Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca2d0789f8cfefc3ae782c9c211e30db8fcfde8211a7aa026f963759ffa596b
+oid sha256:b7199f500237808236c7db3d5064a6acab3ac41d5c44eef1255b1e366d37d6ed
 size 9450448

last-checkpoint/global_step90/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba7f7cb199a096c26f7bdb99e92e8e975851dc0e565c7c549a4709721b38d03
+size 28320208

last-checkpoint/global_step90/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef157cd60fb19d40e37f653a733ec88ca8ab5038fa4193ae672fe035a3ceb8e
+size 28320208

last-checkpoint/global_step90/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8501d3f6f7512e5408b13c6199ae8c726861f2db4a61e1a2f4450273f82c40f
+size 9523692

last-checkpoint/latest

@@ -1 +1 @@
-global_step80
+global_step90

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf0b22231e0aa02f53ac9a900d016562c5e7c021c34b5088c73b5a29b90d23d
+oid sha256:b177fe91b634dee552bfdb8884320c1c49f5f739fd36c0751b428ca7b40e9d3f
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f24bb0f430f282c43aa6537fcfce58560e72b7881eb48726030f0bc77debaf2
+oid sha256:8d85625dac880f235f3fb74a29363e92179ac27ae903013848e6f9d0c8f757f8
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49b8a1dbbf2c2a0b7fde326d57c34bd6c5e5d17e0aaf8b19016c1f721c049db1
+oid sha256:cb97b24f34ff3e53eec5be9cf35c1a7161c58dbc2fed7dda160fb3eb64e5f353
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1368106028217187,
+  "epoch": 0.15391192817443353,
   "eval_steps": 10,
-  "global_step": 80,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -191,6 +191,28 @@
       "eval_samples_per_second": 105.229,
       "eval_steps_per_second": 26.467,
       "step": 80
+    },
+    {
+      "epoch": 0.1453612654980761,
+      "grad_norm": 32.74094009399414,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 3.1578,
+      "step": 85
+    },
+    {
+      "epoch": 0.15391192817443353,
+      "grad_norm": 22.851362228393555,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 3.1172,
+      "step": 90
+    },
+    {
+      "epoch": 0.15391192817443353,
+      "eval_loss": 3.1573593616485596,
+      "eval_runtime": 4.7749,
+      "eval_samples_per_second": 103.249,
+      "eval_steps_per_second": 25.969,
+      "step": 90
     }
   ],
   "logging_steps": 5,
@@ -210,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2044930264399872.0,
+  "total_flos": 2297390790868992.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null