Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97e3286d352aed964add151b5ea1e343330c6ac5054feea0736e430283600e74
+oid sha256:174102fdeae227a3f006707777007e94001646902857074ac1129de6aa27206e
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9516a90fca6d1316a1982fd32b7aa87a098f4e423b466899d02e2d564bdb07e
+oid sha256:c01531964f8d38f3dfb8ad8d8f44233080a9457a5105026a65dfe584f4f45279
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81426847bf34c4e471703157b82b946d91e931d0f757d2fd1092f7f033c18482
+oid sha256:c171e0e776a85a54169fd84c081403ed194b289817efff5244302663347649d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
+oid sha256:7041fa0be7432c15ac468c1425bc3b5d595e4b5b769cfa7728743ab80ef12291
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.616771866546438,
+  "epoch": 2.8764652840396754,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 1.848,
       "eval_steps_per_second": 0.932,
       "step": 90
+    },
+    {
+      "epoch": 2.703336339044184,
+      "grad_norm": 10.809871673583984,
+      "learning_rate": 3.7544763546352834e-06,
+      "loss": 37.0722,
+      "step": 93
+    },
+    {
+      "epoch": 2.78990081154193,
+      "grad_norm": 11.037607192993164,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 35.8129,
+      "step": 96
+    },
+    {
+      "epoch": 2.8764652840396754,
+      "grad_norm": 10.600300788879395,
+      "learning_rate": 7.709637592770991e-08,
+      "loss": 35.964,
+      "step": 99
+    },
+    {
+      "epoch": 2.8764652840396754,
+      "eval_loss": 1.3585889339447021,
+      "eval_runtime": 63.2827,
+      "eval_samples_per_second": 1.849,
+      "eval_steps_per_second": 0.932,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.185173438464e+17,
+  "total_flos": 1.01036907823104e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null