Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65b76113cc66a54ae0d51cf94af5be1af9504b6a1f06b6ce681d5b3db4a8093d
+oid sha256:7f161dce607158201e081116f0ed4853a09b56914d972d608f3ec30ad92d837d
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8354ed4f7a4bea4421fcded7ce83c9bab4384af9af552b5d65672b4ee4f1ac4f
+oid sha256:c9f3dbee8820f26ad218828f408fd116edde91b0f150ff2add16a7c0803e3172
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc64d5d13a3120771ece3c4a2eb4de07fed7796fc4d888af303e82089a1664f1
+oid sha256:40a41b1cfc2d1d2cac5b4a1a7b6d8de286116a44eea4ee32508ab5c0289c1384
 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": 0.06334125098970704,
+  "epoch": 0.09501187648456057,
   "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": 3.3664,
       "step": 18
+    },
+    {
+      "epoch": 0.0665083135391924,
+      "grad_norm": 2.497666358947754,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.6111,
+      "step": 21
+    },
+    {
+      "epoch": 0.07600950118764846,
+      "grad_norm": 2.1342661380767822,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.317,
+      "step": 24
+    },
+    {
+      "epoch": 0.07600950118764846,
+      "eval_loss": 2.974780321121216,
+      "eval_runtime": 15.9151,
+      "eval_samples_per_second": 8.357,
+      "eval_steps_per_second": 4.21,
+      "step": 24
+    },
+    {
+      "epoch": 0.0855106888361045,
+      "grad_norm": 1.8432875871658325,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.1822,
+      "step": 27
+    },
+    {
+      "epoch": 0.09501187648456057,
+      "grad_norm": 2.388378381729126,
+      "learning_rate": 0.0,
+      "loss": 2.7469,
+      "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": 6990386933268480.0,
+  "total_flos": 1.048558039990272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null