Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fe6b87f0c2d2b38a04ccd8bcf087024b0fbd246af0ed037e1db4adaa5645407
+oid sha256:86f922f77057556ba0bcabd0b984085fc186027ffbdf3beefa3e31272d00f7a7
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd4d97059c6a7b6a744ec3f8469782d238205b106c165d8aa25bae5d21156fdb
+oid sha256:8b7fa13844fc30bb2c5c5bf9d11b0a7264158fed85f36fb2d18ed9bbd8862985
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1ca0d26190b1d4e36bc64722c1d3a15d4fbcf10b0297979d5b1a5e865c30f2
+oid sha256:acb51c4fb3a634956d61a25a3ca8fe7d5dc2947935cdb108666d882979263988
 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": 0.008207934336525308,
+  "epoch": 0.016415868673050615,
   "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": 24.879,
       "eval_steps_per_second": 12.44,
       "step": 3
+    },
+    {
+      "epoch": 0.01094391244870041,
+      "grad_norm": 1.6845327615737915,
+      "learning_rate": 8e-05,
+      "loss": 9.9813,
+      "step": 4
+    },
+    {
+      "epoch": 0.013679890560875513,
+      "grad_norm": 1.4942121505737305,
+      "learning_rate": 0.0001,
+      "loss": 8.2704,
+      "step": 5
+    },
+    {
+      "epoch": 0.016415868673050615,
+      "grad_norm": 1.735281229019165,
+      "learning_rate": 0.00012,
+      "loss": 8.8551,
+      "step": 6
+    },
+    {
+      "epoch": 0.016415868673050615,
+      "eval_loss": 2.2669334411621094,
+      "eval_runtime": 6.3486,
+      "eval_samples_per_second": 24.257,
+      "eval_steps_per_second": 12.129,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 610774925967360.0,
+  "total_flos": 1099394866741248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null