Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c890dac25841ad3328e4fb3a782daa8b803618fb11cc4c2528f21764ee15775
+oid sha256:1e67393a2f132428ede22923d723a0645a04dacd871ab0fb21296616b994025d
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb060ee2cac02dd5c62f787910a843ab46452e74449e698ba22f15f76e8c9a2
+oid sha256:1ad763d6e883a8268f407249caf87a6dde724a24360ec16556683f8e92f7cd02
 size 205350

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:755c4134596a2077827fb8f97d56f3bd342fd2c77507989a663da481d9802231
+oid sha256:cfcdcab4388f5a703b3d0dc8f96e589ed1666b084dfced15fee5c930f0db87d7
 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": 0.01991701244813278,
+  "epoch": 0.02987551867219917,
   "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": 177.202,
       "eval_steps_per_second": 44.301,
       "step": 6
+    },
+    {
+      "epoch": 0.023236514522821577,
+      "grad_norm": 0.12177033722400665,
+      "learning_rate": 0.00014,
+      "loss": 10.36,
+      "step": 7
+    },
+    {
+      "epoch": 0.026556016597510373,
+      "grad_norm": 0.11929324269294739,
+      "learning_rate": 0.00016,
+      "loss": 10.3723,
+      "step": 8
+    },
+    {
+      "epoch": 0.02987551867219917,
+      "grad_norm": 0.12620662152767181,
+      "learning_rate": 0.00018,
+      "loss": 10.3648,
+      "step": 9
+    },
+    {
+      "epoch": 0.02987551867219917,
+      "eval_loss": 10.372748374938965,
+      "eval_runtime": 2.6384,
+      "eval_samples_per_second": 192.538,
+      "eval_steps_per_second": 48.134,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1496882085888.0,
+  "total_flos": 2191863054336.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null