Training in progress, step 11000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef4eecea3629afcace64b5a917ddd966970bb97958ca98caf3b5b8b8f4cb9f9
+oid sha256:42f79bcb4242acb92a4f7cb2331724557b975405cdb310b6f75cdab5cb0cf2d0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa46c7ed1d599bf3e19190dd49f7e1e57d3c190ced1afb5d39e58b75b5b6e9d
+oid sha256:93139c8c08d09e4868b40bea372b7bdcca69c0d3b509b09aa1126e67ca651e8b
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3933564f2de09fa9ed32bd0876590ad1ced5b512ea947850a85c5527075c34c
+oid sha256:9a20da3a65d158b87b649074348cf08fe7936ff41d5f292d89b1fa2048fa05d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9b6db394b3d452474e4549621859e2d2c7908c6ab758c808d3d275e4c68c06
+oid sha256:e17c3aa03d4452fd561bbc9a7830a63b2db80786a84498fe104eef97b6075f39
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008031561060314793,
+  "epoch": 0.008180293672542844,
   "eval_steps": 2000,
-  "global_step": 10800,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -385,6 +385,13 @@
       "learning_rate": 1.9999872929636188e-05,
       "loss": 1.5997,
       "step": 10800
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.612062454223633,
+      "learning_rate": 1.9999868174872666e-05,
+      "loss": 1.533,
+      "step": 11000
     }
   ],
   "logging_steps": 200,
@@ -392,7 +399,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.4106137221472256e+17,
+  "total_flos": 1.4349700301888717e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null