Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f79e495154da67b877bea3f63a4a67b50b5bd6dc9f526699f399304facad62e
+oid sha256:c2f4ac6e2904e38a59ae6cd088c42b2010f3ce171b7c42f73e10f89189928510
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90d453de31c2419e4e349d4a4f435ab05d64a46c66c09d9b10ac7145a578d1f
+oid sha256:0c2a67e114a6e0d790034fcdf83357a636db00c48bbbee80bf67f812e4454a73
 size 876185978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18250a969c7e8b744e0a81968b85799869d2e007063948d0e72541065db3bc16
+oid sha256:7c0905be27a588e9c110d86ca5c7f44884f2cff6848f90f999b9096bd6ca85f4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bdb930721cbebdf735b7bba6276bd5739b55ef721382393eeafb8577701beb4
+oid sha256:12b04a1fc0ffeaa6e3a4893e319ebc13a4fb773c4615723d80b4c92ffb7c98f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3715578615665436,
-  "best_model_checkpoint": "results/checkpoint-4000",
-  "epoch": 0.3820804279300793,
+  "best_metric": 0.3664040267467499,
+  "best_model_checkpoint": "results/checkpoint-5000",
+  "epoch": 0.47760053491259913,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,36 @@
       "eval_samples_per_second": 235.496,
       "eval_steps_per_second": 3.683,
       "step": 4000
+    },
+    {
+      "epoch": 0.4298404814213392,
+      "grad_norm": 7.005139350891113,
+      "learning_rate": 3.925398796446652e-05,
+      "loss": 0.4135,
+      "step": 4500
+    },
+    {
+      "epoch": 0.4298404814213392,
+      "eval_loss": 0.3852500319480896,
+      "eval_runtime": 110.8005,
+      "eval_samples_per_second": 236.019,
+      "eval_steps_per_second": 3.691,
+      "step": 4500
+    },
+    {
+      "epoch": 0.47760053491259913,
+      "grad_norm": 7.208944797515869,
+      "learning_rate": 3.8059986627185024e-05,
+      "loss": 0.4172,
+      "step": 5000
+    },
+    {
+      "epoch": 0.47760053491259913,
+      "eval_loss": 0.3664040267467499,
+      "eval_runtime": 110.6088,
+      "eval_samples_per_second": 236.428,
+      "eval_steps_per_second": 3.698,
+      "step": 5000
     }
   ],
   "logging_steps": 500,
@@ -146,7 +176,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.7370944561152e+16,
+  "total_flos": 8.421368070144e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null