Training in progress, step 195000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f733f1c5c973c7f91eb131bb3e82da037f3e993da76db3e2381f388949c28a
+oid sha256:c34ac780b372cb50ed12ba9fbab64719e7e6f0c18cee015d6bdb3bcb76dea71d
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af6cf503e39f082eadf9f2f916981c285c52cb0af0a4f8f6b973948898daf3c7
+oid sha256:99dced181e974fd3eec8a6b81e04bd93e9d3478bda598e89eba595e55d1a22ef
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc0b12df32087251292c25f4f3cf2a3c6284123352afbe84dfbe69e160e5a52
+oid sha256:1e1c87bdea00ca3e6e9b20f6190563c56b2601359c213756f776a09add69b81e
 size 15523

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46e1383180c301938af8e67d4f2fff7658042ee2d23e333a5bc9284cf466c31c
+oid sha256:e9307e85dd6ba8a5ceae8769503e23251f8d4d2261d33516d9a1d3db2d17488d
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bab25e3293bb066cd704ffbf86ce50c9a22d57cf76a430f5a1ab6e08bcbca3ce
+oid sha256:de8c8841ca37efa9880cc96031ae2dad9eefb662fd05d23d903fbf6205093680
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9,
-  "global_step": 190000,
+  "epoch": 0.925,
+  "global_step": 195000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2590,11 +2590,79 @@
       "eval_samples_per_second": 83.49,
       "eval_steps_per_second": 1.305,
       "step": 190000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.0511896082261898e-05,
+      "loss": 0.4103,
+      "step": 190500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0459891899504107e-05,
+      "loss": 0.4098,
+      "step": 191000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0410659256006602e-05,
+      "loss": 0.4087,
+      "step": 191500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0364201188670747e-05,
+      "loss": 0.4101,
+      "step": 192000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0320520563248961e-05,
+      "loss": 0.4103,
+      "step": 192500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.0279699098864594e-05,
+      "loss": 0.4099,
+      "step": 193000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.024157570133687e-05,
+      "loss": 0.4091,
+      "step": 193500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.0206237309840898e-05,
+      "loss": 0.4092,
+      "step": 194000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.0173686104215128e-05,
+      "loss": 0.4102,
+      "step": 194500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.0143924092371245e-05,
+      "loss": 0.4088,
+      "step": 195000
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 0.38611817359924316,
+      "eval_runtime": 81.3319,
+      "eval_samples_per_second": 78.69,
+      "eval_steps_per_second": 1.23,
+      "step": 195000
     }
   ],
   "max_steps": 200000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 4.4743682799304704e+21,
+  "total_flos": 4.592114813612851e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af6cf503e39f082eadf9f2f916981c285c52cb0af0a4f8f6b973948898daf3c7
+oid sha256:99dced181e974fd3eec8a6b81e04bd93e9d3478bda598e89eba595e55d1a22ef
 size 449471589