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:d3bb7b7160471f16bdc46e5261703f5a9156e79468e087a14dda90fab43a46fd
+oid sha256:6de92cbcae6d0bea2bf9ac14e7f0a37137a444cf1c6e4df81cc48aaeba21d0a7
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e403950a9db23d682c08c54c7bab2e9bf3937f42ccf06a31812cb0623315455
+oid sha256:a6de13620b97cb21dac8d918e73e2bc35c6a82dbc2e17430d8fcc79f77284380
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fcac41dbd9142df5390346c9aeb20da7424d647bb3d8dc6eede3f489ba85d01
+oid sha256:4becf341a6778ae5e5bbce77be365f5b4e22fff8d0a8df07faa3437b6b9564bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005977698586044373,
+  "epoch": 0.007663716135954324,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.9047,
       "step": 35
+    },
+    {
+      "epoch": 0.00613097290876346,
+      "grad_norm": 0.3847725987434387,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0814,
+      "step": 40
+    },
+    {
+      "epoch": 0.00613097290876346,
+      "eval_loss": 1.1053937673568726,
+      "eval_runtime": 248.0738,
+      "eval_samples_per_second": 11.073,
+      "eval_steps_per_second": 5.539,
+      "step": 40
+    },
+    {
+      "epoch": 0.006897344522358892,
+      "grad_norm": 0.5520898699760437,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0366,
+      "step": 45
+    },
+    {
+      "epoch": 0.007663716135954324,
+      "grad_norm": 0.284847229719162,
+      "learning_rate": 0.0,
+      "loss": 1.018,
+      "step": 50
+    },
+    {
+      "epoch": 0.007663716135954324,
+      "eval_loss": 1.1014302968978882,
+      "eval_runtime": 247.846,
+      "eval_samples_per_second": 11.083,
+      "eval_steps_per_second": 5.544,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.038317374144512e+16,
+  "total_flos": 1.3111301744099328e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null