Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b2107454ea6860e1284edc7e9108f31247ffc3d2e93988644352851ac820ac
+oid sha256:d3b1bad342ac797ae7f8347634a2ce237e847c6a2d60987518225454f9e747ad
 size 2708729576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:202d6bcbab6b309aad3131baf5e2ca6c813f77c7b116e7b3b7cb0a79739dce02
+oid sha256:5adecf4e9e07fee4c38cefd10b01a139c1b07f5ea9611ec0ade4b7a0c54c74f1
 size 52499200

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca58b79d0725770d46b15f5293d488ed3a1f3b2b0a6f74155f951e2b625e95f4
+oid sha256:9d7c781d03ce544a7aa31375ec1cce20ab821ae066d16219adab4b2436b4176d
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0267fbad859e57b7ff33d6dbd4fbd9fdf3cbf25f82f07754a3b6e19cff3ef2f5
+oid sha256:b514faa73b6e320d8ae19d93f3da594146e59f1072af645ee09b9ce747afd0a1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 5.0,
   "eval_steps": 50,
-  "global_step": 516,
+  "global_step": 645,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,34 @@
       "eval_samples_per_second": 21.835,
       "eval_steps_per_second": 5.459,
       "step": 500
+    },
+    {
+      "epoch": 4.265495363591996,
+      "grad_norm": 605412.375,
+      "learning_rate": 5.703125e-05,
+      "loss": 1325.2478,
+      "step": 550
+    },
+    {
+      "epoch": 4.265495363591996,
+      "eval_runtime": 19.7746,
+      "eval_samples_per_second": 21.846,
+      "eval_steps_per_second": 5.462,
+      "step": 550
+    },
+    {
+      "epoch": 4.65592972181552,
+      "grad_norm": 409170.1875,
+      "learning_rate": 5.3125000000000004e-05,
+      "loss": 1282.363,
+      "step": 600
+    },
+    {
+      "epoch": 4.65592972181552,
+      "eval_runtime": 19.7404,
+      "eval_samples_per_second": 21.884,
+      "eval_steps_per_second": 5.471,
+      "step": 600
     }
   ],
   "logging_steps": 50,