Training in progress, step 2780, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c190a6166666cc6a3c6dfe28e0785131a04c3b23b0a33f3eb47119c767f45be
+oid sha256:08d8095b444dce6d9bac00136d04403b5d0a7c0f9f7458c7cf3e3011d67b8fe1
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944a3f33118ed3a7f56a4fec1c7ca031d80874193b8dd65aa07c5b18cdbe4ffd
+oid sha256:0783c3f3e629fde6e18a99f5435e176c5be2aa711e3f6e822e9cae686c7dd742
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94a1271bb72198f899868d39fc0a5d8b8b2409485f7b536adcd3dba6a2399caa
+oid sha256:64fbea264bb4710fe383c417ca651f8c9522c0f847d06f88decd199fcd48c154
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5d3e36a58ef155ce0b2d43051e1706260aa3ba38a4bd5a2b38dcf71f516cea3
+oid sha256:07d9ab2aee86c49b444258395531f9930a96ed88521cf4cfe3f9685615d5345e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9874776386404294,
+  "epoch": 0.9946332737030411,
   "eval_steps": 500,
-  "global_step": 2760,
+  "global_step": 2780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2215,14 +2215,30 @@
       "loss": 0.3659,
       "num_input_tokens_seen": 1870697,
       "step": 2760
+    },
+    {
+      "epoch": 0.9910554561717353,
+      "grad_norm": 0.2900574803352356,
+      "learning_rate": 1.7889087656529517e-06,
+      "loss": 0.3616,
+      "num_input_tokens_seen": 1876560,
+      "step": 2770
+    },
+    {
+      "epoch": 0.9946332737030411,
+      "grad_norm": 0.3781711459159851,
+      "learning_rate": 1.073345259391771e-06,
+      "loss": 0.3501,
+      "num_input_tokens_seen": 1882565,
+      "step": 2780
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1870697,
+  "num_input_tokens_seen": 1882565,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 4.206536936557978e+16,
+  "total_flos": 4.233223877501952e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null