Training in progress, step 160000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af89620dabb8befadb717e149645c7b1a4baa437ae00fe1a45d193867a75747e
+oid sha256:51c4479b7100b24acffdfd7fb1cff497645cac828edc9bce49ad39669a19e6f1
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4473132994381129211918f004185b9788753aef90d5b6db4b7139479af4a5e
+oid sha256:f45b8970c2fcdae44788b5d4ade86d7949295115594ab3b0d456c282cadcd002
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ce68a515967919f0a865a5bd2e1e8f70571d798e73f414abfc84271b022caff
+oid sha256:02a1d97b2752462543b92ffd0f23922ddd8ffff9e6ba2aaf2b57366a0cea0714
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6380926153299d8b0e27207014365338e9fc035d7cd51dfa2b4a3c25b6edbff5
+oid sha256:29849d211b595c5ac9c137dcd37e20da1964e185621f9086f1491a26e0f460bc
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f61692f187e649a36856bc80d6adc9da2c6f8eb5a5983beddd87644fb8d73c
-size 14439
+oid sha256:e99c0c1e436962d7938fd416d17b1f2b444137c2e5f765032e46157e9b60a3ea
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0c634c62ca05cfd25911633dd33cd6a1a4c0751ac34bfc4f130af2e87b7357
-size 14439
+oid sha256:00c80b4bceef61474bcae1ecae0d1e95d0713b469a0fdc8873f2259acce5bd7e
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6944aac36fb07ee223c68ca3cff3b6f262ad7e802285928ca04ff038bec935ea
+oid sha256:09b0f5af299b689f18c326dad86c4c4c3f628480672d22f22ec90ae66ce6a4f1
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.2905309450730678,
-  "global_step": 150000,
+  "epoch": 2.443233008077939,
+  "global_step": 160000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1116,11 +1116,85 @@
       "eval_samples_per_second": 958.687,
       "eval_steps_per_second": 15.339,
       "step": 150000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00014613168173223585,
+      "loss": 0.3308,
+      "step": 151000
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.00014605543333995113,
+      "loss": 0.3302,
+      "step": 152000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.00014597846257603038,
+      "loss": 0.3294,
+      "step": 153000
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 0.0001459007702822136,
+      "loss": 0.329,
+      "step": 154000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 0.00014582235730813128,
+      "loss": 0.3283,
+      "step": 155000
+    },
+    {
+      "epoch": 2.37,
+      "eval_runtime": 1.0629,
+      "eval_samples_per_second": 940.817,
+      "eval_steps_per_second": 15.053,
+      "step": 155000
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.00014574322451129507,
+      "loss": 0.3281,
+      "step": 156000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.00014566337275708863,
+      "loss": 0.328,
+      "step": 157000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.0001455828029187579,
+      "loss": 0.3272,
+      "step": 158000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 0.00014550151587740178,
+      "loss": 0.3269,
+      "step": 159000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 0.00014541951252196225,
+      "loss": 0.3265,
+      "step": 160000
+    },
+    {
+      "epoch": 2.44,
+      "eval_runtime": 1.0199,
+      "eval_samples_per_second": 980.452,
+      "eval_steps_per_second": 15.687,
+      "step": 160000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 1.0515026013189097e+22,
+  "total_flos": 1.1216028623492568e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4473132994381129211918f004185b9788753aef90d5b6db4b7139479af4a5e
+oid sha256:f45b8970c2fcdae44788b5d4ade86d7949295115594ab3b0d456c282cadcd002
 size 449471589