Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36a3564bcec5a529ed89cae4077ab371093f3024c61ad4945417d3905ad1efb7
+oid sha256:6fb2fe1140bd18da0d59537585b1a320d6f148a3e073233f8f24a15f1054717d
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2a4684e422053d4adc622a772b7f2ae47a52db8023658bef4ab1d3c4d8b551
+oid sha256:5ba2eceb4012b8014cd1c4c54aeb37c9b37ab99ea2c4145113fe8eefe62510f3
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e05042930cbd772da85946159dcb5dddc0f558c0589627a889a9671e95aa522
+oid sha256:9a11b431c48c5d64e25a002804e15211716127584ce0efef99d94719910668dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a58e631e9dd7778c900a95e6edcdcfbefc62841f31a37818bb58f0bab95ca81d
+oid sha256:b5cd77d7aa40b1e78967adb7aa5f482fd9407e5df0aadea6bfa235f73d239c2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6376007199287415,
-  "best_model_checkpoint": "ru_qwen7b_gec_Ga/checkpoint-243",
-  "epoch": 0.8466898954703833,
+  "best_metric": 0.6374460458755493,
+  "best_model_checkpoint": "ru_qwen7b_gec_Ga/checkpoint-252",
+  "epoch": 0.8780487804878049,
   "eval_steps": 9,
-  "global_step": 243,
+  "global_step": 252,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -412,6 +412,21 @@
       "eval_samples_per_second": 13.336,
       "eval_steps_per_second": 1.669,
       "step": 243
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.9245346784591675,
+      "learning_rate": 8.459199147463371e-07,
+      "loss": 0.6092,
+      "step": 252
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "eval_loss": 0.6374460458755493,
+      "eval_runtime": 58.0961,
+      "eval_samples_per_second": 13.34,
+      "eval_steps_per_second": 1.67,
+      "step": 252
     }
   ],
   "logging_steps": 9,
@@ -440,7 +455,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.493320123921203e+16,
+  "total_flos": 8.807887535918285e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null