Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed0466fca68da94dfa3d3d8865ddf941cf2083f32d067ee62f18d6a428dbe72
+oid sha256:f6f429f22f4147a81a4268af380b08f3a69ee523e6599cc6fdc7fb36aab25845
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9b6804656660c8134448e216e28ee63734fb97c5194956390c535ab7bea1a1
+oid sha256:102c5ba5a221148005386de0a2b710da8eb39b39b5f46b2baf873313d6c6c9e2
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96aa2f6932796a349a4e1bc725d9730f67302650fffb525e3d0acc18afed398e
+oid sha256:7734cb6e1786e57532cc69e3ce2c2aeac52a5aa1aa29a95d90dfddc0cb91ddb3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009754041605202156,
+  "epoch": 0.010837824005780173,
   "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": 7.039,
       "eval_steps_per_second": 0.88,
       "step": 81
+    },
+    {
+      "epoch": 0.010115302405394828,
+      "grad_norm": 11.89443588256836,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 5.465,
+      "step": 84
+    },
+    {
+      "epoch": 0.0104765632055875,
+      "grad_norm": 13.721631050109863,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 5.8636,
+      "step": 87
+    },
+    {
+      "epoch": 0.010837824005780173,
+      "grad_norm": 13.445150375366211,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 5.7462,
+      "step": 90
+    },
+    {
+      "epoch": 0.010837824005780173,
+      "eval_loss": 1.4135538339614868,
+      "eval_runtime": 1984.5973,
+      "eval_samples_per_second": 7.048,
+      "eval_steps_per_second": 0.881,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.278142184920187e+17,
+  "total_flos": 2.5312690943557632e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null