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:c2aece845801b443703f004f20953d3d8d92d317d1f49a386447c65b0a666788
+oid sha256:6fed4f3b9eaf01f500fbb303484e2c8f9fe480de53f7768c133db284b35acbfa
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a028707c9a2122ea35fe3d3ed1b358e13450d6787fad21c31cb9a5e6dbdc299b
+oid sha256:27abef5dc22b00c6cdf4ed977b74f68c4817efb54f15202b50e43f2cc58fe9c3
 size 264440954

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:933f733813cf030a4080b8327ee169d771124a29f158d1589fa8bd178b4985ac
+oid sha256:c389ee4c071a3e170fba7925dfad9a3e68224b0beb0eec0071993d6fc7998337
 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": 0.0027785495971103086,
+  "epoch": 0.004167824395665463,
   "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": 8.0246,
       "step": 18
+    },
+    {
+      "epoch": 0.002917477076965824,
+      "grad_norm": 2.209848642349243,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 8.0801,
+      "step": 21
+    },
+    {
+      "epoch": 0.0033342595165323703,
+      "grad_norm": 2.32315731048584,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 8.3483,
+      "step": 24
+    },
+    {
+      "epoch": 0.0033342595165323703,
+      "eval_loss": 2.0858185291290283,
+      "eval_runtime": 532.3087,
+      "eval_samples_per_second": 5.694,
+      "eval_steps_per_second": 2.848,
+      "step": 24
+    },
+    {
+      "epoch": 0.0037510419560989163,
+      "grad_norm": 2.3444344997406006,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 8.8746,
+      "step": 27
+    },
+    {
+      "epoch": 0.004167824395665463,
+      "grad_norm": 8.79526138305664,
+      "learning_rate": 0.0,
+      "loss": 8.669,
+      "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": 7366690649088000.0,
+  "total_flos": 1.1122258430976e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null