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:d835f6730863b88d70068f455956a60f5c96edd55da2eeced7aea2b7c80b95cf
+oid sha256:f98506688bbce49bf7eba567f64e88cd0bc02c6c9880f8aac5bbdd79f21b8845
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:287b9a09e864eb71d68c74c6ba4d81d2fa524dd23b28b7ad9e4457e92f96d9ce
+oid sha256:f94d27d61629bcacac59129ec31dc42ec1246e2a1b8b6ecad2b44806061c31e0
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb693ce61919bf80f2b88c9133c0d8e3384ced58afdc63fffa022c32fd41329e
+oid sha256:02039983a82c84a622c0f99b3680d59d59cf31c5d3a9ed3fc79f91145afbec4d
 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": 0.0508582326764145,
+  "epoch": 0.07628734901462174,
   "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": 1.9495,
       "step": 18
+    },
+    {
+      "epoch": 0.05340114431023522,
+      "grad_norm": 0.6290881037712097,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.9134,
+      "step": 21
+    },
+    {
+      "epoch": 0.06102987921169739,
+      "grad_norm": 0.541335940361023,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.7863,
+      "step": 24
+    },
+    {
+      "epoch": 0.06102987921169739,
+      "eval_loss": 1.8515095710754395,
+      "eval_runtime": 8.9814,
+      "eval_samples_per_second": 18.483,
+      "eval_steps_per_second": 9.241,
+      "step": 24
+    },
+    {
+      "epoch": 0.06865861411315957,
+      "grad_norm": 0.6374207139015198,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.9475,
+      "step": 27
+    },
+    {
+      "epoch": 0.07628734901462174,
+      "grad_norm": 0.6173187494277954,
+      "learning_rate": 0.0,
+      "loss": 1.8881,
+      "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": 2111126410100736.0,
+  "total_flos": 3116424700624896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null