Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:445d7fd8c1cd70e08455528dc215a75488aa0e03c5cef0380c7c5e1c2aec384f
+oid sha256:c9aed8e57559586bc6929e35156dc008a557667e091b397326de1e7761974e15
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7b65de3c1a58ca078e28905e3e9662007ad468c49e03d20e242da8aa8051f5d
+oid sha256:0626a246d13395a9877c91b22bf6a0f72175fad53fd6059f030223195ba01ced
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f794552decd9aa76ab29a20764126af04a4c938707d8fa5c1d538d8352460007
+oid sha256:5256258c422cade61a05f9b7acf2463558d18db9447187b4d8690b3bca3e867f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003413801511826384,
+  "epoch": 0.0063399170933918555,
   "eval_steps": 5,
-  "global_step": 21,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -96,6 +96,72 @@
       "learning_rate": 0.0002,
       "loss": 0.0,
       "step": 21
+    },
+    {
+      "epoch": 0.003901487442087296,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.004064049418840933,
+      "eval_loss": NaN,
+      "eval_runtime": 61.2878,
+      "eval_samples_per_second": 42.276,
+      "eval_steps_per_second": 21.146,
+      "step": 25
+    },
+    {
+      "epoch": 0.0043891733723482075,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.00487685930260912,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.00487685930260912,
+      "eval_loss": NaN,
+      "eval_runtime": 60.2721,
+      "eval_samples_per_second": 42.988,
+      "eval_steps_per_second": 21.502,
+      "step": 30
+    },
+    {
+      "epoch": 0.0053645452328700315,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0056896691863773064,
+      "eval_loss": NaN,
+      "eval_runtime": 60.3314,
+      "eval_samples_per_second": 42.946,
+      "eval_steps_per_second": 21.481,
+      "step": 35
+    },
+    {
+      "epoch": 0.005852231163130944,
+      "grad_norm": NaN,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0063399170933918555,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 39
     }
   ],
   "logging_steps": 3,
@@ -110,12 +176,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1016108698042368.0,
+  "total_flos": 1899155542769664.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null