Training in progress, step 1400, checkpoint

checkpoint-1400/README.md

@@ -0,0 +1,202 @@
+---
+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 0.9.0

checkpoint-1400/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:085d16218172072a247758a55450d8af42e12501d37dc5af6640fef21f2f0e7e
+size 83945296

checkpoint-1400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b15e1d32fd367e4b3b6544e099c708cf5b89dff10fd74c87d37372aa597d6c5
+size 168149074

checkpoint-1400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec09d49098da5cc697950fec97e0772a7ba1b948f5fb8d3ce60748e399bdfbe6
+size 14244

checkpoint-1400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758cccf4883e1b3befb92a14432f922aa1045753bb27859345d514ef9bea987e
+size 1064

checkpoint-1400/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-1400/tokenizer.model

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

checkpoint-1400/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-1400/trainer_state.json

@@ -0,0 +1,455 @@
+{
+  "best_metric": 0.04491905868053436,
+  "best_model_checkpoint": "./Mistral/05-03-24-mistralai-Mistral-7B-Instruct-v0.2_multilang-dataset-3.2.0-2_epochs-1_batch_8/checkpoints/checkpoint-1400",
+  "epoch": 0.8682170542635659,
+  "eval_steps": 100,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.648464679718018,
+      "learning_rate": 3.209876543209876e-05,
+      "loss": 5.2191,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.2440924644470215,
+      "learning_rate": 6.790123456790123e-05,
+      "loss": 0.1533,
+      "step": 60
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.61743426322937,
+      "learning_rate": 0.00010493827160493828,
+      "loss": 0.1164,
+      "step": 90
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.10366858541965485,
+      "eval_runtime": 378.9363,
+      "eval_samples_per_second": 7.566,
+      "eval_steps_per_second": 3.784,
+      "step": 100
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 5.026630878448486,
+      "learning_rate": 0.00014197530864197534,
+      "loss": 0.0978,
+      "step": 120
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.5573928356170654,
+      "learning_rate": 0.00017901234567901234,
+      "loss": 0.1202,
+      "step": 150
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 2.880843162536621,
+      "learning_rate": 0.00019996620349638285,
+      "loss": 0.1355,
+      "step": 180
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.10505001991987228,
+      "eval_runtime": 379.3305,
+      "eval_samples_per_second": 7.558,
+      "eval_steps_per_second": 3.78,
+      "step": 200
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 4.4998297691345215,
+      "learning_rate": 0.00019958625513182815,
+      "loss": 0.1064,
+      "step": 210
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 2.7974424362182617,
+      "learning_rate": 0.00019878572276863294,
+      "loss": 0.1194,
+      "step": 240
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.9094600677490234,
+      "learning_rate": 0.00019756798730611813,
+      "loss": 0.1095,
+      "step": 270
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 3.1164822578430176,
+      "learning_rate": 0.00019593819162318232,
+      "loss": 0.1015,
+      "step": 300
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 0.11415495723485947,
+      "eval_runtime": 379.0247,
+      "eval_samples_per_second": 7.564,
+      "eval_steps_per_second": 3.783,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.27632737159729,
+      "learning_rate": 0.0001939032188583108,
+      "loss": 0.088,
+      "step": 330
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 2.5714831352233887,
+      "learning_rate": 0.00019147166333992205,
+      "loss": 0.1157,
+      "step": 360
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.944558620452881,
+      "learning_rate": 0.00018865379428982271,
+      "loss": 0.1026,
+      "step": 390
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.09923809766769409,
+      "eval_runtime": 379.1528,
+      "eval_samples_per_second": 7.562,
+      "eval_steps_per_second": 3.782,
+      "step": 400
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.4601669311523438,
+      "learning_rate": 0.00018546151245306205,
+      "loss": 0.1002,
+      "step": 420
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 1.8168306350708008,
+      "learning_rate": 0.00018190829983735207,
+      "loss": 0.0924,
+      "step": 450
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.477660894393921,
+      "learning_rate": 0.00017800916277431908,
+      "loss": 0.1002,
+      "step": 480
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.1082511618733406,
+      "eval_runtime": 379.2943,
+      "eval_samples_per_second": 7.559,
+      "eval_steps_per_second": 3.781,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.3156869411468506,
+      "learning_rate": 0.00017378056854305747,
+      "loss": 0.0854,
+      "step": 510
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.603376626968384,
+      "learning_rate": 0.0001692403758236437,
+      "loss": 0.094,
+      "step": 540
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 3.5813493728637695,
+      "learning_rate": 0.00016440775927432753,
+      "loss": 0.0934,
+      "step": 570
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.6073071956634521,
+      "learning_rate": 0.0001593031285509347,
+      "loss": 0.0879,
+      "step": 600
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 0.08940836787223816,
+      "eval_runtime": 379.1574,
+      "eval_samples_per_second": 7.562,
+      "eval_steps_per_second": 3.782,
+      "step": 600
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 25.474618911743164,
+      "learning_rate": 0.00015394804211048702,
+      "loss": 0.0755,
+      "step": 630
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.6535922288894653,
