Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7395d78d40dc43b15bd8a531b0b277923697d43bf549cf4df97a436d5a81ea11
+oid sha256:f27c3e3e21a49cd509589a416b50d6733641668e64de718c388e5bf0f4bb6d29
 size 188784440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e127f02d25d63d40f71581fa199bf2bfcf2c67e8a31e4b6f45edfc3e06360af
+oid sha256:cc16007636d783fa3e3b0c542bd6b655a3faa29975ad5e01d3803eeceeedec32
 size 377658554

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:666da658b919333c192491b671083554125e623cc746a64fb7c027e5393167de
+oid sha256:53091e36e8b798ea49c4107be43a6a431ecf9b0102a8e1877029aea0f52e0fc3
 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": 0.049782202862476664,
+  "epoch": 0.07467330429371499,
   "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": 3.4823,
       "step": 18
+    },
+    {
+      "epoch": 0.0522713130056005,
+      "grad_norm": 1.293418288230896,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.5683,
+      "step": 21
+    },
+    {
+      "epoch": 0.059738643434972,
+      "grad_norm": 1.1531097888946533,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.4569,
+      "step": 24
+    },
+    {
+      "epoch": 0.059738643434972,
+      "eval_loss": 0.8627409338951111,
+      "eval_runtime": 50.8163,
+      "eval_samples_per_second": 3.345,
+      "eval_steps_per_second": 1.673,
+      "step": 24
+    },
+    {
+      "epoch": 0.0672059738643435,
+      "grad_norm": 1.2184909582138062,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.4258,
+      "step": 27
+    },
+    {
+      "epoch": 0.07467330429371499,
+      "grad_norm": 1.494885802268982,
+      "learning_rate": 0.0,
+      "loss": 3.3277,
+      "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": 1.14344142569472e+16,
+  "total_flos": 1.71516213854208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null