Upload folder using huggingface_hub

checkpoint-20/adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "k_proj",
     "v_proj",
-    "o_proj"
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

checkpoint-20/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67f93cdadbe7004e290ff17d7efaf31b1ad0c58e951c63623a7ec2db46baa3a0
+oid sha256:3d92ebaca9f39e58260e5fd0986ae831944b38b613bc026beed264733021292c
 size 436242776

checkpoint-20/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1f3350cd435ac056c183cc29db9441a9f89e9e4bcdebaa06bdd15e0287bb1f1
+oid sha256:218a54094316a9e52229eccf60346ea4f16ea75c546bb58ae1812eac0b1878c7
 size 872568314

checkpoint-20/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d08c0c3fb3de62a4c39c2dd09221b2c5eb71b33e9ddfa0dcea7e1d8b3175714f
-size 14512
+oid sha256:22d602c1deb78b9595b2b25e679aeb5e9164c6fee9da5d72443b40b85c613bd7
+size 15024

checkpoint-20/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3436f6b74a42fc7a55137f98c160bcde850031a076725f6cd3792a86a06ebdbc
-size 14512
+oid sha256:353c60d4bfc98b97ccf640512c4e8cbc1e4fed0b400b0194b18399d7475f986c
+size 15024

checkpoint-20/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c60be257347464a2f4f18286e268e0f4810c0e6453e5c9541c35f430dab6c52
+oid sha256:69ef5eee58b82f54616c0e2c590d3e3b3237d203b45aac85ddccbd8b2b34fb5c
 size 1000

checkpoint-20/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.48089343309402466,
+  "best_metric": 0.467332661151886,
   "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-20",
-  "epoch": 0.09913258983890955,
+  "epoch": 0.19801980198019803,
   "eval_steps": 10,
   "global_step": 20,
   "is_hyper_param_search": false,
@@ -9,26 +9,26 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.05,
-      "eval_loss": 0.6367942690849304,
-      "eval_runtime": 180.8957,
-      "eval_samples_per_second": 15.849,
-      "eval_steps_per_second": 0.995,
+      "epoch": 0.1,
+      "eval_loss": 0.6981944441795349,
+      "eval_runtime": 94.6462,
+      "eval_samples_per_second": 30.292,
+      "eval_steps_per_second": 0.951,
       "step": 10
     },
     {
-      "epoch": 0.1,
-      "grad_norm": 0.34346863627433777,
-      "learning_rate": 0.00019510565162951537,
-      "loss": 0.9774,
+      "epoch": 0.2,
+      "grad_norm": 0.2654201090335846,
+      "learning_rate": 0.0001961261695938319,
+      "loss": 1.0016,
       "step": 20
     },
     {
-      "epoch": 0.1,
-      "eval_loss": 0.48089343309402466,
-      "eval_runtime": 180.8882,
-      "eval_samples_per_second": 15.85,
-      "eval_steps_per_second": 0.995,
+      "epoch": 0.2,
+      "eval_loss": 0.467332661151886,
+      "eval_runtime": 94.5373,
+      "eval_samples_per_second": 30.327,
+      "eval_steps_per_second": 0.952,
       "step": 20
     }
   ],
@@ -37,7 +37,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 9.010061420947046e+16,
+  "total_flos": 1.7984776120041472e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

checkpoint-20/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
+oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
 size 5176

checkpoint-30/adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "k_proj",
     "v_proj",
-    "o_proj"
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

checkpoint-30/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24867322dfb4671521880b7952dfecf869c9ddf50ba8c8d0ab60442d46c3b6e7
+oid sha256:78ab022ca343660d1f280ec34a80faffada6b025a2a7879119d1810181a75394
 size 436242776

checkpoint-30/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a095acb983c64222b3980c352b38e58ba4bd6e2f0b8e559eddea78a65277790
+oid sha256:19650f1cc2280227bbfe7e965edd69b2ee9cacbd13b3e7bb3742aba3a3e324d5
 size 872568314

checkpoint-30/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2a616f0c7a81cc42f0138e0036f3bc925663524713430ec02128feb7cc22f7
-size 14512
+oid sha256:8dadf22c8d1bce4ad601a4f73bbe39dc8987d3b42389b4025267f79988efccce
+size 15024

checkpoint-30/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3547aee58cf2280e2d966f891fba83ef181a792754cf251e62b59ae644dd2253
-size 14512
+oid sha256:528debf43ac8e68f3972cc6eedc188d70690e0a9bfc2feeeff97e757be99c6b8
+size 15024

checkpoint-30/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35079c4c5c54e3e2a4600c729d1fa32b43362d22b0baf443894af8a786492df1
+oid sha256:8783ce7e95711682ad7c1657af7a6be242f3bc4b6aac1f9aa4521dd59b1618c4
 size 1000

