Training in progress, step 320, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97dcc7e92150997caf43f44132f632318f1b3be03b8a1d7deffe1b438a61741f
+oid sha256:3d8a01100c62c7cacac7666b84a6c44a0483196ab6b8c9c7c4be1aaf269b5663
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea973c276ab59bc9e7d64828bf3fc26b4e9ddb52e89e8f9b77b188712df8be6
+oid sha256:e64cb9e6475db44bc10b56c5c1601234f794b800de82fcff62a83d3bd5c038a0
 size 255266042

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8611f7af3b6f1677359f2cd540517569455f69d0137912164f489c86cb1ae269
+oid sha256:988517d151ddb318c6517f3fcf2ff62485ab8c9a84ec571fb5664a92bec4067b
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4727b16984bbba02c1771b73a5cff7b29ebf8f37411164dbbb9c1c46a7e9fdbc
+oid sha256:ae33deae3edf829d48de6c73aa057338b3796fe98797d3f8547591e4e524394f
 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": 25.0,
+  "epoch": 26.666666666666668,
   "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": 2.8095,
       "step": 300
+    },
+    {
+      "epoch": 25.833333333333332,
+      "grad_norm": 3.59375,
+      "learning_rate": 0.00010275543423681621,
+      "loss": 2.7729,
+      "step": 310
+    },
+    {
+      "epoch": 26.666666666666668,
+      "grad_norm": 4.125,
+      "learning_rate": 9.724456576318381e-05,
+      "loss": 2.7436,
+      "step": 320
+    },
+    {
+      "epoch": 26.666666666666668,
+      "eval_loss": 3.106285810470581,
+      "eval_runtime": 10.2808,
+      "eval_samples_per_second": 146.0,
+      "eval_steps_per_second": 2.334,
+      "step": 320
     }
   ],
   "logging_steps": 10,
@@ -300,7 +322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9436991670124544e+16,
+  "total_flos": 2.074867763511296e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null