Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563077ad449d8d91d209fcd9f226014b76be72e7db2fe8609a4ffa3d9b483cf9
+oid sha256:b68e7b2519a003b947349af12f63f85575828e48bbc12f95f0de202dd1e0ee67
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6930d4ceb3274f34b4fe8e972311ea998019e60e082632604206f46271b02ef3
+oid sha256:97748b3437235f620f3b1f9372ab33ee23235727232da3e14a678df3f0e65a6b
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12842ce095b0e2610c386ef94711d2850ceaa47b98aab11f80858505283ff76e
+oid sha256:fc5e17471530b678efd1e1de870c04f06d2f120bda59d2f7f0a3660cfe8fca1d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.045060658578856154,
+  "epoch": 0.057770075101097634,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 28.623,
       "eval_steps_per_second": 3.578,
       "step": 30
+    },
+    {
+      "epoch": 0.046216060080878106,
+      "grad_norm": 1.075261116027832,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1615,
+      "step": 40
+    },
+    {
+      "epoch": 0.046216060080878106,
+      "eval_loss": 1.1079412698745728,
+      "eval_runtime": 204.389,
+      "eval_samples_per_second": 28.529,
+      "eval_steps_per_second": 3.567,
+      "step": 40
+    },
+    {
+      "epoch": 0.057770075101097634,
+      "grad_norm": 1.0194032192230225,
+      "learning_rate": 0.0,
+      "loss": 1.0724,
+      "step": 50
+    },
+    {
+      "epoch": 0.057770075101097634,
+      "eval_loss": 1.0836020708084106,
+      "eval_runtime": 204.0597,
+      "eval_samples_per_second": 28.575,
+      "eval_steps_per_second": 3.572,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.735269745151181e+16,
+  "total_flos": 4.776991368255898e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null