Training in progress, step 33000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee30a202b5c4cf7fda53d0395699d121bcda28082c91bf553e9af5faf8a149b
+oid sha256:4f3fa8a2349c8b7e8ef7591faf4142fae1ab2981c5397d9e3f22dbb692b3d52a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e718a43f6e045c42f385b07d2ace5849f04af633001edd559d8966df49316ab3
+oid sha256:b42426cc36edf758e4d57f94cd488382d45ee0e94746d9273813cf1a72d6fbcc
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:230a3736d669f255b79c1310914eb307cf0cbcaffc29ea6c220c8c34f3f16376
+oid sha256:cb9092d8d8eea8d4b54fe2ad3f4e9f22ac5e285340629fa61e0b094539adabee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:628f3ee901d7a700b603c7233dc69a829b7b7b1f7aa2edec89c4540f453a5834
+oid sha256:5011c95b426af587e7306c32d3c809014be6f544ede16b0ee848cd35fd4378b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1666666666666665,
+  "epoch": 2.2,
   "eval_steps": 500,
-  "global_step": 32500,
+  "global_step": 33000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2298,6 +2298,41 @@
       "learning_rate": 5.560888888888889e-06,
       "loss": 0.0522,
       "step": 32500
+    },
+    {
+      "epoch": 2.1733333333333333,
+      "grad_norm": 0.21274752914905548,
+      "learning_rate": 5.516444444444445e-06,
+      "loss": 0.0523,
+      "step": 32600
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.3107999563217163,
+      "learning_rate": 5.472e-06,
+      "loss": 0.0526,
+      "step": 32700
+    },
+    {
+      "epoch": 2.1866666666666665,
+      "grad_norm": 0.19043102860450745,
+      "learning_rate": 5.4275555555555555e-06,
+      "loss": 0.0522,
+      "step": 32800
+    },
+    {
+      "epoch": 2.1933333333333334,
+      "grad_norm": 0.17905379831790924,
+      "learning_rate": 5.383111111111112e-06,
+      "loss": 0.052,
+      "step": 32900
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.3581301271915436,
+      "learning_rate": 5.338666666666668e-06,
+      "loss": 0.0522,
+      "step": 33000
     }
   ],
   "logging_steps": 100,
@@ -2317,7 +2352,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.91645257728e+16,
+  "total_flos": 8.038244155392e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null