Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e5ebbffbdf2b2b0f373bf3c3ac5fd9b510ca7cfae15dd1959091965542be95
+oid sha256:f319d26b1ad366c07c3084ea643d4b7cf103e0ea3cfc99180ca90e6ff22f890c
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a58a920b26ab294974ce24ca31a5f48242d44c9efa09c510a9b13690844009
+oid sha256:f6678fa1f9c09d653916be8f3cdc82ea8028fd6300ee429b0efc58e5d0e46f43
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f772128fc6a6bf97a7f6d60182a0d96033d8ba15722d63443d2398fe2eb3b92
+oid sha256:454e2261a26e00c9cf3a6608a840e96574aad04f547272f2eedef6eeb6911ada
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54f205adddbfad9c7a0aedb486db2e44512ccc97c43bb3f3ea372ee55b6a066e
+oid sha256:d717934dc91e8975c83e1ef2da99cffa6c43f66dcad18f9c09b9fccac2067289
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0058513879776,
-  "best_model_checkpoint": "./opt_trained/checkpoint-804",
-  "epoch": 4.0,
+  "best_metric": 1.0030816793441772,
+  "best_model_checkpoint": "./opt_trained/checkpoint-1005",
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 804,
+  "global_step": 1005,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -46,6 +46,21 @@
       "eval_samples_per_second": 37.212,
       "eval_steps_per_second": 9.303,
       "step": 804
+    },
+    {
+      "epoch": 4.976338729763388,
+      "grad_norm": 1.9620177745819092,
+      "learning_rate": 0.00030010000000000003,
+      "loss": 0.9962,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.0030816793441772,
+      "eval_runtime": 76.8119,
+      "eval_samples_per_second": 37.182,
+      "eval_steps_per_second": 9.295,
+      "step": 1005
     }
   ],
   "logging_steps": 500,
@@ -65,7 +80,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.706540438528e+16,
+  "total_flos": 3.38317554816e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null