Training in progress, step 460, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c1d813f5aa26feeb60e8865dfa61c223ae0848d343e955f01c29bd4c4eaa8c
+oid sha256:be10d176282a6dad55fe521c2659a5c756cd8682fe7880e2f3107339f0e4de62
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96f716c753b6ebfd0ee340c67bc8ce9f9cc8009288f86bb3e1839939a6c8370
+oid sha256:eb15b49ee20c5f76489e72b92694abdc408eb4ce3362d919c3b6d1a7196e9074
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfba244eb594b94dbaee2a8133c34e6d4fb3321c919b0d4c36bbf3c64495c646
+oid sha256:300d6be6a0627e29641baf29e49bd0ac9ea099599f21c9aa61bbfba24527c848
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5de4c69e76e1426849123e6be19b27395b0e7a791b5cc054f922bb9ef7b0bc5
+oid sha256:00edd3e36fd88028498581207c7af1930a5e4dbdf2075dd176fd55407ffe344f
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3a8d3a9de9d4e767952b9eebe7c2390356d0c8586b110844c79e24bc9bdec0
+oid sha256:776adfde0d7f584a3b4ff8a307fb88545361f677ac68f090fa018fdc36afaca7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 33.84615384615385,
+  "epoch": 35.38461538461539,
   "eval_steps": 40,
-  "global_step": 440,
+  "global_step": 460,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -411,6 +411,20 @@
       "eval_samples_per_second": 284.509,
       "eval_steps_per_second": 4.549,
       "step": 440
+    },
+    {
+      "epoch": 34.61538461538461,
+      "grad_norm": 0.416015625,
+      "learning_rate": 3.227184283742591e-05,
+      "loss": 9.1777,
+      "step": 450
+    },
+    {
+      "epoch": 35.38461538461539,
+      "grad_norm": 0.4140625,
+      "learning_rate": 2.8321748683154893e-05,
+      "loss": 9.1782,
+      "step": 460
     }
   ],
   "logging_steps": 10,
@@ -430,7 +444,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 180029761781760.0,
+  "total_flos": 188212932771840.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null