Training in progress, step 2500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92a0e91accf4228b98caf6fb1d285323d5a1184a6a49e46d0af865a8d6eb057c
+oid sha256:8c1bb94b8a77419efd218015aa078f96d962dddb1d7d803a4037f71edb25081b
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba08a854f6c958770b50e1d0470ae9e0d583109948b4cdfe1d08bd223264cfd
+oid sha256:c397e65bf99adf9a6e0565defce89f241ee1e376a6e7d7145c230f7427e8d116
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0045739043a1f47643b813cbabc473141dd79658dbb66a9080e37f01080f2a
+oid sha256:36fe4f7b36a5388221274c24d05ee4e9199f494788d121bb8791d2cd878af911
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9866a2fe0d11157ea657698adf310adebc8af3b7e4ad7c6e0bfe9124b0e7f879
+oid sha256:36df38c42a3a82df40d06ca73d44edf3651e608b1093fdf04dfb5064b7258c83
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13333333333333333,
+  "epoch": 0.16666666666666666,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,41 @@
       "learning_rate": 1.9112000000000003e-05,
       "loss": 0.0756,
       "step": 2000
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3241085708141327,
+      "learning_rate": 1.9067555555555558e-05,
+      "loss": 0.0787,
+      "step": 2100
+    },
+    {
+      "epoch": 0.14666666666666667,
+      "grad_norm": 0.27297067642211914,
+      "learning_rate": 1.9023111111111113e-05,
+      "loss": 0.0788,
+      "step": 2200
+    },
+    {
+      "epoch": 0.15333333333333332,
+      "grad_norm": 0.08663206547498703,
+      "learning_rate": 1.897866666666667e-05,
+      "loss": 0.0775,
+      "step": 2300
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.29489508271217346,
+      "learning_rate": 1.8934222222222224e-05,
+      "loss": 0.0693,
+      "step": 2400
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.27022987604141235,
+      "learning_rate": 1.888977777777778e-05,
+      "loss": 0.0737,
+      "step": 2500
     }
   ],
   "logging_steps": 100,
@@ -166,7 +201,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4871663124480000.0,
+  "total_flos": 6089578905600000.0,
   "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