End of training

README.md

@@ -3,6 +3,7 @@ library_name: peft
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.1
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.6666666666666665,
+    "eval_loss": 0.8420554995536804,
+    "eval_runtime": 1.5729,
+    "eval_samples": 20,
+    "eval_samples_per_second": 1.907,
+    "eval_steps_per_second": 0.636,
     "total_flos": 2759020687392768.0,
     "train_loss": 1.4311530351638795,
     "train_runtime": 40.306,

config.json

@@ -0,0 +1,28 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-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,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.6666666666666665,
+    "eval_loss": 0.8420554995536804,
+    "eval_runtime": 1.5729,
+    "eval_samples": 20,
+    "eval_samples_per_second": 1.907,
+    "eval_steps_per_second": 0.636
+}

runs/Dec28_12-38-53_xe8545-a100-02/events.out.tfevents.1735386007.xe8545-a100-02.492737.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f30dfb01da8568300c843986c6c2fcfad6c5b05bca354f422164f464ebcd60e1
+size 354