Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9320b3aeb23e76b0c68807683649120817a73f845db631f672f52f693bd38353
+oid sha256:f52989bc4fec8d7975202f9b97d18a7506a1426d85451a57f6121443fb1baaf5
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d22a37deab941b1fad494196f0d81ed40bfb61ee71401e9177a3486c99bed402
+oid sha256:169fd25d71603b3499b978120ff324419c2ba1cf155e1b74b0fd3dd1d94b75b1
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8194e1b8c74d7216b4daf200bbfe7e0ecb859e151ee00b0f9ea8e824e6edee25
+oid sha256:cab4d6c2ce43e24d19e16d85f2f7af6e830104f5a5c4b29ee3dac335d1d10f59
 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": 0.0008056070248932571,
+  "epoch": 0.0012084105373398855,
   "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": 1.4472,
       "step": 18
+    },
+    {
+      "epoch": 0.0008458873761379199,
+      "grad_norm": 1.2412055730819702,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.4521,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009667284298719085,
+      "grad_norm": 1.0540664196014404,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.5259,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009667284298719085,
+      "eval_loss": 1.4515408277511597,
+      "eval_runtime": 183.1921,
+      "eval_samples_per_second": 57.066,
+      "eval_steps_per_second": 28.533,
+      "step": 24
+    },
+    {
+      "epoch": 0.0010875694836058971,
+      "grad_norm": 1.2278207540512085,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.4075,
+      "step": 27
+    },
+    {
+      "epoch": 0.0012084105373398855,
+      "grad_norm": 1.1783462762832642,
+      "learning_rate": 0.0,
+      "loss": 1.4371,
+      "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": 967722569564160.0,
+  "total_flos": 1451583854346240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null