Training in progress, step 4

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: Qwen3-235B-test
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 

adapter_config.json

@@ -25,10 +25,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "q_proj",
-    "v_proj",
     "o_proj",
-    "k_proj"
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:633baa6615812857a5c1a995933ff86fa3d7dced1bf0bc0d0213e5afbc48286f
+oid sha256:c607d6009b8e812634740a9c574b7dea0715f3b7659ebbf1e0d4d684db97becd
 size 101748240

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 1119013765644288.0,
+    "train_loss": 0.5027180115381876,
+    "train_runtime": 2280.628,
+    "train_samples": 6000,
+    "train_samples_per_second": 0.253,
+    "train_steps_per_second": 0.001
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 1119013765644288.0,
+    "train_loss": 0.5027180115381876,
+    "train_runtime": 2280.628,
+    "train_samples": 6000,
+    "train_samples_per_second": 0.253,
+    "train_steps_per_second": 0.001
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.096,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.08931520782232892,
+      "learning_rate": 0.0,
+      "loss": 0.5061,
+      "num_tokens": 2486796.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.0893725392434335,
+      "learning_rate": 4e-05,
+      "loss": 0.4989,
+      "num_tokens": 4894749.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.08786701459200193,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.5032,
+      "num_tokens": 7236668.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.096,
+      "step": 3,
+      "total_flos": 1119013765644288.0,
+      "train_loss": 0.5027180115381876,
+      "train_runtime": 2280.628,
+      "train_samples_per_second": 0.253,
+      "train_steps_per_second": 0.001
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 3,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1119013765644288.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eae859289f663cc784ee7d7fe9ad753ae5c9b1f49727b3515e9b37fe90fc2a6b
+oid sha256:0cead84b001a22971ebeab4558a7457a72948bcd09f35705d5493b173c55e4aa
 size 7416