Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b081ed29616ea796fd10761804e404c807b5bdbf5d51e5b87d9401058d49ea17
+oid sha256:0fac502a9a02aa2ef4f77bd7234708c8a8c7f4e89a2cb0928ecbac08d82dd437
 size 756993928

last-checkpoint/global_step1400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04972d1e840bc29ada15c9fc15b30a121553ca1afec2c5825f69d6352089ffbc
+size 570679973

last-checkpoint/global_step1400/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:ce37d1eaa52440e5c333c61e83ae2c8b8ddd7e5b12aaba2debb6e87b174574ec
+size 570680037

last-checkpoint/global_step1400/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:760ead67626c4d29c02cdec7ad7c0f634d1d015d0cda898897ffd9838f268b43
+size 570680037

last-checkpoint/global_step1400/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29a0482d8e71912cb0d7250a744dcfcc6de6ceeb8b836acce13e64be5d8b6bd5
+size 570680037

last-checkpoint/global_step1400/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b78b45898be183c1431f7528ab7e9ac4f7cc0d382d7427696b5b83d83f5be936
+size 757261081

last-checkpoint/latest

@@ -1 +1 @@
-global_step1350
+global_step1400

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10bb70517d3857c36e2fc0b3224dee1d99b35a00d6fe9ee9feb2bac0f62e5384
+oid sha256:2a6674858f845b1abd45c29d8a99abd0f2bf92191e5678ce6de1f095df5eca45
 size 15429

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba11951e0ccc207525ae8ff533dc15923e756c8619e8d15a0caded6c4a10b815
+oid sha256:317ac78c7bdb5ccdb656233d3e1dcb49d70e652fd18c7c7bb5072bb5be497fdc
 size 15429

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98f09166c52548851d910faec1dd5fc4c821fbe4ed21b13da06f93d495589aaf
+oid sha256:7319d6b38c60ea34f3b5037c08524f1aaf74fcd4a88235f625a4d0e4fe8fe4f0
 size 15429

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a42d2b95956b89aee515c18eef715d630081eaa1fce271f6cb05846ea36818b8
+oid sha256:736b40bc7902f5fab9fdf407d69f7458ee61b208004efb0012974dfd3d29d63c
 size 15429

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3469f15564be2aafad06679ef296083aa563eb48f7450e2fec91e288bb2857a4
+oid sha256:77c61f3dc774e2ae12e317628af20231bf2f2c8db7789a152dfc53f365e55748
 size 1401

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
   "best_global_step": null,
-  "best_metric": 0.8181790113449097,
+  "best_metric": 0.8163571357727051,
   "best_model_checkpoint": null,
-  "epoch": 0.962223806129722,
+  "epoch": 0.9978617248752673,
   "eval_steps": 50,
-  "global_step": 1350,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2114,6 +2114,84 @@
       "eval_samples_per_second": 30.404,
       "eval_steps_per_second": 0.951,
       "step": 1350
+    },
+    {
+      "epoch": 0.9657875980042766,
+      "grad_norm": 0.12054579704999924,
+      "learning_rate": 9.701112087714588e-05,
+      "loss": 0.8679,
+      "step": 1355
+    },
+    {
+      "epoch": 0.9693513898788311,
+      "grad_norm": 0.14034906029701233,
+      "learning_rate": 9.691186980793666e-05,
+      "loss": 0.8394,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9729151817533856,
+      "grad_norm": 0.1279161274433136,
+      "learning_rate": 9.681226454609325e-05,
+      "loss": 0.8392,
+      "step": 1365
+    },
+    {
+      "epoch": 0.9764789736279401,
+      "grad_norm": 0.15074440836906433,
+      "learning_rate": 9.67123059245336e-05,
+      "loss": 0.8342,
+      "step": 1370
+    },
+    {
+      "epoch": 0.9800427655024947,
+      "grad_norm": 0.13274189829826355,
+      "learning_rate": 9.661199477913053e-05,
+      "loss": 0.8205,
+      "step": 1375
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "grad_norm": 0.14032673835754395,
+      "learning_rate": 9.651133194870466e-05,
+      "loss": 0.8612,
+      "step": 1380
+    },
+    {
+      "epoch": 0.9871703492516037,
+      "grad_norm": 0.12214959412813187,
+      "learning_rate": 9.641031827501751e-05,
+      "loss": 0.8329,
+      "step": 1385
+    },
+    {
+      "epoch": 0.9907341411261582,
+      "grad_norm": 0.12821224331855774,
+      "learning_rate": 9.630895460276446e-05,
+      "loss": 0.8312,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9942979330007128,
+      "grad_norm": 0.12127358466386795,
+      "learning_rate": 9.620724177956754e-05,
+      "loss": 0.851,
+      "step": 1395
+    },
+    {
+      "epoch": 0.9978617248752673,
+      "grad_norm": 0.13414740562438965,
+      "learning_rate": 9.610518065596853e-05,
+      "loss": 0.8084,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9978617248752673,
+      "eval_loss": 0.8163571357727051,
+      "eval_runtime": 328.1729,
+      "eval_samples_per_second": 30.402,
+      "eval_steps_per_second": 0.951,
+      "step": 1400
     }
   ],
   "logging_steps": 5,
@@ -2142,7 +2220,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0491461337157206e+19,
+  "total_flos": 1.0860706869664547e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null