Training in progress, step 990000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f583ea7c93bc66a9ef8a4e308c8dc630c9ff1c01fbc3af28ec5ab02ff4f79681
+oid sha256:aa56c6244a84a771cf2984aa63900b7128ad40dd69818d54b918bf9b35954fe3
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aff5625e82bdff15b343b27e9d6a9b3efa1fcccca6fcaa49aaf091e12be1731
+oid sha256:45e8cc279c772df75f8d61748adcf8cab41db1f2f7207255b9b48edc3dca234c
 size 449474181

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a20325b16659225e3cd01033074400c13a25610958f69aa9e3e72a98f16147
-size 17577
+oid sha256:7d5b60e0a007a854b2858ef033ce2307ff2527680a1a2fca671d1fe620a358a8
+size 17641

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c4cc1073d6660901cb3dc90d6cc9fa2b9e92470c9b5b2cfa7f8fe0038e768d
+oid sha256:28cacbced11de35b0d6bed5b65452853709959052dcbd10ec95163f3114bda17
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 69.69136680415303,
-  "global_step": 980000,
+  "epoch": 70.40250320011378,
+  "global_step": 990000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7258,11 +7258,85 @@
       "eval_samples_per_second": 163.457,
       "eval_steps_per_second": 5.109,
       "step": 980000
+    },
+    {
+      "epoch": 69.76,
+      "learning_rate": 1.0064131326081175e-05,
+      "loss": 0.1074,
+      "step": 981000
+    },
+    {
+      "epoch": 69.83,
+      "learning_rate": 1.0057560250235656e-05,
+      "loss": 0.1075,
+      "step": 982000
+    },
+    {
+      "epoch": 69.9,
+      "learning_rate": 1.0051343959713499e-05,
+      "loss": 0.1075,
+      "step": 983000
+    },
+    {
+      "epoch": 69.98,
+      "learning_rate": 1.0045482522495065e-05,
+      "loss": 0.1075,
+      "step": 984000
+    },
+    {
+      "epoch": 70.05,
+      "learning_rate": 1.0039976002680097e-05,
+      "loss": 0.1076,
+      "step": 985000
+    },
+    {
+      "epoch": 70.05,
+      "eval_runtime": 519.6166,
+      "eval_samples_per_second": 169.188,
+      "eval_steps_per_second": 5.289,
+      "step": 985000
+    },
+    {
+      "epoch": 70.12,
+      "learning_rate": 1.0034824460487e-05,
+      "loss": 0.1072,
+      "step": 986000
+    },
+    {
+      "epoch": 70.19,
+      "learning_rate": 1.003002795225223e-05,
+      "loss": 0.1071,
+      "step": 987000
+    },
+    {
+      "epoch": 70.26,
+      "learning_rate": 1.0025586530429617e-05,
+      "loss": 0.1076,
+      "step": 988000
+    },
+    {
+      "epoch": 70.33,
+      "learning_rate": 1.0021500243589852e-05,
+      "loss": 0.1073,
+      "step": 989000
+    },
+    {
+      "epoch": 70.4,
+      "learning_rate": 1.0017769136419904e-05,
+      "loss": 0.107,
+      "step": 990000
+    },
+    {
+      "epoch": 70.4,
+      "eval_runtime": 526.375,
+      "eval_samples_per_second": 167.016,
+      "eval_steps_per_second": 5.221,
+      "step": 990000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 72,
-  "total_flos": 3.4348958289582365e+22,
+  "total_flos": 3.4699457134686187e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aff5625e82bdff15b343b27e9d6a9b3efa1fcccca6fcaa49aaf091e12be1731
+oid sha256:45e8cc279c772df75f8d61748adcf8cab41db1f2f7207255b9b48edc3dca234c
 size 449474181