Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f4ac6e2904e38a59ae6cd088c42b2010f3ce171b7c42f73e10f89189928510
+oid sha256:3aedc483c54107bbbfbb4bb1751df0aed26deff999446826ab8ca980fcec25dd
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2a67e114a6e0d790034fcdf83357a636db00c48bbbee80bf67f812e4454a73
+oid sha256:154f1752e769875ff6f0ae366579fb67e74d70b42f6c854396947ca0d63dd1f0
 size 876185978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c0905be27a588e9c110d86ca5c7f44884f2cff6848f90f999b9096bd6ca85f4
+oid sha256:0618c22de064a9e67950f0d7435b0233d7612609e6eed8ccb0e0691b2cc04e0c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b04a1fc0ffeaa6e3a4893e319ebc13a4fb773c4615723d80b4c92ffb7c98f7
+oid sha256:c128e1cb8981a4a5f7e552e0f21f2b975cf3565755201ff1ed706660ddb069c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3664040267467499,
-  "best_model_checkpoint": "results/checkpoint-5000",
-  "epoch": 0.47760053491259913,
+  "best_metric": 0.36337631940841675,
+  "best_model_checkpoint": "results/checkpoint-6000",
+  "epoch": 0.5731206418951189,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,6 +157,36 @@
       "eval_samples_per_second": 236.428,
       "eval_steps_per_second": 3.698,
       "step": 5000
+    },
+    {
+      "epoch": 0.525360588403859,
+      "grad_norm": 4.011592864990234,
+      "learning_rate": 3.6865985289903526e-05,
+      "loss": 0.4164,
+      "step": 5500
+    },
+    {
+      "epoch": 0.525360588403859,
+      "eval_loss": 0.36664679646492004,
+      "eval_runtime": 108.0591,
+      "eval_samples_per_second": 242.006,
+      "eval_steps_per_second": 3.785,
+      "step": 5500
+    },
+    {
+      "epoch": 0.5731206418951189,
+      "grad_norm": 3.7559821605682373,
+      "learning_rate": 3.567198395262203e-05,
+      "loss": 0.4124,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5731206418951189,
+      "eval_loss": 0.36337631940841675,
+      "eval_runtime": 105.397,
+      "eval_samples_per_second": 248.119,
+      "eval_steps_per_second": 3.881,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -176,7 +206,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.421368070144e+16,
+  "total_flos": 1.01056416841728e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null