初始化项目，由ModelHub XC社区提供模型
Model: W-61/mistral-7b-base-sft-hh-helpful-4xh200-batch-64 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
68
README.md
Normal file
68
README.md
Normal file
@@ -0,0 +1,68 @@
|
||||
---
|
||||
library_name: transformers
|
||||
base_model: mistralai/Mistral-7B-v0.3
|
||||
tags:
|
||||
- alignment-handbook
|
||||
- generated_from_trainer
|
||||
datasets:
|
||||
- Anthropic/hh-rlhf
|
||||
model-index:
|
||||
- name: mistral-7b-base-sft-hh-helpful-4xh200-batch-64-20260418-015332
|
||||
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. -->
|
||||
|
||||
# mistral-7b-base-sft-hh-helpful-4xh200-batch-64-20260418-015332
|
||||
|
||||
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the Anthropic/hh-rlhf dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 0.7902
|
||||
|
||||
## 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: 2e-05
|
||||
- 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: Use OptimizerNames.ADAMW_TORCH 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: 1
|
||||
|
||||
### Training results
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss |
|
||||
|:-------------:|:------:|:----:|:---------------:|
|
||||
| 1.1916 | 0.3226 | 100 | 1.2298 |
|
||||
| 0.9281 | 0.6452 | 200 | 0.9367 |
|
||||
| 0.7683 | 0.9677 | 300 | 0.7902 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.51.0
|
||||
- Pytorch 2.3.1+cu121
|
||||
- Datasets 2.21.0
|
||||
- Tokenizers 0.21.4
|
||||
14
all_results.json
Normal file
14
all_results.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 0.7899015545845032,
|
||||
"eval_runtime": 5.3882,
|
||||
"eval_samples": 2339,
|
||||
"eval_samples_per_second": 199.326,
|
||||
"eval_steps_per_second": 6.31,
|
||||
"total_flos": 1.0839391709062758e+17,
|
||||
"train_loss": 1.0778046692571333,
|
||||
"train_runtime": 974.833,
|
||||
"train_samples": 43598,
|
||||
"train_samples_per_second": 20.339,
|
||||
"train_steps_per_second": 0.318
|
||||
}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"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": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.51.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32768
|
||||
}
|
||||
8
eval_results.json
Normal file
8
eval_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"eval_loss": 0.7899015545845032,
|
||||
"eval_runtime": 5.3882,
|
||||
"eval_samples": 2339,
|
||||
"eval_samples_per_second": 199.326,
|
||||
"eval_steps_per_second": 6.31
|
||||
}
|
||||
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": "4.51.0"
|
||||
}
|
||||
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e7ba2e3bf40595bdf03d982c888c4cfe17c1ce304d71caafeb57bb0bdf194e1a
|
||||
size 4999779856
|
||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a6e54c566931f7b8075da0870368dd0016eb60eb64f09339437fb206b28d8fc8
|
||||
size 4899116440
|
||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:13304ff3079dd32372fd9dd94f39a7395ce4483ed19cc8a9611defd84244d6ca
|
||||
size 4999813120
|
||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:66826434b981c2f0803860db733d84fe384ee84b296ce2a0a4212e55ccffa87b
|
||||
size 4999813128
|
||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b132e40320a864bdbf15eb82b958ddc0d51101e64a4a21222b54f7e55615bc4c
|
||||
size 4832007496
|
||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:782cdd9a7112ebc9d7151c5c3ad24c0e0cbb538e7aaeabf3c9ff505388e50fd3
|
||||
size 4261597808
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 28992094208
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00006-of-00006.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.norm.weight": "model-00006-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"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": "</s>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
275733
tokenizer.json
Normal file
275733
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
||||
size 587404
|
||||
6188
tokenizer_config.json
Normal file
6188
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
9
train_results.json
Normal file
9
train_results.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"total_flos": 1.0839391709062758e+17,
|
||||
"train_loss": 1.0778046692571333,
|
||||
"train_runtime": 974.833,
|
||||
"train_samples": 43598,
|
||||
"train_samples_per_second": 20.339,
