Model save

README.md

@@ -0,0 +1,160 @@
+---
+library_name: transformers
+tags:
+- axolotl
+- generated_from_trainer
+datasets:
+- PocketDoc/Dans-Personamaxx-Logs
+- anthracite-org/kalo-opus-instruct-22k-no-refusal
+- lodrick-the-lafted/kalo-opus-instruct-3k-filtered
+- anthracite-org/nopm_claude_writing_fixed
+- anthracite-org/kalo_opus_misc_240827
+- anthracite-org/kalo_misc_part2
+- NewEden/Claude-Instruct-5K
+- NewEden/Claude-Instruct-2.7K
+model-index:
+- name: 32b-mag
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.8.0.dev0`
+```yaml
+base_model: ./qwq
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+hub_model_id: NewEden/32b-mag
+hub_strategy: "all_checkpoints"
+push_dataset_to_hub:
+hf_use_auth_token: true
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_layer_norm: true
+liger_glu_activation: true
+liger_fused_linear_cross_entropy: false
+cut_cross_entropy: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: PocketDoc/Dans-Personamaxx-Logs
+    type: dan-chat-advanced
+  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
+    type: dan-chat-advanced
+  - path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
+    type: dan-chat-advanced
+  - path: anthracite-org/nopm_claude_writing_fixed
+    type: dan-chat-advanced
+  - path: anthracite-org/kalo_opus_misc_240827
+    type: dan-chat-advanced
+  - path: anthracite-org/kalo_misc_part2
+    type: dan-chat-advanced
+  - path: NewEden/Claude-Instruct-5K
+    type: dan-chat-advanced
+  - path: NewEden/Claude-Instruct-2.7K
+    type: dan-chat-advanced
+dataset_prepared_path: prepared_data
+val_set_size: 0.0
+output_dir: ./qwq-mag
+sequence_len: 32768
+sample_packing: true
+pad_to_sequence_len: true
+
+wandb_project: qwq
+wandb_entity:
+wandb_watch:
+wandb_name: mag-attempt-01
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 2
+num_epochs: 2
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 4e-5
+max_grad_norm: 1.0
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: unsloth
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 40
+saves_per_epoch: 2
+debug:
+deepspeed: deepspeed_configs/zero3_bf16.json
+weight_decay: 0.02
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# 32b-mag
+
+This model was trained from scratch on the PocketDoc/Dans-Personamaxx-Logs, the anthracite-org/kalo-opus-instruct-22k-no-refusal, the lodrick-the-lafted/kalo-opus-instruct-3k-filtered, the anthracite-org/nopm_claude_writing_fixed, the anthracite-org/kalo_opus_misc_240827, the anthracite-org/kalo_misc_part2, the NewEden/Claude-Instruct-5K and the NewEden/Claude-Instruct-2.7K datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 4e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 40
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42346fcee4c84b21716f181c28a0c2fdc62a9fadf4b258f468bdc20c9c87ce50
+oid sha256:9cf10ce50a8d003eaff8d51daae1bc78a87469963f79d7c53a3ce107db3666e5
 size 4891730992

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2bded2abc95e816bbfd41d45fdaf02c472b93e39b186c2c67e64c1ef584090c
+oid sha256:e4e81bf27bad3b96697389808a44a571dbff4db739f57f41582ec0f7db527d76
 size 4876059352

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1381b8a8d48b624aea2de2d3e7dcf7e53a5d4dc237f757b8c263eef405faa9d
+oid sha256:dcf6bf13b7617ff05293691beafd48c4a928a91fba50e1e1388a4a5c3d269109
 size 4876059384

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac15677e790996976ec66bda89206c21574de8ea8939648e68c9c5e5def35123
+oid sha256:2ac13aaae6bdd992d8a58d0e596db8d562469b45316b604efb60b7c3780ccf8b
 size 4876059416

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565a75ee8993f80a7040893b826028fc6daf5578d3ba851232548dd5d51862bf
+oid sha256:4b0c3632f86a8031f6cd02e8b6f7813b235993f6a7a65ca7ca3529885e4b24f0
 size 4876059416

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9efb5296f2182c7153f643050a69d2ab537e27fc15b488055775b6ef40f5159
+oid sha256:01b5ffdf2e2c4c78ba4a60e3bc3014ee88c48a6069ecf274b06882eb679af1db
 size 4876059416

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abfe635f0c526f713e09761d51c5305bd3685d47a4669e02588c3e792d5a1d71
+oid sha256:a48c262fd09b64848047caca69fc42deb1c0ef7d5f059f3163b708128737319a
 size 4876059416

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c86b874ee5475c8e4698541d2a33a4e89c2a4bb9e78aa3b3175f3e12afc7851e
+oid sha256:e8d2a6506e468823609ad1a0c20c9b137c1fb686cc179c052bd0a576340e433e
 size 4876059416

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0993083a57a47d22c37e184fb1fa7dda6ad6c176afb0cad4dbd41951b76a96b7
+oid sha256:4aeb06318c94ab8ae043d59a01f8b66b39df677db6bef203523608b396d823fe
 size 4876059416

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d40d444856e5594ff19f8dd60cc68c223ade5e49a24aa5247616897a01bc473a
+oid sha256:ec1eed2a46b3a63174b1020cf13f4b3841e6a7d0fb1e28ead346fb0d36a68f60
 size 4876059416

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:296c0eb8bc9910e7f8c211fe26b54269a2e83b438d1a9e2e4967aba5ff9a11e0
+oid sha256:c0cdd742a90b658ebd2e3ba8c13768db9306f507e2615ae25f9a29c38fbf401d
 size 4876059416

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472fb6923b910b57bb3701a378b63e2cea67b082eeb75015675686cbf4340919
+oid sha256:82e664c4014f96f9ce810b8804b2a30aa18f9896b4c2760974f39e0e8a1c94cf
 size 4876059416

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cf6936306c154f4646fbef8f831d6945fb42944d4c9491c1b28ae5d4cd73e74
+oid sha256:77bae41788091207a2adafa153a080d989fc7dec91f121873d81b4ed1ba455e9
 size 4876059416

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b3a32254b03b9773e446fd45437e3f723cdc245ac93955ef1773a93c5b0335
+oid sha256:ece41c61d65c36120db9a4efe3e9602ecf07c02eacb1462298a677d1e20477f4
 size 2123397800