Training in progress, step 320, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef91c402a00a0ab5044139adeab6e6c84327ec20dcb98519a5dd47c13459484
+oid sha256:47e28928720afbfd431ec4a6381b22773b2e78102af9c1e41480a9554b7a5e4e
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb179df1153cc6ae95ee73badb83521bc1538bf7cfc4bae63de17a2839c6501c
+oid sha256:1055abafe6a0e6141e462e4a9d7c405c2ba30875112c901416cf3dd79cf92466
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c3d9a056933457acb03adc6fbca244787e41f8774a88cacdd231cad1f4c1462
+oid sha256:b9350673392e31b98858f6fe816923eae7f55b9f3f625f62a4fbef924f908709
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8232c83a30fb4990d5c536090c2c4b7a61c630c74ed4091730cf211a2c322f3
+oid sha256:07185e8ad02f9bc11c0bd4a82441f8a3bb2aaa16f696dfa0b75d528de14c8cf9
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c62f46b6ecdcc9452fbe00042ae2d6095daf65d97a17c5763e0d0ed253cea52
+oid sha256:dc99919da5a7742331644c92ad35399b61089cf3cf76c5e4355b2e567e5f74d4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.076923076923077,
+  "epoch": 24.615384615384617,
   "eval_steps": 40,
-  "global_step": 300,
+  "global_step": 320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -281,6 +281,28 @@
       "learning_rate": 0.00010825793454723325,
       "loss": 9.2338,
       "step": 300
+    },
+    {
+      "epoch": 23.846153846153847,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00010275543423681621,
+      "loss": 9.2184,
+      "step": 310
+    },
+    {
+      "epoch": 24.615384615384617,
+      "grad_norm": 0.4140625,
+      "learning_rate": 9.724456576318381e-05,
+      "loss": 9.2101,
+      "step": 320
+    },
+    {
+      "epoch": 24.615384615384617,
+      "eval_loss": 9.220477104187012,
+      "eval_runtime": 5.2726,
+      "eval_samples_per_second": 284.679,
+      "eval_steps_per_second": 4.552,
+      "step": 320
     }
   ],
   "logging_steps": 10,
@@ -300,7 +322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 122747564851200.0,
+  "total_flos": 130930735841280.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null