Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e19d606522cb7c2f8215a31c4b61ac9d7eff9b603775442e30571a684cdca247
+oid sha256:56763c7ec2d7e0a3e8e7fe529f371a3c9e4befecbec70370582e35d76e02f1e1
 size 94422368

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f538e4e26bf1a5f1e6e4b5bcedf83c52bed5374166ef27b166e1e6ec937cc88
+oid sha256:12615b4a695d7b51b2a1108312209fbafcc1ea5f458fb15516e79aeeb566c5a3
 size 189066386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6571f6b089f94bdba2eb5be1863a2b6cc7541fe7c5a56a9d9d475bc0e0d6a2
+oid sha256:fdbc606fe5f3b31bfc8f93ec2425358b0bbafb166c51ee0540140f863555a695
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025196850393700787,
+  "epoch": 0.03779527559055118,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 1.5178,
       "step": 18
+    },
+    {
+      "epoch": 0.026456692913385826,
+      "grad_norm": 2.6561837196350098,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.5161,
+      "step": 21
+    },
+    {
+      "epoch": 0.030236220472440945,
+      "grad_norm": 2.484034776687622,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.4986,
+      "step": 24
+    },
+    {
+      "epoch": 0.030236220472440945,
+      "eval_loss": 1.445595622062683,
+      "eval_runtime": 14.8634,
+      "eval_samples_per_second": 22.539,
+      "eval_steps_per_second": 11.303,
+      "step": 24
+    },
+    {
+      "epoch": 0.03401574803149606,
+      "grad_norm": 2.9928808212280273,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.4991,
+      "step": 27
+    },
+    {
+      "epoch": 0.03779527559055118,
+      "grad_norm": 2.6080515384674072,
+      "learning_rate": 0.0,
+      "loss": 1.5171,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3316441310822400.0,
+  "total_flos": 4892571834777600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null