Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a631b49910c23550db48eead58bba4a7d13636fa15e9766da1c24cd439cdc55
+oid sha256:3e150d0b8daa9c910ce0f5410f75861043de09081aa17746e0ebec1b6948564d
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f03f3a9b40e8fd14ac699a3df1b0dec1c5f941db175785e21c59bb9f52c406f
+oid sha256:777f62e92769a37a5cc4e82a9187d6bb1d5b6595a0f88762997783f8cae4bfde
 size 1656058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456bf484f2805c5eb5383d929dec834f74d12009334db2c37db29af2053d4bfc
+oid sha256:0b9c008c53bd43dddd700dd53d4fc40b32330d14b9af4a071419d30caa919a84
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001144001144001144,
+  "epoch": 0.001716001716001716,
   "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": 19.196,
       "eval_steps_per_second": 9.602,
       "step": 6
+    },
+    {
+      "epoch": 0.001334668001334668,
+      "grad_norm": 5814.517578125,
+      "learning_rate": 0.00014,
+      "loss": 338.7343,
+      "step": 7
+    },
+    {
+      "epoch": 0.001525334858668192,
+      "grad_norm": 3193.739501953125,
+      "learning_rate": 0.00016,
+      "loss": 253.8771,
+      "step": 8
+    },
+    {
+      "epoch": 0.001716001716001716,
+      "grad_norm": 4104.44384765625,
+      "learning_rate": 0.00018,
+      "loss": 306.3705,
+      "step": 9
+    },
+    {
+      "epoch": 0.001716001716001716,
+      "eval_loss": 69.6688232421875,
+      "eval_runtime": 69.1077,
+      "eval_samples_per_second": 31.965,
+      "eval_steps_per_second": 15.99,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 53623740432384.0,
+  "total_flos": 80435610648576.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null