Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a98f9af0a45f19a09c1c186136cd253423faadf90caac3f3ccea9fcfc2529a1b
+oid sha256:14661dd62079aafb6d62a7aa44c4d471eb5869e867f5786f5fec60b869a05884
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31bcd0679d0af1a77f9829764622e3673f9fb683bc9d078c25e7535795e2745f
+oid sha256:878fdf213c549c70e6e58544d458a41774b313b275ecc5a35d91394253732e8c
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616c142757d7ec77ca22084861554955efb9fa5f5da5efb368b0b3385f62bf1c
+oid sha256:193cf8763e811dd3e32b43e244a311e62a543ef8398d3b107ff52fb9af797950
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31f91bc7011a01710cdbc945cab2b4cdfd91aca4b40a50acfda247e6ac17ec3
+oid sha256:7746f1d3dca9d005c3f4add9ea23143cbd616cc0c9a441906d9f1036f61b2904
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5586034912718203,
+  "epoch": 1.6625103906899419,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,6 +120,13 @@
       "learning_rate": 9.61346633416459e-06,
       "loss": 0.3565,
       "step": 7500
+    },
+    {
+      "epoch": 1.6625103906899419,
+      "grad_norm": 0.8116744160652161,
+      "learning_rate": 8.920753671377114e-06,
+      "loss": 0.3635,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -139,7 +146,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9133759400509440.0,
+  "total_flos": 9742717291069440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null