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:b4d51fb577c1148c2ee6c091f835b7fa639057098eeabf96b1fd40acadb93d43
+oid sha256:4fc34257fd6c62c11c26292ecf24cd0407bc3a2ef7bdf75745a54e133aab81f1
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c3d9acf0fb6360949a67fd4fbf602d729b7e3c91f06c0c24da1dec4431be174
+oid sha256:d14e9fc2fa3fd39d52512ce812309b0ee0833260c4c12cc0dd21c44719197196
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61b1e47da96ff7f3b5e32a51bd467ed133d6e247efd0bfaace248cc5f2f4105
+oid sha256:f7701f88edd66004d4466bf636029979f849065c394232d4daaa3f0dc50a5728
 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": 0.00021247211303516414,
+  "epoch": 0.00042494422607032827,
   "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": 24.376,
       "eval_steps_per_second": 12.188,
       "step": 3
+    },
+    {
+      "epoch": 0.0002832961507135522,
+      "grad_norm": 0.5889267921447754,
+      "learning_rate": 8e-05,
+      "loss": 1.1645,
+      "step": 4
+    },
+    {
+      "epoch": 0.0003541201883919402,
+      "grad_norm": 0.8530604839324951,
+      "learning_rate": 0.0001,
+      "loss": 1.3131,
+      "step": 5
+    },
+    {
+      "epoch": 0.00042494422607032827,
+      "grad_norm": 0.24282629787921906,
+      "learning_rate": 0.00012,
+      "loss": 1.1017,
+      "step": 6
+    },
+    {
+      "epoch": 0.00042494422607032827,
+      "eval_loss": 1.2677675485610962,
+      "eval_runtime": 246.6787,
+      "eval_samples_per_second": 24.104,
+      "eval_steps_per_second": 12.052,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 782715888599040.0,
+  "total_flos": 1400649484861440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null