Training in progress, step 240, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f96b7c71372582451a8856d4292de48642291473692ec963deff5ab833b885c
+oid sha256:cc8fd63357e965db07708c36a2a6ae6a6c03fc9d02bf6c61fc572c8f7b789e81
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d3cd83379ee9a0b75766a6d2fa05de4b0412e196e40c20ae17db8468a2a4f74
+oid sha256:feaefc33b89d5098807e8eae0d0a7015b62dd9813ee04ec553624e04230f3ead
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:982ef721154bc6d11d2c93bcbf72ab00515e1bf0940ca62b8577a5bfc9ad31eb
+oid sha256:8ef207b513398f9a5cd5415aae0d38d9a46813960e1af4ca47c167d0338fb7a0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b11a25e8c3f6d77fc413c8d381545b6c097ced995430c3981be2b0781bd184
+oid sha256:343e65a0194c6a62b1ee6752dea639ee422801e05f7e64962871b691822c4617
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07871198568872988,
+  "epoch": 0.08586762075134168,
   "eval_steps": 500,
-  "global_step": 220,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -183,14 +183,30 @@
       "loss": 0.4545,
       "num_input_tokens_seen": 147677,
       "step": 220
+    },
+    {
+      "epoch": 0.08228980322003578,
+      "grad_norm": 0.28675127029418945,
+      "learning_rate": 0.00018354203935599286,
+      "loss": 0.4814,
+      "num_input_tokens_seen": 154847,
+      "step": 230
+    },
+    {
+      "epoch": 0.08586762075134168,
+      "grad_norm": 0.31572216749191284,
+      "learning_rate": 0.00018282647584973166,
+      "loss": 0.446,
+      "num_input_tokens_seen": 162267,
+      "step": 240
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 147677,
+  "num_input_tokens_seen": 162267,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3320734224623616.0,
+  "total_flos": 3648811801614336.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null