Training in progress, step 12500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d368685b466c586ae7754c9d6601a94b88a29fa10089466eaf7691d618758c
+oid sha256:35af312258ec2ecc580cd7ccdb601acf0843f55378f8ced88aa3b6791062f0ec
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be528ec45cd20464a9f579ede6fc32d36b21c545d4649748da7c0e442878da12
+oid sha256:cc0410b7f00647d202243d6032612ef86b9b1ad740cc13589fc9a20d6719723c
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca90357941cc8ba75656fcb364086055fdccb9002e991bd59479c3c303e64d7f
+oid sha256:4f42d5f8190e167df10f51b86e202ce65c6f8b2e34f31e34e57377eb8f3a2ccc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c83b3bacd9fafe4707bb796f339853939afe8625c6ed3b03b48e890e264959d8
+oid sha256:72aa0a4db9a1d4fcb9226563e6d35e410e13273eff2f98d7fe41149f20f9d2f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
+  "epoch": 0.8333333333333334,
   "eval_steps": 500,
-  "global_step": 12000,
+  "global_step": 12500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -847,6 +847,41 @@
       "learning_rate": 1.4668000000000003e-05,
       "loss": 0.0601,
       "step": 12000
+    },
+    {
+      "epoch": 0.8066666666666666,
+      "grad_norm": 0.12947213649749756,
+      "learning_rate": 1.4623555555555558e-05,
+      "loss": 0.07,
+      "step": 12100
+    },
+    {
+      "epoch": 0.8133333333333334,
+      "grad_norm": 0.12053196877241135,
+      "learning_rate": 1.4579111111111113e-05,
+      "loss": 0.0675,
+      "step": 12200
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.15298992395401,
+      "learning_rate": 1.4534666666666668e-05,
+      "loss": 0.0663,
+      "step": 12300
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.11816833913326263,
+      "learning_rate": 1.4490222222222223e-05,
+      "loss": 0.0681,
+      "step": 12400
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.22705060243606567,
+      "learning_rate": 1.4445777777777779e-05,
+      "loss": 0.0666,
+      "step": 12500
     }
   ],
   "logging_steps": 100,
@@ -866,7 +901,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.922997874688e+16,
+  "total_flos": 3.0447894528e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null