Training in progress, step 2120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3612fb6c97d25f57095cd8da238025d105f021876634f942e036be79b23efbc5
+oid sha256:43137dcf390023aa5067a211d636996954c9ca898ec9ee8555959a85c62e7bfe
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57890acb94892b877e4fdf752de51ca28d6d8ba4a8b5ee7ea378f375c626533e
+oid sha256:790c8e59662f43ac84c519659bdaa05cca33252fe4eb1a8e529222ba4b475a33
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671a296d94ac67b9f09b18ab5a94576b53e9c42961d232c595403b7d7a6997ae
+oid sha256:ce8438c68a449ee9662d6e071a644f8c20e7783415ed2d9e7fbb32cddadbcbcc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c427886fe1e96c56c52bab98f8a92bec6316c84f4483ba9d42d61192c219792
+oid sha256:60b6fe67887c52dbf0f864a623d737d0bb3a2cd6bd534693b6fd8d589c2a836a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7513416815742398,
+  "epoch": 0.7584973166368515,
   "eval_steps": 500,
-  "global_step": 2100,
+  "global_step": 2120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1687,14 +1687,30 @@
       "loss": 0.3864,
       "num_input_tokens_seen": 1423004,
       "step": 2100
+    },
+    {
+      "epoch": 0.7549194991055456,
+      "grad_norm": 0.32723429799079895,
+      "learning_rate": 4.901610017889088e-05,
+      "loss": 0.3924,
+      "num_input_tokens_seen": 1429991,
+      "step": 2110
+    },
+    {
+      "epoch": 0.7584973166368515,
+      "grad_norm": 0.37468647956848145,
+      "learning_rate": 4.83005366726297e-05,
+      "loss": 0.3879,
+      "num_input_tokens_seen": 1437151,
+      "step": 2120
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1423004,
+  "num_input_tokens_seen": 1437151,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.199833477505843e+16,
+  "total_flos": 3.231645084645581e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null