Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902502e262414501cd292562b9f544d770e684062e970b58277a53e332ee174a
+oid sha256:bcfed4a7b73c3e52278279d2d1c568d0b6ab1588387c6e6af9931f2f3d1dd9ad
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f359380a5eaea89e574889c437173a2d124339028a7fd2d6b290507afb7500ab
+oid sha256:2e8c0be4e571d656d85f96590d17b93a43fe04aff0986e14024bd33f7c62a00f
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
 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": 0.01312910284463895,
+  "epoch": 0.0262582056892779,
   "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": 365.436,
       "eval_steps_per_second": 184.602,
       "step": 3
+    },
+    {
+      "epoch": 0.0175054704595186,
+      "grad_norm": 0.04674595221877098,
+      "learning_rate": 8e-05,
+      "loss": 10.3633,
+      "step": 4
+    },
+    {
+      "epoch": 0.02188183807439825,
+      "grad_norm": 0.04465850070118904,
+      "learning_rate": 0.0001,
+      "loss": 10.3515,
+      "step": 5
+    },
+    {
+      "epoch": 0.0262582056892779,
+      "grad_norm": 0.05227944254875183,
+      "learning_rate": 0.00012,
+      "loss": 10.3638,
+      "step": 6
+    },
+    {
+      "epoch": 0.0262582056892779,
+      "eval_loss": 10.361228942871094,
+      "eval_runtime": 0.2806,
+      "eval_samples_per_second": 345.638,
+      "eval_steps_per_second": 174.6,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 38792724480.0,
+  "total_flos": 77585448960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null