Training in progress, step 41500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a43c2a0afd3692b4457c78e060bd95a6ca8422aa3f2bfb48776d966c67148820
+oid sha256:ddeba81fa20a347b7f4a8bf56911f542931a9c7a9a28e5b17d8415cffe0f05fc
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb247ef281f39dbf138924be64b77fed104e544ac60daad36b17f01b15edabf4
+oid sha256:c534f106883dfc1dc4725defbacef030c7dba5f5e0888cc081c7906d9d0b8453
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83988fc1574bdb56177858ad2504e5d5e90771242080ec94288ec2934ea05174
+oid sha256:3b282c8a79340622eb958db3d6110bd8f623dfad615139665f1498d8b00a6bed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a519ef81b846f8a03a3bd8bed22cf3df79611baad6f40e402df6bfc345f1aa61
+oid sha256:6abecd6b93d057c006d3ff371902f2a70b673a5fc3d8d5773b1c045cd3372a7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7333333333333334,
+  "epoch": 2.7666666666666666,
   "eval_steps": 500,
-  "global_step": 41000,
+  "global_step": 41500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2893,6 +2893,41 @@
       "learning_rate": 1.784888888888889e-06,
       "loss": 0.046,
       "step": 41000
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.176757350564003,
+      "learning_rate": 1.7404444444444445e-06,
+      "loss": 0.0512,
+      "step": 41100
+    },
+    {
+      "epoch": 2.7466666666666666,
+      "grad_norm": 0.28724828362464905,
+      "learning_rate": 1.6960000000000002e-06,
+      "loss": 0.0514,
+      "step": 41200
+    },
+    {
+      "epoch": 2.7533333333333334,
+      "grad_norm": 0.654242753982544,
+      "learning_rate": 1.6515555555555556e-06,
+      "loss": 0.0497,
+      "step": 41300
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.2873416543006897,
+      "learning_rate": 1.6071111111111112e-06,
+      "loss": 0.0492,
+      "step": 41400
+    },
+    {
+      "epoch": 2.7666666666666666,
+      "grad_norm": 0.28858011960983276,
+      "learning_rate": 1.5626666666666667e-06,
+      "loss": 0.0485,
+      "step": 41500
     }
   ],
   "logging_steps": 100,
@@ -2912,7 +2947,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.986909405184e+16,
+  "total_flos": 1.0108700983296e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null