Training in progress, step 860000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e51d88aff5257549a283e52c14c7816f109ed1c8f1cd4c0209be1013bd750037
+oid sha256:15a77d7445b898e81ba1dbf302ad4aa88b3930b40801531ded9875b083edd127
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2b61d52c517c0fe4a2eaad25ea86eca5fed6ebf386f54b8df5e3364654d10f
+oid sha256:d9da54e69aa4d985aac499cdb17fab8ee1c2bb36a1855c776c5bda5c5106d784
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
+oid sha256:44925a24f970524178a5e9134f37953712fa04674397ceaa739828974d03640e
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
+oid sha256:44925a24f970524178a5e9134f37953712fa04674397ceaa739828974d03640e
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
+oid sha256:44925a24f970524178a5e9134f37953712fa04674397ceaa739828974d03640e
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
+oid sha256:44925a24f970524178a5e9134f37953712fa04674397ceaa739828974d03640e
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
+oid sha256:44925a24f970524178a5e9134f37953712fa04674397ceaa739828974d03640e
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
+oid sha256:44925a24f970524178a5e9134f37953712fa04674397ceaa739828974d03640e
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
+oid sha256:44925a24f970524178a5e9134f37953712fa04674397ceaa739828974d03640e
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3998272c6f0774d9c932f650afe844739a9faa8bc3cb7003f4f32bc8a833e115
+oid sha256:44925a24f970524178a5e9134f37953712fa04674397ceaa739828974d03640e
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fbbdae9c95471a40e6c6d019353b081fa6055bc839ed4f2163c0c1b80837934
+oid sha256:1af16532ed7776301ec2b0d23baf8c67ba74ec07e3f7e0782860705643ea3c80
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.122804278241862,
-  "global_step": 850000,
+  "epoch": 9.234333002464785,
+  "global_step": 860000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17006,11 +17006,211 @@
       "eval_samples_per_second": 857.76,
       "eval_steps_per_second": 13.443,
       "step": 850000
+    },
+    {
+      "epoch": 9.13,
+      "learning_rate": 1.838183407087156e-05,
+      "loss": 0.1843,
+      "step": 850500
+    },
+    {
+      "epoch": 9.13,
+      "learning_rate": 1.8326999187910095e-05,
+      "loss": 0.1843,
+      "step": 851000
+    },
+    {
+      "epoch": 9.13,
+      "eval_loss": 0.17367926239967346,
+      "eval_runtime": 2.6854,
+      "eval_samples_per_second": 855.351,
+      "eval_steps_per_second": 13.406,
+      "step": 851000
+    },
+    {
+      "epoch": 9.14,
+      "learning_rate": 1.8272332916577875e-05,
+      "loss": 0.1846,
+      "step": 851500
+    },
+    {
+      "epoch": 9.15,
+      "learning_rate": 1.8217835406330415e-05,
+      "loss": 0.1844,
+      "step": 852000
+    },
+    {
+      "epoch": 9.15,
+      "eval_loss": 0.17384441196918488,
+      "eval_runtime": 2.6384,
+      "eval_samples_per_second": 870.617,
+      "eval_steps_per_second": 13.645,
+      "step": 852000
+    },
+    {
+      "epoch": 9.15,
+      "learning_rate": 1.81635068061618e-05,
+      "loss": 0.1844,
+      "step": 852500
+    },
+    {
+      "epoch": 9.16,
+      "learning_rate": 1.810934726460436e-05,
+      "loss": 0.1845,
+      "step": 853000
+    },
+    {
+      "epoch": 9.16,
+      "eval_loss": 0.17389260232448578,
+      "eval_runtime": 2.6711,
+      "eval_samples_per_second": 859.942,
+      "eval_steps_per_second": 13.478,
+      "step": 853000
+    },
+    {
+      "epoch": 9.16,
