Training in progress, step 140, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3deef287322f16442c1af0f3d4759b9b94c49d764bad6a816bfce60d94c71c48
+oid sha256:8a4f325fd033a507c13907694cd83ed4dd5598512199bc26a1ea2c561e2da9ff
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a85f3add41e11299940edf2dafaca2ba6ad73c89a200523cd8908a1bc1c8968
+oid sha256:f5c4c911834d7aa1d6fa8a54ac9b83e9b2428c953802fdd31ab64ae361e0dc6b
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a1443ffb31b9a8cbe553da1fd18b9036abf1404b7fdd8944cbae23f4aedcc22
+oid sha256:3c7a6ee6116c3dbc9702a41d4839f08bb22dd133335dc9e279dc28759218f070
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7ef7e01c7f7e481304676211a797020a963cacd6c94a5e1c27d96b74a321887
+oid sha256:3b89886767fbf3bb430f4d52155c956cacde6261e91f36172700564b0debbbfe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04293381037567084,
+  "epoch": 0.05008944543828265,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,14 +103,30 @@
       "loss": 0.4792,
       "num_input_tokens_seen": 81934,
       "step": 120
+    },
+    {
+      "epoch": 0.046511627906976744,
+      "grad_norm": 0.40062326192855835,
+      "learning_rate": 0.00019069767441860466,
+      "loss": 0.4607,
+      "num_input_tokens_seen": 88335,
+      "step": 130
+    },
+    {
+      "epoch": 0.05008944543828265,
+      "grad_norm": 0.5044320225715637,
+      "learning_rate": 0.0001899821109123435,
+      "loss": 0.456,
+      "num_input_tokens_seen": 96192,
+      "step": 140
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 81934,
+  "num_input_tokens_seen": 96192,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1842406318927872.0,
+  "total_flos": 2163018388340736.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null