Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f6c9491adb6089056fda920e27d5868f9c470a97da0823064432f6788c44756
+oid sha256:d748f56c86d9b2ec091d44a85ccd94175df63c0bf630350ae13455b500f5873c
 size 42002584

last-checkpoint/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a3519a1a39e227ba1794212ac52f9ee969bfbc9ef603837beadb366458e497
+size 251710672

last-checkpoint/global_step2000/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:209a7a979e924832a384d3d2fecc6c99d750e116bf2e80357edb2195876eb41a
+size 47955328

last-checkpoint/latest

@@ -1 +1 @@
-global_step1500
+global_step2000

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:721c0a2243fa57a1e6ca760a9478078a0f6bb44a899a4293351badcaa44577ca
+oid sha256:12ff687702c9cb54cfdeb1509074bb19e28d6929ec859a93af35778558181b6e
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.547008547008547,
+  "epoch": 11.396011396011396,
   "eval_steps": 1000,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -224,6 +224,76 @@
       "learning_rate": 0.00012522522522522524,
       "loss": 0.0708,
       "step": 1500
+    },
+    {
+      "epoch": 8.831908831908832,
+      "grad_norm": 1.3793889284133911,
+      "learning_rate": 0.00012272272272272273,
+      "loss": 0.0748,
+      "step": 1550
+    },
+    {
+      "epoch": 9.116809116809117,
+      "grad_norm": 0.7198516130447388,
+      "learning_rate": 0.00012022022022022023,
+      "loss": 0.0695,
+      "step": 1600
+    },
+    {
+      "epoch": 9.401709401709402,
+      "grad_norm": 0.4231278896331787,
+      "learning_rate": 0.00011771771771771771,
+      "loss": 0.0671,
+      "step": 1650
+    },
+    {
+      "epoch": 9.686609686609687,
+      "grad_norm": 2.0300514698028564,
+      "learning_rate": 0.00011521521521521521,
+      "loss": 0.0659,
+      "step": 1700
+    },
+    {
+      "epoch": 9.971509971509972,
+      "grad_norm": 1.0142486095428467,
+      "learning_rate": 0.00011271271271271271,
+      "loss": 0.0714,
+      "step": 1750
+    },
+    {
+      "epoch": 10.256410256410255,
+      "grad_norm": 0.3013649582862854,
+      "learning_rate": 0.0001102102102102102,
+      "loss": 0.0625,
+      "step": 1800
+    },
+    {
+      "epoch": 10.54131054131054,
+      "grad_norm": 0.974827766418457,
+      "learning_rate": 0.00010770770770770771,
+      "loss": 0.0651,
+      "step": 1850
+    },
+    {
+      "epoch": 10.826210826210826,
+      "grad_norm": 1.0164273977279663,
+      "learning_rate": 0.0001052052052052052,
+      "loss": 0.066,
+      "step": 1900
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 0.12340305745601654,
+      "learning_rate": 0.0001027027027027027,
+      "loss": 0.0658,
+      "step": 1950
+    },
+    {
+      "epoch": 11.396011396011396,
+      "grad_norm": 1.1315168142318726,
+      "learning_rate": 0.0001002002002002002,
+      "loss": 0.0611,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -243,7 +313,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.082014482962842e+16,
+  "total_flos": 5.442536950726656e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null