Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef609f37c1c8f485643664e88b507b20e25017d1e377565c96bca34e6938953a
+oid sha256:ab7f542898d6f7e1164d46f6a96ab03ce263b9319f0aeb341d0480e3302d9a85
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0965757a5da678da6f452a150be141634280eaa660b684dcc7cbc09954d19340
+oid sha256:fd61025408e557acce6485e26fa7379f2ee69f9889123cf50208f062a926a4d5
 size 61392180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89543bf84d579f582b61198c508574dee09d2b87564e7637d1b91364413bf11d
+oid sha256:8ed0751afc86b51a475068fd3d064802215f73338970ca437e2aa986730e3cda
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08186469584991472,
+  "epoch": 0.10233086981239341,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 20.609,
       "eval_steps_per_second": 2.587,
       "step": 36
+    },
+    {
+      "epoch": 0.08868675383740762,
+      "grad_norm": 0.4667467176914215,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.6435,
+      "step": 39
+    },
+    {
+      "epoch": 0.09550881182490051,
+      "grad_norm": 0.4430086612701416,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.6451,
+      "step": 42
+    },
+    {
+      "epoch": 0.10233086981239341,
+      "grad_norm": 0.5567775368690491,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 1.5085,
+      "step": 45
+    },
+    {
+      "epoch": 0.10233086981239341,
+      "eval_loss": 1.696839451789856,
+      "eval_runtime": 35.9155,
+      "eval_samples_per_second": 20.632,
+      "eval_steps_per_second": 2.589,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.205711593373696e+16,
+  "total_flos": 2.7019967018827776e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null