Training in progress, epoch 3, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa61242d59dde07b6e124c28e4f02961504a3d80a62d3744879f8d576710c5a1
+oid sha256:d253b566d126f3aba50addeec7b7eb765dcd73cb4b88bcfa0193f7cdfb91c3f5
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bff118783a624c3d4494650098c048335a60deb649201045a57196051f28776
+oid sha256:a3d7ca924fd1345c00abf75278e6b67d1da97a8585f9d4fe25064f0dcd089c7f
 size 107046

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f6811de7fd6719f9ba6d6a0209af7f4bc36fd4331e413781421b0ce2308264
+oid sha256:adef08fda30a046b79221275438406fd995dd5a4dadb0a71a27682a7dcae8f3b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3ab4343fd37af80ff3b7a6d2bbb453cb34e903babf826a940b14f4bd54d6552
+oid sha256:63ac0c876d99cedd1c7e14354171b8bdaaea7163f00b90c59253d9bf8b43e991
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9937106918238996,
+  "epoch": 3.0020964360587,
   "eval_steps": 500,
-  "global_step": 357,
+  "global_step": 358,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -80,6 +80,14 @@
       "eval_samples_per_second": 246.686,
       "eval_steps_per_second": 63.503,
       "step": 357
+    },
+    {
+      "epoch": 3.0020964360587,
+      "eval_loss": 11.916298866271973,
+      "eval_runtime": 0.4304,
+      "eval_samples_per_second": 234.654,
+      "eval_steps_per_second": 60.406,
+      "step": 358
     }
   ],
   "logging_steps": 50,
@@ -94,12 +102,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 402378350592.0,
+  "total_flos": 402704130048.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null