Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9274ae9a45ced44dc9c3b381a71a25ad3e2c73fd0d9c3d57d32e7b3ab8d36016
+oid sha256:6c60d9672411a012af6f98b86089d8ceb049204f30d9234a391451b4ba1db2e5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d1c42879228ce9cd2d2642c6b280b73d3f7a292245cc6cb206b7eb26f0afe7
+oid sha256:76d1c17c0849ca86cf3b21171b76ede801de6d30b2c5eebedbcfdc31e0df4cf3
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96fbdaea3789481a4891c68435883fd5b929f51442ba1c21fab23f868cdca0a5
+oid sha256:825376836d4d61913b05d0cd14c01de2145efac088f88b967ec3f99f782d53d0
 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": 0.0982367758186398,
+  "epoch": 0.12594458438287154,
   "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": 7.6644,
       "step": 35
+    },
+    {
+      "epoch": 0.10075566750629723,
+      "grad_norm": 45.303123474121094,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.0491,
+      "step": 40
+    },
+    {
+      "epoch": 0.10075566750629723,
+      "eval_loss": 1.4901608228683472,
+      "eval_runtime": 33.8946,
+      "eval_samples_per_second": 4.957,
+      "eval_steps_per_second": 2.478,
+      "step": 40
+    },
+    {
+      "epoch": 0.11335012594458438,
+      "grad_norm": 44.970916748046875,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.8777,
+      "step": 45
+    },
+    {
+      "epoch": 0.12594458438287154,
+      "grad_norm": 67.98702239990234,
+      "learning_rate": 0.0,
+      "loss": 6.1813,
+      "step": 50
+    },
+    {
+      "epoch": 0.12594458438287154,
+      "eval_loss": 1.45742666721344,
+      "eval_runtime": 33.8555,
+      "eval_samples_per_second": 4.962,
+      "eval_steps_per_second": 2.481,
+      "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": 1.248778656940032e+16,
+  "total_flos": 1.6036946962808832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null