Training in progress, step 980000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e432b78001697802935de247a39fbb372c81f0a8a5495fa8b10802c9e09893b
+oid sha256:f583ea7c93bc66a9ef8a4e308c8dc630c9ff1c01fbc3af28ec5ab02ff4f79681
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa80d5373c46fd0ac9bf52389a9e6e9cf3955843a1e3da677ff34d39b7d44c0
+oid sha256:3aff5625e82bdff15b343b27e9d6a9b3efa1fcccca6fcaa49aaf091e12be1731
 size 449474181

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec24cbb8ce4192257d55e6aa76c8de9c95eafe7de9cb3bbb4e920ca7e78fc649
+oid sha256:70a20325b16659225e3cd01033074400c13a25610958f69aa9e3e72a98f16147
 size 17577

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d86d5b3aa53b15a666affdc8015b88ae744c0263f7bb1e6519ffd82b431ab45a
+oid sha256:43c4cc1073d6660901cb3dc90d6cc9fa2b9e92470c9b5b2cfa7f8fe0038e768d
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 68.98023040819228,
-  "global_step": 970000,
+  "epoch": 69.69136680415303,
+  "global_step": 980000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7184,11 +7184,85 @@
       "eval_samples_per_second": 168.183,
       "eval_steps_per_second": 5.257,
       "step": 970000
+    },
+    {
+      "epoch": 69.05,
+      "learning_rate": 1.0149337548616087e-05,
+      "loss": 0.1075,
+      "step": 971000
+    },
+    {
+      "epoch": 69.12,
+      "learning_rate": 1.0139223211606578e-05,
+      "loss": 0.1076,
+      "step": 972000
+    },
+    {
+      "epoch": 69.19,
+      "learning_rate": 1.012946276686737e-05,
+      "loss": 0.1078,
+      "step": 973000
+    },
+    {
+      "epoch": 69.26,
+      "learning_rate": 1.0120056321137129e-05,
+      "loss": 0.1079,
+      "step": 974000
+    },
+    {
+      "epoch": 69.34,
+      "learning_rate": 1.0111003977283231e-05,
+      "loss": 0.1074,
+      "step": 975000
+    },
+    {
+      "epoch": 69.34,
+      "eval_runtime": 524.9926,
+      "eval_samples_per_second": 167.456,
+      "eval_steps_per_second": 5.234,
+      "step": 975000
+    },
+    {
+      "epoch": 69.41,
+      "learning_rate": 1.010230583430066e-05,
+      "loss": 0.1073,
+      "step": 976000
+    },
+    {
+      "epoch": 69.48,
+      "learning_rate": 1.009396198731092e-05,
+      "loss": 0.1079,
+      "step": 977000
+    },
+    {
+      "epoch": 69.55,
+      "learning_rate": 1.0085972527560981e-05,
+      "loss": 0.1072,
+      "step": 978000
+    },
+    {
+      "epoch": 69.62,
+      "learning_rate": 1.0078337542422287e-05,
+      "loss": 0.1077,
+      "step": 979000
+    },
+    {
+      "epoch": 69.69,
+      "learning_rate": 1.0071057115389828e-05,
+      "loss": 0.108,
+      "step": 980000
+    },
+    {
+      "epoch": 69.69,
+      "eval_runtime": 537.8359,
+      "eval_samples_per_second": 163.457,
+      "eval_steps_per_second": 5.109,
+      "step": 980000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 72,
-  "total_flos": 3.3998459444478542e+22,
+  "total_flos": 3.4348958289582365e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa80d5373c46fd0ac9bf52389a9e6e9cf3955843a1e3da677ff34d39b7d44c0
+oid sha256:3aff5625e82bdff15b343b27e9d6a9b3efa1fcccca6fcaa49aaf091e12be1731
 size 449474181