End of training

README.md

@@ -2,11 +2,18 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- nthakur/deita-10k-v0-instruct
+- nthakur/Bactrian-X-23-lang-instruct
+- nthakur/GSM8KInstruct-Parallel-instruct
+- nthakur/ultrachat-200k-instruct
 base_model: unsloth/mistral-7b-v0.2
 model-index:
 - name: mistral-7b-v0.2-sft-mix-23rd-mar-v0
@@ -18,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-7b-v0.2-sft-mix-23rd-mar-v0
 
-This model is a fine-tuned version of [unsloth/mistral-7b-v0.2](https://huggingface.co/unsloth/mistral-7b-v0.2) on the generator dataset.
+This model is a fine-tuned version of [unsloth/mistral-7b-v0.2](https://huggingface.co/unsloth/mistral-7b-v0.2) on the nthakur/deita-10k-v0-instruct, the nthakur/Bactrian-X-23-lang-instruct, the nthakur/GSM8KInstruct-Parallel-instruct and the nthakur/ultrachat-200k-instruct datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.9631
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.9631486535072327,
+    "eval_runtime": 5388.1939,
+    "eval_samples": 104366,
+    "eval_samples_per_second": 5.752,
+    "eval_steps_per_second": 0.12,
     "train_loss": 0.9572911218241059,
     "train_runtime": 140901.3648,
     "train_samples": 915466,

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "unsloth/mistral-7b-v0.2",
+  "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": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.9631486535072327,
+    "eval_runtime": 5388.1939,
+    "eval_samples": 104366,
+    "eval_samples_per_second": 5.752,
+    "eval_steps_per_second": 0.12
+}