Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5746549a1e92d4dc4f92122782383cc00a7ac92e8089ff9ef6497b69b930974c
+oid sha256:7437eb3b69207275b5e07dc0bd6b71bfb4b5900389f86280a86fd5e93cedd4cb
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba0ed148826db60c0c69a18bb6b2268d8fbb3f7a445faa5a83ef4e303e73f9f4
+oid sha256:78c1f945c9996a108bb76dd5d4315d62355f268ceb4e4255abd5c8930e7ae848
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d9358611d5238c19c59fb3aa3eac2040cbac245a7cfcfe56e1467f677e36cf
+oid sha256:372c9c91189dafe7a0013b948ff9907e60fc7ad4b32cc7ac3bccb3f603cf2268
 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": 0.08791208791208792,
+  "epoch": 0.13186813186813187,
   "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": 10.3732,
       "step": 18
+    },
+    {
+      "epoch": 0.09230769230769231,
+      "grad_norm": 0.056560974568128586,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.3698,
+      "step": 21
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "grad_norm": 0.06187056005001068,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.3695,
+      "step": 24
+    },
+    {
+      "epoch": 0.1054945054945055,
+      "eval_loss": 10.364975929260254,
+      "eval_runtime": 0.3982,
+      "eval_samples_per_second": 241.109,
+      "eval_steps_per_second": 120.554,
+      "step": 24
+    },
+    {
+      "epoch": 0.11868131868131868,
+      "grad_norm": 0.06369107961654663,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.3706,
+      "step": 27
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.05572490394115448,
+      "learning_rate": 0.0,
+      "loss": 10.3707,
+      "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": 523024465920.0,
+  "total_flos": 784536698880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null