Training in progress, step 2720, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7339f7334e0a031a15795ba5320c294805f948a198df237f83f4e5327e0cad8
+oid sha256:2311db336a74d6027b311eaa653056cb4acaddc6053a9bcfcf31ef286760d5ed
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f00d069498569089a5048ef3befc73614bd70e4e5ed8485f9cc4cbc6780121aa
+oid sha256:2ccc45fddbbe9d221c9887609118bdcd89634d9fbc115859deaaa180775d1c41
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb2d63f8e4e8d5f7bea5acbac004de06c0ad244850838fc3302028e95e97171e
+oid sha256:6f3423ef0180b7cc49d51ed48a15845d80402981893f5feeedb16a233a66fd87
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:717f2df67856162e81b3e0ed9d50fa4a8bb3e40a242042617cbc33e8d11a5c3f
+oid sha256:c3791c6b28f2569893f2f7130add08063530eee9e29c0d2d9ebca8117edde234
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9660107334525939,
+  "epoch": 0.9731663685152058,
   "eval_steps": 500,
-  "global_step": 2700,
+  "global_step": 2720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2167,14 +2167,30 @@
       "loss": 0.3881,
       "num_input_tokens_seen": 1832731,
       "step": 2700
+    },
+    {
+      "epoch": 0.9695885509838998,
+      "grad_norm": 0.36823177337646484,
+      "learning_rate": 6.082289803220036e-06,
+      "loss": 0.3836,
+      "num_input_tokens_seen": 1838814,
+      "step": 2710
+    },
+    {
+      "epoch": 0.9731663685152058,
+      "grad_norm": 0.40080201625823975,
+      "learning_rate": 5.366726296958855e-06,
+      "loss": 0.3393,
+      "num_input_tokens_seen": 1844328,
+      "step": 2720
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1832731,
+  "num_input_tokens_seen": 1844328,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 4.121164809840845e+16,
+  "total_flos": 4.147242367485542e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null