Training in progress, step 30000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a7851a76774c9d24610e8c4b64407ceaf0cba09a83e925a33fb41a03307ed7
+oid sha256:f4cc35e78f4b2875a4e7bc2823bb00b03a35ef0a895f4019b9ee2bc553e87589
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0d795304e92a242fb3daabda286fa8f94b1ee38faba8dda70081c35bf054d0f
+oid sha256:72eceef87bfa3bd9a4ae124be6a652f67324b3717ebee85984495f36f82da2ae
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d483ecbfd7c4ae648878217616c66bacf030cae7b2ded7d170987d76a2250ac
+oid sha256:e5fa93e01617d6f205944a831ee335dee07ebb08b04eafcf9562f4cb23a4302a
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044ec9788542bc63cbbb94478363f427bd5fb7e95aea2357c2a84029d6027b74
+oid sha256:39fcc0dca710a70aacc882ac08d1de25fb93138ed23a4e1e7de926a24206dd2c
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf0219f03126c61d6fe702f807db15414297e302e582e7db754139585c455cc
+oid sha256:bcc311eb216d0f91d79274b66b1cc6a0546d030081f7d13ccdc6a5a80b2096b7
 size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:000f13089b5059ffd9098e2fa284df7971e249ea2a6dfce01fab8815f9fa26de
+oid sha256:10eef73b54f0ee2610594db97b5e21337619a39459c4b5d554e4fc3069d6003e
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca250cf2344e8df6eed15e28ea548564b75ef302cf69c48962d23fb49df8b25
+oid sha256:0eff7bfd19bb5de4a804b312a4895c5e9ec017a31baa7a463d8d86ec7115b34c
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.30540412600974237,
-  "global_step": 20000,
+  "epoch": 0.4581061890146136,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -154,11 +154,85 @@
       "eval_samples_per_second": 982.441,
       "eval_steps_per_second": 15.719,
       "step": 20000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.299999999999999e-05,
+      "loss": 0.6074,
+      "step": 21000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 6.599999999999999e-05,
+      "loss": 0.6039,
+      "step": 22000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.9e-05,
+      "loss": 0.6005,
+      "step": 23000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 0.5968,
+      "step": 24000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.5e-05,
+      "loss": 0.5932,
+      "step": 25000
+    },
+    {
+      "epoch": 0.38,
+      "eval_runtime": 1.1249,
+      "eval_samples_per_second": 888.989,
+      "eval_steps_per_second": 14.224,
+      "step": 25000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 7.8e-05,
+      "loss": 0.5912,
+      "step": 26000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.1e-05,
+      "loss": 0.58,
+      "step": 27000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.4e-05,
+      "loss": 0.5698,
+      "step": 28000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 0.5639,
+      "step": 29000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 0.5601,
+      "step": 30000
+    },
+    {
+      "epoch": 0.46,
+      "eval_runtime": 1.0096,
+      "eval_samples_per_second": 990.512,
+      "eval_steps_per_second": 15.848,
+      "step": 30000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.402005220606943e+21,
+  "total_flos": 2.1030078309104144e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0d795304e92a242fb3daabda286fa8f94b1ee38faba8dda70081c35bf054d0f
+oid sha256:72eceef87bfa3bd9a4ae124be6a652f67324b3717ebee85984495f36f82da2ae
 size 449471589