Training in progress, step 71

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": [
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_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 sha256:2b4802c18977ac0b00393b94a09874f838e1a40dc3321995124a0be106ec89a5
+size 207244392

tokenizer_config.json

@@ -2070,7 +2070,7 @@
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 16000,
+  "model_max_length": 4096,
   "pad_token": "<|eot_id|>",
   "padding_side": "right",
   "split_special_tokens": false,

trainer_log.jsonl

@@ -1,9 +1,10 @@
-{"current_steps": 10, "total_steps": 71, "loss": 1.0004, "lr": 9.975153876827008e-06, "epoch": 0.14010507880910683, "percentage": 14.08, "elapsed_time": "0:09:31", "remaining_time": "0:58:04"}
-{"current_steps": 20, "total_steps": 71, "loss": 0.4861, "lr": 9.131193871579975e-06, "epoch": 0.28021015761821366, "percentage": 28.17, "elapsed_time": "0:18:58", "remaining_time": "0:48:22"}
-{"current_steps": 30, "total_steps": 71, "loss": 0.3534, "lr": 7.281053286765816e-06, "epoch": 0.4203152364273205, "percentage": 42.25, "elapsed_time": "0:28:22", "remaining_time": "0:38:47"}
-{"current_steps": 40, "total_steps": 71, "loss": 0.2909, "lr": 4.875346541309637e-06, "epoch": 0.5604203152364273, "percentage": 56.34, "elapsed_time": "0:37:31", "remaining_time": "0:29:04"}
-{"current_steps": 50, "total_steps": 71, "loss": 0.2979, "lr": 2.5000000000000015e-06, "epoch": 0.7005253940455342, "percentage": 70.42, "elapsed_time": "0:46:46", "remaining_time": "0:19:38"}
-{"current_steps": 50, "total_steps": 71, "eval_loss": 0.30582478642463684, "epoch": 0.7005253940455342, "percentage": 70.42, "elapsed_time": "0:47:19", "remaining_time": "0:19:52"}
-{"current_steps": 60, "total_steps": 71, "loss": 0.272, "lr": 7.33545591839222e-07, "epoch": 0.840630472854641, "percentage": 84.51, "elapsed_time": "0:57:00", "remaining_time": "0:10:27"}
-{"current_steps": 70, "total_steps": 71, "loss": 0.2585, "lr": 6.215393905388278e-09, "epoch": 0.9807355516637478, "percentage": 98.59, "elapsed_time": "1:06:27", "remaining_time": "0:00:56"}
-{"current_steps": 71, "total_steps": 71, "epoch": 0.9947460595446584, "percentage": 100.0, "elapsed_time": "1:08:23", "remaining_time": "0:00:00"}
+{"current_steps": 10, "total_steps": 71, "loss": 0.592, "lr": 9.975153876827008e-05, "epoch": 0.14010507880910683, "percentage": 14.08, "elapsed_time": "0:14:29", "remaining_time": "1:28:22"}
+{"current_steps": 20, "total_steps": 71, "loss": 0.3707, "lr": 9.131193871579975e-05, "epoch": 0.28021015761821366, "percentage": 28.17, "elapsed_time": "0:28:47", "remaining_time": "1:13:25"}
+{"current_steps": 30, "total_steps": 71, "loss": 0.2838, "lr": 7.281053286765815e-05, "epoch": 0.4203152364273205, "percentage": 42.25, "elapsed_time": "0:43:01", "remaining_time": "0:58:48"}
+{"current_steps": 30, "total_steps": 71, "eval_loss": 0.3709219992160797, "epoch": 0.4203152364273205, "percentage": 42.25, "elapsed_time": "0:43:40", "remaining_time": "0:59:41"}
+{"current_steps": 40, "total_steps": 71, "loss": 0.2769, "lr": 4.875346541309637e-05, "epoch": 0.5604203152364273, "percentage": 56.34, "elapsed_time": "0:58:04", "remaining_time": "0:45:00"}
+{"current_steps": 50, "total_steps": 71, "loss": 0.2928, "lr": 2.500000000000001e-05, "epoch": 0.7005253940455342, "percentage": 70.42, "elapsed_time": "1:12:17", "remaining_time": "0:30:21"}
+{"current_steps": 60, "total_steps": 71, "loss": 0.2593, "lr": 7.33545591839222e-06, "epoch": 0.840630472854641, "percentage": 84.51, "elapsed_time": "1:26:37", "remaining_time": "0:15:52"}
+{"current_steps": 60, "total_steps": 71, "eval_loss": 0.3455033600330353, "epoch": 0.840630472854641, "percentage": 84.51, "elapsed_time": "1:27:16", "remaining_time": "0:16:00"}
+{"current_steps": 70, "total_steps": 71, "loss": 0.2559, "lr": 6.215393905388278e-08, "epoch": 0.9807355516637478, "percentage": 98.59, "elapsed_time": "1:41:38", "remaining_time": "0:01:27"}
+{"current_steps": 71, "total_steps": 71, "epoch": 0.9947460595446584, "percentage": 100.0, "elapsed_time": "1:44:24", "remaining_time": "0:00:00"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96db96962f8ed8d2054dc55eb2981bbc287edc5b3ae87961633db253366e2e43
+oid sha256:e5c57957ce40c5422694e24fa90d267daaaba5e1013ef807afcc0aa0d1d22739
 size 7608