Training in progress, step 18

00000000-0000-0000-0000-000000000000.yml

@@ -0,0 +1,50 @@
+base_model: peft-internal-testing/tiny-dummy-qwen2
+batch_size: 8
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- format: custom
+  path: argilla/databricks-dolly-15k-curated-en
+  type:
+    field_input: original-instruction
+    field_instruction: original-instruction
+    field_output: original-response
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/test-repo
+hub_strategy: checkpoint
+learning_rate: 0.002
+load_best_model_at_end: true
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 1
+micro_batch_size: 1
+model_type: AutoModelForCausalLM
+num_epochs: 100
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 8
+tokenizer_type: Qwen2TokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.001
+wandb_entity: ''
+wandb_mode: online
+wandb_name: peft-internal-testing/tiny-dummy-qwen2-argilla/databricks-dolly-15k-curated-en
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

03a659ff-e350-4bb9-8ff3-8c658a5d0dff.yml

@@ -0,0 +1,52 @@
+base_model: fxmarty/tiny-llama-fast-tokenizer
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - fc6136aac03f618a_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/fc6136aac03f618a_train_data.json
+  type:
+    field_instruction: text
+    field_output: title
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/b1c9c4ec-ffa2-429d-9c5b-90b5979c502d
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+special_tokens:
+  pad_token: </s>
+tokenizer_type: LlamaTokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: fxmarty/tiny-llama-fast-tokenizer-/workspace/input_data/fc6136aac03f618a_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

077fd330-87f9-4bc4-b449-7713fbdaf1b0.yml

@@ -0,0 +1,51 @@
+base_model: unsloth/mistral-7b-v0.3
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - ca0152973425c947_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/ca0152973425c947_train_data.json
+  type:
+    field_input: code
+    field_instruction: func_name
+    field_output: docstring
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/5a2f5ce6-446b-4282-bb4d-9ee4e970231f
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: LlamaTokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/mistral-7b-v0.3-/tmp/ca0152973425c947_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

21315ae5-16ee-43cd-9612-743524060933.yml

@@ -0,0 +1,50 @@
+base_model: unsloth/Meta-Llama-3.1-8B
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - 562fa3aeea07046a_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/562fa3aeea07046a_train_data.json
+  type:
+    field_instruction: prompt
+    field_output: text
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/c4596edc-efad-4776-86a1-caa06bffcada
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: PreTrainedTokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/Meta-Llama-3.1-8B-/workspace/input_data/562fa3aeea07046a_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

40f27435-f59d-488f-b2d6-01e356d79c48.yml

@@ -0,0 +1,50 @@
+base_model: Qwen/Qwen2-1.5B-Instruct
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - df925134bb2c32b8_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/df925134bb2c32b8_train_data.json
+  type:
+    field_instruction: prompt
+    field_output: amoral
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/ba640bbe-3257-40d8-88fe-26152f412bb7
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: Qwen2TokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: Qwen/Qwen2-1.5B-Instruct-/tmp/df925134bb2c32b8_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

427d02be-6008-4556-9a5e-9c7cb7503058.yml

@@ -0,0 +1,51 @@
+base_model: unsloth/Phi-3.5-mini-instruct
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - 7e5b54272524b996_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/7e5b54272524b996_train_data.json
+  type:
+    field_input: input
+    field_instruction: instruction
+    field_output: output
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/ae26a9e9-089e-4d4a-b592-d8935df7c18d
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: LlamaTokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/Phi-3.5-mini-instruct-/workspace/input_data/7e5b54272524b996_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

54c39bbc-809b-4c67-a254-0e03a4884b4e.yml

@@ -0,0 +1,51 @@
+base_model: unsloth/codegemma-7b-it
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - 2ebe89763cb3150d_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/2ebe89763cb3150d_train_data.json
+  type:
+    field_input: input
+    field_instruction: instruction
+    field_output: output
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/a0bc38f8-fcd3-4d7e-9a3f-3aa2e8a4204f
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: GemmaTokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/codegemma-7b-it-/tmp/2ebe89763cb3150d_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

5ff7bf5f-96dc-43dd-aeeb-560c0ab78db8.yml

@@ -0,0 +1,51 @@
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - 69447058613b41d8_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/69447058613b41d8_train_data.json
+  type:
+    field_input: sectionParentTitre
+    field_instruction: title_main
+    field_output: texte
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/942aa5fc-b540-46ce-b482-e38c4f637264
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: PreTrainedTokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: NousResearch/Hermes-3-Llama-3.1-8B-/workspace/input_data/69447058613b41d8_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

63345f8a-4ec9-47f0-9956-6eaa52b2c2a6.yml

@@ -0,0 +1,52 @@
+base_model: heegyu/WizardVicuna-open-llama-3b-v2
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - fe9267419ea75ad2_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/fe9267419ea75ad2_train_data.json
+  type:
+    field_instruction: ca_topic
+    field_output: article
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/7114c34f-852f-43da-b985-b7f0b6d6d724
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+special_tokens:
+  pad_token: </s>
+tokenizer_type: LlamaTokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: heegyu/WizardVicuna-open-llama-3b-v2-/tmp/fe9267419ea75ad2_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

6c7ae056-3b4d-460b-ba7b-a4000f32b3f1.yml

@@ -0,0 +1,51 @@
+base_model: unsloth/gemma-2-2b
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - b98d5b59c20c6595_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/b98d5b59c20c6595_train_data.json
+  type:
+    field_input: metadata
+    field_instruction: text
+    field_output: tags_str
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/429ee307-6dd2-4dd7-9e1d-7384d807a3df
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: GemmaTokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/gemma-2-2b-/tmp/b98d5b59c20c6595_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

