Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73bf06e4d9ed07e81652fe07ed7bd5a28f1dcfd590dcee949b0a5eca027fb461
+oid sha256:c759e3dec77073953d9888f51a4bca896cf7cd2c8ada1aa4c09949b42c2615ba
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c433727c4a4690398c5abd17c4a25bb5e5a60e44979b60269c2b2752a8b19035
+oid sha256:2c56372901c54b49dcb7bb2b28cc2bf1eae769aad9f7c83f24c994626008dc34
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbb1d9ed0a2d77b4e3624035b568611f0015a3733047f718195fa123e9b53862
+oid sha256:2291543721be73d2d6dc33b41e525bc5079a377a480e1a0b19be1e57405c6ce2
 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": 0.0011706517603675846,
+  "epoch": 0.001755977640551377,
   "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": 7.9552,
       "step": 18
+    },
+    {
+      "epoch": 0.0012291843483859639,
+      "grad_norm": 1.3535780906677246,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 8.3829,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014047821124411016,
+      "grad_norm": 1.4238219261169434,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 7.6827,
+      "step": 24
+    },
+    {
+      "epoch": 0.0014047821124411016,
+      "eval_loss": 1.9840742349624634,
+      "eval_runtime": 723.8653,
+      "eval_samples_per_second": 9.938,
+      "eval_steps_per_second": 4.969,
+      "step": 24
+    },
+    {
+      "epoch": 0.0015803798764962393,
+      "grad_norm": 0.9212916493415833,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 7.1248,
+      "step": 27
+    },
+    {
+      "epoch": 0.001755977640551377,
+      "grad_norm": 1.530503511428833,
+      "learning_rate": 0.0,
+      "loss": 7.8823,
+      "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": 1.444131316432896e+16,
+  "total_flos": 2.110653462478848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null