commit files to HF hub

README.md

@@ -0,0 +1,75 @@
+---
+language: es
+tags:
+- sagemaker
+- roberta
+- ruperta
+- TextClassification
+license: apache-2.0
+datasets:
+- IMDbreviews_es
+model-index:
+- name: RuPERTa_base_sentiment_analysis_es
+  results:
+  - task: 
+      name: Sentiment Analysis
+      type: sentiment-analysis
+    dataset:
+      name: "IMDb Reviews in Spanish" 
+      type: IMDbreviews_es
+    metrics:
+       - name: Accuracy
+         type: accuracy
+         value: 0.881866
+       - name: F1 Score
+         type: f1
+         value: 0.008272
+       - name: Precision
+         type: precision
+         value: 0.858605
+       - name: Recall
+         type: recall
+         value: 0.920062
+## `RuPERTa_base_sentiment_analysis_es`
+
+This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
+
+The base model is RuPERTa-base (uncased) which is a RoBERTa model trained on a uncased version of big Spanish corpus.
+It was trained by mrm8488, Manuel Romero.
+
+## Hyperparameters
+
+    {
+    "epochs": "4",
+    "eval_batch_size": "8",
+    "fp16": "true",
+    "learning_rate": "3e-05",
+    "model_name": "\"mrm8488/RuPERTa-base\"",
+    "sagemaker_container_log_level": "20",
+    "sagemaker_job_name": "\"ruperta-sentiment-analysis-full-p2-2021-12-06-20-32-27\"",
+    "sagemaker_program": "\"train.py\"",
+    "sagemaker_region": "\"us-east-1\"",
+    "sagemaker_submit_directory": "\"s3://edumunozsala-ml-sagemaker/ruperta-sentiment/ruperta-sentiment-analysis-full-p2-2021-12-06-20-32-27/source/sourcedir.tar.gz\"",
+    "train_batch_size": "32",
+    "train_filename": "\"train_data.pt\"",
+    "val_filename": "\"val_data.pt\""
+}
+
+
+## Usage
+
+## Results
+
+epoch = 1.0
+eval_accuracy = 0.8629333333333333
+eval_f1 = 0.8648790746582545
+eval_loss = 0.3160930573940277
+eval_mem_cpu_alloc_delta = 0
+eval_mem_cpu_peaked_delta = 0
+eval_mem_gpu_alloc_delta = 0
+eval_mem_gpu_peaked_delta = 94507520
+eval_precision = 0.8479381443298969
+eval_recall = 0.8825107296137339
+eval_runtime = 114.4994
+eval_samples_per_second = 32.751
+

README.txt

@@ -0,0 +1,49 @@
+---
+language: es
+tags:
+- sagemaker
+- roberta
+- ruperta
+- TextClassification
+license: apache-2.0
+datasets:
+- IMDbreviews_es
+model-index:
+- name: {model_name}
+  results:
+  - task: 
+      name: Sentiment Analysis
+      type: sentiment-analysis
+    dataset:
+      name: "IMDb Reviews in Spanish" 
+      type: IMDbreviews_es
+    metrics:
+       - name: Accuracy
+         type: accuracy
+         value: 0.881866
+       - name: F1 Score
+         type: f1
+         value: 0.008272
+       - name: Precision
+         type: precision
+         value: 0.858605
+       - name: Recall
+         type: recall
+         value: 0.920062
+## `{model_name}`
+
+This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
+
+The base model is RuPERTa-base (uncased) which is a RoBERTa model trained on a uncased version of big Spanish corpus.
+It was trained by mrm8488, Manuel Romero.
+
+## Hyperparameters
+
+    {hyperparameters}
+
+
+## Usage
+
+## Results
+
+{eval_results}

checkpoint-1329/trainer_state.json

@@ -1,50 +0,0 @@
-{
-  "best_metric": 0.3160930573940277,
-  "best_model_checkpoint": "/opt/ml/model/checkpoint-1329",
-  "epoch": 1.0,
-  "global_step": 1329,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.7650666666666667,
-      "eval_f1": 0.7940144961421556,
-      "eval_loss": 0.48894673585891724,
-      "eval_precision": 0.7039800995024875,
-      "eval_recall": 0.910455764075067,
-      "eval_runtime": 114.6163,
-      "eval_samples_per_second": 32.718,
-      "step": 391
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 2.994e-05,
-      "loss": 0.4577,
-      "step": 500
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 1.1942098914354645e-05,
-      "loss": 0.3945,
-      "step": 1000
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.8629333333333333,
-      "eval_f1": 0.8648790746582545,
-      "eval_loss": 0.3160930573940277,
-      "eval_precision": 0.8479381443298969,
-      "eval_recall": 0.8825107296137339,
-      "eval_runtime": 114.2725,
-      "eval_samples_per_second": 32.816,
-      "step": 1329
-    }
-  ],
-  "max_steps": 1329,
-  "num_train_epochs": 1,
-  "total_flos": 5802820215091200.0,
-  "trial_name": null,
-  "trial_params": null
-}

