Duplicate from jssky/cfe0545d-c311-4406-acae-9d40eac3b878

Co-authored-by: Jasper Smith <[email protected]>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,154 @@
+---
+library_name: peft
+license: bigscience-bloom-rail-1.0
+base_model: bigscience/bloomz-560m
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: cfe0545d-c311-4406-acae-9d40eac3b878
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.5.2`
+```yaml
+adapter: lora
+base_model: bigscience/bloomz-560m
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 437d6156515bf54f_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/437d6156515bf54f_train_data.json
+  type:
+    field_input: new-context
+    field_instruction: new-instruction
+    field_output: new-response
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: 1
+eval_max_new_tokens: 128
+eval_steps: 25
+eval_table_size: null
+flash_attention: false
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 16
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: jssky/cfe0545d-c311-4406-acae-9d40eac3b878
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: cosine
+max_steps: 50
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/437d6156515bf54f_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 25
+sequence_len: 2048
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: cfe0545d-c311-4406-acae-9d40eac3b878
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: cfe0545d-c311-4406-acae-9d40eac3b878
+warmup_ratio: 0.05
+weight_decay: 0.01
+xformers_attention: true
+
+```
+
+</details><br>
+
+# cfe0545d-c311-4406-acae-9d40eac3b878
+
+This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7002
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2
+- training_steps: 50
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.1331        | 0.0091 | 1    | 2.1480          |
+| 0.8535        | 0.2273 | 25   | 1.7152          |
+| 0.7838        | 0.4545 | 50   | 1.7002          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.3
+- Pytorch 2.3.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigscience/bloomz-560m",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense_h_to_4h",
+    "query_key_value",
+    "dense_4h_to_h",
+    "dense"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df31e0d402bd51957ce61e3602182c2b887e179068f8e8bf24921ef13571430
+size 50402250

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb10d8bd0fb89a556c1e4d763900866c216d0de4e38073c5d3b75aaaaeacf65b
+size 50358592

config.json

@@ -0,0 +1,33 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "bigscience/bloomz-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "transformers_version": "4.46.3",
+  "unk_token_id": 0,
+  "use_cache": false,
+  "vocab_size": 250880
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: bigscience/bloomz-560m
+library_name: peft
+---
+
+# 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 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigscience/bloomz-560m",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense_h_to_4h",
+    "query_key_value",
+    "dense_4h_to_h",
+    "dense"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb10d8bd0fb89a556c1e4d763900866c216d0de4e38073c5d3b75aaaaeacf65b
+size 50358592

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d3f454591f1441c893bc5f6d67ed960e826dd4c664484f4e4f25440ef81827f
+size 100824826

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57cac8e737fae0d3fddca6c0b3be6103b99a96f5ea30a5af2945495e22221b55
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0163dd04c7ac47456afc8e2bd8ef91c2043a2abf9966f65afe33afa9f4f17f50
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:485b2a1f251d1abffa872377ec2eed334f5d89b6c2710a8cdb4617f1e1c427d5
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29a44c9bfe5f58b8f38b7808db205fdb1a7052fd0f404654923a302657ee7a6d
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d963066d6adae5034a1dc114c3ac444512de09928cf14ed4562ba94d9a440e66
+size 21763085

