End of training

README.md

@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [riotu-lab/ArabianGPT-01B](https://huggingface.co/riotu-lab/ArabianGPT-01B) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4885
-- Bleu: 0.2560
-- Rouge1: 0.6116
-- Rouge2: 0.3795
-- Rougel: 0.6086
+- Loss: 0.4720
+- Bleu: 0.2297
+- Rouge1: 0.5777
+- Rouge2: 0.3341
+- Rougel: 0.5758
 
 ## Model description
 

all_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 11.0,
+    "eval_bleu": 0.22970619705356748,
+    "eval_loss": 0.47202983498573303,
+    "eval_rouge1": 0.5777164933812552,
+    "eval_rouge2": 0.33405816844574837,
+    "eval_rougeL": 0.5758449342460217,
+    "eval_runtime": 1.2669,
+    "eval_samples": 304,
+    "eval_samples_per_second": 239.949,
+    "eval_steps_per_second": 29.994,
+    "perplexity": 1.603245215811176,
+    "total_flos": 876634767360000.0,
+    "train_loss": 0.9867972013005457,
+    "train_runtime": 2886.3238,
+    "train_samples": 1220,
+    "train_samples_per_second": 8.454,
+    "train_steps_per_second": 1.06
+}

egy_training_log.txt

@@ -170,3 +170,5 @@ INFO:root:Epoch 11.0: Train Loss = 0.1042, Eval Loss = 0.4852388799190521
 INFO:absl:Using default tokenizer.
 WARNING:huggingface_hub.utils._http:'(MaxRetryError("HTTPSConnectionPool(host='hf-hub-lfs-us-east-1.s3-accelerate.amazonaws.com', port=443): Max retries exceeded with url: /repos/4e/c5/4ec5c12bd4b31fb218515ee480d86e26419d948a9a596a06a6ad09ce77d37e3a/7e7cfbb2940a8097a9e6e8e5bc5cd9f274cf2ba28fd92151cbe4dd0e72ae5712?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIA2JU7TKAQLC2QXPN7%2F20240831%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240831T191048Z&X-Amz-Expires=86400&X-Amz-Signature=d59b69eb9175411687ff7810cd33c6c85c44bf981f49b4f8ae534408ec3562e2&X-Amz-SignedHeaders=host&partNumber=2&uploadId=xNqFvN721XV0SFXx42EP0sJDJW.W2QqIOgUvk5YQWI9SYvlnvF8kCxC_2mjzHt0k5t51hFB.oftAU6tGWfNhGNpUPE9HMn_UnOlRe.JGXG5J64HYNr3rofly6kQEo7ZO&x-id=UploadPart (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:2406)')))"), '(Request ID: 784209eb-439a-4fa9-b9f8-072965b6bd5d)')' thrown while requesting PUT https://hf-hub-lfs-us-east-1.s3-accelerate.amazonaws.com/repos/4e/c5/4ec5c12bd4b31fb218515ee480d86e26419d948a9a596a06a6ad09ce77d37e3a/7e7cfbb2940a8097a9e6e8e5bc5cd9f274cf2ba28fd92151cbe4dd0e72ae5712?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIA2JU7TKAQLC2QXPN7%2F20240831%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240831T191048Z&X-Amz-Expires=86400&X-Amz-Signature=d59b69eb9175411687ff7810cd33c6c85c44bf981f49b4f8ae534408ec3562e2&X-Amz-SignedHeaders=host&partNumber=2&uploadId=xNqFvN721XV0SFXx42EP0sJDJW.W2QqIOgUvk5YQWI9SYvlnvF8kCxC_2mjzHt0k5t51hFB.oftAU6tGWfNhGNpUPE9HMn_UnOlRe.JGXG5J64HYNr3rofly6kQEo7ZO&x-id=UploadPart
 WARNING:huggingface_hub.utils._http:Retrying in 1s [Retry 1/5].
+INFO:__main__:*** Evaluate ***
+INFO:absl:Using default tokenizer.

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 11.0,
+    "eval_bleu": 0.22970619705356748,
+    "eval_loss": 0.47202983498573303,
+    "eval_rouge1": 0.5777164933812552,
+    "eval_rouge2": 0.33405816844574837,
+    "eval_rougeL": 0.5758449342460217,
+    "eval_runtime": 1.2669,
+    "eval_samples": 304,
+    "eval_samples_per_second": 239.949,
+    "eval_steps_per_second": 29.994,
+    "perplexity": 1.603245215811176
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 11.0,
+    "total_flos": 876634767360000.0,
+    "train_loss": 0.9867972013005457,
+    "train_runtime": 2886.3238,
+    "train_samples": 1220,
+    "train_samples_per_second": 8.454,
+    "train_steps_per_second": 1.06
+}

