Training in progress, step 9340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e12c37b04f848c57b1fbaa1586497570ce04b4c474a41d82ca6927d46cfafc8
+oid sha256:751f9f960dca5d1bc5b5f0841d1b2cd22831c5a9dd0e4a5ca9f8a71c9bacbd5a
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be6249a73b51acc1e605e0c726f6b0c6b5b71b95e8e1b3bd37e1fd6605c078f1
+oid sha256:568119d120e0792ab2007ac43295445f846bf7d46a353f3c9997e7874c17c32e
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4030094ed5282ad80d870d012a583b682ade163de00f842f2ba8ebc8caafb7bc
+oid sha256:b9a0d75844d6619f1d43c17c2161774384d43f6fff4ebf0f3423379b5d726d2c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab2f7e65908b7a6affd31bf3469c124def8863b28efc3fb8855df9f9b8567a7c
+oid sha256:c57b84b3c01996ecacc9d6df616fa036107288915c2593ed0d7afa9b69854186
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7456,
+  "epoch": 0.7472,
   "eval_steps": 500,
-  "global_step": 9320,
+  "global_step": 9340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3269,6 +3269,13 @@
       "learning_rate": 1.7370505494839012e-05,
       "loss": 3.4542,
       "step": 9320
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 30.222015380859375,
+      "learning_rate": 1.73225223029007e-05,
+      "loss": 3.5017,
+      "step": 9340
     }
   ],
   "logging_steps": 20,
@@ -3276,7 +3283,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.203989782819635e+16,
+  "total_flos": 2.208257832045773e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null