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:c7abf2175e2f63aa4330f78032916682476b30f8c83334038cbb7b1180ce43d2
+oid sha256:0fc9c0b92f2d7906ff1992c665c2f817e0d35bcb5c7b10e311bbc823b714fe2d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9fef4f775dfeb638f4d3b6471a38bf37e9d7142748285586c320cb1a91e0dd1
+oid sha256:76341ed1fa825a784d73bd5edbc3342b7ddf6e9cc275838515728647dad15a4d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
+oid sha256:83e1d42fa3a43f0b49fecc1fb9869481eef60e0607192a6ff7e39173952f7302
 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": 0.0017052721330112265,
+  "epoch": 0.003410544266022453,
   "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": 29.926,
       "eval_steps_per_second": 14.983,
       "step": 3
+    },
+    {
+      "epoch": 0.002273696177348302,
+      "grad_norm": 1.4716559648513794,
+      "learning_rate": 8e-05,
+      "loss": 2.8779,
+      "step": 4
+    },
+    {
+      "epoch": 0.002842120221685377,
+      "grad_norm": 1.7448276281356812,
+      "learning_rate": 0.0001,
+      "loss": 2.546,
+      "step": 5
+    },
+    {
+      "epoch": 0.003410544266022453,
+      "grad_norm": 1.155127763748169,
+      "learning_rate": 0.00012,
+      "loss": 2.2414,
+      "step": 6
+    },
+    {
+      "epoch": 0.003410544266022453,
+      "eval_loss": 2.4394571781158447,
+      "eval_runtime": 24.8085,
+      "eval_samples_per_second": 29.869,
+      "eval_steps_per_second": 14.955,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1155977655091200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null