Training in progress, step 1000000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa56c6244a84a771cf2984aa63900b7128ad40dd69818d54b918bf9b35954fe3
+oid sha256:a41c0cfdbba59adb55e48f4497cb58e6acc6b3452b49124d5a5f0fe8e60c1ed5
 size 893441093

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e8cc279c772df75f8d61748adcf8cab41db1f2f7207255b9b48edc3dca234c
+oid sha256:c27f116a4294f22674c90e68e437b33583a613d34e7b53d5073c3c54064bc66c
 size 449474181

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d5b60e0a007a854b2858ef033ce2307ff2527680a1a2fca671d1fe620a358a8
+oid sha256:0ff52e12d1ecb30cb53f7d49f3e0645dc2a062bffe7e31ad2d54f6553c1e3bcf
 size 17641

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28cacbced11de35b0d6bed5b65452853709959052dcbd10ec95163f3114bda17
+oid sha256:00fbdf9131638fc1a94afc0c7252f3e83640538433d010f21c313201f00efd8a
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 70.40250320011378,
-  "global_step": 990000,
+  "epoch": 71.11363959607452,
+  "global_step": 1000000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7332,11 +7332,85 @@
       "eval_samples_per_second": 167.016,
       "eval_steps_per_second": 5.221,
       "step": 990000
+    },
+    {
+      "epoch": 70.47,
+      "learning_rate": 1.001439324972257e-05,
+      "loss": 0.1073,
+      "step": 991000
+    },
+    {
+      "epoch": 70.54,
+      "learning_rate": 1.0011372620416e-05,
+      "loss": 0.1072,
+      "step": 992000
+    },
+    {
+      "epoch": 70.62,
+      "learning_rate": 1.0008707281533315e-05,
+      "loss": 0.1071,
+      "step": 993000
+    },
+    {
+      "epoch": 70.69,
+      "learning_rate": 1.0006397262222235e-05,
+      "loss": 0.1071,
+      "step": 994000
+    },
+    {
+      "epoch": 70.76,
+      "learning_rate": 1.0004442587744758e-05,
+      "loss": 0.107,
+      "step": 995000
+    },
+    {
+      "epoch": 70.76,
+      "eval_runtime": 521.8934,
+      "eval_samples_per_second": 168.45,
+      "eval_steps_per_second": 5.265,
+      "step": 995000
+    },
+    {
+      "epoch": 70.83,
+      "learning_rate": 1.0002843279476897e-05,
+      "loss": 0.1068,
+      "step": 996000
+    },
+    {
+      "epoch": 70.9,
+      "learning_rate": 1.0001599354908423e-05,
+      "loss": 0.1071,
+      "step": 997000
+    },
+    {
+      "epoch": 70.97,
+      "learning_rate": 1.0000710827642701e-05,
+      "loss": 0.1072,
+      "step": 998000
+    },
+    {
+      "epoch": 71.04,
+      "learning_rate": 1.0000177707396518e-05,
+      "loss": 0.1068,
+      "step": 999000
+    },
+    {
+      "epoch": 71.11,
+      "learning_rate": 1e-05,
+      "loss": 0.1067,
+      "step": 1000000
+    },
+    {
+      "epoch": 71.11,
+      "eval_runtime": 522.5962,
+      "eval_samples_per_second": 168.224,
+      "eval_steps_per_second": 5.258,
+      "step": 1000000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 72,
-  "total_flos": 3.4699457134686187e+22,
+  "total_flos": 3.504995597979001e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e8cc279c772df75f8d61748adcf8cab41db1f2f7207255b9b48edc3dca234c
+oid sha256:c27f116a4294f22674c90e68e437b33583a613d34e7b53d5073c3c54064bc66c
 size 449474181