Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af15712c0a3794e9c1d0a4647d80824418034babf4a3bb3b12da49cbbd4591f
+oid sha256:3deef287322f16442c1af0f3d4759b9b94c49d764bad6a816bfce60d94c71c48
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d3ec05dc2a420e6b6f433431a7210a9f8b5b939c17e338af4fcfd032a22568f
+oid sha256:9a85f3add41e11299940edf2dafaca2ba6ad73c89a200523cd8908a1bc1c8968
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf5ebe402c7dce97f342040c0f0b95bb1430955f10f0a17d27e4f469c8ee708
+oid sha256:1a1443ffb31b9a8cbe553da1fd18b9036abf1404b7fdd8944cbae23f4aedcc22
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84612bd3f396f7cad2af4e3f356db64f473c832d56581301631417d37a7919d2
+oid sha256:b7ef7e01c7f7e481304676211a797020a963cacd6c94a5e1c27d96b74a321887
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03577817531305903,
+  "epoch": 0.04293381037567084,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,14 +87,30 @@
       "loss": 0.4824,
       "num_input_tokens_seen": 66414,
       "step": 100
+    },
+    {
+      "epoch": 0.03935599284436494,
+      "grad_norm": 0.35169002413749695,
+      "learning_rate": 0.00019212880143112702,
+      "loss": 0.4863,
+      "num_input_tokens_seen": 73451,
+      "step": 110
+    },
+    {
+      "epoch": 0.04293381037567084,
+      "grad_norm": 0.4088020324707031,
+      "learning_rate": 0.00019141323792486585,
+      "loss": 0.4792,
+      "num_input_tokens_seen": 81934,
+      "step": 120
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 66414,
+  "num_input_tokens_seen": 81934,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1493416326131712.0,
+  "total_flos": 1842406318927872.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null