End of training

README.md

@@ -1,8 +1,13 @@
 ---
 base_model: mistralai/Mistral-7B-Instruct-v0.3
+datasets:
+- GaetanMichelet/chat-60_ft_task-1_auto
+- GaetanMichelet/chat-120_ft_task-1_auto
+- GaetanMichelet/chat-180_ft_task-1_auto
 library_name: peft
 license: apache-2.0
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -16,9 +21,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Mistral-7B_task-1_180-samples_config-2_full_auto
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the GaetanMichelet/chat-60_ft_task-1_auto, the GaetanMichelet/chat-120_ft_task-1_auto and the GaetanMichelet/chat-180_ft_task-1_auto datasets.
 It achieves the following results on the evaluation set:
-- Loss: 1.2855
+- Loss: 0.8198
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 12.0,
+    "eval_loss": 0.819804310798645,
+    "eval_runtime": 14.9939,
+    "eval_samples": 36,
+    "eval_samples_per_second": 2.401,
+    "eval_steps_per_second": 2.401,
     "total_flos": 2.747429741710541e+16,
     "train_loss": 0.645151332459029,
     "train_runtime": 1987.9039,

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "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,
+  "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": 32768
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 12.0,
+    "eval_loss": 0.819804310798645,
+    "eval_runtime": 14.9939,
+    "eval_samples": 36,
+    "eval_samples_per_second": 2.401,
+    "eval_steps_per_second": 2.401
+}

runs/Aug25_18-02-36_9mqd6r3-l/events.out.tfevents.1724603788.9mqd6r3-l.889587.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea9f22480c0dce03206496dc6d0bee5e41c90c758bf100b445fd8377eb02b08
+size 354