Add files using upload-large-folder tool

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
-    "gate_proj",
+    "down_proj",
     "k_proj",
+    "o_proj",
+    "up_proj",
     "v_proj",
-    "down_proj",
-    "o_proj"
+    "q_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e73c946a8c6976ed95b4be5f1694e188145b29d958a90d8551f9bb644f21b7bf
+oid sha256:47feda9f0da80a8169fb143b1852937819325618c06ae934508ede76d8a0bdc5
 size 275341720

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.9904761904761905,
-    "total_flos": 1.1855717021096346e+17,
-    "train_loss": 0.5348628270320404,
-    "train_runtime": 803.1773,
-    "train_samples_per_second": 1.569,
-    "train_steps_per_second": 0.049
+    "epoch": 0.6666666666666666,
+    "total_flos": 5127839837847552.0,
+    "train_loss": 0.6043767929077148,
+    "train_runtime": 41.7151,
+    "train_samples_per_second": 1.151,
+    "train_steps_per_second": 0.024
 }

card.json

@@ -1,7 +1,7 @@
 {
     "name": "openshift-builds-operator-epoch1-2025-Jun-08",
     "base_model": "Qwen/Qwen2.5-Coder-14B-Instruct" ,
-    "context_length": "3180",
+    "context_length": "4081",
     "model_type": "qwen",
     "quantized": "True",
     "finetune_steps": [
@@ -9,7 +9,7 @@
             "model_repo": "taguser/openshift-builds-operator-epoch1-2025-Jun-08",
             "base_model": "Qwen/Qwen2.5-Coder-14B-Instruct",
             "step": 2,
-            "data": "cia-tools/parsed_data",
+            "data": "cia-tools/smallds",
             "epochs": "1",
             "batch_size": "32",
             "dataset_size": "48",

checkpoint-1/adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
-    "gate_proj",
+    "down_proj",
     "k_proj",
+    "o_proj",
+    "up_proj",
     "v_proj",
-    "down_proj",
-    "o_proj"
+    "q_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

checkpoint-1/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6f54188f7668fc1d69b3fdec8ebb95d0891242b7736d6f52527318f441ec3e
+oid sha256:9cc2ca16d3bff49bcd53e33f7f58bfb39e819d8de87d1c5a9b3077b05b28c70e
 size 551070979

checkpoint-1/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f58a513cd0857709df493227d4bf4fe8df294021f339dc3c315675b6824b1543
+oid sha256:17f268ca93c88b4d82f442bd1280edcc0606fe9d52a665ccd6a004f3d3832534
 size 14917

checkpoint-1/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0070bb4cb00ec3dc3f9e4ced2f85698f7b32cdfbbf4bb2dc23198456a9e73896
+oid sha256:c690eabcc123561ee0f29f969ab9c61ebc9aaf6fbde86b41586c49dbfa7001b5
 size 14917

checkpoint-1/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6afcff6e27e60a2bfb38f5eb37f1e72b0551015bab2db232483e28c88d01030c
+oid sha256:d47405cf868a21e2c387f73023f8c9b17a7966fb2f86d736ea5850c65a0716f4
 size 1465

checkpoint-1/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025396825396825397,
+  "epoch": 0.6666666666666666,
   "eval_steps": 500,
   "global_step": 1,
   "is_hyper_param_search": false,
@@ -10,7 +10,7 @@
   "is_world_process_zero": true,
   "log_history": [],
   "logging_steps": 5,
-  "max_steps": 39,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 1,
@@ -21,12 +21,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2916214342942720.0,
+  "total_flos": 5127839837847552.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

checkpoint-1/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df62c6b3c891ce82ecd4497b02ca5a9f9048b25b92bbe3c2d8dfe6ccf7d014e4
+oid sha256:0315bf318104bf2951c648b1327dd0c081b6b91b6d39aede83507e1003d3f279
 size 6097

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.9904761904761905,
-    "total_flos": 1.1855717021096346e+17,
-    "train_loss": 0.5348628270320404,
-    "train_runtime": 803.1773,
-    "train_samples_per_second": 1.569,
-    "train_steps_per_second": 0.049
+    "epoch": 0.6666666666666666,
+    "total_flos": 5127839837847552.0,
+    "train_loss": 0.6043767929077148,
+    "train_runtime": 41.7151,
+    "train_samples_per_second": 1.151,
+    "train_steps_per_second": 0.024
 }

