Training in progress, step 100

README.md

@@ -0,0 +1,58 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- HuggingFaceH4/ultrachat_200k
+library_name: transformers
+model_name: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+- alignment-handbook
+licence: license
+---
+
+# Model Card for mistralai/Mistral-7B-v0.1
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the [['HuggingFaceH4/ultrachat_200k']](https://huggingface.co/datasets/['HuggingFaceH4/ultrachat_200k']) dataset.
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="awsuineg/zephyr-7b-sft-qlora", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.1
+- Transformers: 4.46.2
+- Pytorch: 2.5.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827ec2d540ea378ca61360edf3b0399c4ea7e367b0e4b49680fc2b00dcef513a
+size 671149168

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.1487027058043781e+19,
+    "train_loss": 0.0,
+    "train_runtime": 0.0143,
+    "train_samples": 207864,
+    "train_samples_per_second": 9715326.166,
+    "train_steps_per_second": 404831.526
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

runs/Nov17_16-17-16_d28f7adca72c/events.out.tfevents.1731860823.d28f7adca72c.1455329.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d327dd3dc7f6f0ec6201ce542062b2886ab83a0a7c86c6cac6f1f856e31ffcc0
+size 6644

runs/Nov17_16-45-53_d28f7adca72c/events.out.tfevents.1731862042.d28f7adca72c.1466324.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f931ef15df23c349fad169b9f7462d1db630d2d2a78816699b9c0d8885ee28
+size 20677

runs/Nov17_17-08-29_d28f7adca72c/events.out.tfevents.1731863352.d28f7adca72c.1476963.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40fe602a887d2e907317a93e28b12437738b4a004f0774e2b3bda2fb5b81b1ca
+size 17616

runs/Nov17_17-26-10_d28f7adca72c/events.out.tfevents.1731864414.d28f7adca72c.1485127.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992fda2e94e53c29798c0c4351607b4e9c8f8cbbe49f203404f3aaadd94990ac
+size 6644

runs/Nov17_17-54-38_d28f7adca72c/events.out.tfevents.1731866140.d28f7adca72c.1493987.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa40fcb0a2f01d5ea8a6cff0f9ce973b0d525f05cad2cabeabef0adde757e4e
+size 10020

runs/Nov17_18-05-42_d28f7adca72c/events.out.tfevents.1731866808.d28f7adca72c.1497789.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ee1184685221e6572a692b6e187314310b0b875a2752b07247e0a119d24c24
+size 229874

runs/Nov18_09-06-30_d28f7adca72c/events.out.tfevents.1731920841.d28f7adca72c.1609162.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8319038ea07c5da8c1ca7771696a58956a792eef296dcd151f6d4fed81baafa
+size 6998

runs/Nov20_07-40-49_d28f7adca72c/events.out.tfevents.1732088488.d28f7adca72c.2261562.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2e509964aed74faa557e627c0de135c83923305e7b4690aab75bbb4d9c825f
+size 6644

runs/Nov20_07-45-35_d28f7adca72c/events.out.tfevents.1732088781.d28f7adca72c.2263555.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43168300e80ab14dedc9681882351d0382d6f044c740e17338fd467d232580d3
+size 6644

runs/Nov20_08-00-39_d28f7adca72c/events.out.tfevents.1732089682.d28f7adca72c.2269100.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa39bb29ac4889858038b98286c9be6cd73011a8faad911c09e08f6c816b725
+size 6644

runs/Nov20_08-03-58_d28f7adca72c/events.out.tfevents.1732089882.d28f7adca72c.2270466.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bb5de9fee45edbfb36d13a6b3f444acc72e9eccaa32c351e7d912a217d403a1
+size 6644

runs/Nov20_08-06-30_d28f7adca72c/events.out.tfevents.1732090033.d28f7adca72c.2271569.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b03023784e0f0a70ff615754a4cc0d83db8fb3f8b44839a46bbaab0c3606eca0
+size 6644

runs/Nov20_08-08-06_d28f7adca72c/events.out.tfevents.1732090139.d28f7adca72c.2272351.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4c896a1c2e2918b1b9df3f8fb65cd626a9f4904d66f83c42e8136461d47a2b
+size 6998

runs/Nov21_18-45-34_d28f7adca72c/events.out.tfevents.1732214764.d28f7adca72c.2391037.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e180aae62d2266c11f93b463fd093e21637029f9bc81b56e65611563a0daece
+size 10996

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.1487027058043781e+19,
+    "train_loss": 0.0,
+    "train_runtime": 0.0143,
+    "train_samples": 207864,
+    "train_samples_per_second": 9715326.166,
+    "train_steps_per_second": 404831.526
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b89205840e308ec8a98be86d47c7f58f4520c0bd57a7c95af8f7f45a0bc1dd
+size 6328