Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d017f8ab9df6cf78a2a043d7f0bebef9f4c05ba3b9c855a79d7d717e75bdd628
+oid sha256:bed5f5dd1ffdb028dc4cb52ad89795d269eb7aad76a05750e74eda2d3ccd5a51
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46a535183df4ec7f8bcfe3279d6bf65458287ff4dd0797b9d443af103c87b224
+oid sha256:dfe0f293d59d01dfcf6e1772de552bf8891ecdb6475cf91a0757a05574161cdb
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eee7312ed36813270d0c4465af92d1ab6dcd97ac3785a251ad8cca2bc53326fd
+oid sha256:248b83e156267aeaad0b24a8a39efe5d8e1a4161145b352741eb9e33a27f29d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0050526315789473685,
+  "epoch": 0.010105263157894737,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 86.873,
       "eval_steps_per_second": 43.437,
       "step": 3
+    },
+    {
+      "epoch": 0.006736842105263158,
+      "grad_norm": 31.165403366088867,
+      "learning_rate": 8e-05,
+      "loss": 9.9852,
+      "step": 4
+    },
+    {
+      "epoch": 0.008421052631578947,
+      "grad_norm": 43.4960823059082,
+      "learning_rate": 0.0001,
+      "loss": 10.1151,
+      "step": 5
+    },
+    {
+      "epoch": 0.010105263157894737,
+      "grad_norm": 25.6102352142334,
+      "learning_rate": 0.00012,
+      "loss": 10.5071,
+      "step": 6
+    },
+    {
+      "epoch": 0.010105263157894737,
+      "eval_loss": 2.913226366043091,
+      "eval_runtime": 2.9521,
+      "eval_samples_per_second": 84.685,
+      "eval_steps_per_second": 42.342,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 26318569734144.0,
+  "total_flos": 52637139468288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null