+      "learning_rate": 0.000148365116163075,
+      "loss": 0.0997,
+      "step": 660
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.3517935276031494,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 0.0778,
+      "step": 690
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.09067929536104202,
+      "eval_runtime": 379.1218,
+      "eval_samples_per_second": 7.562,
+      "eval_steps_per_second": 3.782,
+      "step": 700
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.7602508068084717,
+      "learning_rate": 0.00013661092219712802,
+      "loss": 0.0859,
+      "step": 720
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.499081134796143,
+      "learning_rate": 0.00013048929582735723,
+      "loss": 0.0836,
+      "step": 750
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.043173909187317,
+      "learning_rate": 0.00012423890359589368,
+      "loss": 0.0836,
+      "step": 780
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.07465904951095581,
+      "eval_runtime": 379.0646,
+      "eval_samples_per_second": 7.563,
+      "eval_steps_per_second": 3.783,
+      "step": 800
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.594491481781006,
+      "learning_rate": 0.00011788614287006786,
+      "loss": 0.0822,
+      "step": 810
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.741464614868164,
+      "learning_rate": 0.00011145784335147793,
+      "loss": 0.0785,
+      "step": 840
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.201212763786316,
+      "learning_rate": 0.00010498115376574294,
+      "loss": 0.0827,
+      "step": 870
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.8033993244171143,
+      "learning_rate": 9.848342720491665e-05,
+      "loss": 0.0642,
+      "step": 900
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 0.06445665657520294,
+      "eval_runtime": 379.151,
+      "eval_samples_per_second": 7.562,
+      "eval_steps_per_second": 3.782,
+      "step": 900
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 40.951148986816406,
+      "learning_rate": 9.199210560679876e-05,
+      "loss": 0.0856,
+      "step": 930
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.092067003250122,
+      "learning_rate": 8.553460385902189e-05,
+      "loss": 0.0665,
+      "step": 960
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.4154521226882935,
+      "learning_rate": 7.913819401738049e-05,
+      "loss": 0.0496,
+      "step": 990
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.07089055329561234,
+      "eval_runtime": 379.3022,
+      "eval_samples_per_second": 7.559,
+      "eval_steps_per_second": 3.781,
+      "step": 1000
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.431265950202942,
+      "learning_rate": 7.282989012738286e-05,
+      "loss": 0.0657,
+      "step": 1020
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.9289568066596985,
+      "learning_rate": 6.663633413546215e-05,
+      "loss": 0.0689,
+      "step": 1050
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 8.26246452331543,
+      "learning_rate": 6.0583683371678045e-05,
+      "loss": 0.06,
+      "step": 1080
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.06025632470846176,
+      "eval_runtime": 379.2152,
+      "eval_samples_per_second": 7.56,
+      "eval_steps_per_second": 3.781,
+      "step": 1100
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 1.6637234687805176,
+      "learning_rate": 5.4697500079105446e-05,
+      "loss": 0.0497,
+      "step": 1110
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.5166139602661133,
+      "learning_rate": 4.9002643456462527e-05,
+      "loss": 0.0444,
+      "step": 1140
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.845469355583191,
+      "learning_rate": 4.35231646699155e-05,
+      "loss": 0.0534,
+      "step": 1170
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.517876386642456,
+      "learning_rate": 3.828220527745796e-05,
+      "loss": 0.0614,
+      "step": 1200
+    },
+    {
+      "epoch": 0.74,
+      "eval_loss": 0.05674314126372337,
+      "eval_runtime": 379.2962,
+      "eval_samples_per_second": 7.559,
+      "eval_steps_per_second": 3.781,
+      "step": 1200
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.1431076526641846,
+      "learning_rate": 3.330189949485176e-05,
+      "loss": 0.0549,
+      "step": 1230
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.964785575866699,
+      "learning_rate": 2.8603280715889302e-05,
+      "loss": 0.0464,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.28953278064727783,
+      "learning_rate": 2.42061926817729e-05,
+      "loss": 0.0538,
+      "step": 1290
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 0.047811124473810196,
+      "eval_runtime": 379.3775,
+      "eval_samples_per_second": 7.557,
+      "eval_steps_per_second": 3.78,
+      "step": 1300
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 6.412265300750732,
+      "learning_rate": 2.012920567477007e-05,
+      "loss": 0.0477,
+      "step": 1320
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.20676860213279724,
+      "learning_rate": 1.6389538090085464e-05,
+      "loss": 0.0439,
+      "step": 1350
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.3963369131088257,
+      "learning_rate": 1.3002983717175953e-05,
+      "loss": 0.0524,
+      "step": 1380
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 0.04491905868053436,
+      "eval_runtime": 379.1879,
+      "eval_samples_per_second": 7.561,
+      "eval_steps_per_second": 3.782,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 30,
+  "max_steps": 1612,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 7.165941039908782e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b934bc66c84e74712cf0a7647576ea2832610f1d81b30a0d347dfc5aa1763d4
+size 5176