Training in progress, step 9100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3770ccecd860eaef567af11a6ec3b04d13e33c171b98e074f6929c52c14ab5db
+oid sha256:468a053185d605916bf820793d12b24614925085fd9f7a2f4e549894d5f59dae
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fde1105019e6e566af0aeda3ce5519515fc7b06a1547a33aa424d87fdd2151af
+oid sha256:56606a9438fabe4082f5519e609cb92e0fbe7d7afec1ddda2347746ac5262364
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73c81fbff435b662a238d57b3fadd2ee72d676d8e6627b6f9a5ed34c0f07e745
+oid sha256:c2abb20f7f186dacd4425a806114361f63f184fc171798ef008a03511ec36548
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94703c3a4156036807df9d2be447cc51db14ebc6c44453359a3a768c8f5deaa8
+oid sha256:178743d6113fab8b63fed97f6d9317c08986dbdb00366c6482d00ab0e26934b3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7264,
+  "epoch": 0.728,
   "eval_steps": 500,
-  "global_step": 9080,
+  "global_step": 9100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3185,6 +3185,13 @@
       "learning_rate": 1.7944220612429664e-05,
       "loss": 3.4258,
       "step": 9080
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 23.724790573120117,
+      "learning_rate": 1.789656894708132e-05,
+      "loss": 3.4175,
+      "step": 9100
     }
   ],
   "logging_steps": 20,
@@ -3192,7 +3199,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.147530807276339e+16,
+  "total_flos": 2.1519825696129024e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null