Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fb2fe1140bd18da0d59537585b1a320d6f148a3e073233f8f24a15f1054717d
+oid sha256:2a1fa26184e840c327e1f6152c2e8b65631c3b4fb8bd6d5e9618989da82736f6
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ba2eceb4012b8014cd1c4c54aeb37c9b37ab99ea2c4145113fe8eefe62510f3
+oid sha256:e0cbc0277e866c44285c3b27a73b0f54c8c43cfc57e03c3c70332e948723d437
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a11b431c48c5d64e25a002804e15211716127584ce0efef99d94719910668dc
+oid sha256:b9d8c76d6c8a7a3b88e7f5125b78e546dbde485461d800944948e2662f2d8e09
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5cd77d7aa40b1e78967adb7aa5f482fd9407e5df0aadea6bfa235f73d239c2a
+oid sha256:91c73e65fdf914a00fd32cdfca8c34325a0b0f62e22c4eba0ae82508bf3c9b74
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6374460458755493,
-  "best_model_checkpoint": "ru_qwen7b_gec_Ga/checkpoint-252",
-  "epoch": 0.8780487804878049,
+  "best_metric": 0.6373529434204102,
+  "best_model_checkpoint": "ru_qwen7b_gec_Ga/checkpoint-261",
+  "epoch": 0.9094076655052264,
   "eval_steps": 9,
-  "global_step": 252,
+  "global_step": 261,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,6 +427,21 @@
       "eval_samples_per_second": 13.34,
       "eval_steps_per_second": 1.67,
       "step": 252
+    },
+    {
+      "epoch": 0.9094076655052264,
+      "grad_norm": 1.0773546695709229,
+      "learning_rate": 4.788233408928588e-07,
+      "loss": 0.6222,
+      "step": 261
+    },
+    {
+      "epoch": 0.9094076655052264,
+      "eval_loss": 0.6373529434204102,
+      "eval_runtime": 58.0985,
+      "eval_samples_per_second": 13.339,
+      "eval_steps_per_second": 1.67,
+      "step": 261
     }
   ],
   "logging_steps": 9,
@@ -455,7 +470,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.807887535918285e+16,
+  "total_flos": 9.122454947915366e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null