Training in progress, step 684000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640a854826640cb11bbb438619e9a5f60f5a87426480d00dabad12e97faca233
+oid sha256:37c607bba26cfdf38c86d0008c177a08f19a45729aead65386002738a39ce45e
 size 3871544599

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a26387fc1ac2d84d2e2d47f032ad30fd47938871ead17b1dabb23ecf827dd623
+oid sha256:05f8278eaad5064bce348e243541474803f31744bfcd30ad256947619c9ae9f5
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c167da47bdade7586a09b949f4166918ffa8c6af07f7b8b80e2a5401db4033bc
-size 14575
+oid sha256:dfef95a4a19d3c28dbe54f1b9376def4f126fc6365803f9152a5a3d630c2ea72
+size 14639

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63702b724280e1c4c8e8ab4f6b819c3a124dd742aa5b0b382b842c7d7d78d924
+oid sha256:8da14a4d7b374e30001d1fc00d8b9d526bac9574b28d04936c4dec866d2841d6
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:721fef01fcc3fad7b4d237801f38087fe26d546e94d437fb4531bef40429536f
+oid sha256:37a8bcedf9c9c261cc261ff2ba8a990ec5b8474bbc3ead50de227b40f6dbad74
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.85151670843338,
-  "global_step": 681000,
+  "epoch": 17.930156965954012,
+  "global_step": 684000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8178,11 +8178,47 @@
       "learning_rate": 1.4191554616482833e-07,
       "loss": 1.0191,
       "step": 681000
+    },
+    {
+      "epoch": 17.86,
+      "learning_rate": 1.4021105872006806e-07,
+      "loss": 1.0105,
+      "step": 681500
+    },
+    {
+      "epoch": 17.88,
+      "learning_rate": 1.3851657379057583e-07,
+      "loss": 1.0194,
+      "step": 682000
+    },
+    {
+      "epoch": 17.89,
+      "learning_rate": 1.3683209855882006e-07,
+      "loss": 1.0161,
+      "step": 682500
+    },
+    {
+      "epoch": 17.9,
+      "learning_rate": 1.3515764016484245e-07,
+      "loss": 1.0071,
+      "step": 683000
+    },
+    {
+      "epoch": 17.92,
+      "learning_rate": 1.3349320570622464e-07,
+      "loss": 1.0057,
+      "step": 683500
+    },
+    {
+      "epoch": 17.93,
+      "learning_rate": 1.318388022380601e-07,
+      "loss": 1.0081,
+      "step": 684000
     }
   ],
   "max_steps": 762960,
   "num_train_epochs": 20,
-  "total_flos": 8.061448873470935e+17,
+  "total_flos": 8.09446081806803e+17,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a26387fc1ac2d84d2e2d47f032ad30fd47938871ead17b1dabb23ecf827dd623
+oid sha256:05f8278eaad5064bce348e243541474803f31744bfcd30ad256947619c9ae9f5
 size 1944201353

runs/Jun07_08-27-15_3a7f67f8b43f/events.out.tfevents.1686127999.3a7f67f8b43f.172.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4896bc6958b890a5c9625f928d6fe63ae4ba8eab656672a7a07effd4950f43
-size 11181
+oid sha256:05004feb8aae3123de67b4b51994475f6af5d6991098a7a0c1db6e1cd7676114
+size 12141