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:f192d47e2b38d38380e46d317492e6eaabb71a02941ddc52f38923b2de405762
+oid sha256:171ab1f58cd0117dfed413fd892dab584118099d4c1aef7e1152a9e5c63310c8
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:244d4915b665d93a3456e029e5a2667e17b482c96587fe7f38d28eb687fa49c1
+oid sha256:f2af55a7333c4ee7cc4036bff1a9e0f383fc3ae4959b644e7730b147f29bff08
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d28e5f5aa78cef16e62cc6537d3b81b1ea74dc330b0053f2dd2ab2d360377f3
+oid sha256:ab5f6a013153d6987532a0d60eee1ff2d339487feb3395f01a3a00d204323569
 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": 0.03762935089369708,
+  "epoch": 0.05644402634054563,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 67.83,
       "eval_steps_per_second": 33.915,
       "step": 20
+    },
+    {
+      "epoch": 0.03951081843838194,
+      "grad_norm": 0.22199992835521698,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.9307,
+      "step": 21
+    },
+    {
+      "epoch": 0.045155221072436504,
+      "grad_norm": 0.26525187492370605,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.9266,
+      "step": 24
+    },
+    {
+      "epoch": 0.047036688617121354,
+      "eval_loss": 11.929987907409668,
+      "eval_runtime": 3.369,
+      "eval_samples_per_second": 66.489,
+      "eval_steps_per_second": 33.245,
+      "step": 25
+    },
+    {
+      "epoch": 0.05079962370649106,
+      "grad_norm": 0.2282623052597046,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.9327,
+      "step": 27
+    },
+    {
+      "epoch": 0.05644402634054563,
+      "grad_norm": 0.2645018398761749,
+      "learning_rate": 0.0,
+      "loss": 11.9229,
+      "step": 30
+    },
+    {
+      "epoch": 0.05644402634054563,
+      "eval_loss": 11.929728507995605,
+      "eval_runtime": 3.3494,
+      "eval_samples_per_second": 66.877,
+      "eval_steps_per_second": 33.439,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5078054338560.0,
+  "total_flos": 7617081507840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null