Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f8f916144b97d4ddaaa68594ce549a3d0aad2914b41bcaaf1ec89b0fa386bd5
+oid sha256:9d86b8e0a189fe81a8f4525b970e4a618050163f6c5ffd86a59aa345f01f8941
 size 37134420

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c201bc495760ecf81e3a8aac05f9bd362b48b7014ed6b59128128b4804cbe6
+oid sha256:159dea0d8c058e4ce476c3d2fdabfc40a463f22164cf724e43458cacddfb3d15
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e796d3abe6e9bbe48f5638e33ea6d9f90f3f55e92595c8e35f58bacd11f4124
+oid sha256:58d4f096228ba0b5be7639cfab15abd4063c6f2a5a8d0d68d42a3f2e0ef7ac37
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8aa786061f7c99f6db00dcfd8675d7ade5c75f02b1f2bd445ff74fdc042c6de
+oid sha256:23d9f77db71d7a71bcb1184984bdbba4dba65121c20f01a13d10ca4a5a03b10c
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ad7f7e7b759afa79724c3ad270dd1c777cff625092f285c5bd7cf06f792831c
+oid sha256:57bb3185ce4dcc367d32c1c2b0e7ecc83896f53c6a085df04081950319708806
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a808d1867f13d448b79e0f402afc708c7b249b39c403692d66be72b76d2d4589
+oid sha256:9d93dfd306ab87019164a1407bb8000ca56bdf9da4c5368b1ad8ab417b147822
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fbdba7e06e397a97fc796a6bb07243aee073f36afac35c847cf01b85e0af29d
+oid sha256:0aa4899791748f51ff418063bc685904271fc1e7e23817fdceb2368dd5bd65cd
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1470bd4d59e6239f849257c72c690f54f661d542c4aa74cc6380ca38025758f3
+oid sha256:98e5802220949bce824f69a6d71d3f6cb5d6eb0c8fc62d2a4e1ecf76bdc443db
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29aea3631f2553b0a44f1b1251a4fceab067cc6c7873b6857f6e1f8fecd0042e
+oid sha256:a2a1b555144dcede4d2a4907e3165f02815943d61d9ebea490045fc51196f197
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21352313167259787,
+  "epoch": 0.2846975088967972,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 37.649,
       "eval_steps_per_second": 4.766,
       "step": 15
+    },
+    {
+      "epoch": 0.2277580071174377,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1069.6057,
+      "step": 16
+    },
+    {
+      "epoch": 0.24199288256227758,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1501.6047,
+      "step": 17
+    },
+    {
+      "epoch": 0.25622775800711745,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 737.9307,
+      "step": 18
+    },
+    {
+      "epoch": 0.2704626334519573,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 223.4566,
+      "step": 19
+    },
+    {
+      "epoch": 0.2846975088967972,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 1692.3673,
+      "step": 20
+    },
+    {
+      "epoch": 0.2846975088967972,
+      "eval_loss": NaN,
+      "eval_runtime": 12.5841,
+      "eval_samples_per_second": 37.667,
+      "eval_steps_per_second": 4.768,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.685647481438208e+16,
+  "total_flos": 1.0247529975250944e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null