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_prefix_space": 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
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>",
+  "vocab_file": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,416 @@
+{
+  "best_metric": 1.700229287147522,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.45454545454545453,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00909090909090909,
+      "grad_norm": 14.925396919250488,
+      "learning_rate": 5e-05,
+      "loss": 2.1331,
+      "step": 1
+    },
+    {
+      "epoch": 0.00909090909090909,
+      "eval_loss": 2.148017644882202,
+      "eval_runtime": 20.639,
+      "eval_samples_per_second": 35.903,
+      "eval_steps_per_second": 4.506,
+      "step": 1
+    },
+    {
+      "epoch": 0.01818181818181818,
+      "grad_norm": 17.743574142456055,
+      "learning_rate": 0.0001,
+      "loss": 1.9866,
+      "step": 2
+    },
+    {
+      "epoch": 0.02727272727272727,
+      "grad_norm": 20.310686111450195,
+      "learning_rate": 9.989294616193017e-05,
+      "loss": 2.0318,
+      "step": 3
+    },
+    {
+      "epoch": 0.03636363636363636,
+      "grad_norm": 14.211567878723145,
+      "learning_rate": 9.957224306869053e-05,
+      "loss": 2.283,
+      "step": 4
+    },
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": 13.183459281921387,
+      "learning_rate": 9.903926402016153e-05,
+      "loss": 2.0879,
+      "step": 5
+    },
+    {
+      "epoch": 0.05454545454545454,
+      "grad_norm": 9.223968505859375,
+      "learning_rate": 9.829629131445342e-05,
+      "loss": 2.2078,
+      "step": 6
+    },
+    {
+      "epoch": 0.06363636363636363,
+      "grad_norm": 10.695703506469727,
+      "learning_rate": 9.73465064747553e-05,
+      "loss": 2.2194,
+      "step": 7
+    },
+    {
+      "epoch": 0.07272727272727272,
+      "grad_norm": 10.545184135437012,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.0946,
+      "step": 8
+    },
+    {
+      "epoch": 0.08181818181818182,
+      "grad_norm": 10.334756851196289,
+      "learning_rate": 9.484363707663442e-05,
+      "loss": 1.8747,
+      "step": 9
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 12.795695304870605,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 1.7231,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 14.544269561767578,
+      "learning_rate": 9.157348061512727e-05,
+      "loss": 1.3743,
+      "step": 11
+    },
+    {
+      "epoch": 0.10909090909090909,
+      "grad_norm": 17.52605628967285,
+      "learning_rate": 8.966766701456177e-05,
+      "loss": 0.9295,
+      "step": 12
+    },
+    {
+      "epoch": 0.11818181818181818,
+      "grad_norm": 18.505111694335938,
+      "learning_rate": 8.759199037394887e-05,
+      "loss": 1.2863,
+      "step": 13
+    },
+    {
+      "epoch": 0.12727272727272726,
+      "grad_norm": 18.229660034179688,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.842,
+      "step": 14
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "grad_norm": 20.484041213989258,
+      "learning_rate": 8.296729075500344e-05,
+      "loss": 1.914,
+      "step": 15
+    },
+    {
+      "epoch": 0.14545454545454545,
+      "grad_norm": 15.05215072631836,
+      "learning_rate": 8.043807145043604e-05,
+      "loss": 1.8708,
+      "step": 16
+    },
+    {
+      "epoch": 0.15454545454545454,
+      "grad_norm": 14.95174503326416,
+      "learning_rate": 7.777851165098012e-05,
+      "loss": 2.0398,
+      "step": 17
+    },
+    {
+      "epoch": 0.16363636363636364,
+      "grad_norm": 22.141672134399414,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.2095,
+      "step": 18
+    },
+    {
+      "epoch": 0.17272727272727273,
+      "grad_norm": 21.83669090270996,
+      "learning_rate": 7.211443451095007e-05,
+      "loss": 2.1674,
+      "step": 19
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 14.860734939575195,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.9985,
+      "step": 20
+    },
+    {
+      "epoch": 0.19090909090909092,
+      "grad_norm": 9.57990837097168,
+      "learning_rate": 6.607197326515808e-05,
+      "loss": 1.9191,
+      "step": 21
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 9.496389389038086,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 1.6848,
+      "step": 22
+    },
+    {
+      "epoch": 0.20909090909090908,
+      "grad_norm": 10.313212394714355,
+      "learning_rate": 5.9754516100806423e-05,
+      "loss": 1.5411,
+      "step": 23
+    },
+    {
+      "epoch": 0.21818181818181817,
+      "grad_norm": 12.132110595703125,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 1.0935,
+      "step": 24
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 25.194284439086914,
+      "learning_rate": 5.327015646150716e-05,
+      "loss": 0.8535,
+      "step": 25
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "eval_loss": 1.7152154445648193,
+      "eval_runtime": 20.6303,
+      "eval_samples_per_second": 35.918,
