Training in progress, step 860000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5555a3264f90296bf2491c36524039e7c271dde5eda23b82bfd2628385f7d8
+oid sha256:a5c106db74e42dc51679adae4b838c3fc769d432ccf7ad2ad85b3ca08257bba7
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b915770d637a85b511b8ce95890fcc501fb257fa086404572aeee5022ceaa62
+oid sha256:c6b3810346b06651e6d4da88b6c7ab5a4c39c9ed73386ee5a2037c7eee7d792a
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8772dddd6d938192c990459978e84fe841726f65afecb856e653e8f92d71ae84
+oid sha256:91922deb8d5a3dcc119e5076f52f06901e3c1963deb40c98ef6a2a56110eecfe
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:746d31cdff1a7ba11b9440e11b64572184b75f7cc296f7a28b273c21a8883fc1
+oid sha256:eda717afacbcc37a057674c94e7755da0f047a833361ec1cbdae8c11451a0ab4
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f51720bf9dead85db06417d336f89d75a1f13549e41b0ebc50dae00a0a00b614
+oid sha256:f5b4e2d79497f15fdd0b8e63be121802d33321a338ff2ad99cc0c2d94fed90e9
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce8c9d7e6207f2bddc524a75c48baf98682e25fb31bb85ed872f40875802e4db
-size 14567
+oid sha256:4f6dd21c66e6f1818612e884579b2f3fe6cd6395a735470cd934326c7e7a0170
+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": 12.979675355414052,
-  "global_step": 850000,
+  "epoch": 13.132377418418923,
+  "global_step": 860000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6296,11 +6296,85 @@
       "eval_samples_per_second": 1203.685,
       "eval_steps_per_second": 19.259,
       "step": 850000
+    },
+    {
+      "epoch": 12.99,
+      "learning_rate": 1.8326999187910095e-05,
+      "loss": 0.2342,
+      "step": 851000
+    },
+    {
+      "epoch": 13.01,
+      "learning_rate": 1.8217835406330415e-05,
+      "loss": 0.2344,
+      "step": 852000
+    },
+    {
+      "epoch": 13.03,
+      "learning_rate": 1.810934726460436e-05,
+      "loss": 0.2328,
+      "step": 853000
+    },
+    {
+      "epoch": 13.04,
+      "learning_rate": 1.800153594914084e-05,
+      "loss": 0.2326,
+      "step": 854000
+    },
+    {
+      "epoch": 13.06,
+      "learning_rate": 1.7894402638947176e-05,
+      "loss": 0.2325,
+      "step": 855000
+    },
+    {
+      "epoch": 13.06,
+      "eval_runtime": 0.7234,
+      "eval_samples_per_second": 1382.419,
+      "eval_steps_per_second": 22.119,
+      "step": 855000
+    },
+    {
+      "epoch": 13.07,
+      "learning_rate": 1.778794850561604e-05,
+      "loss": 0.2327,
+      "step": 856000
+    },
+    {
+      "epoch": 13.09,
+      "learning_rate": 1.7682174713312805e-05,
+      "loss": 0.2326,
+      "step": 857000
+    },
+    {
+      "epoch": 13.1,
+      "learning_rate": 1.75770824187627e-05,
+      "loss": 0.2325,
+      "step": 858000
+    },
+    {
+      "epoch": 13.12,
+      "learning_rate": 1.747267277123821e-05,
+      "loss": 0.2327,
+      "step": 859000
+    },
+    {
+      "epoch": 13.13,
+      "learning_rate": 1.7368946912546556e-05,
+      "loss": 0.2329,
+      "step": 860000
+    },
+    {
+      "epoch": 13.13,
+      "eval_runtime": 0.7568,
+      "eval_samples_per_second": 1321.327,
+      "eval_steps_per_second": 21.141,
+      "step": 860000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 5.958514302761722e+22,
+  "total_flos": 6.028613906723921e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b915770d637a85b511b8ce95890fcc501fb257fa086404572aeee5022ceaa62
+oid sha256:c6b3810346b06651e6d4da88b6c7ab5a4c39c9ed73386ee5a2037c7eee7d792a
 size 449471589