Upload folder using huggingface_hub

checkpoint-latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:795ea54c34c88b85a3fb35a48aa425148ae783dfc82bb534fc7c366e4eb1ab26
+oid sha256:85e66d01dfa2825d177f148be01e123916ae8ad822352fa3991ddadbd4df846c
 size 62293080

checkpoint-latest/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:945fb964074ba34d7300992c6c559faceb117e18c0aaf4c9961ee8e7f009ba2f
+oid sha256:f2bbd20b1ee747110998970c84ba11f5687a29984dd589bbdc3cd412bf3cf865
 size 124642443

checkpoint-latest/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3791abf31ec6e82ba3d4fb71351beccb33024121dff3a0af48258eb8e3dcf267
+oid sha256:47f551f352c3582aab145c6f54f30ffbeee0b864e47c66aae4b8bf65aa86b3ab
 size 14645

checkpoint-latest/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8b56065bfa25797c49f5e0d00ff60a8f7f9ff8c3dc27a413f7721c344a954c2
+oid sha256:99c0caf2011a7cb0034062f49b1c20f2067d88b910ef9cf32d24c7e9ddd08314
 size 1465

checkpoint-latest/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2165674066053059,
+  "epoch": 0.32485110990795885,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -96,6 +96,50 @@
       "eval_samples_per_second": 112.517,
       "eval_steps_per_second": 7.037,
       "step": 2000
+    },
+    {
+      "epoch": 0.24363833243096913,
+      "grad_norm": 1.0419113636016846,
+      "learning_rate": 9.188233170907778e-05,
+      "loss": 3.8416,
+      "step": 2250
+    },
+    {
+      "epoch": 0.2707092582566324,
+      "grad_norm": 0.9652225375175476,
+      "learning_rate": 9.0979967514889e-05,
+      "loss": 3.807,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2707092582566324,
+      "eval_loss": 3.119335174560547,
+      "eval_runtime": 87.4769,
+      "eval_samples_per_second": 112.601,
+      "eval_steps_per_second": 7.042,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2977801840822956,
+      "grad_norm": 0.8792561888694763,
+      "learning_rate": 9.007760332070024e-05,
+      "loss": 3.7754,
+      "step": 2750
+    },
+    {
+      "epoch": 0.32485110990795885,
+      "grad_norm": 0.9625837206840515,
+      "learning_rate": 8.917523912651147e-05,
+      "loss": 3.7471,
+      "step": 3000
+    },
+    {
+      "epoch": 0.32485110990795885,
+      "eval_loss": 3.0782463550567627,
+      "eval_runtime": 87.7273,
+      "eval_samples_per_second": 112.28,
+      "eval_steps_per_second": 7.022,
+      "step": 3000
     }
   ],
   "logging_steps": 250,
@@ -115,7 +159,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 722108153856000.0,
+  "total_flos": 1083162230784000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null