Upload folder using huggingface_hub

checkpoint-latest/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05526172b6b183727ed691244d8fca12632b8705fa3b5f5582a369439119e9f7
+oid sha256:795ea54c34c88b85a3fb35a48aa425148ae783dfc82bb534fc7c366e4eb1ab26
 size 62293080

checkpoint-latest/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae74e3c93a2f232f2571925d5902330db686e4ed3351b82bafa9a5dbb3dca60
+oid sha256:945fb964074ba34d7300992c6c559faceb117e18c0aaf4c9961ee8e7f009ba2f
 size 124642443

checkpoint-latest/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:111dc925ae2f7248f73dcd9582f2230af09b95cb292fde39121b77d0a24595e6
+oid sha256:3791abf31ec6e82ba3d4fb71351beccb33024121dff3a0af48258eb8e3dcf267
 size 14645

checkpoint-latest/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec9761731a5aa3d5575ffed14f4165db19c93fbedd2eb3e25069def656bd6d84
+oid sha256:e8b56065bfa25797c49f5e0d00ff60a8f7f9ff8c3dc27a413f7721c344a954c2
 size 1465

checkpoint-latest/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10828370330265295,
+  "epoch": 0.2165674066053059,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,50 @@
       "eval_samples_per_second": 112.414,
       "eval_steps_per_second": 7.03,
       "step": 1000
+    },
+    {
+      "epoch": 0.1353546291283162,
+      "grad_norm": 1.041638731956482,
+      "learning_rate": 9.549178848583288e-05,
+      "loss": 4.0201,
+      "step": 1250
+    },
+    {
+      "epoch": 0.16242555495397942,
+      "grad_norm": 0.8976061940193176,
+      "learning_rate": 9.458942429164411e-05,
+      "loss": 3.9802,
+      "step": 1500
+    },
+    {
+      "epoch": 0.16242555495397942,
+      "eval_loss": 3.2597038745880127,
+      "eval_runtime": 87.5921,
+      "eval_samples_per_second": 112.453,
+      "eval_steps_per_second": 7.033,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18949648077964265,
+      "grad_norm": 1.0333911180496216,
+      "learning_rate": 9.368706009745533e-05,
+      "loss": 3.9335,
+      "step": 1750
+    },
+    {
+      "epoch": 0.2165674066053059,
+      "grad_norm": 0.9179081320762634,
+      "learning_rate": 9.278469590326656e-05,
+      "loss": 3.8709,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2165674066053059,
+      "eval_loss": 3.1846394538879395,
+      "eval_runtime": 87.5421,
+      "eval_samples_per_second": 112.517,
+      "eval_steps_per_second": 7.037,
+      "step": 2000
     }
   ],
   "logging_steps": 250,
@@ -71,7 +115,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 361054076928000.0,
+  "total_flos": 722108153856000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null