Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19fa4af5ea6ebabbe2ac1e745ee529fe3305d4e24e4a2f705efa8b89b9cf66a6
+oid sha256:d5c4de29ccda2364131fbb092a05aabee4d1ead0050d6e2a40a7d52bfeb4f473
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79fd6034a7e8fad5ee374fc6097cb2ca1ce43c59e22a22ef62098b1ba27916c4
+oid sha256:6f741136dd6bdebb7dc35b83232b4105acabe01f91edf0c9ab326bec1b46cbcd
 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": 0.006852925672113864,
+  "epoch": 0.008785802143735724,
   "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": 0.8628,
       "step": 35
+    },
+    {
+      "epoch": 0.007028641714988578,
+      "grad_norm": 0.6111838221549988,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.936,
+      "step": 40
+    },
+    {
+      "epoch": 0.007028641714988578,
+      "eval_loss": 0.8869322538375854,
+      "eval_runtime": 297.012,
+      "eval_samples_per_second": 8.07,
+      "eval_steps_per_second": 4.037,
+      "step": 40
+    },
+    {
+      "epoch": 0.00790722192936215,
+      "grad_norm": 0.7134804725646973,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8469,
+      "step": 45
+    },
+    {
+      "epoch": 0.008785802143735724,
+      "grad_norm": 0.5976589322090149,
+      "learning_rate": 0.0,
+      "loss": 0.8012,
+      "step": 50
+    },
+    {
+      "epoch": 0.008785802143735724,
+      "eval_loss": 0.8830190300941467,
+      "eval_runtime": 296.6979,
+      "eval_samples_per_second": 8.079,
+      "eval_steps_per_second": 4.041,
+      "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