Upload folder using huggingface_hub

README.md

@@ -1,3 +1,181 @@
 ---
-license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: workspace/output/cosmosage_qa
+  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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: /workspace/output/cosmosage_base/
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+is_mistral_derived_model: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: /workspace/input/datasets/qa_tune/arxiv_metadata_qa3.jsonl
+    type: sharegpt
+  - path: /workspace/input/datasets/qa_tune/arxiv_refined_qa.jsonl
+    type: sharegpt
+  - path: /workspace/input/datasets/qa_tune/arxiv_summary3.jsonl
+    type: sharegpt
+  - path: /workspace/input/datasets/qa_tune/cosmology_qa.jsonl
+    type: alpaca_chat.load_qa 
+  - path: /workspace/input/datasets/qa_tune/openhermes2_5.jsonl
+    type: sharegpt
+  - path: /workspace/input/datasets/qa_tune/cosmology_textbooks_qa.jsonl
+    type: alpaca_chat.load_qa 
+  - path: /workspace/input/datasets/qa_tune/physics_astro_qa.jsonl
+    type: alpaca_chat.load_qa 
+
+dataset_prepared_path: /workspace/output/qa_tune_prepared
+val_set_size: 0.001
+output_dir: /workspace/output/cosmosage_qa
+
+chat_template: inst
+
+adapter: 
+lora_model_dir:
+
+sequence_len: 4096
+sample_packing: true
+pad_to_sequence_len: true
+
+lora_r:
+lora_alpha:
+lora_dropout:
+lora_target_modules:
+lora_target_linear: 
+lora_fan_in_fan_out:
+
+seed: 702
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 4
+num_epochs: 2.0
+optimizer: adamw_torch
+lr_scheduler: linear
+learning_rate: 0.000002
+max_grad_norm: 3.0
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16: false 
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 100
+eval_steps: 0.05
+eval_table_size:
+eval_table_max_new_tokens: 128
+saves_per_epoch: 1
+save_total_limit: 2
+debug:
+deepspeed: /workspace/axolotl/deepspeed_configs/zero1.json
+weight_decay:
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+
+ddp_timeout: 7200000
+
+```
+
+</details><br>
+
+# workspace/output/cosmosage_qa
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5673
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-06
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 702
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.1004        | 0.0   | 1     | 1.1450          |
+| 0.7343        | 0.1   | 909   | 0.7093          |
+| 0.697         | 0.2   | 1818  | 0.6630          |
+| 0.6386        | 0.3   | 2727  | 0.6380          |
+| 0.5687        | 0.4   | 3636  | 0.6212          |
+| 0.5857        | 0.5   | 4545  | 0.6083          |
+| 0.6161        | 0.6   | 5454  | 0.5986          |
+| 0.522         | 0.7   | 6363  | 0.5894          |
+| 0.5563        | 0.8   | 7272  | 0.5825          |
+| 0.6176        | 0.9   | 8181  | 0.5766          |
+| 0.5948        | 1.0   | 9090  | 0.5719          |
+| 0.4269        | 1.08  | 9999  | 0.5817          |
+| 0.4858        | 1.18  | 10908 | 0.5796          |
+| 0.4909        | 1.28  | 11817 | 0.5765          |
+| 0.4325        | 1.38  | 12726 | 0.5746          |
+| 0.4037        | 1.48  | 13635 | 0.5720          |
+| 0.507         | 1.58  | 14544 | 0.5706          |
+| 0.4778        | 1.68  | 15453 | 0.5697          |
+| 0.4599        | 1.78  | 16362 | 0.5683          |
+| 0.4515        | 1.88  | 17271 | 0.5673          |
+
+
+### Framework versions
+
+- Transformers 4.38.0.dev0
+- Pytorch 2.0.1+cu118
+- Datasets 2.17.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/workspace/output/cosmosage_base/",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e03c47e6826259d2b01ddadf31ed6f8b667a8bc8bc0ba725b650f27d5d34e3
+size 14483504421

runs/Feb17_02-13-35_ga1004/events.out.tfevents.1708103668.ga1004.2237941.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af8bbfffdd93ec1a92a80bc2044733108315abadc7667163214b91514d04650
+size 2869915

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "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 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}