Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc45f662a81cd8da2f3cecda712b0bde184f48920a0b6880ccc83b96ff827a2
+oid sha256:898d6b386bb1c0e3963897c2ed2d1fcd0ac5e63f1032258f17ee42d87dfa22c1
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328edce91614d1e949084d0f0839b97e3cde45034569a6a8b041f56cc7059627
+oid sha256:c46a14ed5aa08816c674541eae30d1993b7fe12a01f2e290dac0b08c097ec37f
 size 14714004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f4f21ebf227d19ef9d4226df0a754a81b16268b7730a8fca801390c48ac89d
+oid sha256:f91788f711a4b886ffc1819cf2dcfe94265eb2cae51ff39ec11a78f7e9bce2a4
 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": 0.4588910133843212,
+  "epoch": 0.6118546845124283,
   "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": 118.289,
       "eval_steps_per_second": 60.22,
       "step": 15
+    },
+    {
+      "epoch": 0.4894837476099426,
+      "grad_norm": 57.453948974609375,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 21.2578,
+      "step": 16
+    },
+    {
+      "epoch": 0.5200764818355641,
+      "grad_norm": 53.67185592651367,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 21.0703,
+      "step": 17
+    },
+    {
+      "epoch": 0.5506692160611855,
+      "grad_norm": 55.76949691772461,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 21.2773,
+      "step": 18
+    },
+    {
+      "epoch": 0.5812619502868069,
+      "grad_norm": 46.442745208740234,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 16.8008,
+      "step": 19
+    },
+    {
+      "epoch": 0.6118546845124283,
+      "grad_norm": 54.886348724365234,
+      "learning_rate": 0.0,
+      "loss": 20.1484,
+      "step": 20
+    },
+    {
+      "epoch": 0.6118546845124283,
+      "eval_loss": 1.225568175315857,
+      "eval_runtime": 0.4457,
+      "eval_samples_per_second": 123.411,
+      "eval_steps_per_second": 62.827,
+      "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": 1792593855774720.0,
+  "total_flos": 2390125141032960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null