Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1bb94b8a77419efd218015aa078f96d962dddb1d7d803a4037f71edb25081b
+oid sha256:995dadf0d3d095797b5dbc557b2d1541ca751ef767140b2eac486d1f7802f08c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c397e65bf99adf9a6e0565defce89f241ee1e376a6e7d7145c230f7427e8d116
+oid sha256:7361a2fab55f925d42ccfef981caf4fa3db8ce7635371819cdbf2b69ea2a0076
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36fe4f7b36a5388221274c24d05ee4e9199f494788d121bb8791d2cd878af911
+oid sha256:eefe6d642f2fec79a1485caf3f0bf5664dd3a0b7470a19b36fef717b4ce4330f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36df38c42a3a82df40d06ca73d44edf3651e608b1093fdf04dfb5064b7258c83
+oid sha256:920ac20f3da0aa073b783e5c39cbf10201482c9a198f2029422a6d2d7dd4763e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16666666666666666,
+  "epoch": 0.2,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,41 @@
       "learning_rate": 1.888977777777778e-05,
       "loss": 0.0737,
       "step": 2500
+    },
+    {
+      "epoch": 0.17333333333333334,
+      "grad_norm": 0.09161335974931717,
+      "learning_rate": 1.8845333333333334e-05,
+      "loss": 0.0714,
+      "step": 2600
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.22928522527217865,
+      "learning_rate": 1.880088888888889e-05,
+      "loss": 0.0753,
+      "step": 2700
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.17746783792972565,
+      "learning_rate": 1.8756444444444445e-05,
+      "loss": 0.0727,
+      "step": 2800
+    },
+    {
+      "epoch": 0.19333333333333333,
+      "grad_norm": 0.14290937781333923,
+      "learning_rate": 1.8712e-05,
+      "loss": 0.0684,
+      "step": 2900
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.15487806499004364,
+      "learning_rate": 1.8667555555555555e-05,
+      "loss": 0.073,
+      "step": 3000
     }
   ],
   "logging_steps": 100,
@@ -201,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6089578905600000.0,
+  "total_flos": 7307494686720000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5da3872b72c31dc28c756543e89c64090a6cb637a3a5de22e6dfe587939acf42
+oid sha256:20d7bfd722c356d3138649856f039df4c593cfd472f7e9aa290a4571f1e6327f
 size 5432