Training in progress, epoch 0, checkpoint

checkpoint-584/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-584/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e0fe87469657b2d0f08c54c77056e1b83661d822a8a377dd03e16646e863b93
+oid sha256:76e84445a191839edf84f1d889f276068e769f9a8bf0b989becc3c63c9de697c
 size 557116312

checkpoint-584/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71c013e908a8066f671b0b031dcf04553bab3a133bfd036b66dc0504c7719941
+oid sha256:3f520b58c6b87f0f6763b360b74cc218710b87ec4cbc35eaa497a7804486ef2f
 size 1113991930

checkpoint-584/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e12ed84ecd5ee97f160ae4fcce9f9313275009e6508a8e14cb7b8606144e40
+oid sha256:1d9e95035cb1be4618fab3d17f62392c1067c951be1666c8daa0117fb090bb41
 size 14244

checkpoint-584/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c56c34f4d3aef6e77819dbdecb8020abe4efb028b5a0b1ff2d67e625aa9229
+oid sha256:2ab9cec4ef0efd312094946ebfdfc4c402610c2b3c556c08dc380f086b68177c
 size 1064

checkpoint-584/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 26.9712,
+  "best_metric": 27.3096,
   "best_model_checkpoint": "/content/drive/MyDrive/Arabart/checkpoint-584",
   "epoch": 0.9986106658116918,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 0.8549748851127498,
-      "grad_norm": 2.031277894973755,
-      "learning_rate": 4.531835205992509e-05,
-      "loss": 2.8999,
+      "grad_norm": 1.4868409633636475,
+      "learning_rate": 4.9128919860627184e-05,
+      "loss": 2.0944,
       "step": 500
     },
     {
       "epoch": 0.9986106658116918,
-      "eval_loss": 2.2065234184265137,
-      "eval_rouge1": 26.9712,
-      "eval_rouge2": 11.457,
-      "eval_rougeL": 23.6934,
-      "eval_runtime": 917.6342,
-      "eval_samples_per_second": 5.11,
-      "eval_steps_per_second": 1.278,
+      "eval_loss": 2.504359483718872,
+      "eval_rouge1": 27.3096,
+      "eval_rouge2": 11.4756,
+      "eval_rougeL": 23.8611,
+      "eval_runtime": 914.3973,
+      "eval_samples_per_second": 5.128,
+      "eval_steps_per_second": 1.283,
       "step": 584
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2920,
+  "max_steps": 14600,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 25,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -44,7 +44,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2403151082008576e+16,
+  "total_flos": 1.893105654301901e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

checkpoint-584/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91c08386842fcbee346408a30719423fe59996a6d54d317350062699341eb49b
+oid sha256:576ede367e64eecc72993edf5019ca711a039a382e750df6eee9b32df90b34f4
 size 7032