Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c694003c0674367016168e4ae40f6eb6459c625fb8ec47da2881bf5e4dbff47
+oid sha256:454cdef2488a80fbd7e890d123a076678ef7329648eeb90e4ba0abd91557eae7
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85031b384d138750a2e428dda7d9346f27c686643a4bd0ee2def06dd159b954f
+oid sha256:32d73271b94ee122c0719d2adbebd0fe218c1f32604eb251f6863e02f3d6fb66
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0248cc520feddc3a8700d5c1d74bf5fcdcc9f3ab19920b8efcdaee0a2f53112
+oid sha256:3805f0cbb677a42ce39936271647e1d6a97e2afb8aa5dca74e817d1e1a1a6bbd
 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": 0.03446295232624928,
+  "epoch": 0.04595060310166571,
   "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": 44.3,
       "eval_steps_per_second": 22.15,
       "step": 15
+    },
+    {
+      "epoch": 0.03676048248133257,
+      "grad_norm": 69.29478454589844,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 63.1268,
+      "step": 16
+    },
+    {
+      "epoch": 0.039058012636415854,
+      "grad_norm": 70.21276092529297,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 56.9275,
+      "step": 17
+    },
+    {
+      "epoch": 0.04135554279149914,
+      "grad_norm": 66.2811279296875,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 56.5232,
+      "step": 18
+    },
+    {
+      "epoch": 0.043653072946582425,
+      "grad_norm": 64.68504333496094,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 54.7725,
+      "step": 19
+    },
+    {
+      "epoch": 0.04595060310166571,
+      "grad_norm": 59.0147705078125,
+      "learning_rate": 0.0,
+      "loss": 54.5287,
+      "step": 20
+    },
+    {
+      "epoch": 0.04595060310166571,
+      "eval_loss": 3.296483278274536,
+      "eval_runtime": 16.5931,
+      "eval_samples_per_second": 44.235,
+      "eval_steps_per_second": 22.118,
+      "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": 6953496836308992.0,
+  "total_flos": 9317226783965184.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null