trainer_log.jsonl

@@ -1,8 +1 @@
-{"current_steps": 5, "total_steps": 39, "loss": 0.5952, "lr": 5e-05, "epoch": 0.12698412698412698, "percentage": 12.82, "elapsed_time": "0:02:55", "remaining_time": "0:19:50"}
-{"current_steps": 10, "total_steps": 39, "loss": 0.583, "lr": 4.752422169756048e-05, "epoch": 0.25396825396825395, "percentage": 25.64, "elapsed_time": "0:04:37", "remaining_time": "0:13:25"}
-{"current_steps": 15, "total_steps": 39, "loss": 0.5784, "lr": 4.058724504646834e-05, "epoch": 0.38095238095238093, "percentage": 38.46, "elapsed_time": "0:06:08", "remaining_time": "0:09:49"}
-{"current_steps": 20, "total_steps": 39, "loss": 0.5345, "lr": 3.056302334890786e-05, "epoch": 0.5079365079365079, "percentage": 51.28, "elapsed_time": "0:07:36", "remaining_time": "0:07:13"}
-{"current_steps": 25, "total_steps": 39, "loss": 0.4879, "lr": 1.9436976651092144e-05, "epoch": 0.6349206349206349, "percentage": 64.1, "elapsed_time": "0:09:02", "remaining_time": "0:05:03"}
-{"current_steps": 30, "total_steps": 39, "loss": 0.5065, "lr": 9.412754953531663e-06, "epoch": 0.7619047619047619, "percentage": 76.92, "elapsed_time": "0:10:30", "remaining_time": "0:03:09"}
-{"current_steps": 35, "total_steps": 39, "loss": 0.5044, "lr": 2.475778302439524e-06, "epoch": 0.8888888888888888, "percentage": 89.74, "elapsed_time": "0:12:05", "remaining_time": "0:01:22"}
-{"current_steps": 39, "total_steps": 39, "epoch": 0.9904761904761905, "percentage": 100.0, "elapsed_time": "0:13:20", "remaining_time": "0:00:00"}
+{"current_steps": 1, "total_steps": 1, "epoch": 0.6666666666666666, "percentage": 100.0, "elapsed_time": "0:00:39", "remaining_time": "0:00:00"}

trainer_state.json

@@ -2,74 +2,25 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9904761904761905,
+  "epoch": 0.6666666666666666,
   "eval_steps": 500,
-  "global_step": 39,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.12698412698412698,
-      "grad_norm": 0.030378561466932297,
-      "learning_rate": 5e-05,
-      "loss": 0.5952,
-      "step": 5
-    },
-    {
-      "epoch": 0.25396825396825395,
-      "grad_norm": 0.05285210907459259,
-      "learning_rate": 4.752422169756048e-05,
-      "loss": 0.583,
-      "step": 10
-    },
-    {
-      "epoch": 0.38095238095238093,
-      "grad_norm": 0.04900702089071274,
-      "learning_rate": 4.058724504646834e-05,
-      "loss": 0.5784,
-      "step": 15
-    },
-    {
-      "epoch": 0.5079365079365079,
-      "grad_norm": 0.041186440736055374,
-      "learning_rate": 3.056302334890786e-05,
-      "loss": 0.5345,
-      "step": 20
-    },
-    {
-      "epoch": 0.6349206349206349,
-      "grad_norm": 0.04592454433441162,
-      "learning_rate": 1.9436976651092144e-05,
-      "loss": 0.4879,
-      "step": 25
-    },
-    {
-      "epoch": 0.7619047619047619,
-      "grad_norm": 0.051714979112148285,
-      "learning_rate": 9.412754953531663e-06,
-      "loss": 0.5065,
-      "step": 30
-    },
-    {
-      "epoch": 0.8888888888888888,
-      "grad_norm": 0.041197337210178375,
-      "learning_rate": 2.475778302439524e-06,
-      "loss": 0.5044,
-      "step": 35
-    },
-    {
-      "epoch": 0.9904761904761905,
-      "step": 39,
-      "total_flos": 1.1855717021096346e+17,
-      "train_loss": 0.5348628270320404,
-      "train_runtime": 803.1773,
-      "train_samples_per_second": 1.569,
-      "train_steps_per_second": 0.049
+      "epoch": 0.6666666666666666,
+      "step": 1,
+      "total_flos": 5127839837847552.0,
+      "train_loss": 0.6043767929077148,
+      "train_runtime": 41.7151,
+      "train_samples_per_second": 1.151,
+      "train_steps_per_second": 0.024
     }
   ],
   "logging_steps": 5,
-  "max_steps": 39,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 1,
@@ -85,7 +36,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1855717021096346e+17,
+  "total_flos": 5127839837847552.0,
   "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:df62c6b3c891ce82ecd4497b02ca5a9f9048b25b92bbe3c2d8dfe6ccf7d014e4
+oid sha256:0315bf318104bf2951c648b1327dd0c081b6b91b6d39aede83507e1003d3f279
 size 6097