Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c836babaf4d991968180a6fcccd76f81e887b469c967e485e98fd3e76ea28712
+oid sha256:9ecc892a83e91e39305146b5cb9cefd649f8d8c2c872be11563f2b3457bf3fde
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f6dfb812baab66badfce2517e92417fe1158fa6ed9c7916c78795142932b78
+oid sha256:5a24387e1d2b4525d050e442375c52f753ea3cb669ec5e078c8afac7f0075171
 size 132798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4fb789b365650e3f58c9c53e286cfb01b2c5613a58ec901de852edf89284dd3
+oid sha256:440fdd9fd5f0522851366529afead4e7ded609da5a42165241765d09c41bfcc9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:9e4cb1249623f16a121f1f7528c255e6aea1cd633fd38f639775465d7feebdcd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003407561378699334,
+  "epoch": 0.00040890736544392005,
   "eval_steps": 2,
-  "global_step": 10,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,28 @@
       "eval_samples_per_second": 108.218,
       "eval_steps_per_second": 54.113,
       "step": 10
+    },
+    {
+      "epoch": 0.0003748317516569267,
+      "grad_norm": 2.2423906326293945,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 44.3149,
+      "step": 11
+    },
+    {
+      "epoch": 0.00040890736544392005,
+      "grad_norm": 2.1097352504730225,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 44.4146,
+      "step": 12
+    },
+    {
+      "epoch": 0.00040890736544392005,
+      "eval_loss": 11.085128784179688,
+      "eval_runtime": 114.1984,
+      "eval_samples_per_second": 108.206,
+      "eval_steps_per_second": 54.108,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -144,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 28075622400.0,
+  "total_flos": 32754892800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null