trainer_state.json

@@ -0,0 +1,260 @@
+{
+  "best_metric": 0.47202983498573303,
+  "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_yem/checkpoint-918",
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 1683,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 43.000205993652344,
+      "learning_rate": 1.53e-05,
+      "loss": 7.8314,
+      "step": 153
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 0.010356123410675664,
+      "eval_loss": 2.359743595123291,
+      "eval_rouge1": 0.09828786255795381,
+      "eval_rouge2": 0.0018177296310952823,
+      "eval_rougeL": 0.09639405964210626,
+      "eval_runtime": 1.1837,
+      "eval_samples_per_second": 256.818,
+      "eval_steps_per_second": 32.102,
+      "step": 153
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3453600406646729,
+      "learning_rate": 3.06e-05,
+      "loss": 0.9995,
+      "step": 306
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 0.11609954154539694,
+      "eval_loss": 0.5537932515144348,
+      "eval_rouge1": 0.47363801342590006,
+      "eval_rouge2": 0.18538347478382655,
+      "eval_rougeL": 0.4727595492611425,
+      "eval_runtime": 9.2767,
+      "eval_samples_per_second": 32.77,
+      "eval_steps_per_second": 4.096,
+      "step": 306
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2846729755401611,
+      "learning_rate": 4.5900000000000004e-05,
+      "loss": 0.4848,
+      "step": 459
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 0.14721751205352876,
+      "eval_loss": 0.5034472942352295,
+      "eval_rouge1": 0.500839694175635,
+      "eval_rouge2": 0.21735831386751384,
+      "eval_rougeL": 0.5001625449149274,
+      "eval_runtime": 10.2581,
+      "eval_samples_per_second": 29.635,
+      "eval_steps_per_second": 3.704,
+      "step": 459
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.2576143741607666,
+      "learning_rate": 4.7812500000000003e-05,
+      "loss": 0.3823,
+      "step": 612
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 0.1911807573581778,
+      "eval_loss": 0.4827471375465393,
+      "eval_rouge1": 0.5330693017126298,
+      "eval_rouge2": 0.27439720992270494,
+      "eval_rougeL": 0.531424425624079,
+      "eval_runtime": 5.4191,
+      "eval_samples_per_second": 56.098,
+      "eval_steps_per_second": 7.012,
+      "step": 612
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.7599295377731323,
+      "learning_rate": 4.482421875e-05,
+      "loss": 0.293,
+      "step": 765
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 0.20959557277319146,
+      "eval_loss": 0.4732062816619873,
+      "eval_rouge1": 0.5619100572084703,
+      "eval_rouge2": 0.30991934212678557,
+      "eval_rougeL": 0.5587085347101918,
+      "eval_runtime": 2.8763,
+      "eval_samples_per_second": 105.69,
+      "eval_steps_per_second": 13.211,
+      "step": 765
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.4758834838867188,
+      "learning_rate": 4.18359375e-05,
+      "loss": 0.2239,
+      "step": 918
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 0.22970619705356748,
+      "eval_loss": 0.47202983498573303,
+      "eval_rouge1": 0.5777164933812552,
+      "eval_rouge2": 0.33405816844574837,
+      "eval_rougeL": 0.5758449342460217,
+      "eval_runtime": 1.7018,
+      "eval_samples_per_second": 178.629,
+      "eval_steps_per_second": 22.329,
+      "step": 918
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.1557574272155762,
+      "learning_rate": 3.884765625e-05,
+      "loss": 0.1766,
+      "step": 1071
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu": 0.23015149161791434,
+      "eval_loss": 0.47373390197753906,
+      "eval_rouge1": 0.588487328464713,
+      "eval_rouge2": 0.3467647604638442,
+      "eval_rougeL": 0.5872191002290259,
+      "eval_runtime": 19.3271,
+      "eval_samples_per_second": 15.729,
+      "eval_steps_per_second": 1.966,
+      "step": 1071
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.236377477645874,
+      "learning_rate": 3.5859375e-05,
+      "loss": 0.1434,
+      "step": 1224
+    },
+    {
+      "epoch": 8.0,
+      "eval_bleu": 0.24506232565608202,
+      "eval_loss": 0.47583380341529846,
+      "eval_rouge1": 0.5938395263674476,
+      "eval_rouge2": 0.3647516376509473,
+      "eval_rougeL": 0.5903133777624114,
+      "eval_runtime": 12.6597,
+      "eval_samples_per_second": 24.013,
+      "eval_steps_per_second": 3.002,
+      "step": 1224
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.2275965213775635,
+      "learning_rate": 3.287109375e-05,
+      "loss": 0.1202,
+      "step": 1377
+    },
+    {
+      "epoch": 9.0,
+      "eval_bleu": 0.2508515461433435,
+      "eval_loss": 0.4827924072742462,
+      "eval_rouge1": 0.6046956358537867,
+      "eval_rouge2": 0.3682856780453533,
+      "eval_rougeL": 0.6015063720236549,
+      "eval_runtime": 30.4628,
+      "eval_samples_per_second": 9.979,
+      "eval_steps_per_second": 1.247,
+      "step": 1377
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.9903411865234375,
+      "learning_rate": 2.9882812500000002e-05,
+      "loss": 0.1042,
+      "step": 1530
+    },
+    {
+      "epoch": 10.0,
+      "eval_bleu": 0.24386094085391116,
+      "eval_loss": 0.4852388799190521,
+      "eval_rouge1": 0.5980129828644593,
+      "eval_rouge2": 0.3703776134768108,
+      "eval_rougeL": 0.5951273362785527,
+      "eval_runtime": 23.4553,
+      "eval_samples_per_second": 12.961,
+      "eval_steps_per_second": 1.62,
+      "step": 1530
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 1.104041337966919,
+      "learning_rate": 2.689453125e-05,
+      "loss": 0.0955,
+      "step": 1683
+    },
+    {
+      "epoch": 11.0,
+      "eval_bleu": 0.25597221159625966,
+      "eval_loss": 0.4884573221206665,
+      "eval_rouge1": 0.6115922153776887,
+      "eval_rouge2": 0.37952408975600893,
+      "eval_rougeL": 0.6085537919616412,
+      "eval_runtime": 1.297,
+      "eval_samples_per_second": 234.387,
+      "eval_steps_per_second": 29.298,
+      "step": 1683
+    },
+    {
+      "epoch": 11.0,
+      "step": 1683,
+      "total_flos": 876634767360000.0,
+      "train_loss": 0.9867972013005457,
+      "train_runtime": 2886.3238,
+      "train_samples_per_second": 8.454,
+      "train_steps_per_second": 1.06
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3060,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 876634767360000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}