Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c30702ff64fa0aba4932e7eadebfb764d6f331c6aba79bc38dd329b15590ba2
+oid sha256:65f41221813633184b2538c9109cba635ca76c786eea27784f452a640f0ed68f
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb2bac883db20ffc2f90dfc94691883c4010a3f4f90dc3d9b417e465fc0af4e5
+oid sha256:bf7a4bf67da87410a6d09254af4d762ab91388990e0e2f7d30094dbe9596864a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3be9ba5208bb0b7f62289ba0a40fc9a2f25e8400d6b589d90ca0f5299037cd9d
+oid sha256:d201843135a1eed508b1bfdef27db8413b4debdba9826e312a0df4e52244dac2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69ad02ad549d13e9ab8b866040bb435de5088d2062ba8ddaadf1f207253684e
+oid sha256:0f12d6282f561619ed37157e6869ea88b19ad7c33ffa9cf992ccd45bf1251ffb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3507896924355778,
+  "epoch": 1.4546965918536992,
   "eval_steps": 500,
-  "global_step": 6500,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -106,6 +106,13 @@
       "learning_rate": 1.1000277085065116e-05,
       "loss": 0.3626,
       "step": 6500
+    },
+    {
+      "epoch": 1.4546965918536992,
+      "grad_norm": 0.35276883840560913,
+      "learning_rate": 1.030756442227764e-05,
+      "loss": 0.352,
+      "step": 7000
     }
   ],
   "logging_steps": 500,
@@ -125,7 +132,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7915843619389440.0,
+  "total_flos": 8524801509949440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null