Training in progress, step 32500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9a244e9cb55adf7cda56ccb82e1a9bee92d342f231471fb5502ab29003b5e6b
+oid sha256:2ee30a202b5c4cf7fda53d0395699d121bcda28082c91bf553e9af5faf8a149b
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2fb02fb3109cf50329151281ddbb10cbbd67d7bcacbec12c415183618e7c8c4
+oid sha256:e718a43f6e045c42f385b07d2ace5849f04af633001edd559d8966df49316ab3
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba3afeb76c9729f93ec4d0e7011fb72d06e1cea76b77b26bfd4a5e76df22f8c2
+oid sha256:230a3736d669f255b79c1310914eb307cf0cbcaffc29ea6c220c8c34f3f16376
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d99968826ce47bd88d7b05d470f4fb17f0bcc9ac13362244060de99696b592
+oid sha256:628f3ee901d7a700b603c7233dc69a829b7b7b1f7aa2edec89c4540f453a5834
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1333333333333333,
+  "epoch": 2.1666666666666665,
   "eval_steps": 500,
-  "global_step": 32000,
+  "global_step": 32500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2263,6 +2263,41 @@
       "learning_rate": 5.782666666666667e-06,
       "loss": 0.0466,
       "step": 32000
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.2384709119796753,
+      "learning_rate": 5.738222222222223e-06,
+      "loss": 0.0567,
+      "step": 32100
+    },
+    {
+      "epoch": 2.1466666666666665,
+      "grad_norm": 0.21881048381328583,
+      "learning_rate": 5.6937777777777785e-06,
+      "loss": 0.0577,
+      "step": 32200
+    },
+    {
+      "epoch": 2.1533333333333333,
+      "grad_norm": 0.1541258692741394,
+      "learning_rate": 5.649333333333334e-06,
+      "loss": 0.0508,
+      "step": 32300
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.23964588344097137,
+      "learning_rate": 5.605333333333334e-06,
+      "loss": 0.0627,
+      "step": 32400
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.27338939905166626,
+      "learning_rate": 5.560888888888889e-06,
+      "loss": 0.0522,
+      "step": 32500
     }
   ],
   "logging_steps": 100,
@@ -2282,7 +2317,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.794660999168e+16,
+  "total_flos": 7.91645257728e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null