初始化项目，由ModelHub XC社区提供模型
Model: jackf857/qwen3-8b-base-simpo-ultrafeedback-4xH200-batch-128 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
76
README.md
Normal file
76
README.md
Normal file
@@ -0,0 +1,76 @@
|
||||
---
|
||||
library_name: transformers
|
||||
base_model: jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128
|
||||
tags:
|
||||
- alignment-handbook
|
||||
- simpo
|
||||
- generated_from_trainer
|
||||
datasets:
|
||||
- HuggingFaceH4/ultrafeedback_binarized
|
||||
model-index:
|
||||
- name: qwen3-8b-base-simpo-ultrafeedback-4xh200-batch-128
|
||||
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. -->
|
||||
|
||||
# qwen3-8b-base-simpo-ultrafeedback-4xh200-batch-128
|
||||
|
||||
This model is a fine-tuned version of [jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128](https://huggingface.co/jackf857/qwen3-8b-base-sft-ultrachat-4xh200-batch-128) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
||||
It achieves the following results on the evaluation set:
|
||||
- Loss: 1.0770
|
||||
- Rewards/chosen: -2.1095
|
||||
- Rewards/rejected: -2.9493
|
||||
- Rewards/accuracies: 0.6660
|
||||
- Rewards/margins: 0.8398
|
||||
- Logps/rejected: -1.4746
|
||||
- Logps/chosen: -1.0548
|
||||
- Logits/rejected: 2.1566
|
||||
- Logits/chosen: 2.1386
|
||||
|
||||
## 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: 6e-07
|
||||
- train_batch_size: 4
|
||||
- eval_batch_size: 2
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 4
|
||||
- gradient_accumulation_steps: 8
|
||||
- total_train_batch_size: 128
|
||||
- total_eval_batch_size: 8
|
||||
- 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 | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
||||
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
||||
| 9.1298 | 0.4188 | 200 | 1.1165 | -2.0802 | -2.7440 | 0.6360 | 0.6638 | -1.3720 | -1.0401 | 2.1249 | 2.1120 |
|
||||
| 8.8992 | 0.8377 | 400 | 1.0770 | -2.1095 | -2.9493 | 0.6660 | 0.8398 | -1.4746 | -1.0548 | 2.1566 | 2.1386 |
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.51.0
|
||||
- Pytorch 2.3.1+cu121
|
||||
- Datasets 2.21.0
|
||||
- Tokenizers 0.21.4
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
22
all_results.json
Normal file
22
all_results.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"epoch": 0.9989528795811519,
|
||||
"eval_logits/chosen": 2.1443471908569336,
|
||||
"eval_logits/rejected": 2.1642587184906006,
|
||||
"eval_logps/chosen": -1.0595875978469849,
|
||||
"eval_logps/rejected": -1.4812482595443726,
|
||||
"eval_loss": 1.0770305395126343,
|
||||
"eval_rewards/accuracies": 0.6660000085830688,
|
||||
"eval_rewards/chosen": -2.1191751956939697,
|
||||
"eval_rewards/margins": 0.8433210253715515,
|
||||
"eval_rewards/rejected": -2.962496519088745,
|
||||
"eval_runtime": 45.3759,
|
||||
"eval_samples": 2000,
|
||||
"eval_samples_per_second": 44.076,
|
||||
"eval_steps_per_second": 5.51,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 9.188309121681709,
|
||||
"train_runtime": 5401.7608,
|
||||
"train_samples": 61135,
|
||||
"train_samples_per_second": 11.318,
|
||||
"train_steps_per_second": 0.088
|
||||
}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.51.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
16
eval_results.json
Normal file
16
eval_results.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"epoch": 0.9989528795811519,
|
||||
"eval_logits/chosen": 2.1443471908569336,
|
||||
"eval_logits/rejected": 2.1642587184906006,
|
||||
"eval_logps/chosen": -1.0595875978469849,
|
||||
"eval_logps/rejected": -1.4812482595443726,
|
||||
"eval_loss": 1.0770305395126343,
|
||||
"eval_rewards/accuracies": 0.6660000085830688,
|
||||
"eval_rewards/chosen": -2.1191751956939697,
|
||||
"eval_rewards/margins": 0.8433210253715515,
|
||||
"eval_rewards/rejected": -2.962496519088745,
|
||||
"eval_runtime": 45.3759,
|
||||
"eval_samples": 2000,
|
||||
"eval_samples_per_second": 44.076,
|
||||
"eval_steps_per_second": 5.51
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"max_new_tokens": 2048,
|
||||
"transformers_version": "4.51.0"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00007.safetensors
Normal file
3
model-00001-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3cbeaa89a4d375b73329535ea36876843a640be5b53f689bf83e7fdfded0d612
