Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d98edc3d2ca1aec91433e9987eee768c36fddb0d2cde139c9b53415ce830ce40
+oid sha256:0d5259f63701323f722761a70bc120c9eac3ca5b4f21ffa24b7e0b55f0a2771e
 size 1192135096

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9069b63adcfe2746e98414c2c83d0ddd2f1f9d6d20a61a295651cba33be78589
+oid sha256:ec5cc8aa219267408c45a4d037896a55c856faab11e2505858c17e4c6415d0f3
 size 2384459962

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
+oid sha256:69f50a692634404f2eebb2eab9f456865957578d752987bc52d843ac2a774366
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3062b0a02968eef37b0d0a0387798ef4cd562c0a577e5e8055c6181ccd441515
+oid sha256:de16677c82ff272c2a0bd0cd189a45a0e7a858ab45925adad4f6dc891d27b809
 size 1064

trainer_state.json

@@ -2,151 +2,106 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9994666666666666,
+  "epoch": 1.0,
   "eval_steps": 100,
-  "global_step": 937,
+  "global_step": 625,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.10666666666666667,
-      "grad_norm": 6.6875,
-      "learning_rate": 4.471718249733191e-05,
-      "loss": 1.2181,
+      "epoch": 0.16,
+      "grad_norm": 6.5,
+      "learning_rate": 4.2080000000000004e-05,
+      "loss": 1.2105,
       "step": 100
     },
     {
-      "epoch": 0.10666666666666667,
-      "eval_loss": 1.4656692743301392,
-      "eval_runtime": 128.3122,
-      "eval_samples_per_second": 44.703,
-      "eval_steps_per_second": 5.588,
+      "epoch": 0.16,
+      "eval_loss": 1.458847165107727,
+      "eval_runtime": 128.1964,
+      "eval_samples_per_second": 44.744,
+      "eval_steps_per_second": 5.593,
       "step": 100
     },
     {
-      "epoch": 0.21333333333333335,
-      "grad_norm": 6.5625,
-      "learning_rate": 3.938100320170758e-05,
-      "loss": 1.1539,
+      "epoch": 0.32,
+      "grad_norm": 6.34375,
+      "learning_rate": 3.408e-05,
+      "loss": 1.1564,
       "step": 200
     },
     {
-      "epoch": 0.21333333333333335,
-      "eval_loss": 1.4585195779800415,
-      "eval_runtime": 128.2644,
-      "eval_samples_per_second": 44.72,
-      "eval_steps_per_second": 5.59,
+      "epoch": 0.32,
+      "eval_loss": 1.4528062343597412,
+      "eval_runtime": 128.0959,
+      "eval_samples_per_second": 44.779,
+      "eval_steps_per_second": 5.597,
       "step": 200
     },
     {
-      "epoch": 0.32,
-      "grad_norm": 5.625,
-      "learning_rate": 3.4044823906083245e-05,
-      "loss": 1.1353,
+      "epoch": 0.48,
+      "grad_norm": 7.40625,
+      "learning_rate": 2.6079999999999998e-05,
+      "loss": 1.1265,
       "step": 300
     },
     {
-      "epoch": 0.32,
-      "eval_loss": 1.4478052854537964,
-      "eval_runtime": 128.1523,
-      "eval_samples_per_second": 44.759,
-      "eval_steps_per_second": 5.595,
+      "epoch": 0.48,
+      "eval_loss": 1.4363205432891846,
+      "eval_runtime": 128.0611,
+      "eval_samples_per_second": 44.791,
+      "eval_steps_per_second": 5.599,
       "step": 300
     },
     {
-      "epoch": 0.4266666666666667,
-      "grad_norm": 5.8125,
-      "learning_rate": 2.8708644610458914e-05,
-      "loss": 1.133,
+      "epoch": 0.64,
+      "grad_norm": 6.1875,
+      "learning_rate": 1.808e-05,
+      "loss": 1.1266,
       "step": 400
     },
     {
