Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aac0658232c5c92bca73f4a88889f22b92b298916261c076026e27ee13f910e
+oid sha256:479c05b705ebc5b1ba9b6d67547c1627b07c52d4ac024c2a4903e9544610ecf1
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00660cc7836a1d12e458523f72fe790c385d7c621fcc3e8ddb93ce103fe34564
+oid sha256:981007848c0ff8eded5974d8d52c99622678687cc9cf56628a81cbafc3f833de
 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": 0.05155746509129968,
+  "epoch": 0.06874328678839957,
   "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": 13.088,
       "eval_steps_per_second": 6.544,
       "step": 15
+    },
+    {
+      "epoch": 0.05499462943071966,
+      "grad_norm": 0.7372962832450867,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.4173,
+      "step": 16
+    },
+    {
+      "epoch": 0.058431793770139635,
+      "grad_norm": 0.7817841172218323,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.3822,
+      "step": 17
+    },
+    {
+      "epoch": 0.06186895810955961,
+      "grad_norm": 0.7767869234085083,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.4632,
+      "step": 18
+    },
+    {
+      "epoch": 0.0653061224489796,
+      "grad_norm": 0.7745295166969299,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.4015,
+      "step": 19
+    },
+    {
+      "epoch": 0.06874328678839957,
+      "grad_norm": 0.8225830793380737,
+      "learning_rate": 0.0,
+      "loss": 2.3646,
+      "step": 20
+    },
+    {
+      "epoch": 0.06874328678839957,
+      "eval_loss": 2.3743178844451904,
+      "eval_runtime": 37.5929,
+      "eval_samples_per_second": 13.034,
+      "eval_steps_per_second": 6.517,
+      "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