End of training

README.md

@@ -2,12 +2,16 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.1
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: zephyr-7b-sft-qlora
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-qlora
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-qlora](https://huggingface.co/alignment-handbook/zephyr-7b-sft-qlora) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9918
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.9918339848518372,
+    "eval_runtime": 1941.2068,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 7.949,
+    "eval_steps_per_second": 0.994,
     "train_loss": 0.9995975574413953,
     "train_runtime": 68593.2406,
     "train_samples": 207864,

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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,
+  "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": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9918339848518372,
+    "eval_runtime": 1941.2068,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 7.949,
+    "eval_steps_per_second": 0.994
+}

runs/Apr15_11-10-02_holygpu8a17102.rc.fas.harvard.edu/events.out.tfevents.1713264461.holygpu8a17102.rc.fas.harvard.edu.2490248.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32805e47a2952e61215699aa8afb8b0fd4bfd77a19b545049f2ac0f6877e29aa
+size 364