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:beaed11cfb046c6fb0e7ebd5cfc1f202457d5af1bca965d49dd947a347d3380c
+oid sha256:a785c1d2de406011c3dc9b501a7603f718548a59e3ed9e9ef13ad248d6c803c3
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ddacfdeaa2e82f29844e4df4b4a9bcfe979076c5ce376350e7103cd568aa99
+oid sha256:5490566851e0c5a24149f57d3d70004fae3c228a18c902b9d7230a1a94cde5f9
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37224de670c69583a766c3e614daa998f0bc8dd77d75ee56d895923256ee064
+oid sha256:6ea772e52ba8e61a6cd1fc3da52d4d33b6c75da1d61540dfcb943db3ee330458
 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": 0.03346203346203346,
+  "epoch": 0.0429000429000429,
   "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": 2.4102,
       "step": 35
+    },
+    {
+      "epoch": 0.03432003432003432,
+      "grad_norm": 1.228721022605896,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.396,
+      "step": 40
+    },
+    {
+      "epoch": 0.03432003432003432,
+      "eval_loss": 2.349761486053467,
+      "eval_runtime": 14.0476,
+      "eval_samples_per_second": 34.953,
+      "eval_steps_per_second": 17.512,
+      "step": 40
+    },
+    {
+      "epoch": 0.03861003861003861,
+      "grad_norm": 1.2431485652923584,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.4303,
+      "step": 45
+    },
+    {
+      "epoch": 0.0429000429000429,
+      "grad_norm": 1.1994407176971436,
+      "learning_rate": 0.0,
+      "loss": 2.3418,
+      "step": 50
+    },
+    {
+      "epoch": 0.0429000429000429,
+      "eval_loss": 2.347376823425293,
+      "eval_runtime": 13.813,
+      "eval_samples_per_second": 35.546,
+      "eval_steps_per_second": 17.809,
+      "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": 974209337524224.0,
+  "total_flos": 1244823042392064.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null