Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3d4df4846ce0403472729dc55ecbd3c6c369d9a6847d4dd14ba11a5cde8b60
+oid sha256:6ee8237a11d66d1857c56ed569722289342a78c054e09fb50e7f2c7aa39c5281
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd7bd4ae7ba956596e02a432ed6d1276e6ae7d8a46d2bfed229f8aa1b43e094
+oid sha256:5fea9f655f624a49e56a923ef172258f0c13568cb7c288c4fae52563cdb56af5
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd824ab7bf9f8eea6d9bd6e51d86488e2d9ca4852207360bea549e24419edb8
+oid sha256:2f617907754a3158ebf8e17c619f13e8171c7ed1aa526943456a456051502466
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.914377405024737e-05,
+  "epoch": 0.00013371566107537106,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 25.131,
       "eval_steps_per_second": 12.566,
       "step": 6
+    },
+    {
+      "epoch": 0.00010400106972528861,
+      "grad_norm": 8.097797393798828,
+      "learning_rate": 0.00014,
+      "loss": 9.8669,
+      "step": 7
+    },
+    {
+      "epoch": 0.00011885836540032983,
+      "grad_norm": 7.445133686065674,
+      "learning_rate": 0.00016,
+      "loss": 8.7606,
+      "step": 8
+    },
+    {
+      "epoch": 0.00013371566107537106,
+      "grad_norm": 6.71532678604126,
+      "learning_rate": 0.00018,
+      "loss": 7.8511,
+      "step": 9
+    },
+    {
+      "epoch": 0.00013371566107537106,
+      "eval_loss": 2.059540271759033,
+      "eval_runtime": 1124.6565,
+      "eval_samples_per_second": 25.199,
+      "eval_steps_per_second": 12.599,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1099394866741248.0,
+  "total_flos": 1628733135912960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null