|
||||
size 4972454376
|
||||
3
model-00002-of-00007.safetensors
Normal file
3
model-00002-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c841dfc1634b0e2434cf35c06c6c36a2b82731154ffef4e915c1ec1706573360
|
||||
size 4832048608
|
||||
3
model-00003-of-00007.safetensors
Normal file
3
model-00003-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dba6af3c0700ad944cb7ce5c2675eaed1aca452f445336ace3916c30d33974ec
|
||||
size 4832048656
|
||||
3
model-00004-of-00007.safetensors
Normal file
3
model-00004-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:668168b0ad41e9df10199aa2dc7a0b3b89e56d738a12194d4e09380145f936d5
|
||||
size 4999855528
|
||||
3
model-00005-of-00007.safetensors
Normal file
3
model-00005-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d93e56c0d1947d8d7d5ad07c0c392c33c4d70fde72644afff2433af4c644d46b
|
||||
size 4832048672
|
||||
3
model-00006-of-00007.safetensors
Normal file
3
model-00006-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2c3bd05b414cc273e7c39f3895cf5cda22129f5d52f318b186687385b96c16c4
|
||||
size 4832048672
|
||||
3
model-00007-of-00007.safetensors
Normal file
3
model-00007-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c6a09e42af084017e92e3d78b3cbc7858ba684017e15a70c5ed172fe1022082
|
||||
size 3462482728
|
||||
406
model.safetensors.index.json
Normal file
406
model.safetensors.index.json
Normal file
@@ -0,0 +1,406 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 32762941440
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00007-of-00007.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.norm.weight": "model-00007-of-00007.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
9
train_results.json
Normal file
9
train_results.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"epoch": 0.9989528795811519,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 9.188309121681709,
|
||||
"train_runtime": 5401.7608,
|
||||
"train_samples": 61135,
|
||||
"train_samples_per_second": 11.318,
|
||||
"train_steps_per_second": 0.088
|
||||
}
|
||||
795
trainer_state.json
Normal file
795
trainer_state.json
Normal file
@@ -0,0 +1,795 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.9989528795811519,
|
||||
"eval_steps": 200,
|
||||
"global_step": 477,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.0020942408376963353,
|
||||
"grad_norm": 63.87941360473633,
|
||||
"learning_rate": 0.0,
|
||||
"logits/chosen": 2.203179359436035,
|
||||
"logits/rejected": 2.035616397857666,
|
||||
"logps/chosen": -1.1535288095474243,
|
||||
"logps/rejected": -1.4391145706176758,
|
||||
"loss": 10.7981,
|
||||
"rewards/accuracies": 0.6875,
|
||||
"rewards/chosen": -2.3070576190948486,
|
||||
"rewards/margins": 0.5711714625358582,
|
||||
"rewards/rejected": -2.8782291412353516,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.020942408376963352,
|
||||
"grad_norm": 32.67357635498047,
|
||||
"learning_rate": 1.125e-07,
|
||||
"logits/chosen": 2.019272804260254,
|
||||
"logits/rejected": 1.9496015310287476,
|
||||
"logps/chosen": -1.1085267066955566,
|
||||
"logps/rejected": -1.3239415884017944,
|
||||
"loss": 10.102,
|
||||
"rewards/accuracies": 0.6076388955116272,
|
||||
"rewards/chosen": -2.2170534133911133,
|
||||
"rewards/margins": 0.4308299422264099,
|
||||
"rewards/rejected": -2.647883176803589,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.041884816753926704,
|
||||
"grad_norm": 65.35013580322266,
|
||||
"learning_rate": 2.3749999999999998e-07,
|
||||
"logits/chosen": 1.9201877117156982,
|
||||
"logits/rejected": 1.8487052917480469,
|
||||
"logps/chosen": -1.1284211874008179,
|
||||
"logps/rejected": -1.3107967376708984,
|
||||
"loss": 9.9907,
|
||||
"rewards/accuracies": 0.578125,
|
||||
"rewards/chosen": -2.2568423748016357,
|
||||
"rewards/margins": 0.3647509813308716,
|
||||
"rewards/rejected": -2.621593475341797,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06282722513089005,
|
||||
"grad_norm": 46.34416198730469,
|
||||
"learning_rate": 3.6249999999999997e-07,
|
||||
"logits/chosen": 1.9416582584381104,
|
||||
"logits/rejected": 1.8945503234863281,
|
||||
"logps/chosen": -1.090599775314331,
|
||||
"logps/rejected": -1.200209140777588,
|
||||
"loss": 9.8702,
|
||||
"rewards/accuracies": 0.578125,
|
||||
"rewards/chosen": -2.181199550628662,
