Training in progress, step 813, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a652c5fae11ea2adca853738ad01096d957c3c9179219d103154b7cc54bf3ad3
+oid sha256:82f42dafde8f43d8daef05a4b4d895dfe5a001795fdca9d06910d9afd94e8d12
 size 13648688

last-checkpoint/global_step813/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bad71d1ebc275d7bb3182ad2c097070e419821346aa2bb8bb1e7246ee424872
+size 20450800

last-checkpoint/global_step813/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a774541938625f33c41bbeacf87ab4f887899f2f6a4eb4168367163b287002
+size 20450800

last-checkpoint/global_step813/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e36f27eee3a87894e7dae0012f2d579a1718c83fdfb269d8a1363c039ce9559
+size 20450800

last-checkpoint/global_step813/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d12ae5970e0e9ce7b3fb316f04c6ca531d00f5d8adac41f6ae85bb1e7e818b
+size 20450800

last-checkpoint/global_step813/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbab6ee33dad0697672121182b18248e538e76ad2257d4886e8a8c975d1b4bf3
+size 152238

last-checkpoint/global_step813/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd4459ed95d081ddede2eb7e8ea970ecf7c6fe0ae8e806ef35f343969d0b393
+size 152238

last-checkpoint/global_step813/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83ddf22a5d52c4c48fbcddb99a7578eee212f0e265959f0eb8e814f70d197ba
+size 152238

last-checkpoint/global_step813/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22651ffccbfea86821a3c658c3091101f4071a2b3a731393b19db211cedf6049
+size 152238

last-checkpoint/latest

@@ -1 +1 @@
-global_step800
+global_step813

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87cb02e8cd64657a53dc5b5e254ac5f48ae8d194a60165370a55a19b22db6f41
+oid sha256:3d52343dd98f7e84cc6844ba76b296b31c694fd088ebee51a2f941bc914e318c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e24d98488b8ee4c9ae33c4ceab244d33a0b8840dd5bba055edd1d451f13ad848
+oid sha256:948e8d7f2d8d0352f1c9bc8f2562829625ff1fe1528c837b5de4d5af696571ae
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d2cd121bedf7b6b76721153b7cef441f373f23cfeb4d690fa2511614d4a9fde
+oid sha256:700dfabfd03da7587a28bec96ee413548ed6d788958615735d670351ebea332d
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e241a5faad1af0a2c7b86616994b8a556b97dd87a2d34edfc821f52d2592e9ec
+oid sha256:edcbb08a6204513b16df25179848ad245c36614faceacb1e278073cf0cd7da20
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7ed681055e4d6c45b04422cd95ffb42b03b2ad7470799d0056fdac3772ffaa
+oid sha256:eb808850397266aba5d69abcc6e0dbdcd4eae38bfc8a304204140ecb9e3ba047
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9837073470642483,
+  "epoch": 0.9996925914540424,
   "eval_steps": 40,
-  "global_step": 800,
+  "global_step": 813,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5859,6 +5859,97 @@
       "eval_samples_per_second": 2.165,
       "eval_steps_per_second": 0.173,
       "step": 800
+    },
+    {
+      "epoch": 0.9849369812480787,
+      "grad_norm": 0.4737970220793768,
+      "learning_rate": 1.329539452907036e-08,
+      "loss": 0.2434,
+      "step": 801
+    },
+    {
+      "epoch": 0.986166615431909,
+      "grad_norm": 0.27628624700617177,
+      "learning_rate": 1.117222008286456e-08,
+      "loss": 0.1413,
+      "step": 802
+    },
+    {
+      "epoch": 0.9873962496157394,
+      "grad_norm": 0.4484471355218967,
+      "learning_rate": 9.233538192963132e-09,
+      "loss": 0.2062,
+      "step": 803
+    },
+    {
+      "epoch": 0.9886258837995696,
+      "grad_norm": 0.3948729656766095,
+      "learning_rate": 7.479384666608802e-09,
+      "loss": 0.1296,
+      "step": 804
+    },
+    {
+      "epoch": 0.9898555179834,
+      "grad_norm": 0.32852852414095784,
+      "learning_rate": 5.909791902823925e-09,
+      "loss": 0.219,
+      "step": 805
+    },
+    {
+      "epoch": 0.9910851521672303,
+      "grad_norm": 0.42167582713648133,
+      "learning_rate": 4.524788891816512e-09,
+      "loss": 0.1242,
+      "step": 806
+    },
+    {
+      "epoch": 0.9923147863510605,
+      "grad_norm": 0.4186302604931252,
+      "learning_rate": 3.3244012144395545e-09,
+      "loss": 0.2346,
+      "step": 807
+    },
+    {
+      "epoch": 0.9935444205348909,
+      "grad_norm": 0.5241641959513683,
+      "learning_rate": 2.3086510417225093e-09,
+      "loss": 0.22,
+      "step": 808
+    },
+    {
+      "epoch": 0.9947740547187212,
+      "grad_norm": 0.5432971120883086,
+      "learning_rate": 1.4775571344605167e-09,
+      "loss": 0.1391,
+      "step": 809
+    },
+    {
+      "epoch": 0.9960036889025515,
+      "grad_norm": 0.36894298305824874,
+      "learning_rate": 8.311348428657884e-10,
+      "loss": 0.1366,
+      "step": 810
+    },
+    {
+      "epoch": 0.9972333230863818,
+      "grad_norm": 0.49102427432843837,
+      "learning_rate": 3.6939610628894396e-10,
+      "loss": 0.3079,
+      "step": 811
+    },
+    {
+      "epoch": 0.9984629572702121,
+      "grad_norm": 0.6049830604783123,
+      "learning_rate": 9.234945299363418e-11,
+      "loss": 0.2577,
+      "step": 812
+    },
+    {
+      "epoch": 0.9996925914540424,
+      "grad_norm": 0.4658029933791719,
+      "learning_rate": 0.0,
+      "loss": 0.2186,
+      "step": 813
     }
   ],
   "logging_steps": 1,
@@ -5873,12 +5964,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 785744118972416.0,
+  "total_flos": 798189487620096.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null