Training in progress, step 560, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76cf2cfb8acb6251db267638caae88710cf88816ace06f8acd7cae72037b7e23
+oid sha256:0e938d2e6c79fd63eb1bf7556472b175170f1e1fcb7490186628ef3502bcb601
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29600bcee487c1a01dc32b2722f7c8862c9e02614484b036be9fdfa628bf8bb9
+oid sha256:6afdd36c2c13a653549d0d71f18e3e7d5187494fb4c71994a47849ec6c82bbff
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9238b7add585066cbb06da0e32e6be6507c64165fbe42aa9ed19eca4092e8ab
+oid sha256:aa472c1d2e1ad30011add0ce83904e37d2caa36216037fbad49576f2756efb5b
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:672fecd4dfa047902993b09ba8fc51ecd2a72c6903902bf77e4b09f779d46548
+oid sha256:743d3a9f693b684ee3153d836a21fe12defa659ab9ab57ee619a05a569102f6c
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db496ff339a198f08c0b8942170220cef7c7f05387b73d30643172645a9da2c1
+oid sha256:b1c1b0efcf3afa634fda84640ee52e51b8f239aa7ea918845652fbaccafc77f8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 41.53846153846154,
+  "epoch": 43.07692307692308,
   "eval_steps": 40,
-  "global_step": 540,
+  "global_step": 560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -497,6 +497,28 @@
       "learning_rate": 5.418275829936537e-06,
       "loss": 9.1786,
       "step": 540
+    },
+    {
+      "epoch": 42.30769230769231,
+      "grad_norm": 0.41796875,
+      "learning_rate": 3.7731999690749585e-06,
+      "loss": 9.1761,
+      "step": 550
+    },
+    {
+      "epoch": 43.07692307692308,
+      "grad_norm": 0.4140625,
+      "learning_rate": 2.420361737256438e-06,
+      "loss": 9.1784,
+      "step": 560
+    },
+    {
+      "epoch": 43.07692307692308,
+      "eval_loss": 9.194928169250488,
+      "eval_runtime": 5.2748,
+      "eval_samples_per_second": 284.561,
+      "eval_steps_per_second": 4.55,
+      "step": 560
     }
   ],
   "logging_steps": 10,
@@ -516,7 +538,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 220945616732160.0,
+  "total_flos": 229128787722240.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null