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:bbddf4e00159827e50b3da63f7ad7c89208bc8d8e251a7c4a407c804c54b9398
+oid sha256:a46c01071526778f5a08e4fa7f1357f682633a0f427d779957fc980493047fbe
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2fcc9d5ad7fddfc130eb4ca0e09afed81ff7e53bf6e38f128ffa3f735a244f6
+oid sha256:bb564e440fcfdc04f31a85466885154db2d7a54793f040cebf9dc7ee72eda154
 size 21505540

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": 0.25316455696202533,
+  "epoch": 0.33755274261603374,
   "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": 71.587,
       "eval_steps_per_second": 35.793,
       "step": 15
+    },
+    {
+      "epoch": 0.270042194092827,
+      "grad_norm": 0.7985799908638,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.7817,
+      "step": 16
+    },
+    {
+      "epoch": 0.2869198312236287,
+      "grad_norm": 0.8057142496109009,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.8432,
+      "step": 17
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 0.9057028293609619,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.9959,
+      "step": 18
+    },
+    {
+      "epoch": 0.3206751054852321,
+      "grad_norm": 0.8086792826652527,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.853,
+      "step": 19
+    },
+    {
+      "epoch": 0.33755274261603374,
+      "grad_norm": 0.7937332987785339,
+      "learning_rate": 0.0,
+      "loss": 1.9697,
+      "step": 20
+    },
+    {
+      "epoch": 0.33755274261603374,
+      "eval_loss": 1.9533212184906006,
+      "eval_runtime": 1.3964,
+      "eval_samples_per_second": 71.613,
+      "eval_steps_per_second": 35.807,
+      "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": 3075598583857152.0,
+  "total_flos": 4100798111809536.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null