Training in progress, step 75

README.md

@@ -0,0 +1,169 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen1.5-7B
+tags:
+- axolotl
+- generated_from_trainer
+- trl
+- grpo
+model-index:
+- name: 2296f73f-99bd-4e6b-95ca-b2cd4a1e78af
+  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: `0.11.0.dev0`
+```yaml
+adapter: lora
+base_model: Qwen/Qwen1.5-7B
+bf16: true
+chat_template: llama3
+dataloader_num_workers: 0
+dataloader_pin_memory: false
+dataset_info: dcaeb768-0f9e-4c34-920e-d80288595c2a
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - ecb638fa488a6a93_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/
+  type:
+    field_instruction: instruct
+    field_output: output
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+ddp_broadcast_buffers: false
+ddp_bucket_cap_mb: 25
+ddp_timeout: 7200
+debug: null
+deepspeed: null
+evaluation_strategy: 'no'
+flash_attention: false
+flash_attn_cross_entropy: false
+flash_attn_rms_norm: false
+fp16: false
+fsdp: null
+fsdp_config: null
+gpu_memory_limit: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+group_by_length: false
+hub_model_commit_message: Training checkpoint - step {current_step}
+hub_model_id: dada22231/2296f73f-99bd-4e6b-95ca-b2cd4a1e78af
+hub_model_revision: main
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0002
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 256
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_modules_to_save:
+- embed_tokens
+- lm_head
+lora_r: 128
+lora_target_linear: true
+lr_scheduler: constant_with_warmup
+max_memory: null
+max_steps: 1500
+micro_batch_size: 8
+mlflow_experiment_name: /tmp/ecb638fa488a6a93_train_data.json
+model_type: AutoModelForCausalLM
+optimizer: adamw_torch_fused
+output_dir: ./outputs
+pad_to_sequence_len: true
+push_dataset_card: false
+push_to_hub: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: true
+save_lora_adapter: false
+save_merged_lora_model: true
+save_only_model: true
+save_safetensors: true
+save_steps: 75
+save_strategy: steps
+save_total_limit: 5
+sequence_len: 4096
+special_tokens: null
+strict: false
+tf32: true
+tokenizer_type: AutoTokenizer
+torch_compile: false
+torch_compile_backend: inductor
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0
+wandb_entity: null
+wandb_mode: online
+wandb_name: dcaeb768-0f9e-4c34-920e-d80288595c2a
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: dcaeb768-0f9e-4c34-920e-d80288595c2a
+warmup_steps: 150
+weight_decay: 0.01
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 2296f73f-99bd-4e6b-95ca-b2cd4a1e78af
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B) on an unknown 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant_with_warmup
+- lr_scheduler_warmup_steps: 150
+- training_steps: 1500
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.7.1+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/SmolLM-1.7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465744cb64224a402eabbe8d37014239041dbc83f5545b208ef159d0fe46a18c
+size 981512984

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

chat_template.jinja

@@ -0,0 +1,5 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
+
+'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "do_sample": true,
+  "eos_token_id": 50256,
+  "transformers_version": "4.51.3"
+}

runs/Jun09_23-22-31_c114e6e933dd/events.out.tfevents.1749511355.c114e6e933dd.281.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29549a0ad006d8bc912aad7003ba48351b1251cf4cb142801e51af06509dd80
+size 13612

runs/Jun09_23-31-32_9c235502913a/events.out.tfevents.1749511899.9c235502913a.281.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82fb21d4c6709ed19de023a56fe96bf99c64a9d55de9bd24a6d56eca957bf785
+size 7964

runs/Jun10_08-35-17_13b1206c444e/events.out.tfevents.1749544520.13b1206c444e.281.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c1eabc3881eb8b03f46a893ca5ff6923e893e5622f62e719adc1ce8defcf173
+size 2342413

runs/Jun10_15-32-42_9609e117153f/events.out.tfevents.1749569582.9609e117153f.280.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fb82e81c9f7a16b79e78ac8386a6676e2bb46540a1e64ee13e61e17e6e61f59
+size 7735

runs/Jun10_15-36-01_4ac9cfab9c4f/events.out.tfevents.1749569781.4ac9cfab9c4f.280.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89ae32d0ddfce162814d3e2f659898d441b422d823bba93c39b3d2aba88b1d6
+size 7762

runs/Jun10_15-41-31_66aabbe28b99/events.out.tfevents.1749570111.66aabbe28b99.280.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e300b1341d7d49a7bb644fd40e7550b0525f07835e57a1f79fdcb6c9e2fb4e99
+size 7760

runs/Jun10_15-43-46_ed3e63477d80/events.out.tfevents.1749570233.ed3e63477d80.281.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0190cdb1353a4900e54ddca040ce5f57075cab85fb6cdebc355c831112295cd6
+size 2865114

runs/Jun10_15-43-49_cb3333f60b74/events.out.tfevents.1749570249.cb3333f60b74.280.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29bce4e30493f9064af0cf40e1a2b81732c0ce13e598d20be02b44fb28940abb
+size 11816

runs/Jun10_15-52-24_79913464786a/events.out.tfevents.1749570765.79913464786a.280.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22201be31b78560a708bd4c403c8f2ffca43e5e553364964b16be4805a70ba55
+size 7732

runs/Jun10_15-55-31_d2fb0129b76c/events.out.tfevents.1749570951.d2fb0129b76c.280.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bce72a313ace4b3ad3d38e7509f82e40abbc551d6876ef1a10b06259c895d089
+size 1107390

runs/Jun10_18-18-52_281190cd23f4/events.out.tfevents.1749579538.281190cd23f4.281.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e0e99b9d2393448a8df149d455afe759a2a04f58f7ae11ca18d308cebd9ff8
+size 7904

runs/Jun10_18-50-44_658ebac1f2a9/events.out.tfevents.1749581450.658ebac1f2a9.281.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631994a159ba98dce996e687535d7db3079de1d02261c57f5c41a2d376ccff4f
+size 7877

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<empty_output>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,155 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<empty_output>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d03a7322ecf5b32667396bffe140e92ebcd720c4f3d7af5b2a9578dbddafb2b
+size 8273