Training in progress, step 55, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa9ec871a9a1ec88f5ab2eecbc17cd812242c822009eb58326e5e30a48b905c
+oid sha256:4ab9d469586a2d2dbecd61da93bd282b58542cfc74ed9e6bf4f313d329453365
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de4737d5e501253cc9b990c9ad3a63249b6371e2fbff977e3b84db2a501c4d74
+oid sha256:996b0f72fd8c1b43356945b05e8cbbec4c6c9fdaaf2c567c3ea7ca020653b3c9
 size 75471860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb415ea26e870302de4384a029ef7ff77e384ddb696ca258894875114dc0a21
+oid sha256:cf45e4402320c6640eb2293e0130379c33d21f14d23e9f891e48da3b5a649f0e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43352a0ea01b8f309df99bb65027960564fe5f2f452a04b8b6c955b0ecfed4cf
+oid sha256:8b16062161cca6c6d42c840fa02f9c59f431931479788fa87a822481c8e65827
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009682550660488278,
+  "epoch": 0.0012679530626829886,
   "eval_steps": 14,
-  "global_step": 42,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,13 @@
       "eval_samples_per_second": 49.011,
       "eval_steps_per_second": 24.506,
       "step": 42
+    },
+    {
+      "epoch": 0.0011526846024390806,
+      "grad_norm": 2.3784372806549072,
+      "learning_rate": 0.0002,
+      "loss": 1.0844,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -81,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 695320732237824.0,
+  "total_flos": 910539054120960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null