Training in progress, step 9320, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85beb4e63f2c5b59a9fb44c1941465e25467b6f51e0595870a1ed098da9eb3a9
+oid sha256:4e12c37b04f848c57b1fbaa1586497570ce04b4c474a41d82ca6927d46cfafc8
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bfa466e47344fdb4b82ac2e27349b5aa4a9780daa2a9dd909396e056672be06
+oid sha256:be6249a73b51acc1e605e0c726f6b0c6b5b71b95e8e1b3bd37e1fd6605c078f1
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3cda8d8dfc43c49473f34af5d9dbd59701d7b0b55fa4d024a4a95d2b0775e60
+oid sha256:4030094ed5282ad80d870d012a583b682ade163de00f842f2ba8ebc8caafb7bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e194f1dd757c906a836decafb805f1dccfe64bb4c1bfe3207704010eaaa32fd
+oid sha256:ab2f7e65908b7a6affd31bf3469c124def8863b28efc3fb8855df9f9b8567a7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.744,
+  "epoch": 0.7456,
   "eval_steps": 500,
-  "global_step": 9300,
+  "global_step": 9320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3262,6 +3262,13 @@
       "learning_rate": 1.7418463821296398e-05,
       "loss": 3.4075,
       "step": 9300
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 52.64670944213867,
+      "learning_rate": 1.7370505494839012e-05,
+      "loss": 3.4542,
+      "step": 9320
     }
   ],
   "logging_steps": 20,
@@ -3269,7 +3276,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.199570826395648e+16,
+  "total_flos": 2.203989782819635e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null