End of training

README.md

@@ -1,10 +1,11 @@
 ---
 base_model: mistralai/Mistral-7B-v0.3
 datasets:
-- generator
+- llama-duo/synth_summarize_dataset_dedup
 library_name: peft
 license: apache-2.0
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral_7b_0_3-summarize-gpt4o-128k
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the llama-duo/synth_summarize_dataset_dedup dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.0012
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 9.979633401221996,
+    "eval_loss": 2.0012366771698,
+    "eval_runtime": 0.3604,
+    "eval_samples": 25,
+    "eval_samples_per_second": 33.301,
+    "eval_steps_per_second": 2.775,
     "total_flos": 6.866432485157241e+18,
     "train_loss": 0.5986210168137842,
     "train_runtime": 9994.3917,

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 32768,
+  "eos_token_id": 32769,
+  "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,
+  "pad_token_id": 32769,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 32770
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.979633401221996,
+    "eval_loss": 2.0012366771698,
+    "eval_runtime": 0.3604,
+    "eval_samples": 25,
+    "eval_samples_per_second": 33.301,
+    "eval_steps_per_second": 2.775
+}

runs/Aug10_08-59-16_e8f6cb577ded/events.out.tfevents.1723290551.e8f6cb577ded.287371.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c03d73aaf973ecb543091f8cc524988d21353f414df4f07658f62cb0952839
+size 359