End of training

all_results.json

@@ -2,7 +2,7 @@
     "epoch": 0.8844339622641509,
     "total_flos": 1.393076937424896e+19,
     "train_loss": 0.0,
-    "train_runtime": 0.0093,
+    "train_runtime": 0.0091,
     "train_samples": 100,
     "train_samples_per_second": 0.0,
     "train_steps_per_second": 0.0

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "./ckpts/Mistral-7B-Instruct-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,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "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": "4.41.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

runs/May25_13-39-15_br1t43-s3-25/events.out.tfevents.1716644371.br1t43-s3-25.186970.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36c3716f6ce74440954d2c1f34976c672e57a36d91536e148d7495cd83a4259
+size 5808

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 0.8844339622641509,
     "total_flos": 1.393076937424896e+19,
     "train_loss": 0.0,
-    "train_runtime": 0.0093,
+    "train_runtime": 0.0091,
     "train_samples": 100,
     "train_samples_per_second": 0.0,
     "train_steps_per_second": 0.0

trainer_state.json

@@ -6320,7 +6320,7 @@
       "step": 4500,
       "total_flos": 1.393076937424896e+19,
       "train_loss": 0.0,
-      "train_runtime": 0.0093,
+      "train_runtime": 0.0091,
       "train_samples_per_second": 0.0,
       "train_steps_per_second": 0.0
     }