Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d37015bf243e15cd96cf024c1187375a351961f8338b04cf3d000489f1078e3
+oid sha256:8f603a94f13509ab16251fbd198ef0186e986d1dca641d349447253e7fe274d8
 size 1101572914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c39189b58fbe393a71835dfbcc8173a038fd39751a45b5b8649aa9086707cc6a
+oid sha256:ff05f55f392d4c102b9c4b1c7b33e76bd9eedb2df459e47bd4300df6270441ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf7ee3ad8033dc89ac477e4347a2567ff89d6c0358e1d7a1b0f70057a3434847
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.027979854504756575,
+  "epoch": 0.05595970900951315,
   "eval_steps": 500,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,181 @@
       "learning_rate": 2.663507823075358e-05,
       "loss": 0.0,
       "step": 25
+    },
+    {
+      "epoch": 0.029099048684946838,
+      "grad_norm": NaN,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.0302182428651371,
+      "grad_norm": NaN,
+      "learning_rate": 2.3364921769246423e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.03133743704532736,
+      "grad_norm": NaN,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.032456631225517625,
+      "grad_norm": NaN,
+      "learning_rate": 2.0122741949596797e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.03357582540570789,
+      "grad_norm": NaN,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03469501958589815,
+      "grad_norm": NaN,
+      "learning_rate": 1.6964013367420966e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.03581421376608842,
+      "grad_norm": NaN,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.03693340794627868,
+      "grad_norm": NaN,
+      "learning_rate": 1.3942782744524973e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.038052602126468944,
+      "grad_norm": NaN,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.03917179630665921,
+      "grad_norm": NaN,
+      "learning_rate": 1.1110744174509952e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.04029099048684947,
+      "grad_norm": NaN,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.04141018466703973,
+      "grad_norm": NaN,
+      "learning_rate": 8.51635462249828e-06,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.042529378847229994,
+      "grad_norm": NaN,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.04364857302742026,
+      "grad_norm": NaN,
+      "learning_rate": 6.204004813025568e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.04476776720761052,
+      "grad_norm": NaN,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.04588696138780078,
+      "grad_norm": NaN,
+      "learning_rate": 4.213259692436367e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.047006155567991044,
+      "grad_norm": NaN,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.048125349748181306,
+      "grad_norm": NaN,
+      "learning_rate": 2.578181461682794e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.049244543928371576,
+      "grad_norm": NaN,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.05036373810856184,
+      "grad_norm": NaN,
+      "learning_rate": 1.3267467626223606e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.0514829322887521,
+      "grad_norm": NaN,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.05260212646894236,
+      "grad_norm": NaN,
+      "learning_rate": 4.803679899192392e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.053721320649132626,
+      "grad_norm": NaN,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.05484051482932289,
+      "grad_norm": NaN,
+      "learning_rate": 5.352691903491303e-08,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.05595970900951315,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -196,12 +371,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.5070892031606784e+16,
+  "total_flos": 6.979454750844518e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null