Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec3c984bcd90bcd40c1a3e894b532019984341efb298b127e03b32936cf4f6a
+oid sha256:cc356220d1d00dbbd7a3f6fbcaa8339e007e7faa1f3bdda3bc619285a0c18f18
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbdf20ba2a59eb7f487df26419d78f785769bc6787a6391704744910212b416f
+oid sha256:4aaa84720254d526e0c9a37e8c382618bb01438fa4e87f8b19c5b6d7e2a84737
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c87ab912118f041388cdb50adb42883f0498061dcbfe13deb335b062f452d87
+oid sha256:d3729714535361d3da6c603911f3ed24e523c8e6dffe566c724638ee5b65d672
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0053705692803437165,
+  "epoch": 0.010741138560687433,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 1.5065,
       "step": 5
+    },
+    {
+      "epoch": 0.00644468313641246,
+      "grad_norm": 1.8599263429641724,
+      "learning_rate": 0.00012,
+      "loss": 1.1595,
+      "step": 6
+    },
+    {
+      "epoch": 0.00644468313641246,
+      "eval_loss": 1.4259953498840332,
+      "eval_runtime": 37.0719,
+      "eval_samples_per_second": 10.574,
+      "eval_steps_per_second": 5.287,
+      "step": 6
+    },
+    {
+      "epoch": 0.007518796992481203,
+      "grad_norm": 2.1810078620910645,
+      "learning_rate": 0.00014,
+      "loss": 1.3973,
+      "step": 7
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "grad_norm": 1.4867852926254272,
+      "learning_rate": 0.00016,
+      "loss": 0.9254,
+      "step": 8
+    },
+    {
+      "epoch": 0.00966702470461869,
+      "grad_norm": 1.1330220699310303,
+      "learning_rate": 0.00018,
+      "loss": 0.7735,
+      "step": 9
+    },
+    {
+      "epoch": 0.00966702470461869,
+      "eval_loss": 0.8766637444496155,
+      "eval_runtime": 37.0542,
+      "eval_samples_per_second": 10.579,
+      "eval_steps_per_second": 5.29,
+      "step": 9
+    },
+    {
+      "epoch": 0.010741138560687433,
+      "grad_norm": 1.8013813495635986,
+      "learning_rate": 0.0002,
+      "loss": 0.8574,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2052393617326080.0,
+  "total_flos": 4104787234652160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null