Training in progress, step 11200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42f79bcb4242acb92a4f7cb2331724557b975405cdb310b6f75cdab5cb0cf2d0
+oid sha256:e978a3dd631581b3085b0ba38c6e47c5baef5e3766e2ff1b44fe2bab4c83f0b4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93139c8c08d09e4868b40bea372b7bdcca69c0d3b509b09aa1126e67ca651e8b
+oid sha256:cdc657b03435bb6036ff9119a02ab148c9d23c955e9af628c8f81d4a57890a66
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a20da3a65d158b87b649074348cf08fe7936ff41d5f292d89b1fa2048fa05d5
+oid sha256:2c99279038b507bc5d43a7a4b5bc357533051098093ca7eb76dbe75fa2a95d6f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e17c3aa03d4452fd561bbc9a7830a63b2db80786a84498fe104eef97b6075f39
+oid sha256:1c195caf8ca639dd51bdc47a7a6d637f5c72f6cdcb49eec092ef0892b56f6e72
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008180293672542844,
+  "epoch": 0.008329026284770896,
   "eval_steps": 2000,
-  "global_step": 11000,
+  "global_step": 11200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -392,6 +392,13 @@
       "learning_rate": 1.9999868174872666e-05,
       "loss": 1.533,
       "step": 11000
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.553364276885986,
+      "learning_rate": 1.9999863357206127e-05,
+      "loss": 1.5328,
+      "step": 11200
     }
   ],
   "logging_steps": 200,
@@ -399,7 +406,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.4349700301888717e+17,
+  "total_flos": 1.463004983428055e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null