Training in progress, step 122000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b66425b94f2e83e9f2d0ef0a5a9619097cea94f688140b6355837c6862e130d4
+oid sha256:fce8febb2716108038efaaf937387d62f02be7c96e83f3460099c8d88b73dbfc
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca4050210e3e0b53086ab39ce001a08cbf8ed7f8ce6ede11116945d8c1f4075
+oid sha256:cdd7d351278922d4e3181ae6bf23825526c0663f6c38a764181920285733d7a9
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b1977d3bd75beb86c861efe86a2ecbbc84d67eabe3c546ad1f9cc4b0c95cfb5
+oid sha256:9342fe6807deef12394bcdf0dc46806c9965d5485e123099bca4e5a6f2e9f9a0
 size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be817e3410feaa10ca81244df169cdce850a393c8c8d757e09a32a186f0361ca
+oid sha256:16b6e7175e1fcf2517ba9872702af9426a0051ef5f446636eb4dab154365c7ce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 29.14609177405757,
+  "epoch": 29.386968565578705,
   "eval_steps": 500,
-  "global_step": 121000,
+  "global_step": 122000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -854,6 +854,13 @@
       "learning_rate": 2.834658315265398e-05,
       "loss": 0.7454,
       "step": 121000
+    },
+    {
+      "epoch": 29.386968565578705,
+      "grad_norm": 0.5853854417800903,
+      "learning_rate": 2.0316389624989963e-05,
+      "loss": 0.7424,
+      "step": 122000
     }
   ],
   "logging_steps": 1000,
@@ -873,7 +880,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.210439597113213e+18,
+  "total_flos": 1.2204434735937618e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null