Training in progress, step 1580, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534add263f0ab1fce24fa011018eefdd2dcddfad7e6b3e3167b8b88e43d1d335
+oid sha256:f701220ec81716a32a4d508f6822b66b2074ec86047f8e8f056187bdc1ab5c09
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae8e9e48314c3831c9e9b379cf12dda16febba948f23260c667cfcefdb811cd
+oid sha256:b7b80e2f0ca9bc62e7fcaa505129fa793f6189b638ee9cff07d5b5b21cf2d026
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2490d49251dc1bfa591e0e3acdc7c7d22ca5de91839e3e61e572022e72d3d8d2
+oid sha256:05ad872338f15e42202b963c58b83ef6edf29994e347518dbc0914f0cdbb97b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a759d59fcc4923d52863d19dcf59b3835205ae6c3c6035bc1e96d3a9ecd6ff0
+oid sha256:4510552f5f4688778b1947e191aa031f3e5576fcc244fe154f36949d3b59eca2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5581395348837209,
+  "epoch": 0.5652951699463328,
   "eval_steps": 500,
-  "global_step": 1560,
+  "global_step": 1580,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1255,14 +1255,30 @@
       "loss": 0.3889,
       "num_input_tokens_seen": 1047255,
       "step": 1560
+    },
+    {
+      "epoch": 0.5617173524150268,
+      "grad_norm": 0.3687174916267395,
+      "learning_rate": 8.765652951699464e-05,
+      "loss": 0.3794,
+      "num_input_tokens_seen": 1054159,
+      "step": 1570
+    },
+    {
+      "epoch": 0.5652951699463328,
+      "grad_norm": 0.3228056728839874,
+      "learning_rate": 8.694096601073346e-05,
+      "loss": 0.4095,
+      "num_input_tokens_seen": 1060584,
+      "step": 1580
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1047255,
+  "num_input_tokens_seen": 1060584,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.354906668207104e+16,
+  "total_flos": 2.384878882214707e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null