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:cd98d2f6955a5156cd57ab8ab9cebe0078d2540eab239615ef8331b875df081a
+oid sha256:c7c4f7daad4fd0698779fee193793d2231b11d47fd79f6c14920802f3280be10
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9bce258e896399907ba52d07de79e3037f6aec450b49ed9edaae3be34e78563
+oid sha256:e2f51d4405c76e6d1b30d56e0343b82561e1ed55e8acd951e784db4c872ca333
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c801932c815e2dcc3488b72de19c071ccf4b093291a73d876fa8173f60b868d4
+oid sha256:98928e1126863039d68d24c31d1f4b445df92b7d2d85fd2e0a5ab706a5eed5d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003366125001051914,
+  "epoch": 0.0005049187501577872,
   "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": 0.00013090169943749476,
       "loss": 2.5551,
       "step": 18
+    },
+    {
+      "epoch": 0.00035344312511045097,
+      "grad_norm": 3.7091686725616455,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.244,
+      "step": 21
+    },
+    {
+      "epoch": 0.00040393500012622966,
+      "grad_norm": 4.029706954956055,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.5597,
+      "step": 24
+    },
+    {
+      "epoch": 0.00040393500012622966,
+      "eval_loss": 2.5306174755096436,
+      "eval_runtime": 3247.4102,
+      "eval_samples_per_second": 7.704,
+      "eval_steps_per_second": 3.852,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004544268751420084,
+      "grad_norm": 4.2530412673950195,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.5887,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005049187501577872,
+      "grad_norm": 3.34025502204895,
+      "learning_rate": 0.0,
+      "loss": 2.0085,
+      "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": 7511608746049536.0,
+  "total_flos": 1.1313781074296832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null