Training in progress, step 27500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aee5c58e4fc85927dc4013d0fe750e56e604920994d516f324190a1a8d7a05f
+oid sha256:5fbf8423ff110283327b1f8b90f9081b1058c9376cd2711b7771ceec771519e1
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d58926cc53cc96e7baec8d580220f0a290e47d6bc25d45f7fd7e61bf35d05d9a
+oid sha256:5ef9caf61392dd46c560c432d5d06b4ae3b7fe098c753ce284032c427faa732e
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8469fa4abc9740f9af7a5dacb10ea8c5107fb6c8cbc91f6fcad8c8b05132d7d0
+oid sha256:e92aea66aa69545e4cc667c6773e4db275b023af14af95463bf526993dcaef01
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc2ab4847205143252d3ebb3c6929a744853487e6aadfb5f1c78d5dcdea141c
+oid sha256:5d7857c6094c610d98d2faa905fca5f4d7aec2a9e3d0f066c66f0a11bdc1413e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8,
+  "epoch": 1.8333333333333335,
   "eval_steps": 500,
-  "global_step": 27000,
+  "global_step": 27500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1905,6 +1905,41 @@
       "learning_rate": 8.004e-06,
       "loss": 0.0572,
       "step": 27000
+    },
+    {
+      "epoch": 1.8066666666666666,
+      "grad_norm": 0.10920804738998413,
+      "learning_rate": 7.959555555555555e-06,
+      "loss": 0.0538,
+      "step": 27100
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 0.10139674693346024,
+      "learning_rate": 7.915111111111112e-06,
+      "loss": 0.0536,
+      "step": 27200
+    },
+    {
+      "epoch": 1.8199999999999998,
+      "grad_norm": 0.17728354036808014,
+      "learning_rate": 7.870666666666667e-06,
+      "loss": 0.0582,
+      "step": 27300
+    },
+    {
+      "epoch": 1.8266666666666667,
+      "grad_norm": 0.19340912997722626,
+      "learning_rate": 7.826222222222223e-06,
+      "loss": 0.0594,
+      "step": 27400
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.2556203603744507,
+      "learning_rate": 7.781777777777778e-06,
+      "loss": 0.0593,
+      "step": 27500
     }
   ],
   "logging_steps": 100,
@@ -1924,7 +1959,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.576745218048e+16,
+  "total_flos": 6.69853679616e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null