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:a18ef6ef584da33c04a332bd6ae737c6bed91f6929ba202d96b2a699a690c0f1
+oid sha256:f7a0c177aa431a5dc9528a6db36f318d326cf96918719b89b2cac4a8bda17876
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2785d20564bbf6dea90bf9a5aa2a7a66f427ac50bb4c322ca96b414b4f5f00e
+oid sha256:a9e3f0294bdf25a041dcae3ab48b6c887919c916fde7f8865b8bdf3ea9ddcdb2
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e937940b4c50d2c34688c1733687d397eafe869f24c05dab544ae1f63e72c7
+oid sha256:981ce7b7f67cafb9cfb2187e425baa18fa619b690db2bc6f72fd17da307986ed
 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": 0.18045112781954886,
+  "epoch": 0.24060150375939848,
   "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": 14.107,
       "eval_steps_per_second": 7.054,
       "step": 15
+    },
+    {
+      "epoch": 0.1924812030075188,
+      "grad_norm": 8.766792297363281,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 25.016,
+      "step": 16
+    },
+    {
+      "epoch": 0.20451127819548873,
+      "grad_norm": 5.95711612701416,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 21.8665,
+      "step": 17
+    },
+    {
+      "epoch": 0.21654135338345865,
+      "grad_norm": 6.319004535675049,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 22.8829,
+      "step": 18
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 4.247712135314941,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 20.6744,
+      "step": 19
+    },
+    {
+      "epoch": 0.24060150375939848,
+      "grad_norm": 3.0739986896514893,
+      "learning_rate": 0.0,
+      "loss": 20.0761,
+      "step": 20
+    },
+    {
+      "epoch": 0.24060150375939848,
+      "eval_loss": 1.3583178520202637,
+      "eval_runtime": 9.9315,
+      "eval_samples_per_second": 14.097,
+      "eval_steps_per_second": 7.048,
+      "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": 4.0768408387584e+16,
+  "total_flos": 5.4357877850112e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null