Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc89545303c18949c80b514edaddae7e84866cb623a18f98c413b46a1c9d4d7
+oid sha256:8894b9d8ac36c38b5080b99880a8e14b512f8a931c448da5c52fd1c66e52710e
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bcbdedded29af27703691374a9e8cead9c5c687c0bfbef0d54c617b6a2a6aa0
+oid sha256:b0a912df019ebbdc3ddc598a4fec6725c894e15a123235800b9e94429b6e5469
 size 61926

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c14142dfa46f49a566546178fbf9bb75cb8ea3abe4d872b9fb0e81794f00f4
+oid sha256:c21c3dc74b2937662ccab666858bfec21c3948be77f6128755465d6a551d61e7
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1707e0d4ace56f38c459da3c06c617c019d432eebcd26c94637a7024d10c4043
+oid sha256:cc7c1ef018b1e6de2abd772589c59dd72358c0b6677c85a565a049eb95faabc1
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002726536872150982,
+  "epoch": 0.004089805308226473,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 135.268,
       "eval_steps_per_second": 33.821,
       "step": 10
+    },
+    {
+      "epoch": 0.00299919055936608,
+      "grad_norm": 0.03368884697556496,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 11.9436,
+      "step": 11
+    },
+    {
+      "epoch": 0.0032718442465811785,
+      "grad_norm": 0.03182883933186531,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9372,
+      "step": 12
+    },
+    {
+      "epoch": 0.0035444979337962766,
+      "grad_norm": 0.04742654412984848,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 11.9381,
+      "step": 13
+    },
+    {
+      "epoch": 0.0038171516210113747,
+      "grad_norm": 0.03973816707730293,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.9325,
+      "step": 14
+    },
+    {
+      "epoch": 0.004089805308226473,
+      "grad_norm": 0.03192592039704323,
+      "learning_rate": 5e-05,
+      "loss": 11.9413,
+      "step": 15
+    },
+    {
+      "epoch": 0.004089805308226473,
+      "eval_loss": 11.938648223876953,
+      "eval_runtime": 182.7753,
+      "eval_samples_per_second": 135.188,
+      "eval_steps_per_second": 33.801,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 239830302720.0,
+  "total_flos": 359745454080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null