Training in progress, step 980000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6337e42221c0412df86c7992210272b9971c9d1fc461208785aaf4d8ac59d2f
+oid sha256:90e6f74ca02156084fa05f854168c4cbdee8fc0fa6687cea7dfffc7ceaa970ef
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e43adcfc82aa259193d845850177a25c81c1a4194053ab16836d335061826a
+oid sha256:44a8bb7d1ad03b47ab97301f2bf5aa4416e913d62ffabd09bdd937d55c43233d
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:896791a7c2af828c5892ebdd0c2594828d16ab816d74f045b54f109ae6d9494f
+oid sha256:2693c812482df2fdf768d0c19e41d192e583b64a43dbe767a2677f629f2520e7
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2b1d003a5601ab66979661e59677be128945b2fa99167367a5f20eee9647c21
+oid sha256:39770cef90df6052fa5bdc49403a83d0e05cc2d3766019022596476c4a73f3b2
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:881d6829cb0acc89bbda293c5817890086c3d5c60b0bada5736d21401b19e6e3
-size 14567
+oid sha256:708a00e78f0bdafbd2eb890af573c704006de2c61a1f639e3fb47ce38e039820
+size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df3df06c4c66eb76fd186c61e084b6f3a769bb5d036f690f217d70cc8d7d4fc4
+oid sha256:c3d789d948e2afb641edc41de23d3e0ac8454e4ca3cace740853515e0185e05d
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af3eb0d3db8162f6de4427ee5f19b1787f4bdb865e0ebda13f4fed6034a8890
+oid sha256:b1f60f9446cba0320cf9ced93c4b14816af8d6988d011f7cc2f5b01e8ada101d
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.812100111472507,
-  "global_step": 970000,
+  "epoch": 14.964802174477377,
+  "global_step": 980000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7184,11 +7184,85 @@
       "eval_samples_per_second": 1327.252,
       "eval_steps_per_second": 21.236,
       "step": 970000
+    },
+    {
+      "epoch": 14.83,
+      "learning_rate": 1.032165010471157e-05,
+      "loss": 0.2277,
+      "step": 971000
+    },
+    {
+      "epoch": 14.84,
+      "learning_rate": 1.0299865378844936e-05,
+      "loss": 0.2275,
+      "step": 972000
+    },
+    {
+      "epoch": 14.86,
+      "learning_rate": 1.0278842882483569e-05,
+      "loss": 0.2275,
+      "step": 973000
+    },
+    {
+      "epoch": 14.87,
+      "learning_rate": 1.025858284552612e-05,
+      "loss": 0.2276,
+      "step": 974000
+    },
+    {
+      "epoch": 14.89,
+      "learning_rate": 1.023908548953311e-05,
+      "loss": 0.2275,
+      "step": 975000
+    },
+    {
+      "epoch": 14.89,
+      "eval_runtime": 0.7861,
+      "eval_samples_per_second": 1272.066,
+      "eval_steps_per_second": 20.353,
+      "step": 975000
+    },
+    {
+      "epoch": 14.9,
+      "learning_rate": 1.02203510277245e-05,
+      "loss": 0.2276,
+      "step": 976000
+    },
+    {
+      "epoch": 14.92,
+      "learning_rate": 1.0202379664977364e-05,
+      "loss": 0.2272,
+      "step": 977000
+    },
+    {
+      "epoch": 14.93,
+      "learning_rate": 1.018517159782365e-05,
+      "loss": 0.2274,
+      "step": 978000
+    },
+    {
+      "epoch": 14.95,
+      "learning_rate": 1.0168727014448004e-05,
+      "loss": 0.2272,
+      "step": 979000
+    },
+    {
+      "epoch": 14.96,
+      "learning_rate": 1.0153046094685783e-05,
+      "loss": 0.227,
+      "step": 980000
+    },
+    {
+      "epoch": 14.96,
+      "eval_runtime": 0.7489,
+      "eval_samples_per_second": 1335.226,
+      "eval_steps_per_second": 21.364,
+      "step": 980000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 6.7997161209895905e+22,
+  "total_flos": 6.869816382019938e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e43adcfc82aa259193d845850177a25c81c1a4194053ab16836d335061826a
+oid sha256:44a8bb7d1ad03b47ab97301f2bf5aa4416e913d62ffabd09bdd937d55c43233d
 size 449471589