Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04a023d8eae2b5ccc492ba729567d59e031019da2e3ca4bafb6d61d0d3388d86
+oid sha256:7f6c9491adb6089056fda920e27d5868f9c470a97da0823064432f6788c44756
 size 42002584

last-checkpoint/global_step1500/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:f4d6134158e7c13a72c0bffc0be795bbfef434634617e8cf04f155ed2264f145
+size 251710672

last-checkpoint/global_step1500/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf5aaaab0959575e566af04b3c87174d7001e7459c813c42a628f90466e3b99
+size 47955328

last-checkpoint/latest

@@ -1 +1 @@
-global_step1000
+global_step1500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c98879aba5b00d81dca96ce732b312683376f3923af7bda8eb2a40d4da8d98d
+oid sha256:721c0a2243fa57a1e6ca760a9478078a0f6bb44a899a4293351badcaa44577ca
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.698005698005698,
+  "epoch": 8.547008547008547,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -154,6 +154,76 @@
       "learning_rate": 0.00015025025025025026,
       "loss": 0.0876,
       "step": 1000
+    },
+    {
+      "epoch": 5.982905982905983,
+      "grad_norm": 1.0592001676559448,
+      "learning_rate": 0.00014774774774774775,
+      "loss": 0.0909,
+      "step": 1050
+    },
+    {
+      "epoch": 6.267806267806268,
+      "grad_norm": 1.4785758256912231,
+      "learning_rate": 0.00014524524524524526,
+      "loss": 0.0838,
+      "step": 1100
+    },
+    {
+      "epoch": 6.552706552706553,
+      "grad_norm": 0.6601145267486572,
+      "learning_rate": 0.00014274274274274275,
+      "loss": 0.0827,
+      "step": 1150
+    },
+    {
+      "epoch": 6.837606837606837,
+      "grad_norm": 1.1280301809310913,
+      "learning_rate": 0.00014024024024024024,
+      "loss": 0.0762,
+      "step": 1200
+    },
+    {
+      "epoch": 7.122507122507122,
+      "grad_norm": 1.467143177986145,
+      "learning_rate": 0.00013773773773773776,
+      "loss": 0.0799,
+      "step": 1250
+    },
+    {
+      "epoch": 7.407407407407407,
+      "grad_norm": 1.773697018623352,
+      "learning_rate": 0.00013523523523523525,
+      "loss": 0.0765,
+      "step": 1300
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 3.1821281909942627,
+      "learning_rate": 0.00013273273273273274,
+      "loss": 0.0787,
+      "step": 1350
+    },
+    {
+      "epoch": 7.977207977207978,
+      "grad_norm": 0.9911046028137207,
+      "learning_rate": 0.00013023023023023023,
+      "loss": 0.0731,
+      "step": 1400
+    },
+    {
+      "epoch": 8.262108262108262,
+      "grad_norm": 2.560380458831787,
+      "learning_rate": 0.00012772772772772775,
+      "loss": 0.069,
+      "step": 1450
+    },
+    {
+      "epoch": 8.547008547008547,
+      "grad_norm": 1.88752281665802,
+      "learning_rate": 0.00012522522522522524,
+      "loss": 0.0708,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -173,7 +243,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7161049585156096e+16,
+  "total_flos": 4.082014482962842e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null