Training in progress, step 720, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:492e9bfe4ebba8f76c952f180f47c9cd45d836d79bcc296f61bd7c6937f1f837
+oid sha256:11e234e6249350439636d7460378ee2b84249d14c6dee3a2c36d73b5ec77f8e5
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e5e587c0a8509f9abdc181c0e4c8cfa9c47ce2d6e2d2651942fc12828249a48
+oid sha256:b0614d4a3d74c8935ea6bb9dfae42e46c97cd7a85de759de2654b36d6e052287
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d4c85b40db0299b4138faa4f07831cc38c4a75cd15d55868fc1a79092f4af3b
+oid sha256:b80bcd6f3ab18b8a6e4e1a9815a1a307d56309444ef6ece4e0c9e33db3626434
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb4dcda05611092a70b2a0de5cf4d1bbece588e1c89258bd7ebf150f37ad548
+oid sha256:877a12ad1f9d0e7e38bfcb4ffb7f44565110e6cdabfb95d8ce3554269a9604e7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2504472271914132,
+  "epoch": 0.25760286225402507,
   "eval_steps": 500,
-  "global_step": 700,
+  "global_step": 720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,14 +567,30 @@
       "loss": 0.4111,
       "num_input_tokens_seen": 468333,
       "step": 700
+    },
+    {
+      "epoch": 0.25402504472271914,
+      "grad_norm": 0.35491397976875305,
+      "learning_rate": 0.0001491949910554562,
+      "loss": 0.4215,
+      "num_input_tokens_seen": 476220,
+      "step": 710
+    },
+    {
+      "epoch": 0.25760286225402507,
+      "grad_norm": 0.3560994863510132,
+      "learning_rate": 0.000148479427549195,
+      "loss": 0.4011,
+      "num_input_tokens_seen": 481867,
+      "step": 720
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 468333,
+  "num_input_tokens_seen": 481867,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.0531155302590464e+16,
+  "total_flos": 1.0835487168731136e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null