Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d734e6db78f60fbbbccb113593aad2dacb6d4ef24adf3f2d2f765c04c3543ac
+oid sha256:9c3635274eee21ba1976640f8142d5c1fbf66c82e539af94ae87a1f3ee9eb023
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e652abff809338fab18533d877e6e5d8666ad14769f8c73336a2290bb1d2f4
+oid sha256:36b31c0839e033c8fdb5f6e0bfc78e2d9735a0fe9264510a0e2f8d12a0d58d55
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec459b20953804686a31ef9dfbbe457e9e9185e9c16c0990f91f7b84833fdbbf
+oid sha256:9ce1f6957d6020f16416f4fd345e9fae1e2983c0b203bfade0ebefc01a476151
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1809e210db6349fe0ab123cca2b958d44ebb1729354689aaf0244de4c395185
+oid sha256:7d84e3c52aa4a82118b4d8d3c4b8e8c4226ad3a7764da780159cac8984f3a66d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.576659038901602,
+  "epoch": 4.817535830422739,
   "eval_steps": 500,
-  "global_step": 19000,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -140,6 +140,13 @@
       "learning_rate": 0.0008474263229743838,
       "loss": 1.0737,
       "step": 19000
+    },
+    {
+      "epoch": 4.817535830422739,
+      "grad_norm": 0.5085521340370178,
+      "learning_rate": 0.0008393961294467197,
+      "loss": 1.068,
+      "step": 20000
     }
   ],
   "logging_steps": 1000,
@@ -159,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.900695900913664e+17,
+  "total_flos": 2.0007346657191526e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null