Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:639802b07a73c4c37938a525f2d9fc88f0a7eb4bd1543c051cca9b6239e22555
+oid sha256:10a6a1ffd64f7e05989c88da7f083032e30095579a92a376504f200c0e4fe511
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de29cc3fe869959b369942326c7022f322662eeb1fc97731915f64dbd515353d
+oid sha256:eb818be4e19bb55e58e93748844a948c4857805febaf9a0d775da2c57164b3ea
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57283b2cb15d73abd29e2e952b56c116434f132b756b633c772b7f4d8e5b05a5
+oid sha256:6463ff3f0292c2f4dc253548d03eb324fc2ec5143a5cd37816a281f3c32c0ff4
 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": 0.0002204707049550791,
+  "epoch": 0.0004409414099101582,
   "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": 135.617,
       "eval_steps_per_second": 67.808,
       "step": 3
+    },
+    {
+      "epoch": 0.00029396093994010547,
+      "grad_norm": 7.31413459777832,
+      "learning_rate": 8e-05,
+      "loss": 14.0422,
+      "step": 4
+    },
+    {
+      "epoch": 0.0003674511749251318,
+      "grad_norm": 9.078619956970215,
+      "learning_rate": 0.0001,
+      "loss": 14.5767,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004409414099101582,
+      "grad_norm": 6.94755220413208,
+      "learning_rate": 0.00012,
+      "loss": 13.9467,
+      "step": 6
+    },
+    {
+      "epoch": 0.0004409414099101582,
+      "eval_loss": 3.443692684173584,
+      "eval_runtime": 43.1827,
+      "eval_samples_per_second": 132.692,
+      "eval_steps_per_second": 66.346,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6368853491712.0,
+  "total_flos": 12737706983424.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null