Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aeb37187936d017f6bd51736738766a1f2cd5d041a79e47044d4da52589bf50
+oid sha256:cb3944baba224fb9f68ab01233170ab280c7bca8803f3c7e71a714c5f3fdcf93
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d8581669082f016d0e4e6b12b964126b4e2bcf55585a4a4b4bf94b576f2041e
-size 255265850
+oid sha256:2faf34cac979c57dfb55da136bfa774c54eaef839c48e6205e326aa7111a8154
+size 255266042

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ca12c54f4164ace515795e08e0960f0c28e1845dd3bb744b613ac48e9edba6
+oid sha256:c659953fa2749100d286c777ca42cee4acfebcb66827f7bc777ef8c79c6ffa46
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df12b162a1b11037b9375aff4eed1b0f26be6ed2687bf1154d65e88dde5f9250
+oid sha256:6165eeddacf3a11e1b3e53c4e5290a59148da44d6a02a50c118da0899808e516
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748ed266e9432323e41e747f49e84d108918da883711ff6e01c8135af1c286fd
+oid sha256:4c62f46b6ecdcc9452fbe00042ae2d6095daf65d97a17c5763e0d0ed253cea52
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.833333333333332,
+  "epoch": 25.0,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 143.936,
       "eval_steps_per_second": 2.301,
       "step": 250
+    },
+    {
+      "epoch": 21.666666666666668,
+      "grad_norm": 4.03125,
+      "learning_rate": 0.00012985148110016947,
+      "loss": 2.9827,
+      "step": 260
+    },
+    {
+      "epoch": 22.5,
+      "grad_norm": 3.953125,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 2.9238,
+      "step": 270
+    },
+    {
+      "epoch": 23.333333333333332,
+      "grad_norm": 4.25,
+      "learning_rate": 0.00011917106319237386,
+      "loss": 2.8875,
+      "step": 280
+    },
+    {
+      "epoch": 24.166666666666668,
+      "grad_norm": 3.90625,
+      "learning_rate": 0.00011373535578184082,
+      "loss": 2.836,
+      "step": 290
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 3.703125,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 2.8044,
+      "step": 300
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 3.1132636070251465,
+      "eval_runtime": 10.3535,
+      "eval_samples_per_second": 144.976,
+      "eval_steps_per_second": 2.318,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -249,7 +292,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6216828598550528e+16,
+  "total_flos": 1.9436991670124544e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null