Training in progress, step 15000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef358b8abdc8b32586ade83ad626ced2c2ef553c4675a7c7082630bc53b7e271
+oid sha256:f32d05e67336f892684b8c1fd2d6e5abd7a19c7a3f8e60643ae3b6f25370775f
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be11fa803e6017eb3dbc01c05f9b1e5eb55d5c2a51273b624e4418c37cb17a50
+oid sha256:518db281c68ab44504d89afd4194f546b333ca0c39d6413cfd75d77184014cc2
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5b84fb60f620174879deba0342a8a31da5b88033e1cc6fd9fb9fedc3bfe020d
+oid sha256:6a8f9792121fbd04e7178f7b4e43756a5886a8af837b3120c6d50a7ef7909014
 size 15459

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dea577c093f733c5db585f25caa4bcb5b57c2e6ee15524759cbddd90329af41
+oid sha256:61491770594419f1f65e70a85ff1045ef5f026004b37d4207f8d0e52435942a4
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d524b4cb1391ef7e50966a3eef7ac714ecb6ed976eedf165d99a07d29c73b99
+oid sha256:5a1bbe8751f81eef53f97fffae533ac792444b305682e60f93b951d5e4e28b33
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8705493166187864,
-  "global_step": 10000,
+  "epoch": 1.3058239749281797,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -142,11 +142,79 @@
       "eval_samples_per_second": 43.472,
       "eval_steps_per_second": 0.687,
       "step": 10000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.833541625738316e-05,
+      "loss": 0.4543,
+      "step": 10500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.809924007281187e-05,
+      "loss": 0.4532,
+      "step": 11000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.78525261765341e-05,
+      "loss": 0.4529,
+      "step": 11500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.759533544151208e-05,
+      "loss": 0.4523,
+      "step": 12000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.732827688303682e-05,
+      "loss": 0.4506,
+      "step": 12500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 9.705034604088048e-05,
+      "loss": 0.4502,
+      "step": 13000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 9.676213628592508e-05,
+      "loss": 0.4493,
+      "step": 13500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 9.64637187296151e-05,
+      "loss": 0.449,
+      "step": 14000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 9.615516700201724e-05,
+      "loss": 0.448,
+      "step": 14500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 9.583720443927501e-05,
+      "loss": 0.4479,
+      "step": 15000
+    },
+    {
+      "epoch": 1.31,
+      "eval_loss": 0.4363159239292145,
+      "eval_runtime": 91.0649,
+      "eval_samples_per_second": 54.906,
+      "eval_steps_per_second": 0.868,
+      "step": 15000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 4.709861347295232e+20,
+  "total_flos": 7.064748208279152e+20,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be11fa803e6017eb3dbc01c05f9b1e5eb55d5c2a51273b624e4418c37cb17a50
+oid sha256:518db281c68ab44504d89afd4194f546b333ca0c39d6413cfd75d77184014cc2
 size 449471589