Training in progress, step 280, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7061fadd3c867263d87e12e8b7e280976ce200378e43b87f0081a278d4383e7
+oid sha256:9ff86c795108bebbb03197031226302aa1a4886a13a4c842af5b2f335e7d19ba
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24d91ac5539ceabfcf15fbf9d84527d1e791ae4cea2693dbcd256bead5c4bf6a
+oid sha256:706716e7d441014be5a3bd43a61aa37020629b79add63328cb2cbcd5d66bbcab
 size 255266042

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79c164d22927fe2b6be7170e235646a9aaf6d63ba0191dae0d9fe729f5a4a83
+oid sha256:e9ad5498f4f027df932a7a052ce9a16069123583bd9fd4b7011a25707f717929
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc59c27066bac68aa57567d315b438b10f99b59c00a49fca645305936456a77f
+oid sha256:59b2b94e078bb1ccac3fa3d386a21a3b586bcdf3fb3f1fd3aedf58603ddfa9b4
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3a36d0f4565e0cd31cd0465a8062a29bd158a6ba54be5d6acec2d94425b0892
+oid sha256:aa6ea3f731b59c0eb2ad9a4603b6f27b0a7e78ff027cc2874370bdf6bfc7598e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.666666666666668,
+  "epoch": 23.333333333333332,
   "eval_steps": 40,
-  "global_step": 260,
+  "global_step": 280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,28 @@
       "learning_rate": 0.00012985148110016947,
       "loss": 2.9882,
       "step": 260
+    },
+    {
+      "epoch": 22.5,
+      "grad_norm": 3.859375,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 2.931,
+      "step": 270
+    },
+    {
+      "epoch": 23.333333333333332,
+      "grad_norm": 4.0625,
+      "learning_rate": 0.00011917106319237386,
+      "loss": 2.8933,
+      "step": 280
+    },
+    {
+      "epoch": 23.333333333333332,
+      "eval_loss": 3.0961873531341553,
+      "eval_runtime": 10.406,
+      "eval_samples_per_second": 144.243,
+      "eval_steps_per_second": 2.306,
+      "step": 280
     }
   ],
   "logging_steps": 10,
@@ -264,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.686169733562368e+16,
+  "total_flos": 1.814934450287411e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null