Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ff59b2154b7aca3eb37379a29d25112177efa29f23ef92f23858b585e51920
+oid sha256:3d3e2de5196a08b5a6d1a40622867b15f533824969f76e886276a90b81106d58
 size 1770585648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e3d7d07dc8bfe164d49d8c2326b3668de79113c139a16903a6e33b39706d3a
+oid sha256:0496f8ea936e30acf9459255504f5b5b9fd4be4cb7b5231353e7af1744002975
 size 99235764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6a216e76306077697fce369babc722d934631ceab06c507d0d26aa9b1335b22
+oid sha256:05e22fba92b29c1f5f0cd59a19fdf634f506ef846ae85ca8af68d60096387010
 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": 0.021052631578947368,
+  "epoch": 0.042105263157894736,
   "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": 5.021,
       "step": 5
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "grad_norm": 9.20016098022461,
+      "learning_rate": 0.00012,
+      "loss": 4.0351,
+      "step": 6
+    },
+    {
+      "epoch": 0.02526315789473684,
+      "eval_loss": 2.8107352256774902,
+      "eval_runtime": 33.8183,
+      "eval_samples_per_second": 2.957,
+      "eval_steps_per_second": 1.478,
+      "step": 6
+    },
+    {
+      "epoch": 0.029473684210526315,
+      "grad_norm": 9.21462631225586,
+      "learning_rate": 0.00014,
+      "loss": 2.8038,
+      "step": 7
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 10.491095542907715,
+      "learning_rate": 0.00016,
+      "loss": 1.4769,
+      "step": 8
+    },
+    {
+      "epoch": 0.037894736842105266,
+      "grad_norm": 10.90908432006836,
+      "learning_rate": 0.00018,
+      "loss": 0.9007,
+      "step": 9
+    },
+    {
+      "epoch": 0.037894736842105266,
+      "eval_loss": 0.18612316250801086,
+      "eval_runtime": 33.8894,
+      "eval_samples_per_second": 2.951,
+      "eval_steps_per_second": 1.475,
+      "step": 9
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 3.377394676208496,
+      "learning_rate": 0.0002,
+      "loss": 0.2287,
+      "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": 2818744422236160.0,
+  "total_flos": 5637488844472320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null