Training in progress, step 8600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68399e5c313a915751634cf5ffae9ace9416e38938d0103a268d1d11dce06274
+oid sha256:4533d0cc5d4d50b82cfb5df3d5e25daabf3844635d37d8a1136dc9efe3ae8cbf
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4548ac75442441bb1d5da3687ffb1363df171933d0e50d8f215a23de567a8a6b
+oid sha256:d5c5d42eb180a29ed66f0b671c8c70e4743c5ad821b1415728c0f72958e41f51
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d48374e1e6b1447bbeee1d70f64941ccb28e15e76b5206f65f89b25b037eb922
+oid sha256:46108bf4b002a3517fd8a49b94b3b4ed59fda2273b5a44b5a4115826d33fd2b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877cbfb7de479f62248634d105d7b3cf3fb2397e07f0e8b78265a455155762d7
+oid sha256:bdd0fb75028b56249c2d8c029d1a64d4b86a271bd278ff63d1486066e1925aa9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006246769713578172,
+  "epoch": 0.006395502325806224,
   "eval_steps": 2000,
-  "global_step": 8400,
+  "global_step": 8600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,13 @@
       "learning_rate": 1.9999923174987494e-05,
       "loss": 1.5533,
       "step": 8400
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.5668296813964844,
+      "learning_rate": 1.99999194681957e-05,
+      "loss": 1.5581,
+      "step": 8600
     }
   ],
   "logging_steps": 200,
@@ -308,7 +315,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.0986977552390554e+17,
+  "total_flos": 1.1254267984893542e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null