Training in progress, step 180000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b3edb0adadd334561a36e43a4212a4e9514b0b74e249ccb77a9f1a398e42f35
+oid sha256:17a7e34d71622ed2729105fb01520301222c71cea562f151f7179cc6bc4b9b50
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f22bc3eca0ebb0e03246c1e1c410976b12328cb4244ff48da993896225bf4a8
+oid sha256:30751dbb61ea71a9ce0a93f55b70e1a1196dfc0d7905f81e666b241fe83ddb77
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c26ad211585233ad2dccb9325976cb7e71ced6080ea69e9468119115e0c0050
+oid sha256:75d55dc4383f97263c7bbe8d3a50efcb2e3d7e3cace3b3db13ee7da25b48c2b4
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae036049be18d3db0b069d7cdee2136b0e955af29d02ba238e8d63ec3de1819
+oid sha256:1f3b1810a033427b234e2bffc73d00c710ede62d1be2ca4c7afaaf9e382d34f3
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f97d2f076eca9f1526fcbf8cced9c57bd3414f3b9c7f6f76f9126f17c819f1a
+oid sha256:52c10056239563f1c1ae3a50f3e866a02915fb473e9e6b2140de76aa33912655
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1,
-  "global_step": 170000,
+  "epoch": 0.15,
+  "global_step": 180000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2318,11 +2318,147 @@
       "eval_samples_per_second": 143.936,
       "eval_steps_per_second": 2.249,
       "step": 170000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.4807420925791258e-05,
+      "loss": 0.3746,
+      "step": 170500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.4649002129164283e-05,
+      "loss": 0.3739,
+      "step": 171000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.449309646774616e-05,
+      "loss": 0.3747,
+      "step": 171500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.4340017800329543e-05,
+      "loss": 0.3735,
+      "step": 172000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.4189162030934715e-05,
+      "loss": 0.3744,
+      "step": 172500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.4040847761852026e-05,
+      "loss": 0.3739,
+      "step": 173000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.3895084141804244e-05,
+      "loss": 0.374,
+      "step": 173500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.3751880162178036e-05,
+      "loss": 0.3731,
+      "step": 174000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.3611523358351411e-05,
+      "loss": 0.3732,
+      "step": 174500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.3473459838770744e-05,
+      "loss": 0.3751,
+      "step": 175000
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.3473358154296875,
+      "eval_runtime": 291.1365,
+      "eval_samples_per_second": 147.697,
+      "eval_steps_per_second": 2.308,
+      "step": 175000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.3337981967384716e-05,
+      "loss": 0.3742,
+      "step": 175500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.3205098101106558e-05,
+      "loss": 0.374,
+      "step": 176000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.3074816436839109e-05,
+      "loss": 0.3738,
+      "step": 176500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.2947145010969087e-05,
+      "loss": 0.3735,
+      "step": 177000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.2822091698871432e-05,
+      "loss": 0.3736,
+      "step": 177500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.2699906443769858e-05,
+      "loss": 0.3721,
+      "step": 178000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.2580107064687531e-05,
+      "loss": 0.3737,
+      "step": 178500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.2462948440006997e-05,
+      "loss": 0.3731,
+      "step": 179000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.2348437796624094e-05,
+      "loss": 0.3722,
+      "step": 179500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.2236582198094697e-05,
+      "loss": 0.3728,
+      "step": 180000
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 0.34677574038505554,
+      "eval_runtime": 288.6592,
+      "eval_samples_per_second": 148.965,
+      "eval_steps_per_second": 2.328,
+      "step": 180000
     }
   ],
   "max_steps": 200000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 4.003382145200947e+21,
+  "total_flos": 4.238875212565709e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f22bc3eca0ebb0e03246c1e1c410976b12328cb4244ff48da993896225bf4a8
+oid sha256:30751dbb61ea71a9ce0a93f55b70e1a1196dfc0d7905f81e666b241fe83ddb77
 size 449471589