|
||||
"rewards/margins": 0.21921858191490173,
|
||||
"rewards/rejected": -2.400418281555176,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.08376963350785341,
|
||||
"grad_norm": 34.50259780883789,
|
||||
"learning_rate": 4.875e-07,
|
||||
"logits/chosen": 1.869368553161621,
|
||||
"logits/rejected": 1.8852355480194092,
|
||||
"logps/chosen": -1.0211187601089478,
|
||||
"logps/rejected": -1.2025065422058105,
|
||||
"loss": 9.811,
|
||||
"rewards/accuracies": 0.590624988079071,
|
||||
"rewards/chosen": -2.0422375202178955,
|
||||
"rewards/margins": 0.3627752661705017,
|
||||
"rewards/rejected": -2.405013084411621,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.10471204188481675,
|
||||
"grad_norm": 28.40943145751953,
|
||||
"learning_rate": 5.999919559552264e-07,
|
||||
"logits/chosen": 1.989923119544983,
|
||||
"logits/rejected": 2.015007495880127,
|
||||
"logps/chosen": -0.9122698903083801,
|
||||
"logps/rejected": -1.1353458166122437,
|
||||
"loss": 9.6163,
|
||||
"rewards/accuracies": 0.578125,
|
||||
"rewards/chosen": -1.8245397806167603,
|
||||
"rewards/margins": 0.44615206122398376,
|
||||
"rewards/rejected": -2.2706916332244873,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.1256544502617801,
|
||||
"grad_norm": 34.944854736328125,
|
||||
"learning_rate": 5.99027192440263e-07,
|
||||
"logits/chosen": 1.8734846115112305,
|
||||
"logits/rejected": 1.8532871007919312,
|
||||
"logps/chosen": -0.9877859354019165,
|
||||
"logps/rejected": -1.1455579996109009,
|
||||
"loss": 9.9483,
|
||||
"rewards/accuracies": 0.5531250238418579,
|
||||
"rewards/chosen": -1.975571870803833,
|
||||
"rewards/margins": 0.31554415822029114,
|
||||
"rewards/rejected": -2.2911159992218018,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.14659685863874344,
|
||||
"grad_norm": 33.13404846191406,
|
||||
"learning_rate": 5.964595461857045e-07,
|
||||
"logits/chosen": 2.0360629558563232,
|
||||
"logits/rejected": 2.0784692764282227,
|
||||
"logps/chosen": -0.9781535863876343,
|
||||
"logps/rejected": -1.1859705448150635,
|
||||
"loss": 9.5206,
|
||||
"rewards/accuracies": 0.5843750238418579,
|
||||
"rewards/chosen": -1.9563071727752686,
|
||||
"rewards/margins": 0.41563382744789124,
|
||||
"rewards/rejected": -2.371941089630127,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.16753926701570682,
|
||||
"grad_norm": 31.283838272094727,
|
||||
"learning_rate": 5.923027806082798e-07,
|
||||
"logits/chosen": 1.9586601257324219,
|
||||
"logits/rejected": 1.9780356884002686,
|
||||
"logps/chosen": -0.9476488828659058,
|
||||
"logps/rejected": -1.172166109085083,
|
||||
"loss": 9.5782,
|
||||
"rewards/accuracies": 0.640625,
|
||||
"rewards/chosen": -1.8952977657318115,
|
||||
"rewards/margins": 0.44903475046157837,
|
||||
"rewards/rejected": -2.344332218170166,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.18848167539267016,
|
||||
"grad_norm": 52.153682708740234,
|
||||
"learning_rate": 5.865791773197119e-07,
|
||||
"logits/chosen": 1.9691884517669678,
|
||||
"logits/rejected": 1.95147705078125,
|
||||
"logps/chosen": -0.9630438685417175,
|
||||
"logps/rejected": -1.2420399188995361,
|
||||
"loss": 9.5363,
|
||||
"rewards/accuracies": 0.640625,
|
||||
"rewards/chosen": -1.926087737083435,
|
||||
"rewards/margins": 0.5579922795295715,
|
||||
"rewards/rejected": -2.4840798377990723,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.2094240837696335,
|
||||
"grad_norm": 35.23684310913086,
|
||||
"learning_rate": 5.793194166900525e-07,
|
||||
"logits/chosen": 1.859946608543396,
|
||||
"logits/rejected": 1.847818374633789,
|
||||
"logps/chosen": -0.9811749458312988,
|
||||
"logps/rejected": -1.1944254636764526,
|
||||
"loss": 9.6309,
|
||||
"rewards/accuracies": 0.6468750238418579,
|
||||
"rewards/chosen": -1.9623498916625977,
|
||||
"rewards/margins": 0.42650118470191956,
|
||||
"rewards/rejected": -2.3888509273529053,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.23036649214659685,
|
||||
"grad_norm": 41.84571838378906,
|
||||
"learning_rate": 5.705624133909468e-07,
|
||||
"logits/chosen": 2.0235304832458496,
|
||||
"logits/rejected": 2.071727752685547,
|
||||
"logps/chosen": -0.9354808926582336,
|
||||
"logps/rejected": -1.2987582683563232,
|
||||
"loss": 9.1676,
|
||||
"rewards/accuracies": 0.6625000238418579,
