Training in progress, step 900000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42ed7fe58b215bb0dbec2af4a7d664e938d635b1ef05290da2036605b37704a3
+oid sha256:81603416f1fba3109b9ef2dfed9df589999e06f1186e2baeac09426d5454ae3d
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa4ab0c6834a759e55baa287a48208abf39c778ed277af3b0afe1b1b96d8b552
+oid sha256:0cd0588845ddc4a31c9c47550dec41eb37349d2edd4e1f34356e1f993b492ba0
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f483f771a26716cfd70c3a5175a315dd25e3cc6dc8bc56308db21f3af0dc88d6
-size 14503
+oid sha256:9f495dfd7f4ccee04d72bad0e351a96e4d86b89643197cb94dfee5e43013e7b2
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b2fa8647e8771b01ebc4433e88606f474979e505ff0f89ae2bd75e3418c26e7
+oid sha256:0a3ab375a848ecaefff3706d2c692ac9259621d2aa93953ba9d5f4510dca87b7
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70df957d931b4b06dbdec01474740c6119583917c674231d25b7b12875e1d7a9
+oid sha256:48bc8ea8a56da3a164d01716edb5b450bdffa75fb03183f592780d30cdcccc55
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbaae9451e4051ab9fe7948d1d8a9c41e70f70568605abb0409e412d5e85feaa
+oid sha256:4bef8a52198e713e41af5f2aacfd75864c1e5d1bcaad410e37c104450edb03f2
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2afa6aa14483adb7c817c2439178a198c4680dbfe427eab82def33bea1566914
+oid sha256:aa624c96f92eaad028a188cf78acc34c38cdc88db165dfecd04176965e65555e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.590483607433537,
-  "global_step": 890000,
+  "epoch": 13.743185670438407,
+  "global_step": 900000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6592,11 +6592,85 @@
       "eval_samples_per_second": 1364.004,
       "eval_steps_per_second": 21.824,
       "step": 890000
+    },
+    {
+      "epoch": 13.61,
+      "learning_rate": 1.4498484122598232e-05,
+      "loss": 0.2308,
+      "step": 891000
+    },
+    {
+      "epoch": 13.62,
+      "learning_rate": 1.4417197081242083e-05,
+      "loss": 0.2305,
+      "step": 892000
+    },
+    {
+      "epoch": 13.64,
+      "learning_rate": 1.433662724291136e-05,
+      "loss": 0.2313,
+      "step": 893000
+    },
+    {
+      "epoch": 13.65,
+      "learning_rate": 1.4256775488704904e-05,
+      "loss": 0.2311,
+      "step": 894000
+    },
+    {
+      "epoch": 13.67,
+      "learning_rate": 1.4177642691868717e-05,
+      "loss": 0.231,
+      "step": 895000
+    },
+    {
+      "epoch": 13.67,
+      "eval_runtime": 0.7236,
+      "eval_samples_per_second": 1382.053,
+      "eval_steps_per_second": 22.113,
+      "step": 895000
+    },
+    {
+      "epoch": 13.68,
+      "learning_rate": 1.4099229717786368e-05,
+      "loss": 0.231,
+      "step": 896000
+    },
+    {
+      "epoch": 13.7,
+      "learning_rate": 1.4021537423969588e-05,
+      "loss": 0.2317,
+      "step": 897000
+    },
+    {
+      "epoch": 13.71,
+      "learning_rate": 1.3944566660048863e-05,
+      "loss": 0.2308,
+      "step": 898000
+    },
+    {
+      "epoch": 13.73,
+      "learning_rate": 1.3868318267764128e-05,
+      "loss": 0.2309,
+      "step": 899000
+    },
+    {
+      "epoch": 13.74,
+      "learning_rate": 1.3792793080955574e-05,
+      "loss": 0.2308,
+      "step": 900000
+    },
+    {
+      "epoch": 13.74,
+      "eval_runtime": 0.7542,
+      "eval_samples_per_second": 1325.982,
+      "eval_steps_per_second": 21.216,
+      "step": 900000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.238914689814962e+22,
+  "total_flos": 6.309014950845309e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa4ab0c6834a759e55baa287a48208abf39c778ed277af3b0afe1b1b96d8b552
+oid sha256:0cd0588845ddc4a31c9c47550dec41eb37349d2edd4e1f34356e1f993b492ba0
 size 449471589