Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6648a41237a7a2278ffd750717f8841ba95250a368dd73cc651be06f16d32f5
+oid sha256:782341ed4d6165e7fd8d209d7ad03cc24ce52fb33f692e3081a749d4315a7e85
 size 241984552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7918592fe825a53ce56575c6d5aa31d320545cf98ef41215df02d4d0d4887d73
+oid sha256:afd1f4d76a2addd80e3181d89997df1a58f9ffb4b1c52e20f08010d329c6795b
 size 121457978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9a23fa52b27eaa5fc22b4213d74495fec88896724f361e788bf3955ddbac40
+oid sha256:ee6cda819c1a2323b565772a3d94d91eb65d9dab5b45edbec9696014f83fdabe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e220a0d9a44c971538f4556a11503eb3a8b03f14341ea5528fade0233a5550d
+oid sha256:71b08411cb0eb53e0a8c7df5f16ee6389613ee5ab9806db0b3a1d1ceeab83e1e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.22815423226100845,
+  "epoch": 0.34223134839151265,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,13 @@
       "learning_rate": 9.543691535477983e-05,
       "loss": 0.9848,
       "step": 1000
+    },
+    {
+      "epoch": 0.34223134839151265,
+      "grad_norm": 1.83408522605896,
+      "learning_rate": 9.315537303216974e-05,
+      "loss": 0.9081,
+      "step": 1500
     }
   ],
   "logging_steps": 500,
@@ -28,7 +35,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1624101617664000.0,
+  "total_flos": 2436152426496000.0,
   "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null