Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91bb60ee728b069aa96221d8ddccb205b6bc74d3bca5226195d5183927e804d3
+oid sha256:949efa076e0641b1bf7440dda4aab0946a6a70724436d0a3ab83660acc1403a2
 size 84962944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f9d860f1e0dbfcdf53555855f9a4471528bf8427d37dfee8a9a003117159ba
+oid sha256:dec3f6f7548b6834b8d8ed0bb9b69af9d9af621c9a1dab11b386eec355c7f0e6
 size 43387339

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71a794c77d91f4dc788c1a70f8619fb0ed76a6803da809d3d2d5f646f92481fb
+oid sha256:53b3a001f6f9b4c549f0bf73e88f33314cd5b26b892e872aa6828133fc723ff8
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dce57d520a5c903ee4baddf780c2b9cb084140d3e348fde0a802253d3fe502b
+oid sha256:6cbdc6c8f1d58fbcd97eca64ad0c1660e5abc38fd1422e1f599bdd89ec16b796
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 55,
-  "best_metric": 1.7220358848571777,
-  "best_model_checkpoint": "./outputs/ctrl_abort_right/checkpoint-55",
-  "epoch": 0.11783610069630424,
+  "best_global_step": 60,
+  "best_metric": 1.7189992666244507,
+  "best_model_checkpoint": "./outputs/ctrl_abort_right/checkpoint-60",
+  "epoch": 0.12854847348687734,
   "eval_steps": 5,
-  "global_step": 55,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -481,6 +481,49 @@
       "eval_samples_per_second": 14.023,
       "eval_steps_per_second": 7.011,
       "step": 55
+    },
+    {
+      "epoch": 0.11997857525441885,
+      "grad_norm": 1.2811716794967651,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 1.6783,
+      "step": 56
+    },
+    {
+      "epoch": 0.12212104981253348,
+      "grad_norm": 1.482115387916565,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 1.8306,
+      "step": 57
+    },
+    {
+      "epoch": 0.1242635243706481,
+      "grad_norm": 1.1114031076431274,
+      "learning_rate": 8.856374635655696e-08,
+      "loss": 1.5695,
+      "step": 58
+    },
+    {
+      "epoch": 0.12640599892876273,
+      "grad_norm": 1.3343108892440796,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 1.6949,
+      "step": 59
+    },
+    {
+      "epoch": 0.12854847348687734,
+      "grad_norm": 1.162011981010437,
+      "learning_rate": 9.866357858642206e-09,
+      "loss": 1.5822,
+      "step": 60
+    },
+    {
+      "epoch": 0.12854847348687734,
+      "eval_loss": 1.7189992666244507,
+      "eval_runtime": 1.158,
+      "eval_samples_per_second": 13.816,
+      "eval_steps_per_second": 6.908,
+      "step": 60
     }
   ],
   "logging_steps": 1,
@@ -504,12 +547,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5508695710003200.0,
+  "total_flos": 6024782336179200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null