Training in progress, step 42000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddeba81fa20a347b7f4a8bf56911f542931a9c7a9a28e5b17d8415cffe0f05fc
+oid sha256:745b8b1d7e5bd21d472de4928ff7acd2ffa83a677380359019a9c4799912b8d9
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c534f106883dfc1dc4725defbacef030c7dba5f5e0888cc081c7906d9d0b8453
+oid sha256:ff26510f9fa790ef0a5e5f59b48491824122de83388e6b8dafee62d5541a9a5f
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b282c8a79340622eb958db3d6110bd8f623dfad615139665f1498d8b00a6bed
+oid sha256:1538e2c63d940ef0e1b73a9e8d73309e15231b1a12e77d8cac6d2db2463579dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6abecd6b93d057c006d3ff371902f2a70b673a5fc3d8d5773b1c045cd3372a7b
+oid sha256:89058407f5b943be63f8348b693549eede8380db14dc40de0b317aff021fa0d0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7666666666666666,
+  "epoch": 2.8,
   "eval_steps": 500,
-  "global_step": 41500,
+  "global_step": 42000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2928,6 +2928,41 @@
       "learning_rate": 1.5626666666666667e-06,
       "loss": 0.0485,
       "step": 41500
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 0.2192191630601883,
+      "learning_rate": 1.5182222222222223e-06,
+      "loss": 0.0514,
+      "step": 41600
+    },
+    {
+      "epoch": 2.7800000000000002,
+      "grad_norm": 0.17543815076351166,
+      "learning_rate": 1.4737777777777778e-06,
+      "loss": 0.0473,
+      "step": 41700
+    },
+    {
+      "epoch": 2.7866666666666666,
+      "grad_norm": 0.25185197591781616,
+      "learning_rate": 1.4293333333333334e-06,
+      "loss": 0.0508,
+      "step": 41800
+    },
+    {
+      "epoch": 2.7933333333333334,
+      "grad_norm": 0.22377026081085205,
+      "learning_rate": 1.3848888888888889e-06,
+      "loss": 0.0617,
+      "step": 41900
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.1886560320854187,
+      "learning_rate": 1.3404444444444445e-06,
+      "loss": 0.0504,
+      "step": 42000
     }
   ],
   "logging_steps": 100,
@@ -2947,7 +2982,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0108700983296e+17,
+  "total_flos": 1.0230492561408e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null