Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: openbmb/MiniCPM-V-2_6
+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 0.12.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "MiniCPMV",
+    "parent_library": "transformers_modules.openbmb.MiniCPM-V-2_6.a38652350cf48f3cedc8e8b2ff73801fe2dcc004.modeling_minicpmv"
+  },
+  "base_model_name_or_path": "openbmb/MiniCPM-V-2_6",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "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": [
+    "embed_tokens",
+    "resampler"
+  ],
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "llm\\..*layers\\.\\d+\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)",
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825bf908aa66c786b7599a49d52fef5bb5e2024fc03f9097987f914aed01815c
+size 1305154312

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</box>": 151651,
+  "</image>": 151647,
+  "</image_id>": 151659,
+  "</point>": 151655,
+  "</quad>": 151653,
+  "</ref>": 151649,
+  "</slice>": 151657,
+  "<box>": 151650,
+  "<image>": 151646,
+  "<image_id>": 151658,
+  "<point>": 151654,
+  "<quad>": 151652,
+  "<ref>": 151648,
+  "<slice>": 151656,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|reserved_special_token_0|>": 151660,
+  "<|reserved_special_token_1|>": 151661,
+  "<|reserved_special_token_2|>": 151662,
+  "<|reserved_special_token_3|>": 151663,
+  "<|reserved_special_token_4|>": 151664,
+  "<|reserved_special_token_5|>": 151665
+}

events.out.tfevents.1723597115.ab7fb61a2d26.2431.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7708921224bbf097d0f97e31264762443d57a80311a88fd56607b570c2b9b4b5
+size 20071

special_tokens_map.json

@@ -0,0 +1,52 @@
+{
+  "additional_special_tokens": [
+    "<image>",
+    "</image>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>",
+    "<quad>",
+    "</quad>",
+    "<point>",
+    "</point>",
+    "<slice>",
+    "</slice>",
+    "<image_id>",
+    "</image_id>",
+    "<|reserved_special_token_0|>",
+    "<|reserved_special_token_1|>",
+    "<|reserved_special_token_2|>",
+    "<|reserved_special_token_3|>",
+    "<|reserved_special_token_4|>",
+    "<|reserved_special_token_5|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,235 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "128244": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "</image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "</ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "</box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "</quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<point>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "</point>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<slice>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "</slice>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151658": {
+      "content": "<image_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151659": {
+      "content": "</image_id>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151660": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151661": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151662": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151663": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151664": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151665": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<image>",
+    "</image>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>",
+    "<quad>",
+    "</quad>",
+    "<point>",
+    "</point>",
+    "<slice>",
+    "</slice>",
+    "<image_id>",
+    "</image_id>",
+    "<|reserved_special_token_0|>",
+    "<|reserved_special_token_1|>",
+    "<|reserved_special_token_2|>",
+    "<|reserved_special_token_3|>",
+    "<|reserved_special_token_4|>",
+    "<|reserved_special_token_5|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "openbmb/MiniCPM-V-2_6--tokenization_minicpmv_fast.MiniCPMVTokenizerFast",
+      null
+    ]
+  },
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "MiniCPMVTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,497 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 34.285714285714285,
+  "eval_steps": 10,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0,
+      "loss": 1.3796,
+      "step": 1
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 2.2001447677612305,
+      "learning_rate": 0.0,
+      "loss": 0.2105,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.2001447677612305,
+      "learning_rate": 0.0,
+      "loss": 0.962,
+      "step": 3
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.8828794360160828,
+      "learning_rate": 0.0002,
+      "loss": 0.2299,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.8828794360160828,
+      "learning_rate": 0.0002,
+      "loss": 0.8788,
+      "step": 5
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.7549806237220764,
+      "learning_rate": 0.0002,
+      "loss": 0.5161,
+      "step": 6
