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:cc4686983b37bec8223e73524ae716a13ec48ff4d26053b07aac639c1976d874
+oid sha256:fd5e086f2896422b85f59fcbd1db75d227348793001b9ac33cef8d43670650a6
 size 40036040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f0ea7967420b595acdeeb10bff627cdc616fdac77c4d8f473d696610aea1e12
+oid sha256:b61b12642b3cf0be8c1052822a4060340d8cd4154a22b75f94eadcf4e66203dd
 size 20814996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e80e63932c8eae7c99e68576eba41b28c2be6da6d5728e9d2106b0941dfcd24
+oid sha256:ea91e2232be6ed0d6bb5c1b35bf8899f30c3c095cf9d69df4b43d597a5a5de3f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011124501715027348,
+  "epoch": 0.014832668953369797,
   "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": 7.977,
       "eval_steps_per_second": 7.977,
       "step": 15
+    },
+    {
+      "epoch": 0.011866135162695838,
+      "grad_norm": 12.487533569335938,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.643,
+      "step": 16
+    },
+    {
+      "epoch": 0.012607768610364327,
+      "grad_norm": 16.057682037353516,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.3111,
+      "step": 17
+    },
+    {
+      "epoch": 0.013349402058032818,
+      "grad_norm": 15.11005687713623,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.0926,
+      "step": 18
+    },
+    {
+      "epoch": 0.014091035505701307,
+      "grad_norm": 14.691518783569336,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 1.8223,
+      "step": 19
+    },
+    {
+      "epoch": 0.014832668953369797,
+      "grad_norm": 28.493478775024414,
+      "learning_rate": 0.0,
+      "loss": 3.0463,
+      "step": 20
+    },
+    {
+      "epoch": 0.014832668953369797,
+      "eval_loss": 0.34163063764572144,
+      "eval_runtime": 71.2174,
+      "eval_samples_per_second": 7.976,
+      "eval_steps_per_second": 7.976,
+      "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": 1219719793213440.0,
+  "total_flos": 1626293057617920.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null