|
||||
"train_steps_per_second": 0.318
|
||||
}
|
||||
508
trainer_state.json
Normal file
508
trainer_state.json
Normal file
@@ -0,0 +1,508 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.0,
|
||||
"eval_steps": 100,
|
||||
"global_step": 310,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.0032258064516129032,
|
||||
"grad_norm": 58.05511474609375,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 1.9,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.016129032258064516,
|
||||
"grad_norm": 21.915355682373047,
|
||||
"learning_rate": 2.580645161290323e-06,
|
||||
"loss": 1.7687,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.03225806451612903,
|
||||
"grad_norm": 8.215951919555664,
|
||||
"learning_rate": 5.806451612903226e-06,
|
||||
"loss": 1.5337,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.04838709677419355,
|
||||
"grad_norm": 4.512474060058594,
|
||||
"learning_rate": 9.03225806451613e-06,
|
||||
"loss": 1.4014,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.06451612903225806,
|
||||
"grad_norm": 5.174832820892334,
|
||||
"learning_rate": 1.2258064516129034e-05,
|
||||
"loss": 1.3709,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.08064516129032258,
|
||||
"grad_norm": 4.159119129180908,
|
||||
"learning_rate": 1.5483870967741936e-05,
|
||||
"loss": 1.3652,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.0967741935483871,
|
||||
"grad_norm": 4.116876602172852,
|
||||
"learning_rate": 1.870967741935484e-05,
|
||||
"loss": 1.3885,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.11290322580645161,
|
||||
"grad_norm": 3.840414047241211,
|
||||
"learning_rate": 1.999429490929718e-05,
|
||||
"loss": 1.3982,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.12903225806451613,
|
||||
"grad_norm": 4.314554691314697,
|
||||
"learning_rate": 1.9959454037227215e-05,
|
||||
"loss": 1.3744,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.14516129032258066,
|
||||
"grad_norm": 4.36101770401001,
|
||||
"learning_rate": 1.989305206325792e-05,
|
||||
"loss": 1.394,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.16129032258064516,
|
||||
"grad_norm": 3.858530282974243,
|
||||
"learning_rate": 1.9795299412524948e-05,
|
||||
"loss": 1.3652,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.1774193548387097,
|
||||
"grad_norm": 4.053957462310791,
|
||||
"learning_rate": 1.9666505859174462e-05,
|
||||
"loss": 1.3825,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.1935483870967742,
|
||||
"grad_norm": 3.8405709266662598,
|
||||
"learning_rate": 1.9507079544701583e-05,
|
||||
"loss": 1.3449,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.20967741935483872,
|
||||
"grad_norm": 3.8573291301727295,
|
||||
"learning_rate": 1.9317525684566686e-05,
|
||||
"loss": 1.3268,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.22580645161290322,
|
||||
"grad_norm": 4.115865230560303,
|
||||
"learning_rate": 1.9098444967188308e-05,
|
||||
"loss": 1.3096,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.24193548387096775,
|
||||
"grad_norm": 3.9826207160949707,
|
||||
"learning_rate": 1.8850531650386154e-05,
|
||||
"loss": 1.3243,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.25806451612903225,
|
||||
"grad_norm": 8.022098541259766,
|
||||
"learning_rate": 1.857457136130651e-05,
|
||||
"loss": 1.309,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.27419354838709675,
|
||||
"grad_norm": 3.8160018920898438,
|
||||
"learning_rate": 1.827143860680199e-05,
|
||||
"loss": 1.278,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.2903225806451613,
|
||||
"grad_norm": 4.026176452636719,
|
||||
"learning_rate": 1.7942094002155122e-05,
|
||||
"loss": 1.2788,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.3064516129032258,
|
||||
"grad_norm": 4.071281909942627,
|
||||
"learning_rate": 1.758758122692791e-05,
|
||||
"loss": 1.2412,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 0.3225806451612903,
|
||||
"grad_norm": 3.6679961681365967,
|
||||
"learning_rate": 1.7209023717584013e-05,
|
||||
"loss": 1.1916,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.3225806451612903,
|
||||
"eval_loss": 1.2297844886779785,
|
||||
"eval_runtime": 5.4527,
|
||||
"eval_samples_per_second": 196.965,
|
||||
"eval_steps_per_second": 6.235,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.3387096774193548,
