Upload folder using huggingface_hub

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f3fce1da1767cbc487d04a29ef53c099bfd9607ba6b2229856ff91b3dc7314b
+oid sha256:77dc4d66c26910485e16cbf941efb3f1e18f5fc16c30de007a9adf783b66b2e2
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8923a7cde203268848eecbd3e52fd51e9298333511bc6e2be14d20e817a52ba0
+oid sha256:f6e420c54527bae90da6e2680005705a96b5709457b63551bc81a20164b791f8
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb47a976b361d81f99467da90ccb1f5bd37e6bc99f359f65d8b24b42be0dc96
+oid sha256:c7a16ae132ee19eb711b87594d7cd0d9922f5482176d452836c036f7f6b4ace3
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3327db8cd5733dd1769bf040de5d606aec74a48f5c33ae187232291cc659359
+oid sha256:fce6804f766d3624891cc9c813cc833abe49eb9e19ebcfb04f7867a45a85de35
 size 1168138808

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0810636430978775,
-  "best_model_checkpoint": "/workspace/save/checkpoint-233",
-  "epoch": 0.9971469329529244,
+  "best_metric": 0.0754217654466629,
+  "best_model_checkpoint": "/workspace/save/checkpoint-467",
+  "epoch": 1.9985734664764623,
   "eval_steps": 500,
-  "global_step": 233,
+  "global_step": 467,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -43,6 +43,49 @@
       "eval_samples_per_second": 6.834,
       "eval_steps_per_second": 1.711,
       "step": 233
+    },
+    {
+      "epoch": 1.0699001426533523,
+      "grad_norm": 3.546875,
+      "learning_rate": 1.783872400387872e-05,
+      "loss": 0.0695,
+      "step": 250
+    },
+    {
+      "epoch": 1.2838801711840229,
+      "grad_norm": 2.59375,
+      "learning_rate": 1.693123872217086e-05,
+      "loss": 0.0687,
+      "step": 300
+    },
+    {
+      "epoch": 1.4978601997146934,
+      "grad_norm": 1.5,
+      "learning_rate": 1.5897503590956808e-05,
+      "loss": 0.0703,
+      "step": 350
+    },
+    {
+      "epoch": 1.7118402282453637,
+      "grad_norm": 1.3671875,
+      "learning_rate": 1.4756347698365871e-05,
+      "loss": 0.0699,
+      "step": 400
+    },
+    {
+      "epoch": 1.925820256776034,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.3528556760411822e-05,
+      "loss": 0.0673,
+      "step": 450
+    },
+    {
+      "epoch": 1.9985734664764623,
+      "eval_loss": 0.0754217654466629,
+      "eval_runtime": 181.3373,
+      "eval_samples_per_second": 6.871,
+      "eval_steps_per_second": 1.721,
+      "step": 467
     }
   ],
   "logging_steps": 50,
@@ -62,7 +105,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.097013870044365e+17,
+  "total_flos": 1.0202365411202335e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null