Training in progress, step 320, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b3b322d48990102c846aeaa254865304fc12fdd04bd2695a869145afbbafcef
+oid sha256:5f783b68bc77d003b2ec2afb55e3fb0efe7ee75df1d06ba594d78823f698ccfe
 size 8077608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a163a6a4f3ae2483392abae667e1f619616855be905766e4419802a14300e906
+oid sha256:5da3725baf6ae3fc5ba109f906586a34cd88ba766fbb6ad5c773ae39077b66be
 size 4052500

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be460958fd67a6cc36478b0111a9393689e424a2f53f1649e6170ef98e1f9fe
+oid sha256:ac7e5dca6ac0db5488e28541bc9506788bda445f4514abf096440be8842962c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006,
+  "epoch": 0.0064,
   "eval_steps": 500,
-  "global_step": 300,
+  "global_step": 320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,13 @@
       "learning_rate": 1.5e-05,
       "loss": 4.9279,
       "step": 300
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 38.77900695800781,
+      "learning_rate": 1.6e-05,
+      "loss": 4.5021,
+      "step": 320
     }
   ],
   "logging_steps": 20,
@@ -119,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 102518254952448.0,
+  "total_flos": 110841162694656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null