Training in progress, step 2500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d857d487611677e327f686f5bb0b2c412a46dd20a76142f12b663b725d04116
+oid sha256:4e02f0b07888a18f78925c80c0abe3ec0dab6ba81ca6e3ea35f268d2aae3756f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec04c8625fb5e8405492e6ebc4888b578fc58f8848b213588210076bbf8fba0f
+oid sha256:812c8fcbd607abcc509d9f623a466c6bab8999f10f3fd5d8ccfb7735c9b588b5
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55465423aa4bddb0a9699c8aac4197f916d1b1aa5ba2c8f60a7f814d309a283f
+oid sha256:91cbcad44b892d298ee950eef6c79d786cbfe7529198d9a47e907a2ee94a28c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7285ecba5ee57b8ddee91381a24dda5a0f3ce744a4081805f6d4aba444269721
+oid sha256:a3bc27445dbff80295e46a0b4562f639afc40afb528b8350a5016c11891bb6dd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8872987477638641,
+  "epoch": 0.8944543828264758,
   "eval_steps": 500,
-  "global_step": 2480,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1991,14 +1991,30 @@
       "loss": 0.3572,
       "num_input_tokens_seen": 1682014,
       "step": 2480
+    },
+    {
+      "epoch": 0.8908765652951699,
+      "grad_norm": 0.4232490062713623,
+      "learning_rate": 2.182468694096601e-05,
+      "loss": 0.3664,
+      "num_input_tokens_seen": 1687943,
+      "step": 2490
+    },
+    {
+      "epoch": 0.8944543828264758,
+      "grad_norm": 0.4080519676208496,
+      "learning_rate": 2.110912343470483e-05,
+      "loss": 0.391,
+      "num_input_tokens_seen": 1694486,
+      "step": 2500
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1682014,
+  "num_input_tokens_seen": 1694486,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.782255500921651e+16,
+  "total_flos": 3.810300624569549e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null