Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a533890c74d346fe2376488a4c5fe472acc55816467949a8e781cd59659abfd3
+oid sha256:2102bdccfa92e2b5761b882a02028c85086ccc363a1fec210e4309baef3b8022
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02534e54ffc180d8f3cb0f808a6e0d09cea476ee13f96d531cec9703c3906f6d
+oid sha256:3fd8c3012796410d017b8659828645dd3901f32fc9f7b676f0269080f468354a
 size 61226900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb283ec4555eb7546e21a099be97fd9b5af9b4d1d82bdae8c6164e99f5ff8062
+oid sha256:3d8d5251bb4ef4ac83eff64f5333bb4e8c08cd1cfc5374d9340295609449cc6a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3157894736842105,
+  "epoch": 0.42105263157894735,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 10.466,
       "eval_steps_per_second": 1.308,
       "step": 27
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.44399482011795044,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 5.6151,
+      "step": 30
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 0.4025361239910126,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 5.1451,
+      "step": 33
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.3941345810890198,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 4.9181,
+      "step": 36
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": 1.3653277158737183,
+      "eval_runtime": 13.7475,
+      "eval_samples_per_second": 10.475,
+      "eval_steps_per_second": 1.309,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.983927307927552e+16,
+  "total_flos": 5.311903077236736e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null