Training in progress, epoch 1, checkpoint

checkpoint-3743/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "moussakam/Arabart",
+  "_name_or_path": "nour4286/ArabartModel",
   "activation_dropout": 0.1,
   "activation_function": "gelu",
   "add_bias_logits": false,

checkpoint-3743/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2930f8ab2dd0a46858cbba04e476117ffa46128c52f9ef92c761063c84326e
+oid sha256:1121eefca3b4957308588e5490479bc7e5dfe0e28c12dc1ef2b264a712dea926
 size 557116312

checkpoint-3743/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:699a98a7a52d70ff1d86e339f4d11b9683d24fddd3cbdceea50a59f1a8b05f05
+oid sha256:b00fab32c4b4a0c7467ab865cb82f3946a88826109286f603e3643b60531efbf
 size 1113991930

checkpoint-3743/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:557e659df0fae2e63fc7ba4fd94075ae8b0ea2a8d60d30519b66bc17dbd7e027
+oid sha256:9e1af3b209edf367387ccd9ba32486ff7328abe4d196775ffadc967aab340f30
 size 1064

checkpoint-3743/tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

checkpoint-3743/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 26.0848,
+  "best_metric": 26.9521,
   "best_model_checkpoint": "/content/drive/MyDrive/checkpoint-3743",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,62 +10,62 @@
   "log_history": [
     {
       "epoch": 0.1335826876836762,
-      "grad_norm": 4.480758190155029,
-      "learning_rate": 4.7773621871938735e-05,
-      "loss": 3.8388,
+      "grad_norm": 4.5242133140563965,
+      "learning_rate": 5e-05,
+      "loss": 3.2029,
       "step": 500
     },
     {
       "epoch": 0.2671653753673524,
-      "grad_norm": 4.0973663330078125,
-      "learning_rate": 4.554724374387746e-05,
-      "loss": 3.534,
+      "grad_norm": 4.41894006729126,
+      "learning_rate": 4.766986671637618e-05,
+      "loss": 2.8643,
       "step": 1000
     },
     {
       "epoch": 0.4007480630510286,
-      "grad_norm": 3.4115138053894043,
-      "learning_rate": 4.332086561581619e-05,
-      "loss": 3.4407,
+      "grad_norm": 4.079468250274658,
+      "learning_rate": 4.533973343275236e-05,
+      "loss": 2.7844,
       "step": 1500
     },
     {
       "epoch": 0.5343307507347048,
-      "grad_norm": 4.144280910491943,
-      "learning_rate": 4.1094487487754926e-05,
-      "loss": 3.3758,
+      "grad_norm": 3.858260154724121,
+      "learning_rate": 4.3009600149128535e-05,
+      "loss": 2.7501,
       "step": 2000
     },
     {
       "epoch": 0.667913438418381,
-      "grad_norm": 4.332496643066406,
-      "learning_rate": 3.886810935969365e-05,
-      "loss": 3.3258,
+      "grad_norm": 4.262380599975586,
+      "learning_rate": 4.0679466865504706e-05,
+      "loss": 2.6947,
       "step": 2500
     },
     {
       "epoch": 0.8014961261020572,
-      "grad_norm": 3.689181089401245,
-      "learning_rate": 3.6641731231632384e-05,
-      "loss": 3.2834,
+      "grad_norm": 4.304072856903076,
+      "learning_rate": 3.834933358188088e-05,
+      "loss": 2.6785,
       "step": 3000
     },
     {
       "epoch": 0.9350788137857333,
-      "grad_norm": 3.1737449169158936,
-      "learning_rate": 3.441535310357111e-05,
-      "loss": 3.2471,
+      "grad_norm": 3.803712844848633,
+      "learning_rate": 3.601920029825706e-05,
+      "loss": 2.6409,
       "step": 3500
     },
     {
       "epoch": 1.0,
-      "eval_loss": 2.7515902519226074,
-      "eval_rouge1": 26.0848,
-      "eval_rouge2": 12.3268,
-      "eval_rougeL": 23.6134,
-      "eval_runtime": 766.0717,
-      "eval_samples_per_second": 6.121,
-      "eval_steps_per_second": 0.612,
+      "eval_loss": 2.9351165294647217,
+      "eval_rouge1": 26.9521,
+      "eval_rouge2": 12.8371,
+      "eval_rougeL": 24.3565,
+      "eval_runtime": 736.5698,
+      "eval_samples_per_second": 6.366,
+      "eval_steps_per_second": 0.637,
       "step": 3743
     }
   ],

checkpoint-3743/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d05d32a13e629e372fd63a6a56914009e5a295d344b7df97bfa8a0480ad14ed0
+oid sha256:cc12377bc5c5e926d6591071c08141a1e803bbd801c62b57f2957c80f9609e63
 size 7032