|
||||
"grad_norm": 3.7028727531433105,
|
||||
"learning_rate": 1.6807621107364613e-05,
|
||||
"loss": 1.2004,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 0.3548387096774194,
|
||||
"grad_norm": 3.7159862518310547,
|
||||
"learning_rate": 1.6384645424699835e-05,
|
||||
"loss": 1.1933,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.3709677419354839,
|
||||
"grad_norm": 3.5471580028533936,
|
||||
"learning_rate": 1.594143706220273e-05,
|
||||
"loss": 1.1913,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 0.3870967741935484,
|
||||
"grad_norm": 4.138647079467773,
|
||||
"learning_rate": 1.5479400529019987e-05,
|
||||
"loss": 1.1872,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.4032258064516129,
|
||||
"grad_norm": 3.7750704288482666,
|
||||
"learning_rate": 1.5000000000000002e-05,
|
||||
"loss": 1.1359,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 0.41935483870967744,
|
||||
"grad_norm": 3.429034948348999,
|
||||
"learning_rate": 1.4504754675782731e-05,
|
||||
"loss": 1.1518,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.43548387096774194,
|
||||
"grad_norm": 3.416344404220581,
|
||||
"learning_rate": 1.3995233968515105e-05,
|
||||
"loss": 1.1405,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 0.45161290322580644,
|
||||
"grad_norm": 4.399573802947998,
|
||||
"learning_rate": 1.3473052528448203e-05,
|
||||
"loss": 1.1137,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.46774193548387094,
|
||||
"grad_norm": 3.7525525093078613,
|
||||
"learning_rate": 1.2939865127176771e-05,
|
||||
"loss": 1.1235,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 0.4838709677419355,
|
||||
"grad_norm": 3.8501410484313965,
|
||||
"learning_rate": 1.2397361413735785e-05,
|
||||
"loss": 1.0858,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"grad_norm": 3.5585899353027344,
|
||||
"learning_rate": 1.1847260560171895e-05,
|
||||
"loss": 1.0692,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"epoch": 0.5161290322580645,
|
||||
"grad_norm": 3.620709180831909,
|
||||
"learning_rate": 1.1291305813557616e-05,
|
||||
"loss": 1.0313,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.532258064516129,
|
||||
"grad_norm": 3.7223265171051025,
|
||||
"learning_rate": 1.0731258971712762e-05,
|
||||
"loss": 1.0268,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"epoch": 0.5483870967741935,
|
||||
"grad_norm": 3.67724871635437,
|
||||
"learning_rate": 1.0168894800139311e-05,
|
||||
"loss": 1.0123,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.5645161290322581,
|
||||
"grad_norm": 4.000744342803955,
|
||||
"learning_rate": 9.605995407862248e-06,
|
||||
"loss": 0.9905,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 0.5806451612903226,
|
||||
"grad_norm": 3.4585959911346436,
|
||||
"learning_rate": 9.04434459999902e-06,
|
||||
"loss": 0.9682,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.5967741935483871,
|
||||
"grad_norm": 3.573272466659546,
|
||||
"learning_rate": 8.485722224954237e-06,
|
||||
"loss": 0.9364,
|
||||
"step": 185
|
||||
},
|
||||
{
|
||||
"epoch": 0.6129032258064516,
|
||||
"grad_norm": 3.517512083053589,
|
||||
"learning_rate": 7.93189853415293e-06,
|
||||
"loss": 0.9559,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.6290322580645161,
|
||||
"grad_norm": 3.629652500152588,
|
||||
"learning_rate": 7.384628572186334e-06,
|
||||
"loss": 0.9376,
|
||||
"step": 195
|
||||
},
|
||||
{
|
||||
"epoch": 0.6451612903225806,
|
||||
"grad_norm": 3.6871094703674316,
|
||||
"learning_rate": 6.845646615147445e-06,
|
||||
"loss": 0.9281,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.6451612903225806,
|
||||
"eval_loss": 0.9366754293441772,
|
||||
"eval_runtime": 5.3925,
|
||||
"eval_samples_per_second": 199.164,
|
||||
"eval_steps_per_second": 6.305,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.6612903225806451,
|
||||
"grad_norm": 3.7159454822540283,
|
||||
"learning_rate": 6.31666067478113e-06,
|
||||
"loss": 0.9359,
|
||||
"step": 205
|
||||
},
|
||||
{
|
||||
"epoch": 0.6774193548387096,
|
||||
"grad_norm": 3.5741474628448486,
|
||||
"learning_rate": 5.799347085864851e-06,
|
||||
"loss": 0.8788,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.6935483870967742,
|
||||
"grad_norm": 3.8699448108673096,
|
||||