|
||||
"rewards/chosen": -1.8709617853164673,
|
||||
"rewards/margins": 0.7265545129776001,
|
||||
"rewards/rejected": -2.5975165367126465,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.2513089005235602,
|
||||
"grad_norm": 35.44133758544922,
|
||||
"learning_rate": 5.603551078003725e-07,
|
||||
"logits/chosen": 1.958561658859253,
|
||||
"logits/rejected": 1.9417177438735962,
|
||||
"logps/chosen": -1.0246690511703491,
|
||||
"logps/rejected": -1.231858491897583,
|
||||
"loss": 9.6426,
|
||||
"rewards/accuracies": 0.578125,
|
||||
"rewards/chosen": -2.0493381023406982,
|
||||
"rewards/margins": 0.41437870264053345,
|
||||
"rewards/rejected": -2.463716983795166,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.27225130890052357,
|
||||
"grad_norm": 35.418907165527344,
|
||||
"learning_rate": 5.487522143869884e-07,
|
||||
"logits/chosen": 1.781296968460083,
|
||||
"logits/rejected": 1.8837049007415771,
|
||||
"logps/chosen": -1.019592046737671,
|
||||
"logps/rejected": -1.2727988958358765,
|
||||
"loss": 9.2965,
|
||||
"rewards/accuracies": 0.65625,
|
||||
"rewards/chosen": -2.039184093475342,
|
||||
"rewards/margins": 0.5064135789871216,
|
||||
"rewards/rejected": -2.545597791671753,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.2931937172774869,
|
||||
"grad_norm": 33.78614807128906,
|
||||
"learning_rate": 5.358159284228362e-07,
|
||||
"logits/chosen": 1.831496000289917,
|
||||
"logits/rejected": 1.8257663249969482,
|
||||
"logps/chosen": -1.017618179321289,
|
||||
"logps/rejected": -1.2920626401901245,
|
||||
"loss": 9.7072,
|
||||
"rewards/accuracies": 0.609375,
|
||||
"rewards/chosen": -2.035236358642578,
|
||||
"rewards/margins": 0.5488889813423157,
|
||||
"rewards/rejected": -2.584125280380249,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.31413612565445026,
|
||||
"grad_norm": 41.28224182128906,
|
||||
"learning_rate": 5.216155925965094e-07,
|
||||
"logits/chosen": 1.9868301153182983,
|
||||
"logits/rejected": 1.9190441370010376,
|
||||
"logps/chosen": -0.9844843149185181,
|
||||
"logps/rejected": -1.2851510047912598,
|
||||
"loss": 9.3868,
|
||||
"rewards/accuracies": 0.625,
|
||||
"rewards/chosen": -1.9689686298370361,
|
||||
"rewards/margins": 0.6013331413269043,
|
||||
"rewards/rejected": -2.5703020095825195,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.33507853403141363,
|
||||
"grad_norm": 28.384824752807617,
|
||||
"learning_rate": 5.062273253138518e-07,
|
||||
"logits/chosen": 1.9291102886199951,
|
||||
"logits/rejected": 1.90181565284729,
|
||||
"logps/chosen": -1.0036952495574951,
|
||||
"logps/rejected": -1.3095722198486328,
|
||||
"loss": 9.2335,
|
||||
"rewards/accuracies": 0.6468750238418579,
|
||||
"rewards/chosen": -2.0073904991149902,
|
||||
"rewards/margins": 0.6117540597915649,
|
||||
"rewards/rejected": -2.6191444396972656,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.35602094240837695,
|
||||
"grad_norm": 34.20272445678711,
|
||||
"learning_rate": 4.897336126786132e-07,
|
||||
"logits/chosen": 1.9849627017974854,
|
||||
"logits/rejected": 1.9100704193115234,
|
||||
"logps/chosen": -0.9672800302505493,
|
||||
"logps/rejected": -1.2293925285339355,
|
||||
"loss": 9.3151,
|
||||
"rewards/accuracies": 0.625,
|
||||
"rewards/chosen": -1.9345600605010986,
|
||||
"rewards/margins": 0.5242254137992859,
|
||||
"rewards/rejected": -2.458785057067871,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.3769633507853403,
|
||||
"grad_norm": 31.79982566833496,
|
||||
"learning_rate": 4.722228663401794e-07,
|
||||
"logits/chosen": 1.9956668615341187,
|
||||
"logits/rejected": 1.9031591415405273,
|
||||
"logps/chosen": -0.9950326681137085,
|
||||
"logps/rejected": -1.2332713603973389,
|
||||
"loss": 9.2109,
|
||||
"rewards/accuracies": 0.625,
|
||||
"rewards/chosen": -1.990065336227417,
|
||||
"rewards/margins": 0.47647732496261597,
|
||||
"rewards/rejected": -2.4665427207946777,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.39790575916230364,
|
||||
"grad_norm": 48.42845153808594,
|
||||
"learning_rate": 4.537889495784557e-07,
|
||||
"logits/chosen": 1.8380305767059326,
|
||||
"logits/rejected": 1.8153343200683594,
|
||||
"logps/chosen": -0.9896278381347656,
|
||||
"logps/rejected": -1.3258594274520874,
|
||||
"loss": 9.0701,
|
||||
