Training in progress, epoch 1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-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": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "q_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 sha256:649ab626fe435a012ec7190978985fb1ae753fb0abc56e3e4ecb50652457d438
+size 323014560

trainer_log.jsonl

@@ -1,19 +1,6 @@
-{"current_steps": 1, "total_steps": 18, "loss": 1.2823, "lr": 5e-06, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:01:20", "remaining_time": "0:22:55"}
-{"current_steps": 2, "total_steps": 18, "loss": 1.3191, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:02:25", "remaining_time": "0:19:25"}
-{"current_steps": 3, "total_steps": 18, "loss": 1.2058, "lr": 9.903926402016153e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:03:30", "remaining_time": "0:17:32"}
-{"current_steps": 4, "total_steps": 18, "loss": 1.1293, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:04:35", "remaining_time": "0:16:03"}
-{"current_steps": 5, "total_steps": 18, "loss": 1.144, "lr": 9.157348061512728e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:05:39", "remaining_time": "0:14:43"}
-{"current_steps": 6, "total_steps": 18, "loss": 1.0848, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:06:34", "remaining_time": "0:13:09"}
-{"current_steps": 7, "total_steps": 18, "loss": 1.0694, "lr": 7.777851165098012e-06, "epoch": 1.1666666666666667, "percentage": 38.89, "elapsed_time": "0:08:30", "remaining_time": "0:13:22"}
-{"current_steps": 8, "total_steps": 18, "loss": 1.0375, "lr": 6.913417161825449e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:09:35", "remaining_time": "0:11:59"}
-{"current_steps": 9, "total_steps": 18, "loss": 1.0121, "lr": 5.975451610080643e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:10:40", "remaining_time": "0:10:40"}
-{"current_steps": 10, "total_steps": 18, "loss": 0.9652, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:11:44", "remaining_time": "0:09:23"}
-{"current_steps": 11, "total_steps": 18, "loss": 0.9329, "lr": 4.02454838991936e-06, "epoch": 1.8333333333333335, "percentage": 61.11, "elapsed_time": "0:12:49", "remaining_time": "0:08:09"}
-{"current_steps": 12, "total_steps": 18, "loss": 0.9326, "lr": 3.0865828381745515e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:13:44", "remaining_time": "0:06:52"}
-{"current_steps": 13, "total_steps": 18, "loss": 0.9088, "lr": 2.2221488349019903e-06, "epoch": 2.1666666666666665, "percentage": 72.22, "elapsed_time": "0:15:45", "remaining_time": "0:06:03"}
-{"current_steps": 14, "total_steps": 18, "loss": 0.8942, "lr": 1.4644660940672628e-06, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "0:16:49", "remaining_time": "0:04:48"}
-{"current_steps": 15, "total_steps": 18, "loss": 0.9139, "lr": 8.426519384872733e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:17:54", "remaining_time": "0:03:34"}
-{"current_steps": 16, "total_steps": 18, "loss": 0.905, "lr": 3.8060233744356634e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "0:18:59", "remaining_time": "0:02:22"}
-{"current_steps": 17, "total_steps": 18, "loss": 0.9043, "lr": 9.607359798384785e-08, "epoch": 2.8333333333333335, "percentage": 94.44, "elapsed_time": "0:20:04", "remaining_time": "0:01:10"}
-{"current_steps": 18, "total_steps": 18, "loss": 0.8928, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:20:59", "remaining_time": "0:00:00"}
-{"current_steps": 18, "total_steps": 18, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:22:31", "remaining_time": "0:00:00"}
+{"current_steps": 1, "total_steps": 18, "loss": 1.2823, "lr": 5e-06, "epoch": 0.16666666666666666, "percentage": 5.56, "elapsed_time": "0:01:21", "remaining_time": "0:23:04"}
+{"current_steps": 2, "total_steps": 18, "loss": 1.3191, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:02:24", "remaining_time": "0:19:17"}
+{"current_steps": 3, "total_steps": 18, "loss": 1.287, "lr": 9.903926402016153e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:03:27", "remaining_time": "0:17:19"}
+{"current_steps": 4, "total_steps": 18, "loss": 1.2686, "lr": 9.619397662556434e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:04:31", "remaining_time": "0:15:49"}
+{"current_steps": 5, "total_steps": 18, "loss": 1.294, "lr": 9.157348061512728e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:05:34", "remaining_time": "0:14:30"}
+{"current_steps": 6, "total_steps": 18, "loss": 1.2551, "lr": 8.535533905932739e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:06:28", "remaining_time": "0:12:57"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89665dc44e089d3c3a046b6644efba1a5ef05727fb074154081441c9acbf307b
+oid sha256:18dde55e6e0031fae769fe4bfcde9bbf091e3587da8a8a9b624bd654aa093b7e
 size 7224