Training in progress, step 700000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c116c94691fe83930a5993880bd8c0998a3e0ec38012be8fad0b40e1c29568
+oid sha256:fca1ce8e1321c185070051c404827dfc693fe55a6777dd0acded04344c9c30fd
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b586adc3a504918e31f8a9a7e0f4be94f03956b7f0114b4da9476acb22a6ef
+oid sha256:ab594cbb8d871dbbf2b25c376be7c8da151b2a99217825751fae78b7561f2ad5
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a77fe6605383afb833ca53fc48599ad56cfe3eec3e43ed5ccdec337bfa0ca8
-size 14503
+oid sha256:7e22039e8547ad63b2ace49f210f4357ab45439130e9ce4cde64ab4d788dae45
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:815de40461412919a5889eec61609965c9d2866910047894a4dc0f6b20abb0b4
+oid sha256:0035334d6d79118a4fbb19f853805075e8cbb76d056e9372535b5cc2b4046af0
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ae17687fd76755d54219d89fc11c8946b10678e74c0c01048fa01e50274084
+oid sha256:523d1db2472a9cc3cbeb9c091f0349bda45803d7d0a416b91c4a707a5260de91
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c17905fc96ebc0f02fa95bfe12b431ac787bae4299fa05067fe9a564d5bb62cc
+oid sha256:89bdfe288c33ce02d82b7c3c74d7eb542a7bb82b47a44b8ec4cd489dc5c385c0
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4ee1c07d4ce16af70500d9164050fdd6814fe5b1c70d5ddc9dc0d403bb72893
+oid sha256:8867e21d1b6a1acf6d7736261e75716fa7b5040d081c92aba0073b066f2ada16
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.536442347336113,
-  "global_step": 690000,
+  "epoch": 10.689144410340983,
+  "global_step": 700000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5112,11 +5112,85 @@
       "eval_samples_per_second": 1199.26,
       "eval_steps_per_second": 19.188,
       "step": 690000
+    },
+    {
+      "epoch": 10.55,
+      "learning_rate": 4.347445648076057e-05,
+      "loss": 0.2463,
+      "step": 691000
+    },
+    {
+      "epoch": 10.57,
+      "learning_rate": 4.327718256369826e-05,
+      "loss": 0.2458,
+      "step": 692000
+    },
+    {
+      "epoch": 10.58,
+      "learning_rate": 4.3080310241483885e-05,
+      "loss": 0.2451,
+      "step": 693000
+    },
+    {
+      "epoch": 10.6,
+      "learning_rate": 4.2883841667081675e-05,
+      "loss": 0.2454,
+      "step": 694000
+    },
+    {
+      "epoch": 10.61,
+      "learning_rate": 4.268777898904044e-05,
+      "loss": 0.2455,
+      "step": 695000
+    },
+    {
+      "epoch": 10.61,
+      "eval_runtime": 0.794,
+      "eval_samples_per_second": 1259.505,
+      "eval_steps_per_second": 20.152,
+      "step": 695000
+    },
+    {
+      "epoch": 10.63,
+      "learning_rate": 4.2492124351470214e-05,
+      "loss": 0.2453,
+      "step": 696000
+    },
+    {
+      "epoch": 10.64,
+      "learning_rate": 4.2296879894018835e-05,
+      "loss": 0.2449,
+      "step": 697000
+    },
+    {
+      "epoch": 10.66,
+      "learning_rate": 4.210204775184834e-05,
+      "loss": 0.245,
+      "step": 698000
+    },
+    {
+      "epoch": 10.67,
+      "learning_rate": 4.190763005561186e-05,
+      "loss": 0.2447,
+      "step": 699000
+    },
+    {
+      "epoch": 10.69,
+      "learning_rate": 4.171362893143013e-05,
+      "loss": 0.2444,
+      "step": 700000
+    },
+    {
+      "epoch": 10.69,
+      "eval_runtime": 0.7798,
+      "eval_samples_per_second": 1282.444,
+      "eval_steps_per_second": 20.519,
+      "step": 700000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 4.8369114404124654e+22,
+  "total_flos": 4.9070117014428126e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b586adc3a504918e31f8a9a7e0f4be94f03956b7f0114b4da9476acb22a6ef
+oid sha256:ab594cbb8d871dbbf2b25c376be7c8da151b2a99217825751fae78b7561f2ad5
 size 449471589