+      "learning_rate": 1.80553569297282e-05,
+      "loss": 0.1843,
+      "step": 853500
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 1.800153594914084e-05,
+      "loss": 0.1843,
+      "step": 854000
+    },
+    {
+      "epoch": 9.17,
+      "eval_loss": 0.17477978765964508,
+      "eval_runtime": 2.681,
+      "eval_samples_per_second": 856.769,
+      "eval_steps_per_second": 13.428,
+      "step": 854000
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 1.7947884469986816e-05,
+      "loss": 0.1841,
+      "step": 854500
+    },
+    {
+      "epoch": 9.18,
+      "learning_rate": 1.7894402638947176e-05,
+      "loss": 0.1841,
+      "step": 855000
+    },
+    {
+      "epoch": 9.18,
+      "eval_loss": 0.1744370311498642,
+      "eval_runtime": 2.6199,
+      "eval_samples_per_second": 876.754,
+      "eval_steps_per_second": 13.741,
+      "step": 855000
+    },
+    {
+      "epoch": 9.18,
+      "learning_rate": 1.7841090602239237e-05,
+      "loss": 0.1841,
+      "step": 855500
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 1.778794850561604e-05,
+      "loss": 0.1844,
+      "step": 856000
+    },
+    {
+      "epoch": 9.19,
+      "eval_loss": 0.17599613964557648,
+      "eval_runtime": 2.6232,
+      "eval_samples_per_second": 875.655,
+      "eval_steps_per_second": 13.724,
+      "step": 856000
+    },
+    {
+      "epoch": 9.2,
+      "learning_rate": 1.7734976494366073e-05,
+      "loss": 0.1837,
+      "step": 856500
+    },
+    {
+      "epoch": 9.2,
+      "learning_rate": 1.7682174713312805e-05,
+      "loss": 0.1843,
+      "step": 857000
+    },
+    {
+      "epoch": 9.2,
+      "eval_loss": 0.17385347187519073,
+      "eval_runtime": 2.7089,
+      "eval_samples_per_second": 847.948,
+      "eval_steps_per_second": 13.29,
+      "step": 857000
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 1.7629543306814255e-05,
+      "loss": 0.1838,
+      "step": 857500
+    },
+    {
+      "epoch": 9.21,
+      "learning_rate": 1.75770824187627e-05,
+      "loss": 0.1839,
+      "step": 858000
+    },
+    {
+      "epoch": 9.21,
+      "eval_loss": 0.17458127439022064,
+      "eval_runtime": 2.75,
+      "eval_samples_per_second": 835.274,
+      "eval_steps_per_second": 13.091,
+      "step": 858000
+    },
+    {
+      "epoch": 9.22,
+      "learning_rate": 1.7524792192584186e-05,
+      "loss": 0.1843,
+      "step": 858500
+    },
+    {
+      "epoch": 9.22,
+      "learning_rate": 1.747267277123821e-05,
+      "loss": 0.1839,
+      "step": 859000
+    },
+    {
+      "epoch": 9.22,
+      "eval_loss": 0.1746589094400406,
+      "eval_runtime": 2.6359,
+      "eval_samples_per_second": 871.432,
+      "eval_steps_per_second": 13.658,
+      "step": 859000
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 1.74207242972173e-05,
+      "loss": 0.1837,
+      "step": 859500
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 1.7368946912546556e-05,
+      "loss": 0.1836,
+      "step": 860000
+    },
+    {
+      "epoch": 9.23,
+      "eval_loss": 0.1775263249874115,
+      "eval_runtime": 2.6639,
+      "eval_samples_per_second": 862.261,
+      "eval_steps_per_second": 13.514,
+      "step": 860000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 5.958472899551867e+22,
+  "total_flos": 6.028573160582214e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2b61d52c517c0fe4a2eaad25ea86eca5fed6ebf386f54b8df5e3364654d10f
+oid sha256:d9da54e69aa4d985aac499cdb17fab8ee1c2bb36a1855c776c5bda5c5106d784
 size 449471589