Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7959cae58e80bd0fb8d60d65a45f63b1f579738614b5db62741600cc49fa2268
+oid sha256:658f76f9f3e7518ee1b0cee4f0c37022c796c19340ce6cebc22df44d94819f37
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c94ac4108c23214031109b0807c6e70cfc2cf7ab70e771d0b1c98216fc96d2f
+oid sha256:2747f099862a54e623c5fb9e95a4e71c3d024d1049d07b75c3d5de709f49a5e4
 size 48260756

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": 0.024489795918367346,
+  "epoch": 0.0326530612244898,
   "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": 28.096,
       "eval_steps_per_second": 14.048,
       "step": 15
+    },
+    {
+      "epoch": 0.026122448979591838,
+      "grad_norm": 4.279781341552734,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 14.0078,
+      "step": 16
+    },
+    {
+      "epoch": 0.027755102040816326,
+      "grad_norm": 4.18499231338501,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 12.4355,
+      "step": 17
+    },
+    {
+      "epoch": 0.029387755102040815,
+      "grad_norm": 4.630531311035156,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 12.957,
+      "step": 18
+    },
+    {
+      "epoch": 0.031020408163265307,
+      "grad_norm": 4.716670513153076,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 13.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.0326530612244898,
+      "grad_norm": 5.805507183074951,
+      "learning_rate": 0.0,
+      "loss": 14.8984,
+      "step": 20
+    },
+    {
+      "epoch": 0.0326530612244898,
+      "eval_loss": 0.8439657688140869,
+      "eval_runtime": 36.6541,
+      "eval_samples_per_second": 28.155,
+      "eval_steps_per_second": 14.078,
+      "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": 2.096811938414592e+16,
+  "total_flos": 2.802881264615424e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null