Training in progress, step 117, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df7bdccf9b9ea018cf08637989d48944be5e3ee8a0970bee5233527cdc8082c
+oid sha256:06fa68d78d89a854827883ee55215383e1c1c0760a1ad33c93f2228f78986fd2
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abf811487858e391fe9c39fee5a148ac7ba91980cf9e43cff52525b26848fb97
+oid sha256:3a8ce6d55957a4220034cdaf2960db4f9f9bb3123247090414c373d1298a53bf
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:919715e521e6fafa91c21eb71f1ef59a2a480a7d0fc641c8aac7133bb8caf2b2
+oid sha256:748c00c41dcc9767a3a919d998beb10fbad73a8dec5e63ea35c1f405977a910e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89b61481eb2980a04190d12a0165f95c9fc0a4db20ad8cc3d895835eac42f68
+oid sha256:49a9f08177ba433a82ec0fa599b737a453ff55e83dd9d31c6fddaf5bc4b0a0b3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8909090909090909,
+  "epoch": 2.1272727272727274,
   "eval_steps": 13,
-  "global_step": 104,
+  "global_step": 117,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -317,6 +317,49 @@
       "eval_samples_per_second": 9.964,
       "eval_steps_per_second": 1.286,
       "step": 104
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.5612895488739014,
+      "learning_rate": 2.3398396174233178e-05,
+      "loss": 0.0825,
+      "step": 105
+    },
+    {
+      "epoch": 1.9636363636363636,
+      "grad_norm": 0.5168143510818481,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0798,
+      "step": 108
+    },
+    {
+      "epoch": 2.018181818181818,
+      "grad_norm": 0.3419465124607086,
+      "learning_rate": 1.7956219300748793e-05,
+      "loss": 0.0638,
+      "step": 111
+    },
+    {
+      "epoch": 2.0727272727272728,
+      "grad_norm": 0.3355216085910797,
+      "learning_rate": 1.544686755065677e-05,
+      "loss": 0.0374,
+      "step": 114
+    },
+    {
+      "epoch": 2.1272727272727274,
+      "grad_norm": 0.513612687587738,
+      "learning_rate": 1.3094050125632972e-05,
+      "loss": 0.0367,
+      "step": 117
+    },
+    {
+      "epoch": 2.1272727272727274,
+      "eval_loss": 0.1390739530324936,
+      "eval_runtime": 9.3397,
+      "eval_samples_per_second": 9.958,
+      "eval_steps_per_second": 1.285,
+      "step": 117
     }
   ],
   "logging_steps": 3,
@@ -336,7 +379,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.362237982217339e+17,
+  "total_flos": 2.6351846578716672e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null