Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75626c5f2e0f8aaab8ceadc55f0c38d2b548da8bc191653637ca455fbdd88eb2
+oid sha256:7b3b322d48990102c846aeaa254865304fc12fdd04bd2695a869145afbbafcef
 size 8077608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad74caba41e61db43e7c9423a4d998393851928b64a5ec7fb81bafb5e98d1ecd
+oid sha256:a163a6a4f3ae2483392abae667e1f619616855be905766e4419802a14300e906
 size 4052500

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5be14051bc6f4cf47091c382526d0b0c0e575985613375394c26c4e042510c6f
+oid sha256:8be460958fd67a6cc36478b0111a9393689e424a2f53f1649e6170ef98e1f9fe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0044,
+  "epoch": 0.006,
   "eval_steps": 500,
-  "global_step": 220,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -84,6 +84,34 @@
       "learning_rate": 1.1e-05,
       "loss": 4.9724,
       "step": 220
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 98.215087890625,
+      "learning_rate": 1.2e-05,
+      "loss": 4.4447,
+      "step": 240
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 92.3516845703125,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 4.9076,
+      "step": 260
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 150.6816864013672,
+      "learning_rate": 1.4e-05,
+      "loss": 4.8402,
+      "step": 280
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 162.9401397705078,
+      "learning_rate": 1.5e-05,
+      "loss": 4.9279,
+      "step": 300
     }
   ],
   "logging_steps": 20,
@@ -91,7 +119,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 72982980575232.0,
+  "total_flos": 102518254952448.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null