Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3d71083e91b0a40655feb3a8e35f9ac501b632d72ee3df8362e3ef9166aa773
+oid sha256:8641c909dd0c5c892241206fcfd1a1c7d656ed435fb63e6dcbefe52097eba4e4
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d19bb58d7e95d4a4c5a7bdfa39fe4fb04d041e3efc5f2ee537241fabf2eb7fb7
+oid sha256:0042106e946680d8298d602263e5c6c012b22547b39ba2a0e9b505e7cf325034
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49b63be30ad5ea6dd7741cffe2d5e2097e64fc2bc7414659956d30ee0ca0910e
+oid sha256:05dd11bd3960ad0fa940da6d1dc661f5e30b05ee951391d57c064dbbfbc68d4f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bda3eccb561587882c44f73a771f7bad8a4b1c3754d5593b8ea0a3e51859fbe
+oid sha256:db2f945d95b7f2213fc49d24adce8252948ea4ec843ad966697f46d8ea38c7da
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7015793848711556,
+  "epoch": 2.9093931837073983,
   "eval_steps": 500,
-  "global_step": 6500,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,13 @@
       "learning_rate": 1.99778331947908e-06,
       "loss": 0.3229,
       "step": 6500
+    },
+    {
+      "epoch": 2.9093931837073983,
+      "grad_norm": 0.5834936499595642,
+      "learning_rate": 6.123579939041286e-07,
+      "loss": 0.3166,
+      "step": 7000
     }
   ],
   "logging_steps": 500,
@@ -133,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.583168723877888e+16,
+  "total_flos": 1.704960301989888e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null