Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db8e8dba6e3bd3c727f6a1ba711072f3995a8768785f8cd14805b9660545957
+oid sha256:cca9023d0d66022ae053a59b92aae291bf698793fc375edd8e87151a47edf180
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a336b3ecaa4efee7037b1506e7a9b6ec09429be623032ff58b5c218656ef98cb
+oid sha256:b0aceb55de8342829ebcfa49c0f8f67a20de617beb038e14ca2e537f8c7700c8
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f0feddd7998b877f7ccc370756fc2edae64edd6baec5679a7765fc8dac5cdc
+oid sha256:01ae0673394c6d0448d87a05b8dce85b58d04fafa4d6c418a5ee6c92aeaab53d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004733307694583321,
+  "epoch": 0.0007099961541874981,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 3.361,
       "step": 18
+    },
+    {
+      "epoch": 0.0004969973079312487,
+      "grad_norm": 7.917823791503906,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.8511,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005679969233499985,
+      "grad_norm": 6.947325706481934,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.0211,
+      "step": 24
+    },
+    {
+      "epoch": 0.0005679969233499985,
+      "eval_loss": 2.9022560119628906,
+      "eval_runtime": 519.7035,
+      "eval_samples_per_second": 34.235,
+      "eval_steps_per_second": 17.117,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006389965387687483,
+      "grad_norm": 7.559967517852783,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.9373,
+      "step": 27
+    },
+    {
+      "epoch": 0.0007099961541874981,
+      "grad_norm": 6.675393104553223,
+      "learning_rate": 0.0,
+      "loss": 2.8824,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 360477150412800.0,
+  "total_flos": 540715725619200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null