Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3567a20351978770ac2ddab41a45222aaf8eacddadbe4f79a3a84264e5b66df
+oid sha256:0e2181dd8749c7f2a4b43e1e80240b3223812b12ce7fa630b04c69c2008240eb
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4050464a39fdcd67a1c225f1f7ed17858683a265020d5643073a6c63b2ce21d9
+oid sha256:d0ab9bbb167820a3fa51be259c5c1ad6a40387fe8a372289e2b8a3ef17d9f1fc
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22cdbc90fe5ab190ddc8c8d596470e7106be9ee2374df85af28061b6a32f91c4
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02631578947368421,
+  "epoch": 0.05263157894736842,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 122.584,
       "eval_steps_per_second": 61.292,
       "step": 15
+    },
+    {
+      "epoch": 0.031578947368421054,
+      "grad_norm": 0.03512287512421608,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 10.3797,
+      "step": 18
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "eval_loss": 10.377408027648926,
+      "eval_runtime": 1.9724,
+      "eval_samples_per_second": 121.681,
+      "eval_steps_per_second": 60.84,
+      "step": 20
+    },
+    {
+      "epoch": 0.03684210526315789,
+      "grad_norm": 0.06060842052102089,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.3787,
+      "step": 21
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.04713887721300125,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 10.3795,
+      "step": 24
+    },
+    {
+      "epoch": 0.043859649122807015,
+      "eval_loss": 10.376883506774902,
+      "eval_runtime": 1.971,
+      "eval_samples_per_second": 121.765,
+      "eval_steps_per_second": 60.882,
+      "step": 25
+    },
+    {
+      "epoch": 0.04736842105263158,
+      "grad_norm": 0.036685261875391006,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 10.3774,
+      "step": 27
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.04097767546772957,
+      "learning_rate": 0.0,
+      "loss": 10.3791,
+      "step": 30
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "eval_loss": 10.37677001953125,
+      "eval_runtime": 1.9906,
+      "eval_samples_per_second": 120.567,
+      "eval_steps_per_second": 60.284,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 398806155264.0,
+  "total_flos": 823763533824.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null