Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b91663fde77b761d862c592b96df19ec4ccc66d4deae37d7502bf9dd4347506
+oid sha256:d12dab413dedff4f34489c236dbdf75ae75a3db3295a67f776c95bfbb2d07a2d
 size 276068600

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d0f8339b39c6759a31dcd74995e280d0e732b1baf3741d840aeb4298f2feed
+oid sha256:897b34115f8a6adffb8414ffd6bf1794cb5825ae62282d7849ce3c1b2bf3212a
 size 552199354

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ae52e2a2714d653899ae559ef59a429172834bee6c0630dc9926f91dfab3ef
+oid sha256:b432a4694428a67e1c67a5f91f188b1db8f86a2f0f3797eb3ceb8533c57e3968
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a94c762edfbdea00aa64c21b4f61cfaa749281d208ea08b36756f691efb5843
+oid sha256:a11cbe220c102f9c059467d0267dab4c912bebb82b4fccb9960b6a217e3bd9aa
 size 1064

trainer_state.json

@@ -1,78 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 530,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.75,
-      "eval_f1": 0.8571428571428571,
-      "eval_loss": 0.58056640625,
-      "eval_precision": 0.75,
-      "eval_recall": 1.0,
-      "eval_runtime": 0.0401,
-      "eval_samples_per_second": 498.393,
-      "eval_steps_per_second": 24.92,
-      "step": 4
+      "eval_accuracy": 0.9522006625650734,
+      "eval_f1": 0.9615823507036896,
+      "eval_loss": 0.14178171753883362,
+      "eval_precision": 0.9454001495886313,
+      "eval_recall": 0.978328173374613,
+      "eval_runtime": 0.4692,
+      "eval_samples_per_second": 4503.32,
+      "eval_steps_per_second": 72.462,
+      "step": 265
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.75,
-      "eval_f1": 0.8571428571428571,
-      "eval_loss": 0.48743900656700134,
-      "eval_precision": 0.75,
-      "eval_recall": 1.0,
-      "eval_runtime": 0.0393,
-      "eval_samples_per_second": 508.764,
-      "eval_steps_per_second": 25.438,
-      "step": 8
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.75,
-      "eval_f1": 0.8571428571428571,
-      "eval_loss": 0.4133850038051605,
-      "eval_precision": 0.75,
-      "eval_recall": 1.0,
-      "eval_runtime": 0.0393,
-      "eval_samples_per_second": 509.033,
-      "eval_steps_per_second": 25.452,
-      "step": 12
+      "epoch": 1.8867924528301887,
+      "grad_norm": 8.409027099609375,
+      "learning_rate": 2e-05,
+      "loss": 0.1708,
+      "step": 500
     },
     {
-      "epoch": 4.0,
-      "eval_accuracy": 0.75,
-      "eval_f1": 0.8571428571428571,
-      "eval_loss": 0.3370513916015625,
-      "eval_precision": 0.75,
-      "eval_recall": 1.0,
-      "eval_runtime": 0.0387,
-      "eval_samples_per_second": 517.282,
-      "eval_steps_per_second": 25.864,
-      "step": 16
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.9,
-      "eval_f1": 0.9375,
-      "eval_loss": 0.27671200037002563,
-      "eval_precision": 0.8823529411764706,
-      "eval_recall": 1.0,
-      "eval_runtime": 0.0222,
-      "eval_samples_per_second": 899.255,
-      "eval_steps_per_second": 44.963,
-      "step": 20
+      "epoch": 2.0,
+      "eval_accuracy": 0.9455750118315192,
+      "eval_f1": 0.957169459962756,
+      "eval_loss": 0.18385401368141174,
+      "eval_precision": 0.9224694903086863,
+      "eval_recall": 0.9945820433436533,
+      "eval_runtime": 0.4345,
+      "eval_samples_per_second": 4862.546,
+      "eval_steps_per_second": 78.243,
+      "step": 530
     }
   ],
   "logging_steps": 500,
-  "max_steps": 20,
+  "max_steps": 530,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -86,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7761761640000.0,
+  "total_flos": 214275848890824.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e072836b101b71b7df169d945f6bbed009ff414bbbc5004a5426c19b8144db91
+oid sha256:095c479560b5e89b2c47e7d14a88e8cf60de541162f502b79e1905120c15cc1f
 size 5112