Training in progress, step 2480, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bedf1b6d5e32ae60cbf34f929bfa462bde2adec5e00a44530266b9d926cec517
+oid sha256:5d857d487611677e327f686f5bb0b2c412a46dd20a76142f12b663b725d04116
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ab70123d88a30c78dbc1cf668156ef4539a947d64d12664cc583ba9139315b
+oid sha256:ec04c8625fb5e8405492e6ebc4888b578fc58f8848b213588210076bbf8fba0f
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab90daea2cc7962c335eac8ebb5f569b419b5cbc004628f6c9c5c4d750b2fa9b
+oid sha256:55465423aa4bddb0a9699c8aac4197f916d1b1aa5ba2c8f60a7f814d309a283f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c215c6736359b4426fb423f696f85c3a29879ea9d026ccf6cd9e1acb18851c2d
+oid sha256:7285ecba5ee57b8ddee91381a24dda5a0f3ce744a4081805f6d4aba444269721
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8801431127012522,
+  "epoch": 0.8872987477638641,
   "eval_steps": 500,
-  "global_step": 2460,
+  "global_step": 2480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1975,14 +1975,30 @@
       "loss": 0.3874,
       "num_input_tokens_seen": 1668160,
       "step": 2460
+    },
+    {
+      "epoch": 0.8837209302325582,
+      "grad_norm": 0.30337658524513245,
+      "learning_rate": 2.3255813953488374e-05,
+      "loss": 0.3951,
+      "num_input_tokens_seen": 1675594,
+      "step": 2470
+    },
+    {
+      "epoch": 0.8872987477638641,
+      "grad_norm": 0.2993133068084717,
+      "learning_rate": 2.2540250447227194e-05,
+      "loss": 0.3572,
+      "num_input_tokens_seen": 1682014,
+      "step": 2480
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1668160,
+  "num_input_tokens_seen": 1682014,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.751102747312128e+16,
+  "total_flos": 3.782255500921651e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null