Training in progress, step 9800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:757dda966b2f4d181a128ff59f9b919daff4e506360c00213ab3ec0c0ff2691e
+oid sha256:f5abc00b30afb0cc7f11475da5329ddda7a8b54916957489c98976e9146772bb
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c1cbeda60e9c2a4013fcd83f0f4b91298e0a0b17ca0cb5693b8fb2316ae9ce
+oid sha256:20b2d331cc999028b7772cec2bf035150343c98c155579a40021dd1b08f46b51
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83bf192647771b3f8523529c1a3c6ebe56340eb008266267aa5af12c0294e34e
+oid sha256:c05839636fd5cb5be586f924cedf0045977d387805f980599c45c147e0e837b6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce7729d52ceb1dabda5590c3c4f3afbbf1ca186490116815086c48ad76afb3f6
+oid sha256:d8d0791f87a560d6e6d8a6da6d811e646baa7dcb34edbb7ffc991631590e30ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007139165386946482,
+  "epoch": 0.007287897999174534,
   "eval_steps": 2000,
-  "global_step": 9600,
+  "global_step": 9800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,6 +343,13 @@
       "learning_rate": 1.9999899624269806e-05,
       "loss": 1.5278,
       "step": 9600
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.587338924407959,
+      "learning_rate": 1.9999895393491484e-05,
+      "loss": 1.566,
+      "step": 9800
     }
   ],
   "logging_steps": 200,
@@ -350,7 +357,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.2573875538675302e+17,
+  "total_flos": 1.2813345198044774e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null