Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52505d06ff3ae7e7722f22aa43c3fc5b8ad96c0a537d7e9c79da9d5b152aebe2
+oid sha256:a98f9af0a45f19a09c1c186136cd253423faadf90caac3f3ccea9fcfc2529a1b
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db28a6c36094322bfed08993c1daae55a34222efe7ece9b79aad4409b339902a
+oid sha256:31bcd0679d0af1a77f9829764622e3673f9fb683bc9d078c25e7535795e2745f
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d201843135a1eed508b1bfdef27db8413b4debdba9826e312a0df4e52244dac2
+oid sha256:616c142757d7ec77ca22084861554955efb9fa5f5da5efb368b0b3385f62bf1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1fe29dcca1504d02fcda85bfbd112a8c1eec19fab9dfffe8372c01fb4bcb7fd
+oid sha256:e31f91bc7011a01710cdbc945cab2b4cdfd91aca4b40a50acfda247e6ac17ec3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4546965918536992,
+  "epoch": 1.5586034912718203,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -113,6 +113,13 @@
       "learning_rate": 1.0306178996952066e-05,
       "loss": 0.3516,
       "step": 7000
+    },
+    {
+      "epoch": 1.5586034912718203,
+      "grad_norm": 1.4209001064300537,
+      "learning_rate": 9.61346633416459e-06,
+      "loss": 0.3565,
+      "step": 7500
     }
   ],
   "logging_steps": 500,
@@ -132,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8524801509949440.0,
+  "total_flos": 9133759400509440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null