Training in progress, step 2760, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dac76252f1ea6c454a23d0bbec6eeaeb8d90dfaad35efd9ad30249ccf2119c5
+oid sha256:2c190a6166666cc6a3c6dfe28e0785131a04c3b23b0a33f3eb47119c767f45be
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:729d204eef78583ce2389cfa7dc8cda2ae4e1adb786f8db9dc5f44cb7ecb07b8
+oid sha256:944a3f33118ed3a7f56a4fec1c7ca031d80874193b8dd65aa07c5b18cdbe4ffd
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5dcb69f4ac177e15c15ecfe217e43f79f5c314ca2c667a27bad7ba64f808dd4
+oid sha256:94a1271bb72198f899868d39fc0a5d8b8b2409485f7b536adcd3dba6a2399caa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9ea2eb042c7e9028c8b0fad7dc94246e12807e86516795fbebc04c9df82814
+oid sha256:e5d3e36a58ef155ce0b2d43051e1706260aa3ba38a4bd5a2b38dcf71f516cea3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9803220035778175,
+  "epoch": 0.9874776386404294,
   "eval_steps": 500,
-  "global_step": 2740,
+  "global_step": 2760,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2199,14 +2199,30 @@
       "loss": 0.3986,
       "num_input_tokens_seen": 1857019,
       "step": 2740
+    },
+    {
+      "epoch": 0.9838998211091234,
+      "grad_norm": 0.33198845386505127,
+      "learning_rate": 3.2200357781753134e-06,
+      "loss": 0.3699,
+      "num_input_tokens_seen": 1865080,
+      "step": 2750
+    },
+    {
+      "epoch": 0.9874776386404294,
+      "grad_norm": 0.3775390386581421,
+      "learning_rate": 2.5044722719141326e-06,
+      "loss": 0.3659,
+      "num_input_tokens_seen": 1870697,
+      "step": 2760
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1857019,
+  "num_input_tokens_seen": 1870697,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 4.175779944795955e+16,
+  "total_flos": 4.206536936557978e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null