"rewards/accuracies": 0.6468750238418579,
|
||||
"rewards/chosen": -1.9792556762695312,
|
||||
"rewards/margins": 0.6724631190299988,
|
||||
"rewards/rejected": -2.651718854904175,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.418848167539267,
|
||||
"grad_norm": 27.38842010498047,
|
||||
"learning_rate": 4.345306741662423e-07,
|
||||
"logits/chosen": 1.883819580078125,
|
||||
"logits/rejected": 1.9056427478790283,
|
||||
"logps/chosen": -1.014286994934082,
|
||||
"logps/rejected": -1.3301787376403809,
|
||||
"loss": 9.1298,
|
||||
"rewards/accuracies": 0.637499988079071,
|
||||
"rewards/chosen": -2.028573989868164,
|
||||
"rewards/margins": 0.6317834258079529,
|
||||
"rewards/rejected": -2.6603574752807617,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.418848167539267,
|
||||
"eval_logits/chosen": 2.1119980812072754,
|
||||
"eval_logits/rejected": 2.124922752380371,
|
||||
"eval_logps/chosen": -1.0400915145874023,
|
||||
"eval_logps/rejected": -1.3719773292541504,
|
||||
"eval_loss": 1.1164965629577637,
|
||||
"eval_rewards/accuracies": 0.6359999775886536,
|
||||
"eval_rewards/chosen": -2.0801830291748047,
|
||||
"eval_rewards/margins": 0.6637715697288513,
|
||||
"eval_rewards/rejected": -2.743954658508301,
|
||||
"eval_runtime": 45.5084,
|
||||
"eval_samples_per_second": 43.948,
|
||||
"eval_steps_per_second": 5.493,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.4397905759162304,
|
||||
"grad_norm": 37.30736541748047,
|
||||
"learning_rate": 4.145512707060832e-07,
|
||||
"logits/chosen": 2.0058822631835938,
|
||||
"logits/rejected": 2.02673077583313,
|
||||
"logps/chosen": -1.0181465148925781,
|
||||
"logps/rejected": -1.3840270042419434,
|
||||
"loss": 9.2944,
|
||||
"rewards/accuracies": 0.640625,
|
||||
"rewards/chosen": -2.0362930297851562,
|
||||
"rewards/margins": 0.7317610383033752,
|
||||
"rewards/rejected": -2.7680540084838867,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.4607329842931937,
|
||||
"grad_norm": 39.49748992919922,
|
||||
"learning_rate": 3.939578352807537e-07,
|
||||
"logits/chosen": 2.021946907043457,
|
||||
"logits/rejected": 2.058398723602295,
|
||||
"logps/chosen": -1.0262434482574463,
|
||||
"logps/rejected": -1.3750391006469727,
|
||||
"loss": 9.1142,
|
||||
"rewards/accuracies": 0.637499988079071,
|
||||
"rewards/chosen": -2.0524868965148926,
|
||||
"rewards/margins": 0.6975916028022766,
|
||||
"rewards/rejected": -2.7500782012939453,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4816753926701571,
|
||||
"grad_norm": 46.19815444946289,
|
||||
"learning_rate": 3.7286075538352106e-07,
|
||||
"logits/chosen": 1.8356702327728271,
|
||||
"logits/rejected": 1.8795230388641357,
|
||||
"logps/chosen": -1.0263798236846924,
|
||||
"logps/rejected": -1.3885927200317383,
|
||||
"loss": 9.0176,
|
||||
"rewards/accuracies": 0.659375011920929,
|
||||
"rewards/chosen": -2.0527596473693848,
|
||||
"rewards/margins": 0.7244257926940918,
|
||||
"rewards/rejected": -2.7771854400634766,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.5026178010471204,
|
||||
"grad_norm": 37.616127014160156,
|
||||
"learning_rate": 3.5137311820537683e-07,
|
||||
"logits/chosen": 1.7736084461212158,
|
||||
"logits/rejected": 1.7944352626800537,
|
||||
"logps/chosen": -0.9926139116287231,
|
||||
"logps/rejected": -1.3105839490890503,
|
||||
"loss": 9.1917,
|
||||
"rewards/accuracies": 0.653124988079071,
|
||||
"rewards/chosen": -1.9852278232574463,
|
||||
"rewards/margins": 0.6359401941299438,
|
||||
"rewards/rejected": -2.6211678981781006,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.5235602094240838,
|
||||
"grad_norm": 47.60890197753906,
|
||||
"learning_rate": 3.296101044510136e-07,
|
||||
"logits/chosen": 1.8431848287582397,
|
||||
"logits/rejected": 1.7555633783340454,
|
||||
"logps/chosen": -1.0195379257202148,
|
||||
"logps/rejected": -1.463659644126892,
|
||||
"loss": 8.915,
|
||||
"rewards/accuracies": 0.628125011920929,
|
||||
"rewards/chosen": -2.0390758514404297,
|
||||
"rewards/margins": 0.8882430791854858,
|
||||
"rewards/rejected": -2.927319288253784,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.5445026178010471,
|
||||
"grad_norm": 53.570133209228516,
|
||||
"learning_rate": 3.076883709328898e-07,
|
||||
"logits/chosen": 1.885573387145996,
|
||||
"logits/rejected": 1.8557020425796509,
