End of training

README.md

@@ -2,10 +2,18 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - unsloth
 - generated_from_trainer
+- trl
+- sft
+- unsloth
+- generated_from_trainer
+- unsloth
+datasets:
+- zeta-labs/mind2web_combined_236_18_01
 base_model: unsloth/mistral-7b
 model-index:
 - name: shortstep_test
@@ -17,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # shortstep_test
 
-This model is a fine-tuned version of [unsloth/mistral-7b](https://huggingface.co/unsloth/mistral-7b) on the None dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the zeta-labs/mind2web_combined_236_18_01 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.3442
 

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "unsloth/mistral-7b",
+  "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,
+  "pad_token_id": 2,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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": "4.37.0",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}