Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1ae2351e5b6769177f452d6bdf75ceebbf4284094efd31c781f1654ded23a8
+oid sha256:4ee3e8177e6fadd097833e7afe6be3da19174e3ec791ceabfd5e2aef8276dfb7
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d241bb3d465dc9b7c7c3e682722788888cdd912a2bcd56b4c7ea4839c03df6f
+oid sha256:a3b2b702f5cef156784c924666ba6f0516aba8a128ff1c8252b58be7c17dd2df
 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 sha256:887c24a9d6576cc94882e0f1848007f533f1d1fcf23382be01b3a312abe3db85
+oid sha256:f8b02bc33df1b7c20f0491626d0e42bd29d99a710da7df8f3162d39edb7196e8
 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": 9.19866999168745e-06,
       "loss": 0.3406,
       "step": 6500
+    },
+    {
+      "epoch": 2.9093931837073983,
+      "grad_norm": 0.5342724323272705,
+      "learning_rate": 8.367414796342478e-06,
+      "loss": 0.3333,
+      "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