Training in progress, step 31500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35881b4a958bf056508d114860b14084addd8682c5b35498eb4cbf8f6a42ffcc
+oid sha256:6b61d5a5a0f5b7ace55f8bc3cfcc9327599d34056cf4715c1510e9c33291ed41
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a03972f1e2c45bae275800dd72230f94d0382cbf9d6d293e189b2e288ac62bf
+oid sha256:31972f8c5588889908297685ea316a6c5603a5c6d49476ca372f9024aae59d33
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5a75fa06d8e0567428171895f2f5be669b2393bf43f572fee60b1f39d5db02
+oid sha256:2d03e6c49a145ce2e51d87480bb76687cc7b5c7b56e94d2991de3e2ab67bd210
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cadac78638c6cb012c738c824827d4d4609dcfa94ea2fed086f7884c5c610aa
+oid sha256:c724d2349acf4c39c5d4d83bc11668bbfaa5c5543e4339570ed104ddf6da9c9e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.066666666666667,
+  "epoch": 2.1,
   "eval_steps": 500,
-  "global_step": 31000,
+  "global_step": 31500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2193,6 +2193,41 @@
       "learning_rate": 6.2271111111111115e-06,
       "loss": 0.046,
       "step": 31000
+    },
+    {
+      "epoch": 2.0733333333333333,
+      "grad_norm": 0.2015141099691391,
+      "learning_rate": 6.182666666666667e-06,
+      "loss": 0.0552,
+      "step": 31100
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.13618551194667816,
+      "learning_rate": 6.138222222222223e-06,
+      "loss": 0.0504,
+      "step": 31200
+    },
+    {
+      "epoch": 2.086666666666667,
+      "grad_norm": 0.11296480149030685,
+      "learning_rate": 6.093777777777779e-06,
+      "loss": 0.0527,
+      "step": 31300
+    },
+    {
+      "epoch": 2.0933333333333333,
+      "grad_norm": 0.16036346554756165,
+      "learning_rate": 6.049333333333334e-06,
+      "loss": 0.0513,
+      "step": 31400
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.17830543220043182,
+      "learning_rate": 6.004888888888889e-06,
+      "loss": 0.053,
+      "step": 31500
     }
   ],
   "logging_steps": 100,
@@ -2212,7 +2247,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.551077842944e+16,
+  "total_flos": 7.672869421056e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null