Upload trainer_state.json with huggingface_hub

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.246376811594203,
+  "epoch": 7.50103519668737,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 3623,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2457,6 +2457,90 @@
       "learning_rate": 6.298747245393699e-07,
       "loss": 0.0155,
       "step": 3500
+    },
+    {
+      "epoch": 7.267080745341615,
+      "grad_norm": 0.15611431002616882,
+      "learning_rate": 5.317066030354534e-07,
+      "loss": 0.0213,
+      "step": 3510
+    },
+    {
+      "epoch": 7.287784679089027,
+      "grad_norm": 0.24354061484336853,
+      "learning_rate": 4.418295795629246e-07,
+      "loss": 0.02,
+      "step": 3520
+    },
+    {
+      "epoch": 7.308488612836439,
+      "grad_norm": 0.2028241902589798,
+      "learning_rate": 3.6025114574734785e-07,
+      "loss": 0.0124,
+      "step": 3530
+    },
+    {
+      "epoch": 7.329192546583851,
+      "grad_norm": 0.2744869887828827,
+      "learning_rate": 2.8697810149219686e-07,
+      "loss": 0.0226,
+      "step": 3540
+    },
+    {
+      "epoch": 7.349896480331263,
+      "grad_norm": 0.24214069545269012,
+      "learning_rate": 2.2201655441199676e-07,
+      "loss": 0.0158,
+      "step": 3550
+    },
+    {
+      "epoch": 7.370600414078675,
+      "grad_norm": 0.1712854951620102,
+      "learning_rate": 1.653719193232206e-07,
+      "loss": 0.0161,
+      "step": 3560
+    },
+    {
+      "epoch": 7.391304347826087,
+      "grad_norm": 0.22905586659908295,
+      "learning_rate": 1.1704891779298344e-07,
+      "loss": 0.0248,
+      "step": 3570
+    },
+    {
+      "epoch": 7.412008281573499,
+      "grad_norm": 0.22215716540813446,
+      "learning_rate": 7.705157774545724e-08,
+      "loss": 0.0202,
+      "step": 3580
+    },
+    {
+      "epoch": 7.432712215320911,
+      "grad_norm": 0.41476190090179443,
+      "learning_rate": 4.538323312610615e-08,
+      "loss": 0.0217,
+      "step": 3590
+    },
+    {
+      "epoch": 7.453416149068323,
+      "grad_norm": 0.13812510669231415,
+      "learning_rate": 2.2046523623853178e-08,
+      "loss": 0.0169,
+      "step": 3600
+    },
+    {
+      "epoch": 7.474120082815735,
+      "grad_norm": 0.2017739713191986,
+      "learning_rate": 7.043394450956254e-09,
+      "loss": 0.0178,
+      "step": 3610
+    },
+    {
+      "epoch": 7.494824016563147,
+      "grad_norm": 0.2699184715747833,
+      "learning_rate": 3.7509618097120167e-10,
+      "loss": 0.0182,
+      "step": 3620
     }
   ],
   "logging_steps": 10,
@@ -2471,12 +2555,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.269351656215514e+17,
+  "total_flos": 1.3139658769115318e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null