Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67cbfd447d6dce42f193b54306ae8710ab7704b25231cb6b2f91bc577fe954f1
+oid sha256:9a2b91aa6ca483f4d727f84845bc2e395b80799336360d39235c0d732338cd32
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e85f0afb01f8e94e92c72c31a8b6b8d0dbacbb76e5c5cc53561a768a43ee5e1
+oid sha256:e6753caeb57b7c6e30077bc22f303369c454b404d6b6835b6e73d2b3cd132b5d
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0da2b5f23d3489165028f8d68fa12a6a70080861eda5a5350b82eed3fba589e
+oid sha256:abdf165e69bde774f8fbea9f6c3d36d1ada3cc287696d8d7f1f4bbb7eabb61c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03950737714912816,
+  "epoch": 0.043897085721253504,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 12.13,
       "eval_steps_per_second": 1.518,
       "step": 81
+    },
+    {
+      "epoch": 0.040970613339836606,
+      "grad_norm": 0.38511985540390015,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 0.8136,
+      "step": 84
+    },
+    {
+      "epoch": 0.042433849530545055,
+      "grad_norm": 0.45352721214294434,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 0.8204,
+      "step": 87
+    },
+    {
+      "epoch": 0.043897085721253504,
+      "grad_norm": 0.32951414585113525,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.7356,
+      "step": 90
+    },
+    {
+      "epoch": 0.043897085721253504,
+      "eval_loss": 0.770723819732666,
+      "eval_runtime": 284.6788,
+      "eval_samples_per_second": 12.129,
+      "eval_steps_per_second": 1.517,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3281735173210112e+17,
+  "total_flos": 1.4819620298529178e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null