accuracies": 0.90625,
|
||||
"eval_rewards/generated": -20.326812744140625,
|
||||
"eval_rewards/margins": 17.705642700195312,
|
||||
"eval_rewards/real": -2.6211698055267334,
|
||||
"eval_runtime": 75.909,
|
||||
"eval_samples_per_second": 4.848,
|
||||
"eval_steps_per_second": 0.158,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.58,
|
||||
"learning_rate": 7.912087912087911e-08,
|
||||
"logits/generated": -2.877678394317627,
|
||||
"logits/real": -2.8707680702209473,
|
||||
"logps/generated": -755.6437377929688,
|
||||
"logps/real": -290.04058837890625,
|
||||
"loss": 0.2615,
|
||||
"rewards/accuracies": 0.96875,
|
||||
"rewards/generated": -25.02899742126465,
|
||||
"rewards/margins": 23.474206924438477,
|
||||
"rewards/real": -1.5547949075698853,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.78,
|
||||
"learning_rate": 6.813186813186813e-08,
|
||||
"logits/generated": -2.839968681335449,
|
||||
"logits/real": -2.8121862411499023,
|
||||
"logps/generated": -673.220703125,
|
||||
"logps/real": -257.77001953125,
|
||||
"loss": 0.1816,
|
||||
"rewards/accuracies": 0.956250011920929,
|
||||
"rewards/generated": -24.732364654541016,
|
||||
"rewards/margins": 26.96199607849121,
|
||||
"rewards/real": 2.2296276092529297,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.97,
|
||||
"learning_rate": 5.714285714285714e-08,
|
||||
"logits/generated": -2.8406929969787598,
|
||||
"logits/real": -2.8268864154815674,
|
||||
"logps/generated": -727.8557739257812,
|
||||
"logps/real": -274.7761535644531,
|
||||
"loss": 0.1487,
|
||||
"rewards/accuracies": 0.981249988079071,
|
||||
"rewards/generated": -29.384685516357422,
|
||||
"rewards/margins": 30.1076717376709,
|
||||
"rewards/real": 0.7229812145233154,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.97,
|
||||
"eval_logits/generated": -2.821841239929199,
|
||||
"eval_logits/real": -2.8065903186798096,
|
||||
"eval_logps/generated": -702.32763671875,
|
||||
"eval_logps/real": -278.1448974609375,
|
||||
"eval_loss": 0.131888747215271,
|
||||
"eval_rewards/accuracies": 0.9375,
|
||||
"eval_rewards/generated": -29.145910263061523,
|
||||
"eval_rewards/margins": 26.238248825073242,
|
||||
"eval_rewards/real": -2.9076578617095947,
|
||||
"eval_runtime": 74.4579,
|
||||
"eval_samples_per_second": 4.942,
|
||||
"eval_steps_per_second": 0.161,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 1.17,
|
||||
"learning_rate": 4.615384615384615e-08,
|
||||
"logits/generated": -2.8634510040283203,
|
||||
"logits/real": -2.8573107719421387,
|
||||
"logps/generated": -768.2184448242188,
|
||||
"logps/real": -281.481201171875,
|
||||
"loss": 0.0249,
|
||||
"rewards/accuracies": 0.9937499761581421,
|
||||
"rewards/generated": -33.38450241088867,
|
||||
"rewards/margins": 33.606407165527344,
|
||||
"rewards/real": 0.22189739346504211,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 1.36,
|
||||
"learning_rate": 3.516483516483517e-08,
|
||||
"logits/generated": -2.846198797225952,
|
||||
"logits/real": -2.818643093109131,
|
||||
"logps/generated": -667.6427001953125,
|
||||
"logps/real": -262.6141052246094,
|
||||
"loss": 0.006,
|
||||
"rewards/accuracies": 0.987500011920929,
|
||||
"rewards/generated": -29.605731964111328,
|
||||
"rewards/margins": 33.2759895324707,
|
||||
"rewards/real": 3.670259952545166,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 1.46,
|
||||
"eval_logits/generated": -2.8174571990966797,
|
||||
"eval_logits/real": -2.8036582469940186,
|
||||
"eval_logps/generated": -702.328857421875,
|
||||
"eval_logps/real": -278.0840759277344,
|
||||
"eval_loss": 0.12692251801490784,
|
||||
"eval_rewards/accuracies": 0.9583333134651184,
|
||||
"eval_rewards/generated": -29.151870727539062,
|
||||
"eval_rewards/margins": 26.54817008972168,
|
||||
"eval_rewards/real": -2.6037025451660156,
|
||||
"eval_runtime": 74.2997,
|
||||
"eval_samples_per_second": 4.953,
|
||||
"eval_steps_per_second": 0.162,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 1.55,
|
||||
"learning_rate": 2.4175824175824175e-08,
|
||||
"logits/generated": -2.8320305347442627,
|
||||
"logits/real": -2.810762882232666,
|
||||
"logps/generated": -708.1215209960938,
|
||||
"logps/real": -277.090576171875,
|
||||
"loss": 0.0292,
|
||||
"rewards/accuracies": 0.9937499761581421,
|
||||
"rewards/generated": -33.68733215332031,
|
||||
"rewards/margins": 36.958492279052734,
|
||||
"rewards/real": 3.271162748336792,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 1.75,
|
||||
"learning_rate": 1.3186813186813187e-08,
|
||||
"logits/generated": -2.8205840587615967,
|
||||
"logits/real": -2.8130674362182617,
|
||||
"logps/generated": -704.9281005859375,
|
||||
"logps/real": -273.8406066894531,
|
||||
"loss": 0.0322,
|
||||
"rewards/accuracies": 0.987500011920929,
|
||||
"rewards/generated": -31.48798179626465,
|
||||
"rewards/margins": 33.98870849609375,
|
||||
"rewards/real": 2.500725746154785,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 1.94,
|
||||
"learning_rate": 2.197802197802198e-09,
|
||||
"logits/generated": -2.872133255004883,
|
||||
"logits/real": -2.856153964996338,
|
||||
"logps/generated": -711.3128662109375,
|
||||
"logps/real": -259.7333068847656,
|
||||
"loss": 0.0086,
|
||||
"rewards/accuracies": 1.0,
|
||||
"rewards/generated": -35.352970123291016,
|
||||
"rewards/margins": 39.97649383544922,
|
||||
"rewards/real": 4.623520851135254,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 1.94,
|
||||
"eval_logits/generated": -2.817664384841919,
|
||||
"eval_logits/real": -2.805149793624878,
|
||||
"eval_logps/generated": -702.4378051757812,
|
||||
"eval_logps/real": -278.1470031738281,
|
||||
"eval_loss": 0.10993197560310364,
|
||||
"eval_rewards/accuracies": 0.9270833134651184,
|
||||
"eval_rewards/generated": -29.69696617126465,
|
||||
"eval_rewards/margins": 26.778860092163086,
|
||||
"eval_rewards/real": -2.918107748031616,
|
||||
"eval_runtime": 73.9005,
|
||||
"eval_samples_per_second": 4.98,
|
||||
"eval_steps_per_second": 0.162,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 1.98,
|
||||
"step": 102,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.1742458962578573,
|
||||
"train_runtime": 2590.1164,
|
||||
"train_samples_per_second": 2.545,
|
||||
"train_steps_per_second": 0.039
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 102,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 500,
|
||||
"total_flos": 0.0,
|
||||
"train_batch_size": 8,
|
||||
"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 sha256:29a60630d5cc5d69fe9ecd6aa807355e74046dc05f0e784134cda8541bb5e382
|
||||
size 5752
|
||||
Reference in New Issue
Block a user