Training in progress, step 50000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21e0468f83252fbd857b959ddace7a9f33b4b96fb87a6baf73ead5e873aabb0c
+oid sha256:f6f460e22729b026f332d2bbd58361fd7555bb5ce353e6bf9e9337dd07a16fd2
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc7e4def826ce0471f39109f9fdb3314c8bc2030700c1f3907e774f1c01f478
+oid sha256:79523338e928e9a7fd3dc7b6a94546daade275fb1ce8b2909431e7af5e11c453
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85d1c2df1a9b702c1ab654e9e5e408f92b9742bb1e3ca9287f5761ef0b320b84
+oid sha256:5c8a9a1cf72e4f2a5fde4519f00b51f996087fefce4d88bad27c5094268cbceb
 size 15523

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c80c9fc8381c1a21d068329ef7b88e8e389828d1de4a65d282cc16135a4f7204
+oid sha256:d419d70f318fa2e30e9d316c6fcb2475e360580d97334e925184e9f3c7f37a2d
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3321618f4e6ed92cd7e76689475cb3f46497297ac6a6a8342c9bad133a001350
+oid sha256:ad72afbc8c0bb1254e98f3b0c83e6599b2d9a0f1bddb89ae821c17bf6f39f9af
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.483410258643212,
-  "global_step": 40000,
+  "epoch": 4.354262823304015,
+  "global_step": 50000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -550,11 +550,147 @@
       "eval_samples_per_second": 81.507,
       "eval_steps_per_second": 1.288,
       "step": 40000
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 6.875501637243646e-05,
+      "loss": 0.4131,
+      "step": 40500
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 6.807200639723347e-05,
+      "loss": 0.4117,
+      "step": 41000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 6.738586748092632e-05,
+      "loss": 0.4111,
+      "step": 41500
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 6.669953098278655e-05,
+      "loss": 0.4112,
+      "step": 42000
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 6.600765361692337e-05,
+      "loss": 0.4111,
+      "step": 42500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 6.531315665811498e-05,
+      "loss": 0.4101,
+      "step": 43000
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 6.461621146309398e-05,
+      "loss": 0.4106,
+      "step": 43500
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 6.39169899926586e-05,
+      "loss": 0.409,
+      "step": 44000
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 6.321706940430336e-05,
+      "loss": 0.4103,
+      "step": 44500
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 6.25138171578181e-05,
+      "loss": 0.4076,
+      "step": 45000
+    },
+    {
+      "epoch": 3.92,
+      "eval_loss": 0.3885731101036072,
+      "eval_runtime": 62.3283,
+      "eval_samples_per_second": 80.22,
+      "eval_steps_per_second": 1.267,
+      "step": 45000
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 6.18088073702545e-05,
+      "loss": 0.4084,
+      "step": 45500
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 6.110221399222838e-05,
+      "loss": 0.4087,
+      "step": 46000
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 6.0394211365082756e-05,
+      "loss": 0.4069,
+      "step": 46500
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 5.9686393768070895e-05,
+      "loss": 0.4067,
+      "step": 47000
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 5.897609895876622e-05,
+      "loss": 0.4059,
+      "step": 47500
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 5.826491948741281e-05,
+      "loss": 0.4064,
+      "step": 48000
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 5.755303082690363e-05,
+      "loss": 0.4065,
+      "step": 48500
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 5.6840608625113427e-05,
+      "loss": 0.4072,
+      "step": 49000
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 5.61278286615603e-05,
+      "loss": 0.4054,
+      "step": 49500
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 5.541486680403469e-05,
+      "loss": 0.4061,
+      "step": 50000
+    },
+    {
+      "epoch": 4.35,
+      "eval_loss": 0.38421276211738586,
+      "eval_runtime": 77.975,
+      "eval_samples_per_second": 64.123,
+      "eval_steps_per_second": 1.013,
+      "step": 50000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 1.8838402100126674e+21,
+  "total_flos": 2.354791568440382e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc7e4def826ce0471f39109f9fdb3314c8bc2030700c1f3907e774f1c01f478
+oid sha256:79523338e928e9a7fd3dc7b6a94546daade275fb1ce8b2909431e7af5e11c453
 size 449471589