End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9970326409495549,
+    "eval_loss": 1.881588339805603,
+    "eval_runtime": 1.5168,
+    "eval_samples": 15,
+    "eval_samples_per_second": 9.23,
+    "eval_steps_per_second": 0.659,
     "total_flos": 8.227900459906499e+17,
     "train_loss": 1.2795698436952772,
     "train_runtime": 2845.3749,

config.json

@@ -0,0 +1,43 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 32768,
+  "eos_token_id": 32769,
+  "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,
+  "pad_token_id": 32769,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "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": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 32770
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9970326409495549,
+    "eval_loss": 1.881588339805603,
+    "eval_runtime": 1.5168,
+    "eval_samples": 15,
+    "eval_samples_per_second": 9.23,
+    "eval_steps_per_second": 0.659
+}

runs/Nov17_19-51-59_main-lora-mistral7b-closedqa-0-0/events.out.tfevents.1731894677.main-lora-mistral7b-closedqa-0-0.457.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ce26c90a1acdead8f400952ce5d3c31e8c8303f6f574c60ec9f2e0df713e6c
+size 359