Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5f1b072d203d5b76fe9560659963ef8f781250b4a92e1868c89f6c51fb112d6
+oid sha256:2ca2d0789f8cfefc3ae782c9c211e30db8fcfde8211a7aa026f963759ffa596b
 size 9450448

last-checkpoint/global_step80/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09093f6dc5f091ecd2b49cf68f93f21db705787b0ca6a27718fc730b6f546628
+size 28320208

last-checkpoint/global_step80/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62bf6856c03735d6594a4ccc20a1b0fec307282dcb03baa95c101b9a439cbbc
+size 28320208

last-checkpoint/global_step80/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3176959e987ae88695bfb58dd388a6206667bec907cea4cef0eb31b822525d62
+size 9523692

last-checkpoint/latest

@@ -1 +1 @@
-global_step70
+global_step80

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:041c1299befadbb78df28d6c51995637fdc42b23b8c9a0ddd6d7b9d2b7b43095
+oid sha256:2cf0b22231e0aa02f53ac9a900d016562c5e7c021c34b5088c73b5a29b90d23d
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d39b95751aa22f7c631b63c6ae50b62913410b70130404c3fc20f638c1f28ddb
+oid sha256:6f24bb0f430f282c43aa6537fcfce58560e72b7881eb48726030f0bc77debaf2
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f98a8feef34550913a6c17e6d111551876ee5198dbf8b76141d29b9c822b726
+oid sha256:49b8a1dbbf2c2a0b7fde326d57c34bd6c5e5d17e0aaf8b19016c1f721c049db1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11970927746900385,
+  "epoch": 0.1368106028217187,
   "eval_steps": 10,
-  "global_step": 70,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,28 @@
       "eval_samples_per_second": 102.941,
       "eval_steps_per_second": 25.892,
       "step": 70
+    },
+    {
+      "epoch": 0.12825994014536127,
+      "grad_norm": 37.37099075317383,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 3.4387,
+      "step": 75
+    },
+    {
+      "epoch": 0.1368106028217187,
+      "grad_norm": 14.69621467590332,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 3.0516,
+      "step": 80
+    },
+    {
+      "epoch": 0.1368106028217187,
+      "eval_loss": 3.148390054702759,
+      "eval_runtime": 4.685,
+      "eval_samples_per_second": 105.229,
+      "eval_steps_per_second": 26.467,
+      "step": 80
     }
   ],
   "logging_steps": 5,
@@ -188,7 +210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1786158224769024.0,
+  "total_flos": 2044930264399872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null