End of training

README.md

@@ -1,8 +1,12 @@
 ---
 base_model: google/gemma-2-2b-it
+datasets:
+- GaetanMichelet/chat-60_ft_task-1_auto
+- GaetanMichelet/chat-120_ft_task-1_auto
 library_name: peft
 license: gemma
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -16,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Gemma-2-2B_task-1_120-samples_config-1_auto
 
-This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the None dataset.
+This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the GaetanMichelet/chat-60_ft_task-1_auto and the GaetanMichelet/chat-120_ft_task-1_auto datasets.
 It achieves the following results on the evaluation set:
-- Loss: 2.3115
+- Loss: 0.9736
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 12.0,
+    "eval_loss": 0.9736120104789734,
+    "eval_runtime": 2.3113,
+    "eval_samples": 24,
+    "eval_samples_per_second": 10.384,
+    "eval_steps_per_second": 10.384,
     "total_flos": 4581273894912000.0,
     "train_loss": 0.5821334374221888,
     "train_runtime": 471.3358,

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "google/gemma-2-2b-it",
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1,
+    107
+  ],
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2304,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "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"
+  },
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 256000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 12.0,
+    "eval_loss": 0.9736120104789734,
+    "eval_runtime": 2.3113,
+    "eval_samples": 24,
+    "eval_samples_per_second": 10.384,
+    "eval_steps_per_second": 10.384
+}

runs/Aug22_22-03-40_9mqd6r3-l/events.out.tfevents.1724357526.9mqd6r3-l.738300.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219acd15f3135a95b69859c157149da8c891181accb4d60a0fa2c91d86819603
+size 359