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:eb56d32bb37774bec306b90fa3be47e97cc6458e77ff78bf8b13210320d9629a
+oid sha256:591476412675b9780b51b6589529a2e599261875ae4cfc25c704aa18d917bcb2
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4da3bece2c27b9cc63a7140ef00a6427e6b154e7cf1f8257777d47f5deb9124b
+oid sha256:3db5ff2704e3804876448cf429e9ca0c21fd6ae139daef4a88809c59e9d88bb8
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 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": 0.05488223187742968,
+  "epoch": 0.07317630916990624,
   "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": 39.193,
       "eval_steps_per_second": 19.639,
       "step": 15
+    },
+    {
+      "epoch": 0.058541047335924995,
+      "grad_norm": 1.4047224521636963,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.121,
+      "step": 16
+    },
+    {
+      "epoch": 0.06219986279442031,
+      "grad_norm": 1.4101364612579346,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.138,
+      "step": 17
+    },
+    {
+      "epoch": 0.06585867825291562,
+      "grad_norm": 1.18840754032135,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0061,
+      "step": 18
+    },
+    {
+      "epoch": 0.06951749371141093,
+      "grad_norm": 1.0608042478561401,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.044,
+      "step": 19
+    },
+    {
+      "epoch": 0.07317630916990624,
+      "grad_norm": 1.103515625,
+      "learning_rate": 0.0,
+      "loss": 1.0507,
+      "step": 20
+    },
+    {
+      "epoch": 0.07317630916990624,
+      "eval_loss": 1.0364336967468262,
+      "eval_runtime": 11.7584,
+      "eval_samples_per_second": 39.206,
+      "eval_steps_per_second": 19.646,
+      "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": 1.14665484976128e+16,
+  "total_flos": 1.52887313301504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null