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.7549806237220764,
+      "learning_rate": 0.0002,
+      "loss": 0.5018,
+      "step": 7
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.5643095970153809,
+      "learning_rate": 0.0002,
+      "loss": 0.5318,
+      "step": 8
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5643095970153809,
+      "learning_rate": 0.0002,
+      "loss": 0.3574,
+      "step": 9
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 0.6527697443962097,
+      "learning_rate": 0.0002,
+      "loss": 0.6326,
+      "step": 10
+    },
+    {
+      "epoch": 5.714285714285714,
+      "eval_loss": 0.7977780103683472,
+      "eval_runtime": 1.1094,
+      "eval_samples_per_second": 6.31,
+      "eval_steps_per_second": 6.31,
+      "step": 10
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.6527697443962097,
+      "learning_rate": 0.0002,
+      "loss": 0.1602,
+      "step": 11
+    },
+    {
+      "epoch": 6.857142857142857,
+      "grad_norm": 0.6531093716621399,
+      "learning_rate": 0.0002,
+      "loss": 0.5492,
+      "step": 12
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.6531093716621399,
+      "learning_rate": 0.0002,
+      "loss": 0.1361,
+      "step": 13
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5385488867759705,
+      "learning_rate": 0.0002,
+      "loss": 0.5893,
+      "step": 14
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.5385488867759705,
+      "learning_rate": 0.0002,
+      "loss": 0.475,
+      "step": 15
+    },
+    {
+      "epoch": 9.142857142857142,
+      "grad_norm": 0.5094980001449585,
+      "learning_rate": 0.0002,
+      "loss": 0.0501,
+      "step": 16
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.5094980001449585,
+      "learning_rate": 0.0002,
+      "loss": 0.3318,
+      "step": 17
+    },
+    {
+      "epoch": 10.285714285714286,
+      "grad_norm": 0.5739837884902954,
+      "learning_rate": 0.0002,
+      "loss": 0.154,
+      "step": 18
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.5739837884902954,
+      "learning_rate": 0.0002,
+      "loss": 0.1339,
+      "step": 19
+    },
+    {
+      "epoch": 11.428571428571429,
+      "grad_norm": 0.5782333016395569,
+      "learning_rate": 0.0002,
+      "loss": 0.1008,
+      "step": 20
+    },
+    {
+      "epoch": 11.428571428571429,
+      "eval_loss": 0.1741267442703247,
+      "eval_runtime": 1.0921,
+      "eval_samples_per_second": 6.41,
+      "eval_steps_per_second": 6.41,
+      "step": 20
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.5782333016395569,
+      "learning_rate": 0.0002,
+      "loss": 0.1043,
+      "step": 21
+    },
+    {
+      "epoch": 12.571428571428571,
+      "grad_norm": 0.558684229850769,
+      "learning_rate": 0.0002,
+      "loss": 0.1308,
+      "step": 22
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.558684229850769,
+      "learning_rate": 0.0002,
+      "loss": 0.0082,
+      "step": 23
+    },
+    {
+      "epoch": 13.714285714285714,
+      "grad_norm": 0.3258131444454193,
+      "learning_rate": 0.0002,
+      "loss": 0.0663,
+      "step": 24
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.3258131444454193,
+      "learning_rate": 0.0002,
+      "loss": 0.0114,
+      "step": 25
+    },
+    {
+      "epoch": 14.857142857142858,
+      "grad_norm": 0.3965975046157837,
+      "learning_rate": 0.0002,
+      "loss": 0.0503,
+      "step": 26
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.3965975046157837,
+      "learning_rate": 0.0002,
+      "loss": 0.0026,
+      "step": 27
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.6329053044319153,
+      "learning_rate": 0.0002,
+      "loss": 0.0271,
+      "step": 28
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.6329053044319153,
+      "learning_rate": 0.0002,
+      "loss": 0.0145,
+      "step": 29
+    },
+    {
+      "epoch": 17.142857142857142,
+      "grad_norm": 0.1660483181476593,
+      "learning_rate": 0.0002,
+      "loss": 0.0003,
+      "step": 30
+    },
+    {
+      "epoch": 17.142857142857142,
+      "eval_loss": 0.008966931141912937,
+      "eval_runtime": 1.1273,
+      "eval_samples_per_second": 6.21,
+      "eval_steps_per_second": 6.21,
+      "step": 30
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.1660483181476593,
+      "learning_rate": 0.0002,
+      "loss": 0.0076,
+      "step": 31
+    },
+    {
+      "epoch": 18.285714285714285,
+      "grad_norm": 0.16035296022891998,
+      "learning_rate": 0.0002,
+      "loss": 0.0006,
+      "step": 32
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.16035296022891998,
+      "learning_rate": 0.0002,
+      "loss": 0.0027,
+      "step": 33
+    },
+    {
+      "epoch": 19.428571428571427,
+      "grad_norm": 0.22989660501480103,
+      "learning_rate": 0.0002,
+      "loss": 0.0022,
+      "step": 34
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.22989660501480103,
