Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c3ae45a134aeabf5c340275e335c1c9c7a161c90bb0e9a813ad6b703e04bdc
+oid sha256:91b931b705519d99d94b64f8328e2dec318bb68d896b01bc8586e7cf4a2cf45b
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:625aa9477ca8586bb161eecc95b21487151ea2103b2347c3ffd5415b5586c62c
+oid sha256:6e527f7b54183211bb35e4320ad84ee4e1d9e16450ac564db64a37604a870b8a
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8288cb8cb0b54526d97f2ff59da883c307360a17e99a5d7d1d6e7afb2436e03b
+oid sha256:cdf286495b2f9086f0435e305d486647eb1934cc509a3961a7bfe47275b3ca95
 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": 0.03368421052631579,
+  "epoch": 0.05052631578947368,
   "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": 1.2323,
       "step": 18
+    },
+    {
+      "epoch": 0.03536842105263158,
+      "grad_norm": 2.9023444652557373,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.9628,
+      "step": 21
+    },
+    {
+      "epoch": 0.04042105263157895,
+      "grad_norm": 2.346060276031494,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.9069,
+      "step": 24
+    },
+    {
+      "epoch": 0.04042105263157895,
+      "eval_loss": 0.9707378149032593,
+      "eval_runtime": 33.5386,
+      "eval_samples_per_second": 7.454,
+      "eval_steps_per_second": 3.727,
+      "step": 24
+    },
+    {
+      "epoch": 0.04547368421052632,
+      "grad_norm": 2.3689370155334473,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.8106,
+      "step": 27
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 2.2287442684173584,
+      "learning_rate": 0.0,
+      "loss": 0.8476,
+      "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": 1.26955844272128e+16,
+  "total_flos": 1.90433766408192e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null