Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0689e666d1bd66454d6cba95201ca9d3eec871d2e6b3b6de0451fa5fd6274238
+oid sha256:1a94bd6a59dc7851c7932f18bdd98f393a187f19442f574b7a804d3d1c59b11c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39f088e1fc8badf64198f3f6c8295ebe0fccb48bc91b175f96012f4706c3b419
+oid sha256:7cf4d338a705553fc69a897481f7c91c4b6b6225a88d7079103e850e85e8961c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a39a41f912d3765e4194e7bf2d118cba79dcbe423e3417f95fa83853160b690
+oid sha256:fdde6ac87a64995609da02d0ac08c227f29316a78167a5224ca4e6df927f97ad
 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": 0.0007215137358177456,
+  "epoch": 0.0009620183144236609,
   "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": 41.504,
       "eval_steps_per_second": 20.752,
       "step": 15
+    },
+    {
+      "epoch": 0.0007696146515389287,
+      "grad_norm": 1.8937203884124756,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.4878,
+      "step": 16
+    },
+    {
+      "epoch": 0.0008177155672601117,
+      "grad_norm": 2.0600931644439697,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.581,
+      "step": 17
+    },
+    {
+      "epoch": 0.0008658164829812948,
+      "grad_norm": 1.9563463926315308,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.4161,
+      "step": 18
+    },
+    {
+      "epoch": 0.0009139173987024778,
+      "grad_norm": 2.333648204803467,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 3.2874,
+      "step": 19
+    },
+    {
+      "epoch": 0.0009620183144236609,
+      "grad_norm": 2.211129903793335,
+      "learning_rate": 0.0,
+      "loss": 3.4981,
+      "step": 20
+    },
+    {
+      "epoch": 0.0009620183144236609,
+      "eval_loss": 3.6328890323638916,
+      "eval_runtime": 1003.4934,
+      "eval_samples_per_second": 34.893,
+      "eval_steps_per_second": 17.447,
+      "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": 1.109738548887552e+16,
+  "total_flos": 1.479651398516736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null