|
||||
"logps/chosen": -1.0390733480453491,
|
||||
"logps/rejected": -1.3984655141830444,
|
||||
"loss": 9.3265,
|
||||
"rewards/accuracies": 0.643750011920929,
|
||||
"rewards/chosen": -2.0781466960906982,
|
||||
"rewards/margins": 0.7187842726707458,
|
||||
"rewards/rejected": -2.796931028366089,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.5654450261780105,
|
||||
"grad_norm": 52.018001556396484,
|
||||
"learning_rate": 2.857254252528773e-07,
|
||||
"logits/chosen": 1.815469741821289,
|
||||
"logits/rejected": 1.8461593389511108,
|
||||
"logps/chosen": -1.0356584787368774,
|
||||
"logps/rejected": -1.3995596170425415,
|
||||
"loss": 9.1513,
|
||||
"rewards/accuracies": 0.653124988079071,
|
||||
"rewards/chosen": -2.071316957473755,
|
||||
"rewards/margins": 0.7278021574020386,
|
||||
"rewards/rejected": -2.799119234085083,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.5863874345549738,
|
||||
"grad_norm": 47.29704284667969,
|
||||
"learning_rate": 2.638389959234031e-07,
|
||||
"logits/chosen": 1.8500423431396484,
|
||||
"logits/rejected": 1.827164888381958,
|
||||
"logps/chosen": -0.9695369601249695,
|
||||
"logps/rejected": -1.464297890663147,
|
||||
"loss": 8.6549,
|
||||
"rewards/accuracies": 0.659375011920929,
|
||||
"rewards/chosen": -1.939073920249939,
|
||||
"rewards/margins": 0.9895218014717102,
|
||||
"rewards/rejected": -2.928595781326294,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.6073298429319371,
|
||||
"grad_norm": 46.65730285644531,
|
||||
"learning_rate": 2.421464013044373e-07,
|
||||
"logits/chosen": 1.9609591960906982,
|
||||
"logits/rejected": 1.9269940853118896,
|
||||
"logps/chosen": -1.0431578159332275,
|
||||
"logps/rejected": -1.36538827419281,
|
||||
"loss": 9.1695,
|
||||
"rewards/accuracies": 0.6343749761581421,
|
||||
"rewards/chosen": -2.086315631866455,
|
||||
"rewards/margins": 0.6444610357284546,
|
||||
"rewards/rejected": -2.73077654838562,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 0.6282722513089005,
|
||||
"grad_norm": 42.485137939453125,
|
||||
"learning_rate": 2.2076392073903244e-07,
|
||||
"logits/chosen": 1.8708031177520752,
|
||||
"logits/rejected": 1.8845112323760986,
|
||||
"logps/chosen": -1.1147522926330566,
|
||||
"logps/rejected": -1.3503917455673218,
|
||||
"loss": 9.1503,
|
||||
"rewards/accuracies": 0.606249988079071,
|
||||
"rewards/chosen": -2.2295045852661133,
|
||||
"rewards/margins": 0.4712789058685303,
|
||||
"rewards/rejected": -2.7007834911346436,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.6492146596858639,
|
||||
"grad_norm": 112.9022445678711,
|
||||
"learning_rate": 1.9980617125832958e-07,
|
||||
"logits/chosen": 1.9049968719482422,
|
||||
"logits/rejected": 1.908156156539917,
|
||||
"logps/chosen": -1.0263423919677734,
|
||||
"logps/rejected": -1.3653188943862915,
|
||||
"loss": 8.8053,
|
||||
"rewards/accuracies": 0.643750011920929,
|
||||
"rewards/chosen": -2.052684783935547,
|
||||
"rewards/margins": 0.6779530644416809,
|
||||
"rewards/rejected": -2.730637788772583,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 0.6701570680628273,
|
||||
"grad_norm": 42.80693054199219,
|
||||
"learning_rate": 1.7938549319709663e-07,
|
||||
"logits/chosen": 1.9933536052703857,
|
||||
"logits/rejected": 2.0374882221221924,
|
||||
"logps/chosen": -1.0420429706573486,
|
||||
"logps/rejected": -1.4136046171188354,
|
||||
"loss": 8.8744,
|
||||
"rewards/accuracies": 0.671875,
|
||||
"rewards/chosen": -2.0840859413146973,
|
||||
"rewards/margins": 0.7431236505508423,
|
||||
"rewards/rejected": -2.827209234237671,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.6910994764397905,
|
||||
"grad_norm": 64.53388977050781,
|
||||
"learning_rate": 1.5961134801309614e-07,
|
||||
"logits/chosen": 1.9328991174697876,
|
||||
"logits/rejected": 1.9388740062713623,
|
||||
"logps/chosen": -1.0375453233718872,
|
||||
"logps/rejected": -1.4853423833847046,
|
||||
"loss": 9.0326,
|
||||
"rewards/accuracies": 0.659375011920929,
|
||||
"rewards/chosen": -2.0750906467437744,
|
||||
"rewards/margins": 0.8955942392349243,
|
||||
"rewards/rejected": -2.970684766769409,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 0.7120418848167539,
|
||||
"grad_norm": 64.71541595458984,
|
||||
"learning_rate": 1.4058973153816886e-07,
|
