Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b483071d6edc7d858cfecf20e7ae727d12dbd209bf181666f2eb776afa43797
+oid sha256:9c925f50ed7de50eeb7b5c2532d551a568884c65aec23dee0552d0fbde5a0c4e
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f248cfb2029cade34eebaa6f0101c7c7aea66c159b059f41923dbf9c5ea2af1
+oid sha256:98f4a9ccaf279d36776b2208e0aabe119b38951dbeac2e8cdd59a85e8810f1fe
 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": 0.012084592145015106,
+  "epoch": 0.02416918429003021,
   "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": 70.577,
       "eval_steps_per_second": 35.625,
       "step": 3
+    },
+    {
+      "epoch": 0.016112789526686808,
+      "grad_norm": 15.097208023071289,
+      "learning_rate": 8e-05,
+      "loss": 15.5187,
+      "step": 4
+    },
+    {
+      "epoch": 0.02014098690835851,
+      "grad_norm": 13.481897354125977,
+      "learning_rate": 0.0001,
+      "loss": 15.1496,
+      "step": 5
+    },
+    {
+      "epoch": 0.02416918429003021,
+      "grad_norm": 15.7518949508667,
+      "learning_rate": 0.00012,
+      "loss": 13.9951,
+      "step": 6
+    },
+    {
+      "epoch": 0.02416918429003021,
+      "eval_loss": 3.5103189945220947,
+      "eval_runtime": 1.5424,
+      "eval_samples_per_second": 68.075,
+      "eval_steps_per_second": 34.361,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22520895897600.0,
+  "total_flos": 45041791795200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null