Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b66c7b85bba815a8496aa5bfc93e033b16bb59359391fe05c32b291939b0aa8
+oid sha256:5bb9a096db4afd4939889cf29b28bce0cd60c204e43b83bde086473e9fa95635
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0141d94ab6887d19d624f67d83f76f79885deaeac459ecb525ff6e5b7df4afe
+oid sha256:2f93824adee0ed2d7e519db2a451ec9064b5bb5f6d49be8d009d012c5ec3eda2
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005d9a86e0834fe0802ab2e1c3fa9eca806e3cae26d1cbb14ab848a758219c13
+oid sha256:a4faae14a1aa6472da1e35d90c3eeeb0dd65ba4a4be7087c6d32cacd0c607e1b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07900677200902935,
+  "epoch": 0.09029345372460497,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 553.69,
       "eval_steps_per_second": 69.675,
       "step": 35
+    },
+    {
+      "epoch": 0.08126410835214447,
+      "grad_norm": 0.54636549949646,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 10.3207,
+      "step": 36
+    },
+    {
+      "epoch": 0.08803611738148984,
+      "grad_norm": 0.703861653804779,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 10.3198,
+      "step": 39
+    },
+    {
+      "epoch": 0.09029345372460497,
+      "eval_loss": 10.316521644592285,
+      "eval_runtime": 1.3669,
+      "eval_samples_per_second": 546.511,
+      "eval_steps_per_second": 68.771,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3904273121280.0,
+  "total_flos": 4462026424320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null