Training in progress, step 200000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd03613df05982cc6cd8521404bf2d7d311a82ab0ee46fc664ebdeffd43ec5fb
+oid sha256:3278127396f5d3f8558d8e933cd802503bc96eb286ac4ab8615fdd148bdb7c65
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75854e0ff3e7c4405dc53eac04c2010a206af7aae27dae0d9ee35db9ad0a959a
+oid sha256:f55e8b51abb099c47f1d26ef4448005ca8276d7a11a4fd49a19180fc80b2825a
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3586f2d8b7a9d0704645682c4f2d417639e4cca27eecf545ccb9e56c8d74df
+oid sha256:88004fc539503ca7b97859aa1d0c5a82fcb7f351b44fb5ff1b5865391c2b3cde
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38e985eb8bf02ef58974d91bc1d920b2617a41af091b03e6ddbcd3b7548fe4b3
+oid sha256:ccdf82dc05f3b4b6efaa6b42846dbff856f1303f57b4b6c56f7597dda3131a18
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d738b37d6429a4b318ddcdaacb6b35096cf2474500c27a66a5a92064653d6fd
+oid sha256:de21128fb4d2d9fbd6335f650a62e3e1299cfe449b8f64957937f253cda36cc0
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
-  "global_step": 190000,
+  "epoch": 0.05,
+  "global_step": 200000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2590,11 +2590,147 @@
       "eval_samples_per_second": 156.162,
       "eval_steps_per_second": 2.44,
       "step": 190000
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0512109659997981e-05,
+      "loss": 0.3699,
+      "step": 190500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0460195662993147e-05,
+      "loss": 0.3694,
+      "step": 191000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0410946381032989e-05,
+      "loss": 0.3682,
+      "step": 191500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.036447165752325e-05,
+      "loss": 0.3681,
+      "step": 192000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.03207743592438e-05,
+      "loss": 0.368,
+      "step": 192500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0279857181649817e-05,
+      "loss": 0.3678,
+      "step": 193000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0241722648705564e-05,
+      "loss": 0.3673,
+      "step": 193500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0206373112728653e-05,
+      "loss": 0.3683,
+      "step": 194000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0173810754244984e-05,
+      "loss": 0.3686,
+      "step": 194500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.0144037581854202e-05,
+      "loss": 0.3678,
+      "step": 195000
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.34533271193504333,
+      "eval_runtime": 293.19,
+      "eval_samples_per_second": 146.663,
+      "eval_steps_per_second": 2.292,
+      "step": 195000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.0117055432105827e-05,
+      "loss": 0.3686,
+      "step": 195500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.0092865969385957e-05,
+      "loss": 0.3676,
+      "step": 196000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.0071470685814586e-05,
+      "loss": 0.3662,
+      "step": 196500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0052905310023697e-05,
+      "loss": 0.3689,
+      "step": 197000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0037096577272572e-05,
+      "loss": 0.368,
+      "step": 197500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0024085463788748e-05,
+      "loss": 0.3678,
+      "step": 198000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0013872772159007e-05,
+      "loss": 0.37,
+      "step": 198500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0006471165843453e-05,
+      "loss": 0.3681,
+      "step": 199000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.000185143580406e-05,
+      "loss": 0.369,
+      "step": 199500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0000031499118314e-05,
+      "loss": 0.3671,
+      "step": 200000
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 0.3454923629760742,
+      "eval_runtime": 277.6346,
+      "eval_samples_per_second": 154.88,
+      "eval_steps_per_second": 2.42,
+      "step": 200000
     }
   ],
   "max_steps": 200000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 4.4743682799304704e+21,
+  "total_flos": 4.709861347295232e+21,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c8d520d84739d0748a1ea61094afdc642629ce6412053854db2541abbd8d18
+oid sha256:d97d297980a836fa96a55b93de6b63b6bdd01f5d972c55cfc32c86f75c5c6b99
 size 5551

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75854e0ff3e7c4405dc53eac04c2010a206af7aae27dae0d9ee35db9ad0a959a
+oid sha256:f55e8b51abb099c47f1d26ef4448005ca8276d7a11a4fd49a19180fc80b2825a
 size 449471589

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c8d520d84739d0748a1ea61094afdc642629ce6412053854db2541abbd8d18
+oid sha256:d97d297980a836fa96a55b93de6b63b6bdd01f5d972c55cfc32c86f75c5c6b99
 size 5551