Training in progress, step 360, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99afcca2ca463465c80ebc2ad481b7a4ed0caf2ca83dd48c6cb23804e9eb9066
+oid sha256:9af49c9edcfed02b10af1339bb92fe78215e858603f350eeb4b2d0a7a8edf71f
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fde729599458b8685083cec6dbecbabdb6de1fa6bfa6aaa52e8fac8029ce439
+oid sha256:df52e6474cfc30205300327d8d9e754caf001c5369da3112af4a70df85644e55
 size 255266042

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7708d765c69898ac6704acdc2b9aef6ebc71ee392dc45c5b50d1715bf3068ddb
+oid sha256:7a118a9514a549b1c1a133d1f1df15ac8c05ca218ab71dcc6f8414e1eadc4a59
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c46256615d40b83cb0b5dbb74b01f9ee649dc90f7b090c538d38a043381326
+oid sha256:69815878e03356d8bd8371d309e329aee88a4c051e989648a0e943e2a8937207
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:775af4447ea22c8fde6b9577374f0010f59aa5050c5eb44816a7c00e793e5d27
+oid sha256:abff5f72bffb1872fbb50b3d3804321242e45865d0e2233d397521c6e944caf4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 28.333333333333332,
+  "epoch": 30.0,
   "eval_steps": 40,
-  "global_step": 340,
+  "global_step": 360,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -317,6 +317,28 @@
       "learning_rate": 8.626464421815919e-05,
       "loss": 2.692,
       "step": 340
+    },
+    {
+      "epoch": 29.166666666666668,
+      "grad_norm": 3.765625,
+      "learning_rate": 8.082893680762619e-05,
+      "loss": 2.6466,
+      "step": 350
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 3.71875,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 2.6371,
+      "step": 360
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 3.0690042972564697,
+      "eval_runtime": 10.5907,
+      "eval_samples_per_second": 141.728,
+      "eval_steps_per_second": 2.266,
+      "step": 360
     }
   ],
   "logging_steps": 10,
@@ -336,7 +358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.203527958180659e+16,
+  "total_flos": 2.3321881528500224e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null