Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:532f0f89cecc224bf3700c9aa484f3cfdc62df04c9f11e6e59c5f55b2359f5f5
+oid sha256:05e1f80cc0cc10a8a81953881186f299d56d93cac657be91df4a0e4a91ba688e
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99d4000fa2bfc42da9c7b4153091e99b0c418f643583fea93bc66e5c090d582a
+oid sha256:9bd7838d34d4b70cf2f052565e56fc000f6c95177cd0add91c5edc7be5c4a5f0
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab010c7e4728fa6256df0a4e6be34f71b99003e4e5282e7d5c75a1c113c74bbe
+oid sha256:1a28d3d72b82f0c7b8998ff975bd3a144879e91f12fe7a904ea1a9d41a2159e4
 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": 0.029873039581777446,
+  "epoch": 0.039830719442369926,
   "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": 14.326,
       "eval_steps_per_second": 7.163,
       "step": 15
+    },
+    {
+      "epoch": 0.03186457555389594,
+      "grad_norm": 1.835963249206543,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 35.5193,
+      "step": 16
+    },
+    {
+      "epoch": 0.03385611152601444,
+      "grad_norm": 1.7558304071426392,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 34.8392,
+      "step": 17
+    },
+    {
+      "epoch": 0.035847647498132934,
+      "grad_norm": 1.7630927562713623,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 34.1804,
+      "step": 18
+    },
+    {
+      "epoch": 0.037839183470251433,
+      "grad_norm": 1.4566975831985474,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 34.0237,
+      "step": 19
+    },
+    {
+      "epoch": 0.039830719442369926,
+      "grad_norm": 1.7513006925582886,
+      "learning_rate": 0.0,
+      "loss": 35.0961,
+      "step": 20
+    },
+    {
+      "epoch": 0.039830719442369926,
+      "eval_loss": 2.1275408267974854,
+      "eval_runtime": 58.9542,
+      "eval_samples_per_second": 14.35,
+      "eval_steps_per_second": 7.175,
+      "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": 3.00791309008896e+16,
+  "total_flos": 4.013189307039744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null