Training in progress, step 34000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b97182c688d993733fe30b3cd254e6701a753aa3cc2386b86d587fdb03bb6673
+oid sha256:3e4ab360c914af5780dbdab371c96384f68fadc50929f69d6d527fb768d4c4fc
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7856bcf04b20cd8307ae2c76430eb38324a8c0698517e73495150d5bd27dff1b
+oid sha256:efe48f4318badae6c7301c7e1af6b474ccbe7f71331abdb7cdd8a9a8ea72715a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:137247deb099a0895b19ce9e4c6b96a673b81c10a6ea5cdab1f3338408e77892
+oid sha256:d6d089c8bc4767a68a0971e6301211196ccb288fdbf802f4d0800d2c395bd6e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4fd446a83e934c2d5675c18ca5f4bc5dada518d6ba6f33540a2d77e70605ffe
+oid sha256:b5881a400174694043dc48b7e6a0f928fe1bcddfe30dc261df5a9e4e69d0e718
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2333333333333334,
+  "epoch": 2.2666666666666666,
   "eval_steps": 500,
-  "global_step": 33500,
+  "global_step": 34000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2368,6 +2368,41 @@
       "learning_rate": 5.116444444444445e-06,
       "loss": 0.0486,
       "step": 33500
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.20023219287395477,
+      "learning_rate": 5.072e-06,
+      "loss": 0.0509,
+      "step": 33600
+    },
+    {
+      "epoch": 2.2466666666666666,
+      "grad_norm": 0.24713067710399628,
+      "learning_rate": 5.027555555555555e-06,
+      "loss": 0.0487,
+      "step": 33700
+    },
+    {
+      "epoch": 2.2533333333333334,
+      "grad_norm": 0.2585085928440094,
+      "learning_rate": 4.983111111111111e-06,
+      "loss": 0.0464,
+      "step": 33800
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.10687225311994553,
+      "learning_rate": 4.938666666666667e-06,
+      "loss": 0.0558,
+      "step": 33900
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.2748579680919647,
+      "learning_rate": 4.8942222222222225e-06,
+      "loss": 0.0533,
+      "step": 34000
     }
   ],
   "logging_steps": 100,
@@ -2387,7 +2422,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.160035733504e+16,
+  "total_flos": 8.281827311616e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null