Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:737176acb2f58e64d05846a53ccea8d22dd661d6de333d8c74a086012a666c81
+oid sha256:1c3fea1f7a63daade9cd825196a90e4039e424e1ce4036987105c90a8b0e3457
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7cf92d0327a57c268d425c2358353c613f0c40b583c22a0baec4b4c0481e2ab
+oid sha256:116b0438d7861d85aa0fd640dac46cbe0302d3706719420571d7234b1d8361e7
 size 67216698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c3d5cbeb8cdb702c7af2051ef34525b3edb220b994d650ce737f871f3d07c8
+oid sha256:ade7405352f21c3d4ca15e46ecacef02979b1c2444e0503889766e280e03c62d
 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": 0.00984251968503937,
+  "epoch": 0.014763779527559055,
   "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": 4.542,
       "step": 18
+    },
+    {
+      "epoch": 0.01033464566929134,
+      "grad_norm": 1.8949321508407593,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.4775,
+      "step": 21
+    },
+    {
+      "epoch": 0.011811023622047244,
+      "grad_norm": 2.249910354614258,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.5871,
+      "step": 24
+    },
+    {
+      "epoch": 0.011811023622047244,
+      "eval_loss": 1.2030678987503052,
+      "eval_runtime": 12.5283,
+      "eval_samples_per_second": 68.325,
+      "eval_steps_per_second": 34.163,
+      "step": 24
+    },
+    {
+      "epoch": 0.01328740157480315,
+      "grad_norm": 1.5551438331604004,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.0494,
+      "step": 27
+    },
+    {
+      "epoch": 0.014763779527559055,
+      "grad_norm": 1.6855121850967407,
+      "learning_rate": 0.0,
+      "loss": 4.6834,
+      "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": 1048101657772032.0,
+  "total_flos": 1589057352105984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null