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:e39c0d6c258a59a72f139a2611f470e17454f6a513d90eeeea23c3848ff9d72a
+oid sha256:d5c2e3606fecc34fe19cc8330e4e37d820d494b981d1b7ff2ce3d375b51a6087
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e9581944951df25a175ca1528cbe2dfb8c38b1dcd06adc624d02a870c055af6
+oid sha256:74de8fd337367aa82705bc97a8efef46ab683b93b59391fa2527ed31bf8c3337
 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": 0.04496065942300487,
+  "epoch": 0.059947545897339825,
   "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": 41.115,
       "eval_steps_per_second": 20.558,
       "step": 15
+    },
+    {
+      "epoch": 0.04795803671787186,
+      "grad_norm": 0.7655222415924072,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1367,
+      "step": 16
+    },
+    {
+      "epoch": 0.050955414012738856,
+      "grad_norm": 0.7342327833175659,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.091,
+      "step": 17
+    },
+    {
+      "epoch": 0.053952791307605844,
+      "grad_norm": 0.5940383672714233,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.1205,
+      "step": 18
+    },
+    {
+      "epoch": 0.05695016860247284,
+      "grad_norm": 0.6847835183143616,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.1174,
+      "step": 19
+    },
+    {
+      "epoch": 0.059947545897339825,
+      "grad_norm": 0.481279194355011,
+      "learning_rate": 0.0,
+      "loss": 0.0931,
+      "step": 20
+    },
+    {
+      "epoch": 0.059947545897339825,
+      "eval_loss": 0.0961824581027031,
+      "eval_runtime": 13.6934,
+      "eval_samples_per_second": 41.042,
+      "eval_steps_per_second": 20.521,
+      "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": 1.1143624595079168e+16,
+  "total_flos": 1.4842753091371008e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null