Training in progress, step 6500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593880cb57f7296249dfb7fd4e4893cea19d4c98de08b77d76321b25dc93b8c3
+oid sha256:9b1ae2351e5b6769177f452d6bdf75ceebbf4284094efd31c781f1654ded23a8
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab45de1f863a2a240ea88b6522e7fafee3ad5f522cb7872c19df7b6a6d5a4adf
+oid sha256:7d241bb3d465dc9b7c7c3e682722788888cdd912a2bcd56b4c7ea4839c03df6f
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6b9c7c0b8987c7e0e5d0153c4f1710b900efe6354c3e9b604bb41f90977c0e
+oid sha256:49b63be30ad5ea6dd7741cffe2d5e2097e64fc2bc7414659956d30ee0ca0910e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289ccbafd4cbc565d30135d7789ffd97a9803f5eaa40921290229dea676c429b
+oid sha256:887c24a9d6576cc94882e0f1848007f533f1d1fcf23382be01b3a312abe3db85
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.493765586034913,
+  "epoch": 2.7015793848711556,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -107,6 +107,13 @@
       "learning_rate": 1.0029925187032419e-05,
       "loss": 0.3438,
       "step": 6000
+    },
+    {
+      "epoch": 2.7015793848711556,
+      "grad_norm": 0.823439359664917,
+      "learning_rate": 9.19866999168745e-06,
+      "loss": 0.3406,
+      "step": 6500
     }
   ],
   "logging_steps": 500,
@@ -126,7 +133,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.461377145765888e+16,
+  "total_flos": 1.583168723877888e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null