Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9d4e4abf2aca225dbc82bbe4834a3cfd41d268fe73f137b810fd7be7ff04b40
+oid sha256:f8eb64e5fc64af89e7d7a6ad7d5fdca548320f515e30052a9b2aa49df90ffb14
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e660d6b7bd584cd4268f3829b97f79b9e6d43de012dbd48dc62bfbb7c516c9ef
+oid sha256:912b2665b93b7b768963683576465e91964b826aef0f8fd420760998594de18f
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:701fccec381f2498ceeea2bd3e9b562a216ce20d81b47c360654e2466c05612f
+oid sha256:75da50fc05ac3af40091fffa29af9b1286ecdf2a5575cc1b1bf98209587348f1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9d76acc0f7ff5f02f45dbdf1e293d52c5b3bc9838ed623c7f1b8796ab90aaa
+oid sha256:b55da3539bea7b2a5ee7e90ae234ebb83f0bcf3370372577761e8ba6d802b8f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5191740412979351,
+  "epoch": 0.7787610619469026,
   "eval_steps": 9,
-  "global_step": 22,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "learning_rate": 5.951955545823342e-05,
       "loss": 177.9139,
       "step": 20
+    },
+    {
+      "epoch": 0.6371681415929203,
+      "eval_loss": 11.031437873840332,
+      "eval_runtime": 0.9695,
+      "eval_samples_per_second": 294.993,
+      "eval_steps_per_second": 37.132,
+      "step": 27
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 19.523183822631836,
+      "learning_rate": 2.282162249993895e-05,
+      "loss": 176.7675,
+      "step": 30
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6789940641792.0,
+  "total_flos": 10184910962688.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null