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:f1850ad0a36f5f06ae33ad7d11b5385daec2ef5ebcb7c9200806a740b22910d1
+oid sha256:ef609f37c1c8f485643664e88b507b20e25017d1e377565c96bca34e6938953a
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89842eda117f5151d4dc9e499841b393060f9c8b5c3d4a427d0a37f927179340
+oid sha256:0965757a5da678da6f452a150be141634280eaa660b684dcc7cbc09954d19340
 size 61392180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6242128082eb014ae85c6e3714c30c384666b1201596e4db91be95e8a257e0
+oid sha256:89543bf84d579f582b61198c508574dee09d2b87564e7637d1b91364413bf11d
 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": 0.061398521887436046,
+  "epoch": 0.08186469584991472,
   "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": 20.631,
       "eval_steps_per_second": 2.589,
       "step": 27
+    },
+    {
+      "epoch": 0.06822057987492894,
+      "grad_norm": 0.7258775234222412,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.7701,
+      "step": 30
+    },
+    {
+      "epoch": 0.07504263786242182,
+      "grad_norm": 0.5846672654151917,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.5202,
+      "step": 33
+    },
+    {
+      "epoch": 0.08186469584991472,
+      "grad_norm": 0.7897035479545593,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.6917,
+      "step": 36
+    },
+    {
+      "epoch": 0.08186469584991472,
+      "eval_loss": 1.7188748121261597,
+      "eval_runtime": 35.9555,
+      "eval_samples_per_second": 20.609,
+      "eval_steps_per_second": 2.587,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.654283695030272e+16,
+  "total_flos": 2.205711593373696e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null