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:d44c86ac356afc443874892db01cda8d2bbb7f04f7e41a7ee82183c4e1e6ccee
+oid sha256:8f8b25056511a713e5b946420be665399db84662469d766b08b7cbf9320b0f18
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:febecf298772c2ce98fde1042b8ec899449c630715af4013d994835a57b15cda
+oid sha256:c61400285cddee9dec9be9c4efee8008b3a0270795fcfc390f3a58f971218f56
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c5b727e8d040df121a56214476a43c2a47e2acac6bd189ce71cc582be22cfbf
+oid sha256:8232ccc1cbb69b33c2e42be9ca4a449e1397688de60f4e79b3017bc139a030cf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.30927835051546393,
+  "epoch": 0.3402061855670103,
   "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": 35.213,
       "eval_steps_per_second": 4.455,
       "step": 90
+    },
+    {
+      "epoch": 0.31958762886597936,
+      "grad_norm": 2.0875370502471924,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 7.8852,
+      "step": 93
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 2.3906922340393066,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 7.884,
+      "step": 96
+    },
+    {
+      "epoch": 0.3402061855670103,
+      "grad_norm": 1.9967540502548218,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 7.6559,
+      "step": 99
+    },
+    {
+      "epoch": 0.3402061855670103,
+      "eval_loss": 1.9455057382583618,
+      "eval_runtime": 13.7004,
+      "eval_samples_per_second": 35.765,
+      "eval_steps_per_second": 4.525,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5961239922475008.0,
+  "total_flos": 6507307701633024.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null