||||
"logits/chosen": 1.8567371368408203,
|
||||
"logits/rejected": 1.851202368736267,
|
||||
"logps/chosen": -1.0736474990844727,
|
||||
"logps/rejected": -1.4988930225372314,
|
||||
"loss": 9.0231,
|
||||
"rewards/accuracies": 0.6875,
|
||||
"rewards/chosen": -2.1472949981689453,
|
||||
"rewards/margins": 0.850490927696228,
|
||||
"rewards/rejected": -2.997786045074463,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.7329842931937173,
|
||||
"grad_norm": 48.053550720214844,
|
||||
"learning_rate": 1.2242260580619538e-07,
|
||||
"logits/chosen": 1.9933841228485107,
|
||||
"logits/rejected": 2.0060808658599854,
|
||||
"logps/chosen": -1.0655163526535034,
|
||||
"logps/rejected": -1.511839747428894,
|
||||
"loss": 8.737,
|
||||
"rewards/accuracies": 0.699999988079071,
|
||||
"rewards/chosen": -2.131032705307007,
|
||||
"rewards/margins": 0.8926466107368469,
|
||||
"rewards/rejected": -3.023679494857788,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 0.7539267015706806,
|
||||
"grad_norm": 119.26463317871094,
|
||||
"learning_rate": 1.0520735250352405e-07,
|
||||
"logits/chosen": 1.9238300323486328,
|
||||
"logits/rejected": 1.964910864830017,
|
||||
"logps/chosen": -1.0357812643051147,
|
||||
"logps/rejected": -1.4163744449615479,
|
||||
"loss": 8.9391,
|
||||
"rewards/accuracies": 0.668749988079071,
|
||||
"rewards/chosen": -2.0715625286102295,
|
||||
"rewards/margins": 0.761186420917511,
|
||||
"rewards/rejected": -2.8327488899230957,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.774869109947644,
|
||||
"grad_norm": 74.86650848388672,
|
||||
"learning_rate": 8.903625097154667e-08,
|
||||
"logits/chosen": 2.0095980167388916,
|
||||
"logits/rejected": 1.9654392004013062,
|
||||
"logps/chosen": -1.075518012046814,
|
||||
"logps/rejected": -1.5022872686386108,
|
||||
"loss": 8.4271,
|
||||
"rewards/accuracies": 0.640625,
|
||||
"rewards/chosen": -2.151036024093628,
|
||||
"rewards/margins": 0.8535385131835938,
|
||||
"rewards/rejected": -3.0045745372772217,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 0.7958115183246073,
|
||||
"grad_norm": 148.51052856445312,
|
||||
"learning_rate": 7.399598355949822e-08,
|
||||
"logits/chosen": 1.9656111001968384,
|
||||
"logits/rejected": 1.9382845163345337,
|
||||
"logps/chosen": -0.987983226776123,
|
||||
"logps/rejected": -1.367729663848877,
|
||||
"loss": 8.8956,
|
||||
"rewards/accuracies": 0.671875,
|
||||
"rewards/chosen": -1.975966453552246,
|
||||
"rewards/margins": 0.7594925165176392,
|
||||
"rewards/rejected": -2.735459327697754,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.8167539267015707,
|
||||
"grad_norm": 61.45123291015625,
|
||||
"learning_rate": 6.01671709789497e-08,
|
||||
"logits/chosen": 1.955004334449768,
|
||||
"logits/rejected": 1.985464334487915,
|
||||
"logps/chosen": -1.0322657823562622,
|
||||
"logps/rejected": -1.4219481945037842,
|
||||
"loss": 8.9243,
|
||||
"rewards/accuracies": 0.6656249761581421,
|
||||
"rewards/chosen": -2.0645315647125244,
|
||||
"rewards/margins": 0.7793648838996887,
|
||||
"rewards/rejected": -2.8438963890075684,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 0.837696335078534,
|
||||
"grad_norm": 44.18227767944336,
|
||||
"learning_rate": 4.76239401506456e-08,
|
||||
"logits/chosen": 1.9698352813720703,
|
||||
"logits/rejected": 1.9627288579940796,
|
||||
"logps/chosen": -1.0838392972946167,
|
||||
"logps/rejected": -1.3468244075775146,
|
||||
"loss": 8.8992,
|
||||
"rewards/accuracies": 0.590624988079071,
|
||||
"rewards/chosen": -2.1676785945892334,
|
||||
"rewards/margins": 0.5259703993797302,
|
||||
"rewards/rejected": -2.6936488151550293,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.837696335078534,
|
||||
"eval_logits/chosen": 2.138575553894043,
|
||||
"eval_logits/rejected": 2.156599521636963,
|
||||
"eval_logps/chosen": -1.054769515991211,
|
||||
"eval_logps/rejected": -1.4746460914611816,
|
||||
"eval_loss": 1.076961874961853,
|
||||
"eval_rewards/accuracies": 0.6660000085830688,
|
||||
"eval_rewards/chosen": -2.109539031982422,
|
||||
"eval_rewards/margins": 0.8397529721260071,
|
||||
"eval_rewards/rejected": -2.9492921829223633,
|
||||
"eval_runtime": 45.4523,
|
||||
"eval_samples_per_second": 44.002,
|
||||
"eval_steps_per_second": 5.5,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.8586387434554974,
