Training in progress, step 520, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1ae0cef03350b13f2142034ec12a4f632f2a167671a45fb33d96be882bf8881
+oid sha256:cd1c83fafb8e02dd0f717cc5a39162f05d7404832c5fc4fbc8120bc5a28a3a34
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4e7bc77588b6383613b88b55c7bb31c785abbac487d86ed9e1ea0688d925796
+oid sha256:4511333d8901550e499feb301ed012fb58032713f2be7e20a710ee1fa928aed4
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86bc4ba66dd9b2678296e8603b5fc45b9513c8a929966cabd3603650c1d00ca8
+oid sha256:89e9e6580a84fd0db2b771e56099822d173da85eac47864d93760d074b498333
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7ddf240f6d195d0e03799bc56610ed87dcf151c18d11e02b13b1a13f27c3bac
+oid sha256:d380d2d68225342e540efbf7273fe50dde428b916e607285dece60ac093c01c5
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:628e045b78e5d559e9fcef6658ed03e911773af6f7354bf6b3b679b0ff34bfdb
+oid sha256:839bffb3b2b97ea56ce77fd476927b3e7c6d86a97c322429166a0d05d8bba56a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 38.46153846153846,
+  "epoch": 40.0,
   "eval_steps": 40,
-  "global_step": 500,
+  "global_step": 520,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -461,6 +461,28 @@
       "learning_rate": 1.4808059116167305e-05,
       "loss": 9.1781,
       "step": 500
+    },
+    {
+      "epoch": 39.23076923076923,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 9.1771,
+      "step": 510
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.419921875,
+      "learning_rate": 9.564283930242257e-06,
+      "loss": 9.1775,
+      "step": 520
+    },
+    {
+      "epoch": 40.0,
+      "eval_loss": 9.193778991699219,
+      "eval_runtime": 5.2716,
+      "eval_samples_per_second": 284.736,
+      "eval_steps_per_second": 4.553,
+      "step": 520
     }
   ],
   "logging_steps": 10,
@@ -480,7 +502,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 204579274752000.0,
+  "total_flos": 212762445742080.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null