Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:751566e7d06f4deb79b830f94d4bcf78192d35cf518cb88d265b041110b2d431
+oid sha256:d49d62df61b64a6f74876c4bb45a948f9eafa476e5f9782398987b0cddda127e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:338d09511b40ae3bc0c7757dda74db1b16f18a8810524cdcab8313d9739f4c9c
+oid sha256:d2506fe1946fb112ec22f7f23dbffd5dd757a2d84522b6a50dd3b3b09913e552
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
+oid sha256:2f3dfab2f15c077a3bfe1d57e8f4dfb9954e3c582cff3d86c56d618335c8d869
 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": 0.7464114832535885,
+  "epoch": 0.9569377990430622,
   "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": 0.1074,
       "step": 35
+    },
+    {
+      "epoch": 0.7655502392344498,
+      "grad_norm": 0.41118383407592773,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1009,
+      "step": 40
+    },
+    {
+      "epoch": 0.7655502392344498,
+      "eval_loss": 0.11148104816675186,
+      "eval_runtime": 4.5675,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 2.627,
+      "step": 40
+    },
+    {
+      "epoch": 0.861244019138756,
+      "grad_norm": 0.33219197392463684,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1239,
+      "step": 45
+    },
+    {
+      "epoch": 0.9569377990430622,
+      "grad_norm": 0.446623831987381,
+      "learning_rate": 0.0,
+      "loss": 0.1281,
+      "step": 50
+    },
+    {
+      "epoch": 0.9569377990430622,
+      "eval_loss": 0.10937495529651642,
+      "eval_runtime": 4.5804,
+      "eval_samples_per_second": 5.021,
+      "eval_steps_per_second": 2.62,
+      "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": 1.4426601135538176e+16,
+  "total_flos": 1.84956424814592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null