Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bbaec19efb64fdbff88b6d715adee9e2871c20fa86828befa335053f4ba3924
+oid sha256:b2eb39c82b7e4463fa912d4bc5cb0f55a7b86f995807fa95776df7a357b33876
 size 684272496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e405cb3a57a3f99e1b936fb48e373e6363d394a0629ecb421d0f277e27918958
+oid sha256:ec363bab102cfe9d24e2771ff8572dc26bf9e81c829c41427c47894b1fd6572f
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2569b8843c8005365c4198b2d30ca0a109afe93a67c8e9ae4255460f521ed82
+oid sha256:22c8616035b67b9f26d3fb98e938253aafd82c5970a05709498268630502a4d3
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0681b36578a1688994f6fd5decaf01633a0ce062d702bffa0ee6216dfc94b7e
+oid sha256:aa2ba6fd1f3e0a9a6776739b89b29c802b0eb1b27f0b72172ef282304348380b
 size 14512

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": 0.04091025313219126,
+  "epoch": 0.05454700417625501,
   "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": 11.253,
       "eval_steps_per_second": 2.816,
       "step": 15
+    },
+    {
+      "epoch": 0.04363760334100401,
+      "grad_norm": 3.428504705429077,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.197,
+      "step": 16
+    },
+    {
+      "epoch": 0.046364953549816755,
+      "grad_norm": 2.601438283920288,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.1705,
+      "step": 17
+    },
+    {
+      "epoch": 0.0490923037586295,
+      "grad_norm": 2.918519973754883,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1809,
+      "step": 18
+    },
+    {
+      "epoch": 0.05181965396744226,
+      "grad_norm": 1.0848146677017212,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1384,
+      "step": 19
+    },
+    {
+      "epoch": 0.05454700417625501,
+      "grad_norm": 0.06631074100732803,
+      "learning_rate": 0.0,
+      "loss": 0.1314,
+      "step": 20
+    },
+    {
+      "epoch": 0.05454700417625501,
+      "eval_loss": 0.13964733481407166,
+      "eval_runtime": 219.3967,
+      "eval_samples_per_second": 11.258,
+      "eval_steps_per_second": 2.817,
+      "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": 3.1366013018701824e+17,
+  "total_flos": 4.182135069160243e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null