checkpoint-30/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.44581571221351624,
+  "best_metric": 0.434685617685318,
   "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-30",
-  "epoch": 0.14869888475836432,
+  "epoch": 0.297029702970297,
   "eval_steps": 10,
   "global_step": 30,
   "is_hyper_param_search": false,
@@ -9,34 +9,34 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.05,
-      "eval_loss": 0.6367942690849304,
-      "eval_runtime": 180.8957,
-      "eval_samples_per_second": 15.849,
-      "eval_steps_per_second": 0.995,
+      "epoch": 0.1,
+      "eval_loss": 0.6981944441795349,
+      "eval_runtime": 94.6462,
+      "eval_samples_per_second": 30.292,
+      "eval_steps_per_second": 0.951,
       "step": 10
     },
     {
-      "epoch": 0.1,
-      "grad_norm": 0.34346863627433777,
-      "learning_rate": 0.00019510565162951537,
-      "loss": 0.9774,
+      "epoch": 0.2,
+      "grad_norm": 0.2654201090335846,
+      "learning_rate": 0.0001961261695938319,
+      "loss": 1.0016,
       "step": 20
     },
     {
-      "epoch": 0.1,
-      "eval_loss": 0.48089343309402466,
-      "eval_runtime": 180.8882,
-      "eval_samples_per_second": 15.85,
-      "eval_steps_per_second": 0.995,
+      "epoch": 0.2,
+      "eval_loss": 0.467332661151886,
+      "eval_runtime": 94.5373,
+      "eval_samples_per_second": 30.327,
+      "eval_steps_per_second": 0.952,
       "step": 20
     },
     {
-      "epoch": 0.15,
-      "eval_loss": 0.44581571221351624,
-      "eval_runtime": 180.8305,
-      "eval_samples_per_second": 15.855,
-      "eval_steps_per_second": 0.995,
+      "epoch": 0.3,
+      "eval_loss": 0.434685617685318,
+      "eval_runtime": 94.5899,
+      "eval_samples_per_second": 30.31,
+      "eval_steps_per_second": 0.951,
       "step": 30
     }
   ],
@@ -45,7 +45,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 1.3497349192024064e+17,
+  "total_flos": 2.6847278785573683e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

checkpoint-30/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
+oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
 size 5176

checkpoint-60/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

checkpoint-60/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-60/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a577788564336cd758857128393efbd78731bd63c646a0a8868069a04bc06d
+size 436242776

checkpoint-60/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9944a4e4f4a5467e99ea0ad58063a2c1b25b19bc23f0078c6f2d353021b5f6e
+size 872568314

checkpoint-60/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c630bd23adfff720203169b24dd4380dc27f0d69719769ee1e1ceeb3c5c10fcb
+size 15024

checkpoint-60/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52463e6d4b8fae410009495cb4e850467249c01e85e6a48fd855d781d74722bd
+size 15024

checkpoint-60/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3c039fdeb45ea8aa8146ad01ff86eb68fca445a815f5700c498f5b143c8232
+size 15024

checkpoint-60/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d233069ff367e405677712709d910c8c25ad8d71df8c7065b76f9442832efb
+size 15024

checkpoint-60/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b84a77370cc727f7aa593f3181d7f46c2c1dfa4c5366599579edf64898dd719
+size 1000

checkpoint-60/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-60/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-60/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_lenght": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding": true,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-60/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.39164847135543823,
+  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-60",
+  "epoch": 0.594059405940594,
+  "eval_steps": 10,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.6981944441795349,
+      "eval_runtime": 94.6462,
+      "eval_samples_per_second": 30.292,
+      "eval_steps_per_second": 0.951,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2654201090335846,
+      "learning_rate": 0.0001961261695938319,
+      "loss": 1.0016,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.467332661151886,
+      "eval_runtime": 94.5373,
+      "eval_samples_per_second": 30.327,
+      "eval_steps_per_second": 0.952,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.434685617685318,
+      "eval_runtime": 94.5899,
+      "eval_samples_per_second": 30.31,
+      "eval_steps_per_second": 0.951,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3763986825942993,
+      "learning_rate": 0.0001559192903470747,
+      "loss": 0.4357,
+      "step": 40
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.4082697033882141,
+      "eval_runtime": 94.551,
+      "eval_samples_per_second": 30.322,
+      "eval_steps_per_second": 0.952,
+      "step": 40
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.40642818808555603,
+      "eval_runtime": 94.5831,
+      "eval_samples_per_second": 30.312,
+      "eval_steps_per_second": 0.952,
+      "step": 50
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.16300354897975922,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.4012,
+      "step": 60
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 0.39164847135543823,
+      "eval_runtime": 94.6074,
+      "eval_samples_per_second": 30.304,
+      "eval_steps_per_second": 0.951,
+      "step": 60
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "total_flos": 5.408920407711416e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-60/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
+size 5176