Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dfb1303c43437d0a5d16c718f1a0be0355a6bc6198d78fcee515c503884a9a2
+oid sha256:f1d368685b466c586ae7754c9d6601a94b88a29fa10089466eaf7691d618758c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9169b770e0ac0200417a6d68811804c1fb73c586cfc8a20550b0caa6beef0a3
+oid sha256:be528ec45cd20464a9f579ede6fc32d36b21c545d4649748da7c0e442878da12
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68393a5eefa6936320457e661ed8769751e258badc1e65d137b49f873ca59e29
+oid sha256:ca90357941cc8ba75656fcb364086055fdccb9002e991bd59479c3c303e64d7f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a1695a275cff99a2c62fc4abe2a84b274a1c4f4a080a28dd6e841bca4417f1
+oid sha256:c83b3bacd9fafe4707bb796f339853939afe8625c6ed3b03b48e890e264959d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7666666666666667,
+  "epoch": 0.8,
   "eval_steps": 500,
-  "global_step": 11500,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -812,6 +812,41 @@
       "learning_rate": 1.4890222222222223e-05,
       "loss": 0.0624,
       "step": 11500
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.2603534758090973,
+      "learning_rate": 1.4845777777777778e-05,
+      "loss": 0.0637,
+      "step": 11600
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.2619217038154602,
+      "learning_rate": 1.4801333333333333e-05,
+      "loss": 0.0593,
+      "step": 11700
+    },
+    {
+      "epoch": 0.7866666666666666,
+      "grad_norm": 0.06773953139781952,
+      "learning_rate": 1.4756888888888889e-05,
+      "loss": 0.0689,
+      "step": 11800
+    },
+    {
+      "epoch": 0.7933333333333333,
+      "grad_norm": 0.09101361781358719,
+      "learning_rate": 1.4712444444444444e-05,
+      "loss": 0.0595,
+      "step": 11900
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.30984750390052795,
+      "learning_rate": 1.4668000000000003e-05,
+      "loss": 0.0601,
+      "step": 12000
     }
   ],
   "logging_steps": 100,
@@ -831,7 +866,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.801206296576e+16,
+  "total_flos": 2.922997874688e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null