+      "learning_rate": 0.0002,
+      "loss": 0.0006,
+      "step": 35
+    },
+    {
+      "epoch": 20.571428571428573,
+      "grad_norm": 0.025392575189471245,
+      "learning_rate": 0.0002,
+      "loss": 0.0004,
+      "step": 36
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 0.025392575189471245,
+      "learning_rate": 0.0002,
+      "loss": 0.0037,
+      "step": 37
+    },
+    {
+      "epoch": 21.714285714285715,
+      "grad_norm": 0.7075601816177368,
+      "learning_rate": 0.0002,
+      "loss": 0.0039,
+      "step": 38
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.7075601816177368,
+      "learning_rate": 0.0002,
+      "loss": 0.0002,
+      "step": 39
+    },
+    {
+      "epoch": 22.857142857142858,
+      "grad_norm": 0.057493291795253754,
+      "learning_rate": 0.0002,
+      "loss": 0.0009,
+      "step": 40
+    },
+    {
+      "epoch": 22.857142857142858,
+      "eval_loss": 0.001083305454812944,
+      "eval_runtime": 1.1213,
+      "eval_samples_per_second": 6.243,
+      "eval_steps_per_second": 6.243,
+      "step": 40
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.057493291795253754,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "step": 41
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.043593935668468475,
+      "learning_rate": 0.0002,
+      "loss": 0.001,
+      "step": 42
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.043593935668468475,
+      "learning_rate": 0.0002,
+      "loss": 0.0017,
+      "step": 43
+    },
+    {
+      "epoch": 25.142857142857142,
+      "grad_norm": 0.1038336306810379,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "step": 44
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 0.1038336306810379,
+      "learning_rate": 0.0002,
+      "loss": 0.0013,
+      "step": 45
+    },
+    {
+      "epoch": 26.285714285714285,
+      "grad_norm": 0.1458902508020401,
+      "learning_rate": 0.0002,
+      "loss": 0.0011,
+      "step": 46
+    },
+    {
+      "epoch": 27.0,
+      "grad_norm": 0.1458902508020401,
+      "learning_rate": 0.0002,
+      "loss": 0.0003,
+      "step": 47
+    },
+    {
+      "epoch": 27.428571428571427,
+      "grad_norm": 0.014756185002624989,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "step": 48
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 0.014756185002624989,
+      "learning_rate": 0.0002,
+      "loss": 0.0005,
+      "step": 49
+    },
+    {
+      "epoch": 28.571428571428573,
+      "grad_norm": 0.032949432730674744,
+      "learning_rate": 0.0002,
+      "loss": 0.0004,
+      "step": 50
+    },
+    {
+      "epoch": 28.571428571428573,
+      "eval_loss": 0.0005236685974523425,
+      "eval_runtime": 1.1017,
+      "eval_samples_per_second": 6.354,
+      "eval_steps_per_second": 6.354,
+      "step": 50
+    },
+    {
+      "epoch": 29.0,
+      "grad_norm": 0.032949432730674744,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "step": 51
+    },
+    {
+      "epoch": 29.714285714285715,
+      "grad_norm": 0.015912260860204697,
+      "learning_rate": 0.0002,
+      "loss": 0.0004,
+      "step": 52
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.015912260860204697,
+      "learning_rate": 0.0002,
+      "loss": 0.0001,
+      "step": 53
+    },
+    {
+      "epoch": 30.857142857142858,
+      "grad_norm": 0.012292955070734024,
+      "learning_rate": 0.0002,
+      "loss": 0.0004,
+      "step": 54
+    },
+    {
+      "epoch": 31.0,
+      "grad_norm": 0.012292955070734024,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 32.0,
+      "grad_norm": 0.009588208049535751,
+      "learning_rate": 0.0002,
+      "loss": 0.0003,
+      "step": 56
+    },
+    {
+      "epoch": 33.0,
+      "grad_norm": 0.009588208049535751,
+      "learning_rate": 0.0002,
+      "loss": 0.0003,
+      "step": 57
+    },
+    {
+      "epoch": 33.142857142857146,
+      "grad_norm": 0.007272060494869947,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 34.0,
+      "grad_norm": 0.007272060494869947,
+      "learning_rate": 0.0002,
+      "loss": 0.0002,
+      "step": 59
+    },
+    {
+      "epoch": 34.285714285714285,
+      "grad_norm": 0.006634233985096216,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 34.285714285714285,
+      "eval_loss": 0.00021448711049742997,
+      "eval_runtime": 1.0979,
+      "eval_samples_per_second": 6.376,
+      "eval_steps_per_second": 6.376,
+      "step": 60
+    },
+    {
+      "epoch": 34.285714285714285,
+      "step": 60,
+      "total_flos": 4016214881861632.0,
+      "train_loss": 0.1554629008491247,
+      "train_runtime": 98.8483,
+      "train_samples_per_second": 4.856,
+      "train_steps_per_second": 0.607
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 60,
+  "save_steps": 1000,
+  "total_flos": 4016214881861632.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453d1e4121a4921810db7811efe18d53e4f3315903a6ad7515c176c8a1c50ce8
+size 6776