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:d6d7ffc2f86bee48cafbd57f7375695396881e663f67ecbf370aa4963f99a002
+oid sha256:ee9cd91ccbcfd3b8fe7324088f5df62f1379fd6265b5af6e7d3ef3392da49de3
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2457f67b3b929bbda3ce5dbe02edf5a594ac277bc55b93133bb3cfdbb5e80e6a
+oid sha256:ca4262284ac237081a4b1e31f82136491a1d80289472ae74b562604133fa02ab
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd1d2b4c2f7deed1ec9c3574be99306bf5177dcc6bd2859acc8825dc004fbb89
+oid sha256:6a549334531a149c3078542b2c532457783bc94ae2e200ad387179cd6e74b26e
 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": 0.034597471723220224,
+  "epoch": 0.04435573297848747,
   "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": 0.481,
       "step": 35
+    },
+    {
+      "epoch": 0.03548458638278998,
+      "grad_norm": 0.8894734978675842,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5409,
+      "step": 40
+    },
+    {
+      "epoch": 0.03548458638278998,
+      "eval_loss": 0.48986321687698364,
+      "eval_runtime": 27.3599,
+      "eval_samples_per_second": 17.361,
+      "eval_steps_per_second": 8.699,
+      "step": 40
+    },
+    {
+      "epoch": 0.03992015968063872,
+      "grad_norm": 0.9562792778015137,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4659,
+      "step": 45
+    },
+    {
+      "epoch": 0.04435573297848747,
+      "grad_norm": 0.7964979410171509,
+      "learning_rate": 0.0,
+      "loss": 0.4744,
+      "step": 50
+    },
+    {
+      "epoch": 0.04435573297848747,
+      "eval_loss": 0.4811477065086365,
+      "eval_runtime": 27.4067,
+      "eval_samples_per_second": 17.332,
+      "eval_steps_per_second": 8.684,
+      "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": 5063800506286080.0,
+  "total_flos": 6539888103260160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null