Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2eb6cc672a6fbb2b89248c42e658196b76139c8581fed0beee6a5457ec199f
+oid sha256:5555eb717158130fc3b91c907f196c1083fde68fe1d95c107af7542d0a5cea54
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0284aad134d312058c58c62ffb3102b45af696a07663de8090315357518fd51
+oid sha256:dc0787487d4791dafe0be7cfd864895b3e9c85acf269b881e53820f2a596b8a9
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693d65ff7d3abbbb13c7ee57d38fa6e7fa5181ebaaabad321dd22b54929bbad4
+oid sha256:04a94b83956618c5f6ad1eb1e148eb701d120c1b0cae59d7acf6b263a4a79491
 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": 5.9766462547595274e-05,
+  "epoch": 8.964969382139291e-05,
   "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": 19.407,
       "eval_steps_per_second": 9.704,
       "step": 6
+    },
+    {
+      "epoch": 6.972753963886115e-05,
+      "grad_norm": 20.417570114135742,
+      "learning_rate": 0.00014,
+      "loss": 26.6501,
+      "step": 7
+    },
+    {
+      "epoch": 7.968861673012702e-05,
+      "grad_norm": 23.798818588256836,
+      "learning_rate": 0.00016,
+      "loss": 22.8077,
+      "step": 8
+    },
+    {
+      "epoch": 8.964969382139291e-05,
+      "grad_norm": 30.659055709838867,
+      "learning_rate": 0.00018,
+      "loss": 18.2496,
+      "step": 9
+    },
+    {
+      "epoch": 8.964969382139291e-05,
+      "eval_loss": 2.7002601623535156,
+      "eval_runtime": 2181.454,
+      "eval_samples_per_second": 19.377,
+      "eval_steps_per_second": 9.688,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1899734583214080.0,
+  "total_flos": 2849601874821120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null