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:dc738c591ed46cb71e6b7d1ce65811f28df463770f6f38eeecf3b1f6ac8534d9
+oid sha256:231537100e8b2412efb9e02ce3a5b6ef18ca5d9938a69099f8d4525ce2e6f59b
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b252ef50ea8e6499c12bf69c6df1f9ab60cb762e42cffffd1ff8bdac7a6c7f05
+oid sha256:c3b0b159739fd96886eda01fe2857c37534e8a48e6e205917bca8ed77ed4dc4e
 size 110412612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c959c0527027f5650ef5eeb7b782c25a910e59249eb7699493013eb24d2f43
+oid sha256:1c3155d165ac4d895a81bc6b43cfc1dcd34e819ced77846badcdacb031b43a8f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008384828700569906,
+  "epoch": 0.010481035875712382,
   "eval_steps": 8,
-  "global_step": 24,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,48 @@
       "eval_samples_per_second": 5.297,
       "eval_steps_per_second": 2.649,
       "step": 24
+    },
+    {
+      "epoch": 0.008734196563093653,
+      "grad_norm": 1.8778541088104248,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4291,
+      "step": 25
+    },
+    {
+      "epoch": 0.009083564425617398,
+      "grad_norm": 1.7002447843551636,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2286,
+      "step": 26
+    },
+    {
+      "epoch": 0.009432932288141144,
+      "grad_norm": 2.428805351257324,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.5176,
+      "step": 27
+    },
+    {
+      "epoch": 0.009782300150664891,
+      "grad_norm": 2.2078659534454346,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.4923,
+      "step": 28
+    },
+    {
+      "epoch": 0.010131668013188638,
+      "grad_norm": 1.8118517398834229,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.456,
+      "step": 29
+    },
+    {
+      "epoch": 0.010481035875712382,
+      "grad_norm": 1.6986387968063354,
+      "learning_rate": 0.0,
+      "loss": 0.1885,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +263,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.5813360806893978e+17,
+  "total_flos": 1.9766701008617472e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null