Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e8af44d25e4403e0410db75087bbe76ea4f8927319fb246b38e44369d3d8502
+oid sha256:0e92f9d6fa8f3943fa6d1539e3fc9c8082440671fbbfe767f34bd7b0b0b7bbcb
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6c7add6d380bbc3dc068128784fbf52d0a610e52c9d69c4e04d246f1309eee
+oid sha256:b52a6542aae59b9e8dbc260d927ca0f2fdc030aeecaf2628fab24bffbce8b859
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75400b2389a630f033d8e61a0b4f394aee67e01ef78d82c0ada4855822939a04
+oid sha256:05a1c8d1b4a5f5df3241839fbe5d279cd2d58633aba6dc35472c1b5348efdb84
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f286fedd044d4cc087ef5238577cf6b6ba1c5ebf29e1b250b79c60640a10a92
+oid sha256:473385105464e09d9e2cd49bbce42350523e82d12bca7455cb9d145ff112729d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0896,
+  "epoch": 0.1152,
   "eval_steps": 500,
-  "global_step": 14000,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,62 @@
       "learning_rate": 4.77608e-05,
       "loss": 0.4247,
       "step": 14000
+    },
+    {
+      "epoch": 0.0928,
+      "grad_norm": 0.839026689529419,
+      "learning_rate": 4.7680960000000004e-05,
+      "loss": 0.4233,
+      "step": 14500
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.8110847473144531,
+      "learning_rate": 4.760096e-05,
+      "loss": 0.4207,
+      "step": 15000
+    },
+    {
+      "epoch": 0.0992,
+      "grad_norm": 0.8462579250335693,
+      "learning_rate": 4.7520960000000005e-05,
+      "loss": 0.421,
+      "step": 15500
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 0.8980106711387634,
+      "learning_rate": 4.744096e-05,
+      "loss": 0.417,
+      "step": 16000
+    },
+    {
+      "epoch": 0.1056,
+      "grad_norm": 0.8297702074050903,
+      "learning_rate": 4.736096000000001e-05,
+      "loss": 0.4139,
+      "step": 16500
+    },
+    {
+      "epoch": 0.1088,
+      "grad_norm": 0.9856173992156982,
+      "learning_rate": 4.728096e-05,
+      "loss": 0.419,
+      "step": 17000
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.934256911277771,
+      "learning_rate": 4.720096e-05,
+      "loss": 0.4098,
+      "step": 17500
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 0.9190649390220642,
+      "learning_rate": 4.712096e-05,
+      "loss": 0.412,
+      "step": 18000
     }
   ],
   "logging_steps": 500,
@@ -222,7 +278,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.820328374272e+16,
+  "total_flos": 8.768993624064e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null