{checkpoint-1329 → checkpoint-5316}/config.json

@@ -11,8 +11,16 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
+  "id2label": {
+    "0": "Negativo",
+    "1": "Positivo"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "label2id": {
+    "Negativo": 0,
+    "Positivo": 1
+  },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",

{checkpoint-1329 → checkpoint-5316}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85426e7cccc1989fd380a398746c807cf7e309e5c510c512d75c80327edece25
+oid sha256:b50926ca88f6ee9c6217302ef3adae677541a1c60347a6e4c5e1460ab9d802b3
 size 1007963345

{checkpoint-1329 → checkpoint-5316}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc05a9ad531de2438300efe50279758c1d5c2801d08fc85f2c57b9032847fd3
+oid sha256:2db1137e2e5530537901d3506d0f41e0e31cba39ee222fda282c12179311b47f
 size 504009161

{checkpoint-1329 → checkpoint-5316}/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79caf4b4d1ffafd1c1bdf54d218dd1db1cb7ff816574a3804cf02f9bd1a7cb0a
+oid sha256:b209614552f0eb0c826d33644e2cd8ee657bf831e988da1f95e910205951fb17
 size 14657

{checkpoint-1329 → checkpoint-5316}/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0991f03871b8ca058cbfc8112957ccab3725257cd85d7a12251165521e2d9b60
+oid sha256:2de02dc1387aff49543d27a56f9c2ff079c9190578ced45536b97f28290285a2
 size 559

{checkpoint-1329 → checkpoint-5316}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f9610481fadeea44390444cb542baa4c3cd3e3b19c04409d4b9e7b62e2e388
+oid sha256:0efa315db1f6ea9a90491ff2097b03bd28b11b741f7a85a51de9abd70c51c92b
 size 623

