Training in progress, step 685, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa4cdb306bf7294222f7b3f970f532c7b4cdc22e6cc372d92a68a5832ae3ac9
+oid sha256:a662f46feddbe2497f49933107c98ff00f401806533aaf98017b0ee6565b00be
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eb132123db17680d8840722840709fbc913fe87e08366059ecb3b185ef779ee
+oid sha256:7d00e266f5b1f45df60e8c44f7e3943273cb57caebf20915b93c9a2bb87831d7
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:477ac7793a58a9aee87e63f0ed0db383646c754c91fbf8cf6726681a3e1bf55c
+oid sha256:ad79945a21a826c0f45869cc500d5d990f1fd3dd860f10e0654ca0015c8252fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59c557a3a19fcbe03c6517f32635519665f582ddfe4481e7465a155c1f572f8b
+oid sha256:b6df9925b4c7f085a8aa1642bfcd531b37d20682fc6e02418e3381af28e29b06
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8799741184082821,
+  "epoch": 0.8864445163377548,
   "eval_steps": 386,
-  "global_step": 680,
+  "global_step": 685,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4783,6 +4783,41 @@
       "learning_rate": 9.340397251217009e-05,
       "loss": 0.8103,
       "step": 680
+    },
+    {
+      "epoch": 0.8812681979941767,
+      "grad_norm": 0.8201668858528137,
+      "learning_rate": 9.338349101318261e-05,
+      "loss": 0.7959,
+      "step": 681
+    },
+    {
+      "epoch": 0.8825622775800712,
+      "grad_norm": 0.814172625541687,
+      "learning_rate": 9.336298001743846e-05,
+      "loss": 0.8074,
+      "step": 682
+    },
+    {
+      "epoch": 0.8838563571659657,
+      "grad_norm": 0.7825469374656677,
+      "learning_rate": 9.33424395388832e-05,
+      "loss": 0.91,
+      "step": 683
+    },
+    {
+      "epoch": 0.8851504367518602,
+      "grad_norm": 0.7842270135879517,
+      "learning_rate": 9.332186959148248e-05,
+      "loss": 0.9331,
+      "step": 684
+    },
+    {
+      "epoch": 0.8864445163377548,
+      "grad_norm": 0.8008681535720825,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.7166,
+      "step": 685
     }
   ],
   "logging_steps": 1,
@@ -4802,7 +4837,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.601972767516262e+17,
+  "total_flos": 7.657869626100941e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null