Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15a5e61507b150febec91fb65a139aac52c422f21588bbee7447873070abe68e
+oid sha256:dce0d09f03f3f156d6b66940c39f98bed51ef2184d82a0ae1be38cece13978bf
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d043b0a210d45339a3fea4cd83be346b5722565a18c85f7b05acb35a7e9abc
+oid sha256:d0099eaa441e129ed7829e977ce4e8981eef84e2f953f4d6461f45d7305fae75
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b800b6d302bd5c5bc6607adcd64c98c8846be4c2323ad836fe3e601910de836
+oid sha256:5393cc6a1817757f20fd81e8db25d70ba44d676dca37db29d40af3d861e60ffc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2686563472cd649084082a2c329fd627ce86023a87d1ac3f5dd126e100dfda
+oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02154591974144896,
+  "epoch": 0.032318879612173446,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 9.189,
       "eval_steps_per_second": 4.606,
       "step": 20
+    },
+    {
+      "epoch": 0.022623215728521412,
+      "grad_norm": 0.6983510851860046,
+      "learning_rate": 0.00014067366430758004,
+      "loss": 0.6017,
+      "step": 21
+    },
+    {
+      "epoch": 0.025855103689738757,
+      "grad_norm": 0.9189296960830688,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6411,
+      "step": 24
+    },
+    {
+      "epoch": 0.026932399676811204,
+      "eval_loss": 0.6164190173149109,
+      "eval_runtime": 42.5383,
+      "eval_samples_per_second": 9.192,
+      "eval_steps_per_second": 4.608,
+      "step": 25
+    },
+    {
+      "epoch": 0.0290869916509561,
+      "grad_norm": 0.5284349918365479,
+      "learning_rate": 7.920883091822408e-05,
+      "loss": 0.506,
+      "step": 27
+    },
+    {
+      "epoch": 0.032318879612173446,
+      "grad_norm": 0.6442975401878357,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.5145,
+      "step": 30
+    },
+    {
+      "epoch": 0.032318879612173446,
+      "eval_loss": 0.597037672996521,
+      "eval_runtime": 42.633,
+      "eval_samples_per_second": 9.171,
+      "eval_steps_per_second": 4.597,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -108,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9217105396236288.0,
+  "total_flos": 1.377268622426112e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null