Training in progress, step 74, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc30cece14f478e2af613381fbb617ac45fe1974313654d9fb3b322c6fce4b1e
+oid sha256:2917a15aa5ba9682ed53879d4460ede976f2dd3146789e83b893657ff753d790
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:544049c4d232dccd5811f61f406354afbeb3ee63151095cf624b3182f2ab0ce4
+oid sha256:22d1a817857097bae254f7f119849eb180e26964af3ab4f080a5cbfc9303ab97
 size 51418196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af0503fd7fbb1b552a733848d5c4fe83e7d6de89c61f8c3678e5a0147d63b66f
+oid sha256:198e42c83d53a6bf92ca7f7c6034bd499cdf81a23127d9a063c1e0a8bdc7b93d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d249aebe1c6718148a5212a9c894a1a659d316ff657a708e08cb3775b5bc11
+oid sha256:7105a509bdfde59e6e4d893f7ae8de5118e3beb17226743671d553509dc9662b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.877551020408163,
+  "epoch": 3.0510204081632653,
   "eval_steps": 7,
-  "global_step": 70,
+  "global_step": 74,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -256,6 +256,13 @@
       "eval_samples_per_second": 22.366,
       "eval_steps_per_second": 3.195,
       "step": 70
+    },
+    {
+      "epoch": 2.9591836734693877,
+      "grad_norm": 1.8807049989700317,
+      "learning_rate": 2.407636663901591e-07,
+      "loss": 3.7945,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -270,12 +277,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.157856223428608e+16,
+  "total_flos": 5.452590864767386e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null