Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:196f95cca6cbc11c0623202d0547ae8ce3edbbf85408eddd472fc0a9322e86bc
+oid sha256:e351ba6ba23fc48709b74f411c6747b9ec34af6b50a543131803a895605d737d
 size 14293800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:092a303651682189e3b6ff0e1ea66a8ee0ce06a43ff07e467edc428163bb1b12
+oid sha256:c5d20b240d4126432c5d4aaac9f0df488ed8743ac25461aac70d500b3372d8ca
 size 7579748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0746126e4298a9e6856357a0ef8d39e8ac4a1f2267410cc94960e7f6751094
+oid sha256:caa3ce5c9c398fbbcfe5a9c0dc895fa3025b6d4c0279a7f25c66bf7102df8c33
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10938924339106655,
+  "epoch": 0.14585232452142205,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 56.863,
       "eval_steps_per_second": 28.555,
       "step": 15
+    },
+    {
+      "epoch": 0.11668185961713765,
+      "grad_norm": 13.522796630859375,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 18.9883,
+      "step": 16
+    },
+    {
+      "epoch": 0.12397447584320875,
+      "grad_norm": 13.67131233215332,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 19.9258,
+      "step": 17
+    },
+    {
+      "epoch": 0.13126709206927986,
+      "grad_norm": 13.722691535949707,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 19.3438,
+      "step": 18
+    },
+    {
+      "epoch": 0.13855970829535097,
+      "grad_norm": 12.327914237976074,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 17.3555,
+      "step": 19
+    },
+    {
+      "epoch": 0.14585232452142205,
+      "grad_norm": 19.96782684326172,
+      "learning_rate": 0.0,
+      "loss": 20.4375,
+      "step": 20
+    },
+    {
+      "epoch": 0.14585232452142205,
+      "eval_loss": 1.1424343585968018,
+      "eval_runtime": 4.0404,
+      "eval_samples_per_second": 57.172,
+      "eval_steps_per_second": 28.71,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 454459851276288.0,
+  "total_flos": 605317893193728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null