|
||||
"grad_norm": 86.99646759033203,
|
||||
"learning_rate": 3.643352686016596e-08,
|
||||
"logits/chosen": 1.959341287612915,
|
||||
"logits/rejected": 1.9492921829223633,
|
||||
"logps/chosen": -1.049546241760254,
|
||||
"logps/rejected": -1.4740784168243408,
|
||||
"loss": 8.7816,
|
||||
"rewards/accuracies": 0.653124988079071,
|
||||
"rewards/chosen": -2.099092483520508,
|
||||
"rewards/margins": 0.8490642309188843,
|
||||
"rewards/rejected": -2.9481568336486816,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 0.8795811518324608,
|
||||
"grad_norm": 77.62808990478516,
|
||||
"learning_rate": 2.665591535230738e-08,
|
||||
"logits/chosen": 1.9194042682647705,
|
||||
"logits/rejected": 1.9090583324432373,
|
||||
"logps/chosen": -1.046962022781372,
|
||||
"logps/rejected": -1.3986111879348755,
|
||||
"loss": 8.6978,
|
||||
"rewards/accuracies": 0.653124988079071,
|
||||
"rewards/chosen": -2.093924045562744,
|
||||
"rewards/margins": 0.7032982110977173,
|
||||
"rewards/rejected": -2.797222375869751,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.900523560209424,
|
||||
"grad_norm": 104.71875,
|
||||
"learning_rate": 1.834351679607603e-08,
|
||||
"logits/chosen": 1.983788251876831,
|
||||
"logits/rejected": 1.991276502609253,
|
||||
"logps/chosen": -0.9792089462280273,
|
||||
"logps/rejected": -1.5666288137435913,
|
||||
"loss": 8.5908,
|
||||
"rewards/accuracies": 0.6781250238418579,
|
||||
"rewards/chosen": -1.9584178924560547,
|
||||
"rewards/margins": 1.174839735031128,
|
||||
"rewards/rejected": -3.1332576274871826,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 0.9214659685863874,
|
||||
"grad_norm": 61.72246170043945,
|
||||
"learning_rate": 1.1540888343822164e-08,
|
||||
"logits/chosen": 2.009519100189209,
|
||||
"logits/rejected": 2.041383743286133,
|
||||
"logps/chosen": -0.999321460723877,
|
||||
"logps/rejected": -1.394999623298645,
|
||||
"loss": 8.7008,
|
||||
"rewards/accuracies": 0.668749988079071,
|
||||
"rewards/chosen": -1.998642921447754,
|
||||
"rewards/margins": 0.7913564443588257,
|
||||
"rewards/rejected": -2.78999924659729,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.9424083769633508,
|
||||
"grad_norm": 47.30830383300781,
|
||||
"learning_rate": 6.284494290451603e-09,
|
||||
"logits/chosen": 2.0252490043640137,
|
||||
"logits/rejected": 2.0139636993408203,
|
||||
"logps/chosen": -1.0534889698028564,
|
||||
"logps/rejected": -1.4194049835205078,
|
||||
"loss": 8.8863,
|
||||
"rewards/accuracies": 0.653124988079071,
|
||||
"rewards/chosen": -2.106977939605713,
|
||||
"rewards/margins": 0.7318320870399475,
|
||||
"rewards/rejected": -2.8388099670410156,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 0.9633507853403142,
|
||||
"grad_norm": 55.95344161987305,
|
||||
"learning_rate": 2.6025106129779263e-09,
|
||||
"logits/chosen": 2.087092161178589,
|
||||
"logits/rejected": 2.062786102294922,
|
||||
"logps/chosen": -1.058509111404419,
|
||||
"logps/rejected": -1.4474523067474365,
|
||||
"loss": 8.995,
|
||||
"rewards/accuracies": 0.6781250238418579,
|
||||
"rewards/chosen": -2.117018222808838,
|
||||
"rewards/margins": 0.777886688709259,
|
||||
"rewards/rejected": -2.894904613494873,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.9842931937172775,
|
||||
"grad_norm": 57.510528564453125,
|
||||
"learning_rate": 5.146739381471921e-10,
|
||||
"logits/chosen": 1.9302631616592407,
|
||||
"logits/rejected": 1.8986546993255615,
|
||||
"logps/chosen": -0.9788550138473511,
|
||||
"logps/rejected": -1.4690487384796143,
|
||||
"loss": 8.7456,
|
||||
"rewards/accuracies": 0.684374988079071,
|
||||
"rewards/chosen": -1.9577100276947021,
|
||||
"rewards/margins": 0.9803873300552368,
|
||||
"rewards/rejected": -2.9380974769592285,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 0.9989528795811519,
|
||||
"step": 477,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 9.188309121681709,
|
||||
"train_runtime": 5401.7608,
|
||||
"train_samples_per_second": 11.318,
|
||||
"train_steps_per_second": 0.088
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 477,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": false,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 0.0,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user