75b21ca4-feab-4bdd-92b0-ea6d90dfa18f.yml

@@ -0,0 +1,51 @@
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - c6adcdcb593a3ee4_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/c6adcdcb593a3ee4_train_data.json
+  type:
+    field_input: abstract
+    field_instruction: question_en_origin
+    field_output: answer_en_origin
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/2faf844e-4a0a-4d23-95f4-a055e4864133
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: Qwen2TokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: Qwen/Qwen2.5-1.5B-Instruct-/workspace/input_data/c6adcdcb593a3ee4_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

879db250-c3f5-4d43-a7c5-c5a456ae5803.yml

@@ -0,0 +1,50 @@
+base_model: unsloth/Qwen2.5-Coder-1.5B-Instruct
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - 4d85b564dafa38db_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/4d85b564dafa38db_train_data.json
+  type:
+    field_instruction: prompt
+    field_output: response
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/876ff803-5357-4240-8766-c54166515403
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: Qwen2TokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/Qwen2.5-Coder-1.5B-Instruct-/workspace/input_data/4d85b564dafa38db_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

8910478d-79cf-499e-8fed-7a2142f7ee60.yml

@@ -0,0 +1,51 @@
+base_model: unsloth/Phi-3-medium-4k-instruct
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - f6199f34ade98809_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/f6199f34ade98809_train_data.json
+  type:
+    field_input: choices
+    field_instruction: question
+    field_output: answer
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/2d37ba50-cd70-4895-be62-3477f5193e86
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: LlamaTokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/Phi-3-medium-4k-instruct-/tmp/f6199f34ade98809_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

README.md

@@ -0,0 +1,122 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: unsloth/SmolLM-135M
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 09370687-f28e-45e5-91f6-f87011850a94
+  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: `0.4.1`
+```yaml
+base_model: unsloth/SmolLM-135M
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - 658988857b0a29c9_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/658988857b0a29c9_train_data.json
+  type:
+    field_input: choices
+    field_instruction: subject
+    field_output: question
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/09370687-f28e-45e5-91f6-f87011850a94
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: GPT2TokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/SmolLM-135M-/workspace/input_data/658988857b0a29c9_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true
+
+```
+
+</details><br>
+
+# 09370687-f28e-45e5-91f6-f87011850a94
+
+This model is a fine-tuned version of [unsloth/SmolLM-135M](https://huggingface.co/unsloth/SmolLM-135M) on the None dataset.
+
+## 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: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- 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
+- training_steps: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0.5   | 1    | 2.4449          |
+
+
+### Framework versions
+
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "fxmarty/tiny-llama-fast-tokenizer",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pad_token_id": -1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

da9e44b3-e4fb-4905-9c7c-6b03aad6b593.yml

@@ -0,0 +1,51 @@
+base_model: unsloth/SmolLM2-360M-Instruct
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - f1ccd02a885008e6_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/f1ccd02a885008e6_train_data.json
+  type:
+    field_input: target
+    field_instruction: user
+    field_output: assistant
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/3da0a03a-adbb-42e3-8fd7-bd7c0b1d3e9f
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: GPT2TokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/SmolLM2-360M-Instruct-/tmp/f1ccd02a885008e6_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

ee62f35d-1a99-4f1c-a69c-c91bc444b71f.yml

@@ -0,0 +1,53 @@
+base_model: EleutherAI/pythia-1b
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - b2a4966d9a5c880e_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/b2a4966d9a5c880e_train_data.json
+  type:
+    field_input: input
+    field_instruction: instruction
+    field_output: output
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/ee937811-31d0-4e11-944a-f4f8e06309d2
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+special_tokens:
+  pad_token: <|endoftext|>
+tokenizer_type: GPTNeoXTokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: EleutherAI/pythia-1b-/workspace/input_data/b2a4966d9a5c880e_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

ef61f40b-eca8-4670-964b-fdd3d1d0f066.yml

@@ -0,0 +1,51 @@
+base_model: unsloth/SmolLM-135M
+batch_size: 32
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- data_files:
+  - 658988857b0a29c9_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/658988857b0a29c9_train_data.json
+  type:
+    field_input: choices
+    field_instruction: subject
+    field_output: question
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+eval_steps: 20
+flash_attention: true
+gpu_memory_limit: 80GiB
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: willtensora/09370687-f28e-45e5-91f6-f87011850a94
+hub_strategy: checkpoint
+learning_rate: 0.0002
+logging_steps: 10
+lr_scheduler: cosine
+max_steps: 2500
+micro_batch_size: 4
+model_type: AutoModelForCausalLM
+optimizer: adamw_bnb_8bit
+output_dir: /workspace/axolotl/configs
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: false
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: GPT2TokenizerFast
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.1
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/SmolLM-135M-/workspace/input_data/658988857b0a29c9_train_data.json
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05
+xformers_attention: true

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 0,
+  "transformers_version": "4.46.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812c47eb394f5b1421d47e7eef591e1ff951c789cc31fb4b5d68a8b1837eac7b
+size 2066752

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34aef3a9bd77f14e9e2815e5fa6d6d034134c670e5a5c3fe9a7310af9a216c7a
+size 269122058

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response: ' + message['content'] + eos_token}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492137edc8d6ffcc24eda892257e04d2830cf1f5da1bcb04692598ac2e8b1ce1
+size 6584