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:c1080c5ea835ae4ac5b1ffa3ed0ddbff81292fbe88a04979893b31b5931390b5
+oid sha256:5952f40e69787f91cb3b0df1cf32d7ead564624a7f868995d2e86274674ea0bb
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7423f9718317d220a696e6c31af07e73536b84ceb26cef7f8ca3778a55772065
+oid sha256:07184f4230cb88ad4eaa2700725b1ff24d16cbbaa7403709e76b0cb322086ada
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
+oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
 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": 0.0033651149747616375,
+  "epoch": 0.005047672462142457,
   "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": 273.223,
       "eval_steps_per_second": 136.793,
       "step": 6
+    },
+    {
+      "epoch": 0.003925967470555244,
+      "grad_norm": 0.01095384731888771,
+      "learning_rate": 0.00014,
+      "loss": 11.9324,
+      "step": 7
+    },
+    {
+      "epoch": 0.00448681996634885,
+      "grad_norm": 0.005873797461390495,
+      "learning_rate": 0.00016,
+      "loss": 11.9349,
+      "step": 8
+    },
+    {
+      "epoch": 0.005047672462142457,
+      "grad_norm": 0.01113384310156107,
+      "learning_rate": 0.00018,
+      "loss": 11.9287,
+      "step": 9
+    },
+    {
+      "epoch": 0.005047672462142457,
+      "eval_loss": 11.93126106262207,
+      "eval_runtime": 2.6867,
+      "eval_samples_per_second": 279.52,
+      "eval_steps_per_second": 139.946,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 738508800.0,
+  "total_flos": 1092993024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null