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:f598d525ffdd6b73acaf9cac0bb0a1c9af34406f61fd444575553f4f0caa9278
+oid sha256:f80c9aca402cfbbf591e593318b9f70f957f0ab87eb54dd3bec7feb17dc184ef
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e71565859861788448040bad3b7258c02a415674df05487dbc8925f7bbb622e7
+oid sha256:89cbc2c12d484f3a1336f266ba11e1ddd4cb9081c7fdc2b8f86d0ecfd16378fc
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2788b9e4a3e02030f83b8e3801e6e323231f28c3256b02d54b3f0741c38af059
+oid sha256:f7db8c8799503ac725f3e85e9e34a31747e78dbced1baebabe9003ce86bf931c
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fff414ace1867b67391b626a8e245a5248361d78f9269e3a675593c0e9e4f5a
+oid sha256:1b2319160d5dd25c12876dc189aa82af20f2eed3bcd566ffee789098a96fe3e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.599281362287143,
+  "epoch": 4.799250117169192,
   "eval_steps": 500,
-  "global_step": 2300,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -200,6 +200,13 @@
       "learning_rate": 8.466666666666667e-05,
       "loss": 1.2912,
       "step": 2300
+    },
+    {
+      "epoch": 4.799250117169192,
+      "grad_norm": 0.15591269731521606,
+      "learning_rate": 8.4e-05,
+      "loss": 1.2801,
+      "step": 2400
     }
   ],
   "logging_steps": 100,
@@ -219,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.589687709846733e+18,
+  "total_flos": 3.7457626810348995e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null