Training in progress, step 4

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: Qwen3-235B-test3
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 

adapter_config.json

@@ -25,10 +25,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
+    "k_proj",
     "q_proj",
-    "k_proj"
+    "o_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:a38e4cddb114cc873c7db5475260cc4934e5cf5032159a2d5c4f656b1b7cfb55
+oid sha256:835f76007b47dd3706a269ffed7f7e7e2c4396ff6a7f4f99982520ec1f2cf716
 size 101748240

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 1128503160340480.0,
+    "train_loss": 0.4949293037255605,
+    "train_runtime": 2254.249,
+    "train_samples": 6000,
+    "train_samples_per_second": 0.256,
+    "train_steps_per_second": 0.001
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 1128503160340480.0,
+    "train_loss": 0.4949293037255605,
+    "train_runtime": 2254.249,
+    "train_samples": 6000,
+    "train_samples_per_second": 0.256,
+    "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": 0.08849904847009908,
+      "learning_rate": 0.0,
+      "loss": 0.5103,
+      "num_tokens": 2508859.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.08907876339443113,
+      "learning_rate": 4e-05,
+      "loss": 0.4846,
+      "num_tokens": 4953058.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.08475559513758006,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.4899,
+      "num_tokens": 7268157.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.096,
+      "step": 3,
+      "total_flos": 1128503160340480.0,
+      "train_loss": 0.4949293037255605,
+      "train_runtime": 2254.249,
+      "train_samples_per_second": 0.256,
+      "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": 1128503160340480.0,
+  "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 sha256:2bfcf4f53f6882d8e2fd2ddde6546e28b1b37e368e817ddec371b5dc2f39dd84
+oid sha256:fd93d39eb43b3a38bedc31adc89a65b1656464c9fa2cecec946a58e3340ad743
 size 7416