Training in progress, step 50000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cccd8b5e6f95d7d23729d6518abbb1c7171130f5a3a3aa208c43d929630d2080
+oid sha256:3a7a7b74f0bb8ba3dd1dd4dc306821d513a5b6eb6e1e61b35cfa900acf2184d9
 size 1668076741

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1109492877baa8385171cce26f0c6475c82a564d58f6669c91912ca645fd8bbc
+oid sha256:673ac62a80dcc8c7dcaf1349eabda0bda23e6d751fefb44d0b2d19229735b6e6
 size 834053717

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca58160f675a0d686e519b17545add52c1791e5dbe907a2e86061685a34b7766
+oid sha256:9798dba2e223f6f58089e1ac563fc21dbbd2a04ee79b7799a73465905128acbc
 size 15597

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5eb5aa26622244bf7286739429fab4e82221f83ea489f4c5df476d8e490e060
+oid sha256:111b606e2964954247e4280c4d2523625af5e370ffbcc02565e12f30d3a20502
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2d0b879ccc77b0aa0757151f84d49c24e909fa2a6b674a23fe5416c55b8698
+oid sha256:65f46bcd9b706c3b50e169ec7299f52079cd259ed510e5bb7185501f5df4ed46
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
-  "global_step": 40000,
+  "epoch": 1.0,
+  "global_step": 50000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -282,11 +282,80 @@
       "eval_samples_per_second": 40.003,
       "eval_steps_per_second": 2.504,
       "step": 40000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.5904465663698255e-06,
+      "loss": 0.7148,
+      "step": 41000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.0606776133616594e-06,
+      "loss": 0.7148,
+      "step": 42000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.5874890249007857e-06,
+      "loss": 0.8135,
+      "step": 43000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.1729499342876049e-06,
+      "loss": 0.8566,
+      "step": 44000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.19196353853926e-07,
+      "loss": 0.8101,
+      "step": 45000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.270672010640238e-07,
+      "loss": 0.7488,
+      "step": 46000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.982245009463186e-07,
+      "loss": 0.6483,
+      "step": 47000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.3393335157752762e-07,
+      "loss": 0.6717,
+      "step": 48000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.425391532401623e-08,
+      "loss": 0.6661,
+      "step": 49000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5878851039041742e-11,
+      "loss": 0.7593,
+      "step": 50000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8603840251781334,
+      "eval_loss": 0.6071112155914307,
+      "eval_runtime": 157.0885,
+      "eval_samples_per_second": 31.829,
+      "eval_steps_per_second": 1.993,
+      "step": 50000
     }
   ],
   "max_steps": 50000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 2.69368537645056e+19,
+  "total_flos": 3.3671067205632e+19,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1109492877baa8385171cce26f0c6475c82a564d58f6669c91912ca645fd8bbc
+oid sha256:673ac62a80dcc8c7dcaf1349eabda0bda23e6d751fefb44d0b2d19229735b6e6
 size 834053717