Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15fc5b65988dba9a92214885439409a56e1a12adf4b7a814f334349a6f059b72
+oid sha256:52505d06ff3ae7e7722f22aa43c3fc5b8ad96c0a537d7e9c79da9d5b152aebe2
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a16e11d8fd6c2ba6c7095d563911bce83b0e9473899f5f7c51df3652f230a47
+oid sha256:db28a6c36094322bfed08993c1daae55a34222efe7ece9b79aad4409b339902a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3be9ba5208bb0b7f62289ba0a40fc9a2f25e8400d6b589d90ca0f5299037cd9d
+oid sha256:d201843135a1eed508b1bfdef27db8413b4debdba9826e312a0df4e52244dac2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10613e0e6a8bbd05857ec6a1df443a776230ca43f27f89f8af0bb353f93e15b8
+oid sha256:f1fe29dcca1504d02fcda85bfbd112a8c1eec19fab9dfffe8372c01fb4bcb7fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3507896924355778,
+  "epoch": 1.4546965918536992,
   "eval_steps": 500,
-  "global_step": 6500,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -106,6 +106,13 @@
       "learning_rate": 1.099889165973954e-05,
       "loss": 0.3624,
       "step": 6500
+    },
+    {
+      "epoch": 1.4546965918536992,
+      "grad_norm": 0.3497615456581116,
+      "learning_rate": 1.0306178996952066e-05,
+      "loss": 0.3516,
+      "step": 7000
     }
   ],
   "logging_steps": 500,
@@ -125,7 +132,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7915843619389440.0,
+  "total_flos": 8524801509949440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null