"learning_rate": 5.295345193972445e-06,
|
||||
"loss": 0.8994,
|
||||
"step": 215
|
||||
},
|
||||
{
|
||||
"epoch": 0.7096774193548387,
|
||||
"grad_norm": 3.681175470352173,
|
||||
"learning_rate": 4.8062521604551245e-06,
|
||||
"loss": 0.8894,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.7258064516129032,
|
||||
"grad_norm": 4.077960968017578,
|
||||
"learning_rate": 4.333617901102592e-06,
|
||||
"loss": 0.8478,
|
||||
"step": 225
|
||||
},
|
||||
{
|
||||
"epoch": 0.7419354838709677,
|
||||
"grad_norm": 4.131643772125244,
|
||||
"learning_rate": 3.878940174523371e-06,
|
||||
"loss": 0.8409,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.7580645161290323,
|
||||
"grad_norm": 3.835108995437622,
|
||||
"learning_rate": 3.4436598358091577e-06,
|
||||
"loss": 0.878,
|
||||
"step": 235
|
||||
},
|
||||
{
|
||||
"epoch": 0.7741935483870968,
|
||||
"grad_norm": 3.9890787601470947,
|
||||
"learning_rate": 3.0291562705240107e-06,
|
||||
"loss": 0.8321,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.7903225806451613,
|
||||
"grad_norm": 3.728030204772949,
|
||||
"learning_rate": 2.6367430234880286e-06,
|
||||
"loss": 0.8269,
|
||||
"step": 245
|
||||
},
|
||||
{
|
||||
"epoch": 0.8064516129032258,
|
||||
"grad_norm": 3.8121144771575928,
|
||||
"learning_rate": 2.2676636362076075e-06,
|
||||
"loss": 0.7872,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.8225806451612904,
|
||||
"grad_norm": 3.7709388732910156,
|
||||
"learning_rate": 1.9230877061433505e-06,
|
||||
"loss": 0.8187,
|
||||
"step": 255
|
||||
},
|
||||
{
|
||||
"epoch": 0.8387096774193549,
|
||||
"grad_norm": 3.6049516201019287,
|
||||
"learning_rate": 1.60410718030361e-06,
|
||||
"loss": 0.8195,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.8548387096774194,
|
||||
"grad_norm": 3.6554863452911377,
|
||||
"learning_rate": 1.3117328949091634e-06,
|
||||
"loss": 0.8091,
|
||||
"step": 265
|
||||
},
|
||||
{
|
||||
"epoch": 0.8709677419354839,
|
||||
"grad_norm": 3.8024368286132812,
|
||||
"learning_rate": 1.0468913720946084e-06,
|
||||
"loss": 0.7855,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.8870967741935484,
|
||||
"grad_norm": 3.79064679145813,
|
||||
"learning_rate": 8.10421883797694e-07,
|
||||
"loss": 0.7959,
|
||||
"step": 275
|
||||
},
|
||||
{
|
||||
"epoch": 0.9032258064516129,
|
||||
"grad_norm": 3.7366783618927,
|
||||
"learning_rate": 6.030737921409169e-07,
|
||||
"loss": 0.7824,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.9193548387096774,
|
||||
"grad_norm": 3.792200803756714,
|
||||
"learning_rate": 4.2550417473364524e-07,
|
||||
"loss": 0.7653,
|
||||
"step": 285
|
||||
},
|
||||
{
|
||||
"epoch": 0.9354838709677419,
|
||||
"grad_norm": 3.850405216217041,
|
||||
"learning_rate": 2.7827574242009434e-07,
|
||||
"loss": 0.759,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 0.9516129032258065,
|
||||
"grad_norm": 3.8457884788513184,
|
||||
"learning_rate": 1.6185505607171027e-07,
|
||||
"loss": 0.7866,
|
||||
"step": 295
|
||||
},
|
||||
{
|
||||
"epoch": 0.967741935483871,
|
||||
"grad_norm": 3.824265241622925,
|
||||
"learning_rate": 7.661104807487607e-08,
|
||||
"loss": 0.7683,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.967741935483871,
|
||||
"eval_loss": 0.7902069091796875,
|
||||
"eval_runtime": 5.4529,
|
||||
"eval_samples_per_second": 196.96,
|
||||
"eval_steps_per_second": 6.235,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.9838709677419355,
|
||||
"grad_norm": 3.8102200031280518,
|
||||
"learning_rate": 2.2813853199292745e-08,
|
||||
"loss": 0.778,
|
||||
"step": 305
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"grad_norm": 3.923637628555298,
|
||||
"learning_rate": 6.339525519594159e-10,
|
||||
"loss": 0.7865,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"step": 310,
|
||||
"total_flos": 1.0839391709062758e+17,
|
||||
"train_loss": 1.0778046692571333,
|
||||
"train_runtime": 974.833,
|
||||
"train_samples_per_second": 20.339,
|
||||
"train_steps_per_second": 0.318
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 310,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"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": 1.0839391709062758e+17,
|
||||
"train_batch_size": 8,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
Reference in New Issue
Block a user