Training in progress, step 2460, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1057e20ef792fc90c9ecff83a00d848ccc0ae3deab4667bd0c2e6bc4d267d1
+oid sha256:bedf1b6d5e32ae60cbf34f929bfa462bde2adec5e00a44530266b9d926cec517
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c5b49a7e6c52ddda0765c314c6cf225b945342c4930ac0976dccb277d23d504
+oid sha256:a8ab70123d88a30c78dbc1cf668156ef4539a947d64d12664cc583ba9139315b
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:977734e5fe7bc11e4d6ed6aad6cba91a2133b09eb5e2150e6fe83ae79e2649ca
+oid sha256:ab90daea2cc7962c335eac8ebb5f569b419b5cbc004628f6c9c5c4d750b2fa9b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a738aa1757ae6fa7df683e4fddbcc331434574a0f55ddc368da19ecd66c122e
+oid sha256:c215c6736359b4426fb423f696f85c3a29879ea9d026ccf6cd9e1acb18851c2d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8729874776386404,
+  "epoch": 0.8801431127012522,
   "eval_steps": 500,
-  "global_step": 2440,
+  "global_step": 2460,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1959,14 +1959,30 @@
       "loss": 0.3905,
       "num_input_tokens_seen": 1655672,
       "step": 2440
+    },
+    {
+      "epoch": 0.8765652951699463,
+      "grad_norm": 0.5768277645111084,
+      "learning_rate": 2.4686940966010734e-05,
+      "loss": 0.3941,
+      "num_input_tokens_seen": 1662028,
+      "step": 2450
+    },
+    {
+      "epoch": 0.8801431127012522,
+      "grad_norm": 0.4279649257659912,
+      "learning_rate": 2.3971377459749554e-05,
+      "loss": 0.3874,
+      "num_input_tokens_seen": 1668160,
+      "step": 2460
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1655672,
+  "num_input_tokens_seen": 1668160,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.723021645314458e+16,
+  "total_flos": 3.751102747312128e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null