Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b4091c38dfe36d1d998b9f8c228df7b1e9b7407d62438d52a58ddfce473fb8e
+oid sha256:d363aab2cad4d7db15cbfd3dbe5933521e7425a2fb71e28fe019cb5ad6a2c99d
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c73588560c8a69080f8336901f856b9982346011b066bf0ad41e2ce20951d95
+oid sha256:3306f2558f6182c9506d657952d8bac2b10e71f2bf1effb51273cb964cd74814
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c5a461af89936754c35931f95b98664491a8f9acb3a39a97a78b0e7b57c4c0e
+oid sha256:d7f50c1df64e9ce923fa951132672a9eccab9dbb4efd31b4e472192d95d27dcc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69d738212e5843d2504ae60ce61d4198b9f8df55970cc251ec9a8253d284849
+oid sha256:3431a81202c958c235de795f85761ea057de30471de243268f4bbd98ce19acd6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014311270125223614,
+  "epoch": 0.02146690518783542,
   "eval_steps": 500,
-  "global_step": 40,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,14 +39,30 @@
       "loss": 0.5092,
       "num_input_tokens_seen": 26884,
       "step": 40
+    },
+    {
+      "epoch": 0.017889087656529516,
+      "grad_norm": 0.6744784116744995,
+      "learning_rate": 0.0001964221824686941,
+      "loss": 0.4799,
+      "num_input_tokens_seen": 34831,
+      "step": 50
+    },
+    {
+      "epoch": 0.02146690518783542,
+      "grad_norm": 0.5413841009140015,
+      "learning_rate": 0.00019570661896243293,
+      "loss": 0.4738,
+      "num_input_tokens_seen": 40074,
+      "step": 60
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 26884,
+  "num_input_tokens_seen": 40074,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 604526222057472.0,
+  "total_flos": 901122742996992.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null