Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3595b12f86459195f8d09179d7c0dbf8792ab5da530439f3a09a0bba7f7a42a1
+oid sha256:7e732afce22ec32ca479327823c15da79bda2c036818cf68dffa6504bebbe039
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58fbfe5c5eaca18bcc1c80efd605fd210e276ac78ec3e25b0dac1bfe7a2ee3d1
+oid sha256:016c49916fc2c8819ea4e88ac71d5999800563cede87d1fbe681c0226feb18c1
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c99e1271397b81fc889fdb77bb7999277542aa1b382e9e22a5a0bd0cd0a478e3
+oid sha256:3717310ed22609eb472cb933e8ce12dc75189c5307a2dd757612d0dafbdd44fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5e00b537e62e61b7fa13230cc02b759e6748bf2bcdb20f27dd8576bd1d7344
+oid sha256:655cb150e23a910120ef43d10145c8ad974ea933a71e70934e13f61b696b9b7e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.851520572450805,
+  "epoch": 0.8586762075134168,
   "eval_steps": 500,
-  "global_step": 2380,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1911,14 +1911,30 @@
       "loss": 0.3792,
       "num_input_tokens_seen": 1615204,
       "step": 2380
+    },
+    {
+      "epoch": 0.855098389982111,
+      "grad_norm": 0.29884225130081177,
+      "learning_rate": 2.898032200357782e-05,
+      "loss": 0.4037,
+      "num_input_tokens_seen": 1621948,
+      "step": 2390
+    },
+    {
+      "epoch": 0.8586762075134168,
+      "grad_norm": 0.36023974418640137,
+      "learning_rate": 2.826475849731664e-05,
+      "loss": 0.3994,
+      "num_input_tokens_seen": 1628983,
+      "step": 2400
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1615204,
+  "num_input_tokens_seen": 1628983,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.632023404151603e+16,
+  "total_flos": 3.663007509246566e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null