-      "epoch": 0.4266666666666667,
-      "eval_loss": 1.4380828142166138,
-      "eval_runtime": 128.2602,
-      "eval_samples_per_second": 44.722,
-      "eval_steps_per_second": 5.59,
+      "epoch": 0.64,
+      "eval_loss": 1.428483009338379,
+      "eval_runtime": 128.0722,
+      "eval_samples_per_second": 44.787,
+      "eval_steps_per_second": 5.598,
       "step": 400
     },
     {
-      "epoch": 0.5333333333333333,
-      "grad_norm": 5.4375,
-      "learning_rate": 2.337246531483458e-05,
-      "loss": 1.1229,
+      "epoch": 0.8,
+      "grad_norm": 6.03125,
+      "learning_rate": 1.008e-05,
+      "loss": 1.1208,
       "step": 500
     },
     {
-      "epoch": 0.5333333333333333,
-      "eval_loss": 1.4234306812286377,
-      "eval_runtime": 128.3478,
-      "eval_samples_per_second": 44.691,
-      "eval_steps_per_second": 5.586,
+      "epoch": 0.8,
+      "eval_loss": 1.4252334833145142,
+      "eval_runtime": 128.0781,
+      "eval_samples_per_second": 44.785,
+      "eval_steps_per_second": 5.598,
       "step": 500
     },
-    {
-      "epoch": 0.64,
-      "grad_norm": 5.71875,
-      "learning_rate": 1.8036286019210247e-05,
-      "loss": 1.1073,
-      "step": 600
-    },
-    {
-      "epoch": 0.64,
-      "eval_loss": 1.4192696809768677,
-      "eval_runtime": 128.1918,
-      "eval_samples_per_second": 44.745,
-      "eval_steps_per_second": 5.593,
-      "step": 600
-    },
-    {
-      "epoch": 0.7466666666666667,
-      "grad_norm": 6.4375,
-      "learning_rate": 1.2700106723585914e-05,
-      "loss": 1.1053,
-      "step": 700
-    },
-    {
-      "epoch": 0.7466666666666667,
-      "eval_loss": 1.4158320426940918,
-      "eval_runtime": 128.2181,
-      "eval_samples_per_second": 44.736,
-      "eval_steps_per_second": 5.592,
-      "step": 700
-    },
-    {
-      "epoch": 0.8533333333333334,
-      "grad_norm": 6.03125,
-      "learning_rate": 7.363927427961579e-06,
-      "loss": 1.1059,
-      "step": 800
-    },
-    {
-      "epoch": 0.8533333333333334,
-      "eval_loss": 1.4143309593200684,
-      "eval_runtime": 128.2757,
-      "eval_samples_per_second": 44.716,
-      "eval_steps_per_second": 5.59,
-      "step": 800
-    },
     {
       "epoch": 0.96,
-      "grad_norm": 5.75,
-      "learning_rate": 2.0277481323372464e-06,
-      "loss": 1.1033,
-      "step": 900
+      "grad_norm": 5.59375,
+      "learning_rate": 2.08e-06,
+      "loss": 1.1074,
+      "step": 600
     },
     {
       "epoch": 0.96,
-      "eval_loss": 1.413725733757019,
-      "eval_runtime": 128.2264,
-      "eval_samples_per_second": 44.733,
-      "eval_steps_per_second": 5.592,
-      "step": 900
+      "eval_loss": 1.4235466718673706,
+      "eval_runtime": 128.1144,
+      "eval_samples_per_second": 44.772,
+      "eval_steps_per_second": 5.597,
+      "step": 600
     }
   ],
   "logging_steps": 100,
-  "max_steps": 937,
+  "max_steps": 625,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -162,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0285915444281344e+16,
+  "total_flos": 1.353116024832e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e22a09f7d57eefb94c0225ca0ecccdde6d19aff2eb73e7914dd16e4c7c4bc5f
+oid sha256:6a7349d2d8120da787c6450659b502b45dafc69ba556136c839ae39ead81bc46
 size 5304