Training in progress, step 440, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58d07caf9aa80839281c79f13b683b604a675fd4afe87e9190eac4d154b49532
+oid sha256:43c1d813f5aa26feeb60e8865dfa61c223ae0848d343e955f01c29bd4c4eaa8c
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68d759b0f923c2bf9fc620f063306846faf916fa0435a3b7512e71b59b8cde72
+oid sha256:e96f716c753b6ebfd0ee340c67bc8ce9f9cc8009288f86bb3e1839939a6c8370
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de8a7d3ae35e0cfde7019bc76a87a4f5d2f57ea272cb1b432abf0d4078169331
+oid sha256:dfba244eb594b94dbaee2a8133c34e6d4fb3321c919b0d4c36bbf3c64495c646
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:846e47b3f08eae7caf9f57a22e4f7db968751c20e77f131354e1ce6ef8905e6d
+oid sha256:b5de4c69e76e1426849123e6be19b27395b0e7a791b5cc054f922bb9ef7b0bc5
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f859ddc3da44307ab9a20989e57c7a9e48c43cb14e7243a363c14a732e7b6863
+oid sha256:9d3a8d3a9de9d4e767952b9eebe7c2390356d0c8586b110844c79e24bc9bdec0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 32.30769230769231,
+  "epoch": 33.84615384615385,
   "eval_steps": 40,
-  "global_step": 420,
+  "global_step": 440,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -389,6 +389,28 @@
       "learning_rate": 4.530518418775733e-05,
       "loss": 9.1782,
       "step": 420
+    },
+    {
+      "epoch": 33.07692307692308,
+      "grad_norm": 0.41796875,
+      "learning_rate": 4.077647473350201e-05,
+      "loss": 9.1776,
+      "step": 430
+    },
+    {
+      "epoch": 33.84615384615385,
+      "grad_norm": 0.416015625,
+      "learning_rate": 3.642762517900322e-05,
+      "loss": 9.1787,
+      "step": 440
+    },
+    {
+      "epoch": 33.84615384615385,
+      "eval_loss": 9.194502830505371,
+      "eval_runtime": 5.2758,
+      "eval_samples_per_second": 284.509,
+      "eval_steps_per_second": 4.549,
+      "step": 440
     }
   ],
   "logging_steps": 10,
@@ -408,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 171846590791680.0,
+  "total_flos": 180029761781760.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null