Training in progress, step 33500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f3fa8a2349c8b7e8ef7591faf4142fae1ab2981c5397d9e3f22dbb692b3d52a
+oid sha256:b97182c688d993733fe30b3cd254e6701a753aa3cc2386b86d587fdb03bb6673
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b42426cc36edf758e4d57f94cd488382d45ee0e94746d9273813cf1a72d6fbcc
+oid sha256:7856bcf04b20cd8307ae2c76430eb38324a8c0698517e73495150d5bd27dff1b
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb9092d8d8eea8d4b54fe2ad3f4e9f22ac5e285340629fa61e0b094539adabee
+oid sha256:137247deb099a0895b19ce9e4c6b96a673b81c10a6ea5cdab1f3338408e77892
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5011c95b426af587e7306c32d3c809014be6f544ede16b0ee848cd35fd4378b6
+oid sha256:e4fd446a83e934c2d5675c18ca5f4bc5dada518d6ba6f33540a2d77e70605ffe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2,
+  "epoch": 2.2333333333333334,
   "eval_steps": 500,
-  "global_step": 33000,
+  "global_step": 33500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2333,6 +2333,41 @@
       "learning_rate": 5.338666666666668e-06,
       "loss": 0.0522,
       "step": 33000
+    },
+    {
+      "epoch": 2.2066666666666666,
+      "grad_norm": 0.1424885094165802,
+      "learning_rate": 5.294222222222223e-06,
+      "loss": 0.0542,
+      "step": 33100
+    },
+    {
+      "epoch": 2.2133333333333334,
+      "grad_norm": 0.29376089572906494,
+      "learning_rate": 5.249777777777778e-06,
+      "loss": 0.0466,
+      "step": 33200
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.21891391277313232,
+      "learning_rate": 5.205333333333333e-06,
+      "loss": 0.051,
+      "step": 33300
+    },
+    {
+      "epoch": 2.2266666666666666,
+      "grad_norm": 0.09811867028474808,
+      "learning_rate": 5.1608888888888894e-06,
+      "loss": 0.053,
+      "step": 33400
+    },
+    {
+      "epoch": 2.2333333333333334,
+      "grad_norm": 0.17383785545825958,
+      "learning_rate": 5.116444444444445e-06,
+      "loss": 0.0486,
+      "step": 33500
     }
   ],
   "logging_steps": 100,
@@ -2352,7 +2387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.038244155392e+16,
+  "total_flos": 8.160035733504e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null