Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d363aab2cad4d7db15cbfd3dbe5933521e7425a2fb71e28fe019cb5ad6a2c99d
+oid sha256:a7fae7fd7b7097062d598f7e39173c3be076fd38a518e39695d38611e173e616
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3306f2558f6182c9506d657952d8bac2b10e71f2bf1effb51273cb964cd74814
+oid sha256:503f7d70ed87b1b9116e473527994a439b84afd2922b7fe9e9c8ca07d7ce6011
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f50c1df64e9ce923fa951132672a9eccab9dbb4efd31b4e472192d95d27dcc
+oid sha256:f86d923ec2b558f5a06989b166ae0440604c2186db868315a47068592d49bc28
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3431a81202c958c235de795f85761ea057de30471de243268f4bbd98ce19acd6
+oid sha256:64f64992c1d4407619f94c2bf93637b1c409030cc8fc813c98252feafc612aaf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02146690518783542,
+  "epoch": 0.028622540250447227,
   "eval_steps": 500,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -55,14 +55,30 @@
       "loss": 0.4738,
       "num_input_tokens_seen": 40074,
       "step": 60
+    },
+    {
+      "epoch": 0.025044722719141325,
+      "grad_norm": 0.33517029881477356,
+      "learning_rate": 0.00019499105545617174,
+      "loss": 0.4907,
+      "num_input_tokens_seen": 47194,
+      "step": 70
+    },
+    {
+      "epoch": 0.028622540250447227,
+      "grad_norm": 0.34275758266448975,
+      "learning_rate": 0.00019427549194991057,
+      "loss": 0.4642,
+      "num_input_tokens_seen": 53439,
+      "step": 80
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 40074,
+  "num_input_tokens_seen": 53439,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 901122742996992.0,
+  "total_flos": 1201654395942912.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null