End of training

README.md

@@ -1,8 +1,13 @@
 ---
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+datasets:
+- GaetanMichelet/chat-60_ft_task-3
+- GaetanMichelet/chat-120_ft_task-3
+- GaetanMichelet/chat-180_ft_task-3
 library_name: peft
 license: llama3.1
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -16,9 +21,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama-31-8B_task-3_180-samples_config-2
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the GaetanMichelet/chat-60_ft_task-3, the GaetanMichelet/chat-120_ft_task-3 and the GaetanMichelet/chat-180_ft_task-3 datasets.
 It achieves the following results on the evaluation set:
-- Loss: 0.8418
+- Loss: 0.4326
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 14.941176470588236,
+    "eval_loss": 0.4326106309890747,
+    "eval_runtime": 31.8529,
+    "eval_samples": 36,
+    "eval_samples_per_second": 1.13,
+    "eval_steps_per_second": 1.13,
     "total_flos": 1.5999389691753267e+17,
     "train_loss": 0.5077414073886013,
     "train_runtime": 5870.3299,

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "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_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 14.941176470588236,
+    "eval_loss": 0.4326106309890747,
+    "eval_runtime": 31.8529,
+    "eval_samples": 36,
+    "eval_samples_per_second": 1.13,
+    "eval_steps_per_second": 1.13
+}

runs/Aug19_16-10-40_9mqd6r3-l/events.out.tfevents.1724082574.9mqd6r3-l.78344.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef49a5914415696acc65664cd51c6196a812837ba5121ee76804e450b2847f7
+size 354