Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45f442ab387d10db0afc02ac5eec297eff2612fb838af59e16e7c350238b29d
+oid sha256:0d1dd18c9b3cefa077921600611dc4202347d245406263ac6b50b4437ccbccf9
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e69427bfd24d2a08e8e64b88f877a79fff8c44145725a1b68e3256241aa7d0c
+oid sha256:e907b2cba4d632db7cbe93f905b8e4c9868f50ee7533a02d89880c2465e0266e
 size 50644602

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786260fdd78904017d7c81f817c412170d207360106f34c9aa7989abdd4adcbe
+oid sha256:88476cca778895e8f6fc0ce62e75c4eb34e2a6753b0330ed367b1810fb7506cc
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1a14cf85ed633a4ede0b591f196774f57d0fe8379f999366f42eeb7c7c97c1
+oid sha256:c67987ed9e4b714a7c9a3a18204371980574e6e97487d2f71430eac95201f642
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016506189821182942,
+  "epoch": 0.024759284731774415,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 29.685,
       "eval_steps_per_second": 14.939,
       "step": 6
+    },
+    {
+      "epoch": 0.01925722145804677,
+      "grad_norm": 1.0555391311645508,
+      "learning_rate": 0.00012,
+      "loss": 1.1325,
+      "step": 7
+    },
+    {
+      "epoch": 0.02200825309491059,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 1.009,
+      "step": 8
+    },
+    {
+      "epoch": 0.024759284731774415,
+      "grad_norm": 0.9899677634239197,
+      "learning_rate": 0.00014,
+      "loss": 1.1344,
+      "step": 9
+    },
+    {
+      "epoch": 0.024759284731774415,
+      "eval_loss": 0.988933265209198,
+      "eval_runtime": 5.1614,
+      "eval_samples_per_second": 29.643,
+      "eval_steps_per_second": 14.918,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 613900747800576.0,
+  "total_flos": 920851121700864.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null