Training in progress, step 33, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cdbcc1be757c7454cf90fd8aa29b25f5b0cca0be808f5588f79a4bd983a1136
+oid sha256:9a0793caa5ab5038e253a0eac6bfce6d50955c7e414023d4c1136b34713d9052
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d39749903c89e821928055ae51ff744c6e300cd5b6165ac2991abdd78d8d9528
+oid sha256:e3072800668f2cc12186d7f2cf4f55f2a506d332a2bbcacd7408d4a6328bef60
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594dcf1d063251cca4c3b70569456a468140193c0f517d256489d095068b4748
+oid sha256:4bcb6468c96e42ca9e19eeef69577865d7a693066e16690bd13303c9f6654183
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0057896977437207325,
+  "epoch": 0.01123882503192848,
   "eval_steps": 5,
-  "global_step": 17,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,72 @@
       "eval_samples_per_second": 22.102,
       "eval_steps_per_second": 11.06,
       "step": 15
+    },
+    {
+      "epoch": 0.006130268199233717,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.006811409110259685,
+      "eval_loss": NaN,
+      "eval_runtime": 56.0375,
+      "eval_samples_per_second": 22.075,
+      "eval_steps_per_second": 11.046,
+      "step": 20
+    },
+    {
+      "epoch": 0.007151979565772669,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.008173690932311623,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.008514261387824606,
+      "eval_loss": NaN,
+      "eval_runtime": 55.9379,
+      "eval_samples_per_second": 22.114,
+      "eval_steps_per_second": 11.066,
+      "step": 25
+    },
+    {
+      "epoch": 0.009195402298850575,
+      "grad_norm": NaN,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.010217113665389528,
+      "grad_norm": NaN,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.010217113665389528,
+      "eval_loss": NaN,
+      "eval_runtime": 55.6874,
+      "eval_samples_per_second": 22.213,
+      "eval_steps_per_second": 11.116,
+      "step": 30
+    },
+    {
+      "epoch": 0.01123882503192848,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 33
     }
   ],
   "logging_steps": 3,
@@ -88,12 +154,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1175641953140736.0,
+  "total_flos": 2269642103980032.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null