Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d98db05f74a397b421aa256cd025bd34fd5366c54b87834887be47a1f99e21
+oid sha256:d96bc0789e155e122eceef18ea0b5c204b3458d35d1e10abc892d5b916db1c53
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dc66a9e34221e9a9a8ff3bc9b152f4b92f88c274545508ec721fab6a26f6b6c
+oid sha256:1f6e236aec4f16087915cad6d69371c7e2af93e13fbb4d029a9185d11b073f02
 size 43122580

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": 0.0033885861124445826,
+  "epoch": 0.004518114816592777,
   "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": 38.034,
       "eval_steps_per_second": 19.017,
       "step": 15
+    },
+    {
+      "epoch": 0.0036144918532742213,
+      "grad_norm": 20.060565948486328,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.59,
+      "step": 16
+    },
+    {
+      "epoch": 0.00384039759410386,
+      "grad_norm": 17.778438568115234,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.3184,
+      "step": 17
+    },
+    {
+      "epoch": 0.004066303334933499,
+      "grad_norm": 16.09156036376953,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.2847,
+      "step": 18
+    },
+    {
+      "epoch": 0.004292209075763138,
+      "grad_norm": 15.134675025939941,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.8811,
+      "step": 19
+    },
+    {
+      "epoch": 0.004518114816592777,
+      "grad_norm": 14.81490707397461,
+      "learning_rate": 0.0,
+      "loss": 2.5459,
+      "step": 20
+    },
+    {
+      "epoch": 0.004518114816592777,
+      "eval_loss": 2.7253942489624023,
+      "eval_runtime": 193.5802,
+      "eval_samples_per_second": 38.516,
+      "eval_steps_per_second": 19.258,
+      "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": 1.109738548887552e+16,
+  "total_flos": 1.479651398516736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null