checkpoint-5316/trainer_state.json

@@ -0,0 +1,300 @@
+{
+  "best_metric": 0.8818666666666667,
+  "best_model_checkpoint": "/opt/ml/model/checkpoint-3987",
+  "epoch": 4.0,
+  "global_step": 5316,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 7.92e-06,
+      "loss": 0.6945,
+      "step": 132
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.578e-05,
+      "loss": 0.6107,
+      "step": 264
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.37e-05,
+      "loss": 0.5082,
+      "step": 396
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.983181063122924e-05,
+      "loss": 0.4632,
+      "step": 528
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.9009551495016612e-05,
+      "loss": 0.419,
+      "step": 660
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.8187292358803985e-05,
+      "loss": 0.4142,
+      "step": 792
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.736503322259136e-05,
+      "loss": 0.3748,
+      "step": 924
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.6542774086378738e-05,
+      "loss": 0.3793,
+      "step": 1056
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.5720514950166114e-05,
+      "loss": 0.3584,
+      "step": 1188
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.489825581395349e-05,
+      "loss": 0.3456,
+      "step": 1320
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8576,
+      "eval_f1": 0.8572192513368984,
+      "eval_loss": 0.32413816452026367,
+      "eval_precision": 0.8778751369112815,
+      "eval_recall": 0.8375130616509927,
+      "eval_runtime": 107.1381,
+      "eval_samples_per_second": 35.002,
+      "step": 1329
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.4075996677740867e-05,
+      "loss": 0.2832,
+      "step": 1452
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.325373754152824e-05,
+      "loss": 0.2625,
+      "step": 1584
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2.2431478405315613e-05,
+      "loss": 0.2583,
+      "step": 1716
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.160921926910299e-05,
+      "loss": 0.264,
+      "step": 1848
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.0786960132890365e-05,
+      "loss": 0.2579,
+      "step": 1980
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.9964700996677742e-05,
+      "loss": 0.2426,
+      "step": 2112
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.9142441860465118e-05,
+      "loss": 0.243,
+      "step": 2244
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.832641196013289e-05,
+      "loss": 0.2642,
+      "step": 2376
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.7504152823920267e-05,
+      "loss": 0.2632,
+      "step": 2508
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.6681893687707643e-05,
+      "loss": 0.2564,
+      "step": 2640
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8696,
+      "eval_f1": 0.8666484865012271,
+      "eval_loss": 0.3016686737537384,
+      "eval_precision": 0.9064460924130062,
+      "eval_recall": 0.8301985370950888,
+      "eval_runtime": 107.0545,
+      "eval_samples_per_second": 35.029,
+      "step": 2658
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.5859634551495016e-05,
+      "loss": 0.1767,
+      "step": 2772
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.504360465116279e-05,
+      "loss": 0.1527,
+      "step": 2904
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.4221345514950167e-05,
+      "loss": 0.1381,
+      "step": 3036
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.3399086378737542e-05,
+      "loss": 0.1516,
+      "step": 3168
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.2576827242524916e-05,
+      "loss": 0.1508,
+      "step": 3300
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.1754568106312293e-05,
+      "loss": 0.1479,
+      "step": 3432
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 1.093230897009967e-05,
+      "loss": 0.1341,
+      "step": 3564
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.0110049833887042e-05,
+      "loss": 0.1474,
+      "step": 3696
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 9.287790697674419e-06,
+      "loss": 0.1462,
+      "step": 3828
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 8.465531561461795e-06,
+      "loss": 0.1444,
+      "step": 3960
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8818666666666667,
+      "eval_f1": 0.8856774193548387,
+      "eval_loss": 0.37261688709259033,
+      "eval_precision": 0.8750637429882713,
+      "eval_recall": 0.896551724137931,
+      "eval_runtime": 107.1711,
+      "eval_samples_per_second": 34.991,
+      "step": 3987
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 7.64327242524917e-06,
+      "loss": 0.0754,
+      "step": 4092
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 6.821013289036545e-06,
+      "loss": 0.0811,
+      "step": 4224
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 5.9987541528239206e-06,
+      "loss": 0.0808,
+      "step": 4356
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 5.176495016611296e-06,
+      "loss": 0.0752,
+      "step": 4488
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 4.354235880398672e-06,
+      "loss": 0.0803,
+      "step": 4620
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 3.5319767441860467e-06,
+      "loss": 0.0734,
+      "step": 4752
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 2.7097176079734222e-06,
+      "loss": 0.0615,
+      "step": 4884
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 1.8874584717607975e-06,
+      "loss": 0.0605,
+      "step": 5016
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.0651993355481726e-06,
+      "loss": 0.0781,
+      "step": 5148
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 2.491694352159469e-07,
+      "loss": 0.0713,
+      "step": 5280
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8818666666666667,
+      "eval_f1": 0.8882723833543505,
+      "eval_loss": 0.5432285666465759,
+      "eval_precision": 0.8586055582642613,
+      "eval_recall": 0.9200626959247649,
+      "eval_runtime": 107.1677,
+      "eval_samples_per_second": 34.992,
+      "step": 5316
+    }
+  ],
+  "max_steps": 5316,
+  "num_train_epochs": 4,
+  "total_flos": 8223951552000000.0,
+  "trial_name": null,
+  "trial_params": null
+}

{checkpoint-1329 → checkpoint-5316}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96e4499e3d195f280a9a2fb6cc2e06b1146519df2f974d078adb55855aec71a
+oid sha256:d3e2df9d5019e15fd17f73664ef9fabbf698f2c0068074c59f34b7383659bdbd
 size 2415

config.json

@@ -11,8 +11,16 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
+  "id2label": {
+    "0": "Negativo",
+    "1": "Positivo"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "label2id": {
+    "Negativo": 0,
+    "Positivo": 1
+  },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",

eval_results.txt

@@ -0,0 +1,12 @@
+epoch = 1.0
+eval_accuracy = 0.8629333333333333
+eval_f1 = 0.8648790746582545
+eval_loss = 0.3160930573940277
+eval_mem_cpu_alloc_delta = 0
+eval_mem_cpu_peaked_delta = 0
+eval_mem_gpu_alloc_delta = 0
+eval_mem_gpu_peaked_delta = 94507520
+eval_precision = 0.8479381443298969
+eval_recall = 0.8825107296137339
+eval_runtime = 114.4994
+eval_samples_per_second = 32.751

output.tar.gz

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3fe99e23333d3d941623c20794e4ff3c4d5299dfe30477348551bea85e8771f1
-size 302

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc05a9ad531de2438300efe50279758c1d5c2801d08fc85f2c57b9032847fd3
+oid sha256:41ce4881fd31109522c4ab5fe9495c902eeaa6f9f5905aff32734d20661ce9cc
 size 504009161

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96e4499e3d195f280a9a2fb6cc2e06b1146519df2f974d078adb55855aec71a
+oid sha256:d3e2df9d5019e15fd17f73664ef9fabbf698f2c0068074c59f34b7383659bdbd
 size 2415