Training in progress, step 28

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555c830797d68f6cd480f6b5757ec531790bca3a34311ecee191a42962c871fd
+size 207244392

tokenizer_config.json

@@ -2070,7 +2070,7 @@
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 8192,
+  "model_max_length": 4096,
   "pad_token": "<|eot_id|>",
   "padding_side": "right",
   "split_special_tokens": false,

trainer_log.jsonl

@@ -1,3 +1,3 @@
-{"current_steps": 10, "total_steps": 28, "loss": 0.8518, "lr": 8.18711994874345e-06, "epoch": 0.35714285714285715, "percentage": 35.71, "elapsed_time": "0:02:28", "remaining_time": "0:04:27"}
-{"current_steps": 20, "total_steps": 28, "loss": 0.5541, "lr": 2.320866025105016e-06, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:04:55", "remaining_time": "0:01:58"}
-{"current_steps": 28, "total_steps": 28, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:07:48", "remaining_time": "0:00:00"}
+{"current_steps": 10, "total_steps": 28, "loss": 0.9027, "lr": 8.18711994874345e-05, "epoch": 0.35714285714285715, "percentage": 35.71, "elapsed_time": "0:13:26", "remaining_time": "0:24:11"}
+{"current_steps": 20, "total_steps": 28, "loss": 0.5519, "lr": 2.3208660251050158e-05, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:26:40", "remaining_time": "0:10:40"}
+{"current_steps": 28, "total_steps": 28, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:38:42", "remaining_time": "0:00:00"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21026669ea2e9446fb5b8c48606587ddff8d5bb6ac32acae5a52be4cda254f6d
+oid sha256:7e0947bee77408dfd8c8570dc593f3b0328326d9dcc6ea4f23a777078d30af2c
 size 7608