Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff86c795108bebbb03197031226302aa1a4886a13a4c842af5b2f335e7d19ba
+oid sha256:97dcc7e92150997caf43f44132f632318f1b3be03b8a1d7deffe1b438a61741f
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706716e7d441014be5a3bd43a61aa37020629b79add63328cb2cbcd5d66bbcab
+oid sha256:2ea973c276ab59bc9e7d64828bf3fc26b4e9ddb52e89e8f9b77b188712df8be6
 size 255266042

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ad5498f4f027df932a7a052ce9a16069123583bd9fd4b7011a25707f717929
+oid sha256:8611f7af3b6f1677359f2cd540517569455f69d0137912164f489c86cb1ae269
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59b2b94e078bb1ccac3fa3d386a21a3b586bcdf3fb3f1fd3aedf58603ddfa9b4
+oid sha256:4727b16984bbba02c1771b73a5cff7b29ebf8f37411164dbbb9c1c46a7e9fdbc
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa6ea3f731b59c0eb2ad9a4603b6f27b0a7e78ff027cc2874370bdf6bfc7598e
+oid sha256:4c62f46b6ecdcc9452fbe00042ae2d6095daf65d97a17c5763e0d0ed253cea52
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.333333333333332,
+  "epoch": 25.0,
   "eval_steps": 40,
-  "global_step": 280,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,20 @@
       "eval_samples_per_second": 144.243,
       "eval_steps_per_second": 2.306,
       "step": 280
+    },
+    {
+      "epoch": 24.166666666666668,
+      "grad_norm": 3.84375,
+      "learning_rate": 0.00011373535578184082,
+      "loss": 2.8435,
+      "step": 290
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 3.53125,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 2.8095,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -286,7 +300,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.814934450287411e+16,
+  "total_flos": 1.9436991670124544e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null