+      "eval_steps_per_second": 4.508,
+      "step": 25
+    },
+    {
+      "epoch": 0.23636363636363636,
+      "grad_norm": 12.246540069580078,
+      "learning_rate": 5e-05,
+      "loss": 1.9386,
+      "step": 26
+    },
+    {
+      "epoch": 0.24545454545454545,
+      "grad_norm": 14.892560005187988,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.9094,
+      "step": 27
+    },
+    {
+      "epoch": 0.2545454545454545,
+      "grad_norm": 15.888422012329102,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.8493,
+      "step": 28
+    },
+    {
+      "epoch": 0.2636363636363636,
+      "grad_norm": 11.783967971801758,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.9648,
+      "step": 29
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 12.020038604736328,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8546,
+      "step": 30
+    },
+    {
+      "epoch": 0.2818181818181818,
+      "grad_norm": 8.23468017578125,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.3328,
+      "step": 31
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 7.17024564743042,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.9034,
+      "step": 32
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.857868194580078,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.8433,
+      "step": 33
+    },
+    {
+      "epoch": 0.3090909090909091,
+      "grad_norm": 8.575061798095703,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7549,
+      "step": 34
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 9.11682415008545,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.6813,
+      "step": 35
+    },
+    {
+      "epoch": 0.32727272727272727,
+      "grad_norm": 11.802390098571777,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.2056,
+      "step": 36
+    },
+    {
+      "epoch": 0.33636363636363636,
+      "grad_norm": 14.423662185668945,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9957,
+      "step": 37
+    },
+    {
+      "epoch": 0.34545454545454546,
+      "grad_norm": 16.499637603759766,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2123,
+      "step": 38
+    },
+    {
+      "epoch": 0.35454545454545455,
+      "grad_norm": 7.119629859924316,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.7253,
+      "step": 39
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 5.824593544006348,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.7196,
+      "step": 40
+    },
+    {
+      "epoch": 0.37272727272727274,
+      "grad_norm": 5.900935173034668,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.9085,
+      "step": 41
+    },
+    {
+      "epoch": 0.38181818181818183,
+      "grad_norm": 5.92130708694458,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.8316,
+      "step": 42
+    },
+    {
+      "epoch": 0.39090909090909093,
+      "grad_norm": 5.6540446281433105,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.0604,
+      "step": 43
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.884941101074219,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0997,
+      "step": 44
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 6.261735439300537,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0049,
+      "step": 45
+    },
+    {
+      "epoch": 0.41818181818181815,
+      "grad_norm": 6.4765496253967285,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.8522,
+      "step": 46
+    },
+    {
+      "epoch": 0.42727272727272725,
+      "grad_norm": 6.866036891937256,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.5718,
+      "step": 47
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 7.530960559844971,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.6204,
+      "step": 48
+    },
+    {
+      "epoch": 0.44545454545454544,
+      "grad_norm": 9.911762237548828,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0242,
+      "step": 49
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 21.745277404785156,
+      "learning_rate": 0.0,
+      "loss": 0.7838,
+      "step": 50
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "eval_loss": 1.700229287147522,
+      "eval_runtime": 20.6021,
+      "eval_samples_per_second": 35.967,
+      "eval_steps_per_second": 4.514,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "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": 2.4834109347987456e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5793618cad93a5ba164d3f4528440c0888961f4c52ed461bb520a4e59de75e5b
+size 6776

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d963066d6adae5034a1dc114c3ac444512de09928cf14ed4562ba94d9a440e66
+size 21763085

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_prefix_space": 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
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>",
+  "vocab_file": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5793618cad93a5ba164d3f4528440c0888961f4c52ed461bb520a4e59de75e5b
+size 6776