Training in progress, step 710000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fca1ce8e1321c185070051c404827dfc693fe55a6777dd0acded04344c9c30fd
+oid sha256:f8b4f5708667fda381a1ab66f80f980e40daa1a707f100921fdae99c2db5e334
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab594cbb8d871dbbf2b25c376be7c8da151b2a99217825751fae78b7561f2ad5
+oid sha256:8c7dafd574b6c18c8b0838dfe7c6fd825d5c841584d2d916d404b3af2a78c999
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e22039e8547ad63b2ace49f210f4357ab45439130e9ce4cde64ab4d788dae45
-size 14439
+oid sha256:1d7fee820bb752afb8f603542eaf0336c5e7c41a61ac1c1147dd536354714a47
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0035334d6d79118a4fbb19f853805075e8cbb76d056e9372535b5cc2b4046af0
+oid sha256:a2561ae8bb02e359a9713b9977fa63ca1b6854d76fd4510a159042ccdda7aff7
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523d1db2472a9cc3cbeb9c091f0349bda45803d7d0a416b91c4a707a5260de91
+oid sha256:330a4501421948528f860e170d41c93583e955ea4b60c53d7ee73adbfd6aa9e2
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89bdfe288c33ce02d82b7c3c74d7eb542a7bb82b47a44b8ec4cd489dc5c385c0
+oid sha256:014d339be1f5943d92bce27af7e1e9d7ced53c7dfd7c34412b3de983c10ddb04
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8867e21d1b6a1acf6d7736261e75716fa7b5040d081c92aba0073b066f2ada16
+oid sha256:099db39f4d942e6817b283451a401c36d6ba4059eea01842b742770347fceca3
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.689144410340983,
-  "global_step": 700000,
+  "epoch": 10.841846473345855,
+  "global_step": 710000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5186,11 +5186,85 @@
       "eval_samples_per_second": 1282.444,
       "eval_steps_per_second": 20.519,
       "step": 700000
+    },
+    {
+      "epoch": 10.7,
+      "learning_rate": 4.1520046500868384e-05,
+      "loss": 0.2442,
+      "step": 701000
+    },
+    {
+      "epoch": 10.72,
+      "learning_rate": 4.1326884880913074e-05,
+      "loss": 0.2454,
+      "step": 702000
+    },
+    {
+      "epoch": 10.73,
+      "learning_rate": 4.1134146183948724e-05,
+      "loss": 0.2445,
+      "step": 703000
+    },
+    {
+      "epoch": 10.75,
+      "learning_rate": 4.0941832517734885e-05,
+      "loss": 0.2448,
+      "step": 704000
+    },
+    {
+      "epoch": 10.77,
+      "learning_rate": 4.0749945985382915e-05,
+      "loss": 0.2445,
+      "step": 705000
+    },
+    {
+      "epoch": 10.77,
+      "eval_runtime": 0.7458,
+      "eval_samples_per_second": 1340.853,
+      "eval_steps_per_second": 21.454,
+      "step": 705000
+    },
+    {
+      "epoch": 10.78,
+      "learning_rate": 4.0558488685333235e-05,
+      "loss": 0.253,
+      "step": 706000
+    },
+    {
+      "epoch": 10.8,
+      "learning_rate": 4.036746271133223e-05,
+      "loss": 0.2533,
+      "step": 707000
+    },
+    {
+      "epoch": 10.81,
+      "learning_rate": 4.0176870152409324e-05,
+      "loss": 0.2547,
+      "step": 708000
+    },
+    {
+      "epoch": 10.83,
+      "learning_rate": 3.998671309285417e-05,
+      "loss": 0.2529,
+      "step": 709000
+    },
+    {
+      "epoch": 10.84,
+      "learning_rate": 3.979699361219395e-05,
+      "loss": 0.2457,
+      "step": 710000
+    },
+    {
+      "epoch": 10.84,
+      "eval_runtime": 0.7472,
+      "eval_samples_per_second": 1338.326,
+      "eval_steps_per_second": 21.413,
+      "step": 710000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.9070117014428126e+22,
+  "total_flos": 4.97711196247316e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab594cbb8d871dbbf2b25c376be7c8da151b2a99217825751fae78b7561f2ad5
+oid sha256:8c7dafd574b6c18c8b0838dfe7c6fd825d5c841584d2d916d404b3af2a78c999
 size 449471589