Training in progress, step 40000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4cc35e78f4b2875a4e7bc2823bb00b03a35ef0a895f4019b9ee2bc553e87589
+oid sha256:1b79098aba355edf15cdcc2ba65841e59d94f2195e6563e00db7a5b77d0de1b0
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72eceef87bfa3bd9a4ae124be6a652f67324b3717ebee85984495f36f82da2ae
+oid sha256:56c9245179e00ecfc159536796459f1277956357c9ae2eeba259fdadb204bca4
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fa93e01617d6f205944a831ee335dee07ebb08b04eafcf9562f4cb23a4302a
+oid sha256:dab27e02a841889dd406a61f3825c3bf16e995606299fd6ab9fd7db009ed4e68
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39fcc0dca710a70aacc882ac08d1de25fb93138ed23a4e1e7de926a24206dd2c
+oid sha256:783ce381375b60e783f2e4204fc7d9689e81e56991f92e086a503c69636e5046
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc311eb216d0f91d79274b66b1cc6a0546d030081f7d13ccdc6a5a80b2096b7
-size 14439
+oid sha256:59eabe2e991b1516dd6b66887718520f904de193e569a87238bb2d8904706701
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10eef73b54f0ee2610594db97b5e21337619a39459c4b5d554e4fc3069d6003e
-size 14503
+oid sha256:24b999227318d7857e7c42c9ad2f2208b186825e80265bff7952618efa8d3e7e
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eff7bfd19bb5de4a804b312a4895c5e9ec017a31baa7a463d8d86ec7115b34c
+oid sha256:06b5c694b40cd5a966b5116288c30b2f19979f1058d82965ee57335ae5f1e596
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4581061890146136,
-  "global_step": 30000,
+  "epoch": 0.6108082520194847,
+  "global_step": 40000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -228,11 +228,85 @@
       "eval_samples_per_second": 990.512,
       "eval_steps_per_second": 15.848,
       "step": 30000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.3e-05,
+      "loss": 0.5536,
+      "step": 31000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.599999999999999e-05,
+      "loss": 0.5496,
+      "step": 32000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.9e-05,
+      "loss": 0.5458,
+      "step": 33000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.000102,
+      "loss": 0.5426,
+      "step": 34000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00010499999999999999,
+      "loss": 0.5394,
+      "step": 35000
+    },
+    {
+      "epoch": 0.53,
+      "eval_runtime": 1.3102,
+      "eval_samples_per_second": 763.27,
+      "eval_steps_per_second": 12.212,
+      "step": 35000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00010799999999999998,
+      "loss": 0.5345,
+      "step": 36000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 0.5302,
+      "step": 37000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 0.527,
+      "step": 38000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.000117,
+      "loss": 0.5232,
+      "step": 39000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 0.5202,
+      "step": 40000
+    },
+    {
+      "epoch": 0.61,
+      "eval_runtime": 1.0146,
+      "eval_samples_per_second": 985.598,
+      "eval_steps_per_second": 15.77,
+      "step": 40000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.1030078309104144e+21,
+  "total_flos": 2.804010441213886e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72eceef87bfa3bd9a4ae124be6a652f67324b3717ebee85984495f36f82da2ae
+oid sha256:56c9245179e00ecfc159536796459f1277956357c9ae2eeba259fdadb204bca4
 size 449471589