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:a01fc0b5aa9b24bb603baa06c9bbc6618e9160faa305e3b387707a3b7907d978
+oid sha256:4887da4add908014cd983f4445d2b947544b120bff63f066248572301af9eb42
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d0214725796057b273c27bd8afc1e2bb4a776953fe5629aa13a377deda5bb4
+oid sha256:2590de21df2c71616d6c80ea30cafee07f8b78aa4f6eb5fe0bc948b73937c0c0
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cfaa812e4e772e2bea19a70de52bcb51d93084a77c635a5159573155257182c
+oid sha256:d15fe51fa3cbb901bfb2befbf96bc2ec7c0ffec4192ee59ce440bc34867e1a44
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c5d68680c3959b31f754e032a712c855d8cfb82a81c8724efeaab58e5bfcbc
+oid sha256:f69d5ba6761ac9f26960ae6afbdbf7137bc92600b7a5d4043e27216619dd3479
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce80496f5ff016a991c7347d19ed4c4662d4190bb5444368af73527e582b904
+oid sha256:621519582414cbcc961b30cff113e8b1e10923f26e46ef8e0ad7c29a35554318
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001701162461015027,
+  "epoch": 0.0025517436915225406,
   "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": 151.809,
       "eval_steps_per_second": 37.978,
       "step": 6
+    },
+    {
+      "epoch": 0.001984689537850865,
+      "grad_norm": 0.0982154831290245,
+      "learning_rate": 7e-05,
+      "loss": 10.3886,
+      "step": 7
+    },
+    {
+      "epoch": 0.0022682166146867026,
+      "grad_norm": 0.10347899794578552,
+      "learning_rate": 8e-05,
+      "loss": 10.3883,
+      "step": 8
+    },
+    {
+      "epoch": 0.0025517436915225406,
+      "grad_norm": 0.10859348624944687,
+      "learning_rate": 9e-05,
+      "loss": 10.3829,
+      "step": 9
+    },
+    {
+      "epoch": 0.0025517436915225406,
+      "eval_loss": 10.385502815246582,
+      "eval_runtime": 19.2386,
+      "eval_samples_per_second": 154.377,
+      "eval_steps_per_second": 38.62,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1255258718208.0,
+  "total_flos": 1882888077312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null