Training in progress, step 16400, checkpoint

last-checkpoint/README.md

@@ -199,4 +199,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.14.0
+- PEFT 0.15.1

last-checkpoint/adapter_config.json

@@ -3,6 +3,7 @@
   "auto_mapping": null,
   "base_model_name_or_path": "Qwen/Qwen3-0.6B",
   "bias": "none",
+  "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -23,15 +24,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "o_proj",
+    "gate_proj",
     "down_proj",
-    "q_proj",
-    "k_proj",
     "v_proj",
-    "gate_proj",
+    "k_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0895ef68999d4dfb943206c62b67cf1ef8c34e6d4531bbf6cbd0164f87b27fb
+oid sha256:f91e3c5f21cf129551bcf7c69bf4d8d16a4ef7f114f3eb09634873a47bacc359
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e8dbf38539f29794be1d65b30108f9525bfcf2e332bab29d374c55513a7d620
+oid sha256:4014d31deb4cce624d0816b7ea019aa4bc828b0109dcbd09f7797bdcac508304
 size 323292202

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16605380cae58712eea4da8f07eab38182175aa614b73a71198f2f8f482fc46a
+oid sha256:6863575074205cdae5bd9a3add89cf69a3951c4f077fb3f56f28f0fe9457c14f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6821192052980134,
+  "epoch": 2.7152317880794703,
   "eval_steps": 100,
-  "global_step": 16200,
+  "global_step": 16400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2308,6 +2308,34 @@
       "learning_rate": 3.3847853001028495e-06,
       "loss": 0.2699,
       "step": 16200
+    },
+    {
+      "epoch": 2.6903973509933774,
+      "grad_norm": 1.1786317825317383,
+      "learning_rate": 3.2127666818151046e-06,
+      "loss": 0.2717,
+      "step": 16250
+    },
+    {
+      "epoch": 2.698675496688742,
+      "grad_norm": 1.0810590982437134,
+      "learning_rate": 3.045088789355488e-06,
+      "loss": 0.277,
+      "step": 16300
+    },
+    {
+      "epoch": 2.706953642384106,
+      "grad_norm": 1.194557785987854,
+      "learning_rate": 2.8817671791847634e-06,
+      "loss": 0.2652,
+      "step": 16350
+    },
+    {
+      "epoch": 2.7152317880794703,
+      "grad_norm": 1.1923502683639526,
+      "learning_rate": 2.7228170036058153e-06,
+      "loss": 0.2617,
+      "step": 16400
     }
   ],
   "logging_steps": 50,
@@ -2327,7 +2355,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2713713196020531e+17,
+  "total_flos": 1.2874605314388787e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03460364198bac94559385f580ca233415d6d940ccd70edd3903925ee0255ba2
+oid sha256:4e7fd7045b4a15373c4d905f915edbb1436664635b44fe1df1bfa95de5188043
 size 5752