Training in progress, step 60000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f460e22729b026f332d2bbd58361fd7555bb5ce353e6bf9e9337dd07a16fd2
+oid sha256:75f490a44ca4db15e7575b8b5617b1840dd0ecf21419611f63f02b99abb69e9b
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79523338e928e9a7fd3dc7b6a94546daade275fb1ce8b2909431e7af5e11c453
+oid sha256:27d58b7a9a0b285b885c546e3dfb7edd5e2459a83480dfbe8cb380fa08f7c48b
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8a9a1cf72e4f2a5fde4519f00b51f996087fefce4d88bad27c5094268cbceb
+oid sha256:40154e4835e4b0b561c3bf4ff2dc5bc26aeff6d6da324651140e34885d603328
 size 15523

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d419d70f318fa2e30e9d316c6fcb2475e360580d97334e925184e9f3c7f37a2d
+oid sha256:f6b7e341561c3473a840ee99225858db17d1117cb5b96bd811d9778b3f6e2cd9
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad72afbc8c0bb1254e98f3b0c83e6599b2d9a0f1bddb89ae821c17bf6f39f9af
+oid sha256:621aa918e7d94e76e980dd52e6d602b019ed8ae919fe1ca65a5ac903747bec67
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.354262823304015,
-  "global_step": 50000,
+  "epoch": 5.225115387964817,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -686,11 +686,147 @@
       "eval_samples_per_second": 64.123,
       "eval_steps_per_second": 1.013,
       "step": 50000
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 5.4701898965206674e-05,
+      "loss": 0.4045,
+      "step": 50500
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 5.398910105922212e-05,
+      "loss": 0.4026,
+      "step": 51000
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 5.327949784484338e-05,
+      "loss": 0.4028,
+      "step": 51500
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 5.256756489949676e-05,
+      "loss": 0.4036,
+      "step": 52000
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 5.18563285019876e-05,
+      "loss": 0.4037,
+      "step": 52500
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 5.114596413925449e-05,
+      "loss": 0.402,
+      "step": 53000
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 5.0436647083074565e-05,
+      "loss": 0.4014,
+      "step": 53500
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 4.972855234681767e-05,
+      "loss": 0.4013,
+      "step": 54000
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 4.90232665274781e-05,
+      "loss": 0.4011,
+      "step": 54500
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 4.8318136905147416e-05,
+      "loss": 0.4011,
+      "step": 55000
+    },
+    {
+      "epoch": 4.79,
+      "eval_loss": 0.381072461605072,
+      "eval_runtime": 56.5742,
+      "eval_samples_per_second": 88.379,
+      "eval_steps_per_second": 1.396,
+      "step": 55000
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 4.761475231342622e-05,
+      "loss": 0.4007,
+      "step": 55500
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 4.691328630193755e-05,
+      "loss": 0.3994,
+      "step": 56000
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 4.621391194692349e-05,
+      "loss": 0.3984,
+      "step": 56500
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 4.551680180854116e-05,
+      "loss": 0.3991,
+      "step": 57000
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 4.482212788828615e-05,
+      "loss": 0.3989,
+      "step": 57500
+    },
+    {
+      "epoch": 5.05,
+      "learning_rate": 4.413144300314575e-05,
+      "loss": 0.3976,
+      "step": 58000
+    },
+    {
+      "epoch": 5.09,
+      "learning_rate": 4.344214935022219e-05,
+      "loss": 0.3982,
+      "step": 58500
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 4.275580380487631e-05,
+      "loss": 0.3973,
+      "step": 59000
+    },
+    {
+      "epoch": 5.18,
+      "learning_rate": 4.2073938945388334e-05,
+      "loss": 0.3976,
+      "step": 59500
+    },
+    {
+      "epoch": 5.23,
+      "learning_rate": 4.1393990142726966e-05,
+      "loss": 0.3976,
+      "step": 60000
+    },
+    {
+      "epoch": 5.23,
+      "eval_loss": 0.3779057562351227,
+      "eval_runtime": 90.9731,
+      "eval_samples_per_second": 54.961,
+      "eval_steps_per_second": 0.868,
+      "step": 60000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 2.354791568440382e+21,
+  "total_flos": 2.8257429268680965e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79523338e928e9a7fd3dc7b6a94546daade275fb1ce8b2909431e7af5e11c453
+oid sha256:27d58b7a9a0b285b885c546e3dfb7edd5e2459a83480dfbe8cb380fa08f7c48b
 size 449471589