Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,4 @@ checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-245/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "v_proj",
-    "down_proj",
     "q_proj",
-    "k_proj",
-    "up_proj",
+    "down_proj",
+    "o_proj",
     "gate_proj",
-    "o_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0e7c4e2f44d5f5a9a2e0d7ba6d3a0620bd8f112ad341010974a7aa8d1c8f45
+oid sha256:d0ab04fc19531cc90fbe416c2f161e7ea8037215d395af8964352639b012baa9
 size 40422168

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-0.6B
+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 0.15.2

checkpoint-200/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-0.6B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ab04fc19531cc90fbe416c2f161e7ea8037215d395af8964352639b012baa9
+size 40422168

checkpoint-200/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-200/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131f0e175c7dfae51a3ad89e3fce0c33f5b5170a628853138425b02f792db129
+size 81070011

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4409056f3a511f32784aeadde6b8987edca6fb1c25c5c6e0043a33427d55a1
+size 14645

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba799122a6b94c5c2d2f3c14916977285cb883d241557db8ade940f37d24ead
+size 1465

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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
+  }
+}

checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "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": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,254 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.054177138954401016,
+  "best_model_checkpoint": "/home/ricoiban/GEMMA/mnlp_chatsplaining/safety_model_output/checkpoint-200",
+  "epoch": 4.082901554404145,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.20725388601036268,
+      "grad_norm": 2.7763237953186035,
+      "learning_rate": 0.0005899999999999999,
+      "loss": 8.1874,
+      "mean_token_accuracy": 0.390625,
+      "num_tokens": 21984.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.41450777202072536,
+      "grad_norm": 1.8894965648651123,
+      "learning_rate": 0.000565,
+      "loss": 0.7121,
+      "mean_token_accuracy": 0.64375,
+      "num_tokens": 44111.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.6217616580310881,
+      "grad_norm": 2.1179754734039307,
+      "learning_rate": 0.00054,
+      "loss": 0.6903,
+      "mean_token_accuracy": 0.659375,
+      "num_tokens": 68120.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.8290155440414507,
+      "grad_norm": 2.2939863204956055,
+      "learning_rate": 0.0005149999999999999,
+      "loss": 0.677,
+      "mean_token_accuracy": 0.653125,
+      "num_tokens": 89669.0,
+      "step": 40
+    },
+    {
+      "epoch": 1.0207253886010363,
+      "grad_norm": 2.18673038482666,
+      "learning_rate": 0.00049,
+      "loss": 0.6974,
+      "mean_token_accuracy": 0.6655405405405406,
+      "num_tokens": 111297.0,
+      "step": 50
+    },
+    {
+      "epoch": 1.0207253886010363,
+      "eval_loss": 0.7593430876731873,
+      "eval_mean_token_accuracy": 0.5,
+      "eval_num_tokens": 111297.0,
+      "eval_runtime": 0.1338,
+      "eval_samples_per_second": 7.475,
+      "eval_steps_per_second": 7.475,
+      "step": 50
+    },
+    {
+      "epoch": 1.2279792746113989,
+      "grad_norm": 3.68613338470459,
+      "learning_rate": 0.00046499999999999997,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.703125,
+      "num_tokens": 133338.0,
+      "step": 60
+    },
+    {
+      "epoch": 1.4352331606217616,
+      "grad_norm": 5.129226207733154,
+      "learning_rate": 0.0004399999999999999,
+      "loss": 0.5701,
+      "mean_token_accuracy": 0.75625,
+      "num_tokens": 156589.0,
+      "step": 70
+    },
+    {
+      "epoch": 1.6424870466321244,
+      "grad_norm": 3.548778772354126,
+      "learning_rate": 0.00041499999999999995,
+      "loss": 0.5314,
+      "mean_token_accuracy": 0.765625,
+      "num_tokens": 178995.0,
+      "step": 80
+    },
+    {
+      "epoch": 1.849740932642487,
+      "grad_norm": 4.861147403717041,
+      "learning_rate": 0.00039,
+      "loss": 0.5636,
+      "mean_token_accuracy": 0.771875,
+      "num_tokens": 203491.0,
+      "step": 90
+    },
+    {
+      "epoch": 2.0414507772020727,
+      "grad_norm": 3.220465660095215,
+      "learning_rate": 0.00036499999999999993,
+      "loss": 0.4901,
+      "mean_token_accuracy": 0.7905405405405406,
+      "num_tokens": 223362.0,
+      "step": 100
+    },
+    {
+      "epoch": 2.0414507772020727,
+      "eval_loss": 0.6653734445571899,
+      "eval_mean_token_accuracy": 0.5,
+      "eval_num_tokens": 223362.0,
+      "eval_runtime": 0.161,
+      "eval_samples_per_second": 6.212,
+      "eval_steps_per_second": 6.212,
+      "step": 100
+    },
+    {
+      "epoch": 2.2487046632124352,
+      "grad_norm": 3.534886360168457,
+      "learning_rate": 0.00033999999999999997,
+      "loss": 0.323,
+      "mean_token_accuracy": 0.86875,
+      "num_tokens": 245475.0,
+      "step": 110
+    },
+    {
+      "epoch": 2.4559585492227978,
+      "grad_norm": 2.073479413986206,
+      "learning_rate": 0.00031499999999999996,
+      "loss": 0.3263,
+      "mean_token_accuracy": 0.875,
+      "num_tokens": 268345.0,
+      "step": 120
+    },
+    {
+      "epoch": 2.6632124352331608,
+      "grad_norm": 5.83317756652832,
+      "learning_rate": 0.00029,
+      "loss": 0.3978,
+      "mean_token_accuracy": 0.84375,
+      "num_tokens": 292072.0,
+      "step": 130
+    },
+    {
+      "epoch": 2.8704663212435233,
+      "grad_norm": 3.23555064201355,
+      "learning_rate": 0.000265,
+      "loss": 0.2859,
+      "mean_token_accuracy": 0.871875,
+      "num_tokens": 314093.0,
+      "step": 140
+    },
+    {
+      "epoch": 3.062176165803109,
+      "grad_norm": 1.8520785570144653,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.4766,
+      "mean_token_accuracy": 0.8885135135135135,
+      "num_tokens": 334669.0,
+      "step": 150
+    },
+    {
+      "epoch": 3.062176165803109,
+      "eval_loss": 1.3390449285507202,
+      "eval_mean_token_accuracy": 0.5,
+      "eval_num_tokens": 334669.0,
+      "eval_runtime": 0.2104,
+      "eval_samples_per_second": 4.753,
+      "eval_steps_per_second": 4.753,
+      "step": 150
+    },
+    {
+      "epoch": 3.2694300518134716,
+      "grad_norm": 13.872314453125,
+      "learning_rate": 0.000215,
+      "loss": 0.1519,
+      "mean_token_accuracy": 0.928125,
+      "num_tokens": 358016.0,
+      "step": 160
+    },
+    {
+      "epoch": 3.476683937823834,
+      "grad_norm": 4.716925144195557,
+      "learning_rate": 0.00018999999999999998,
+      "loss": 0.1854,
+      "mean_token_accuracy": 0.934375,
+      "num_tokens": 380340.0,
+      "step": 170
+    },
+    {
+      "epoch": 3.6839378238341967,
+      "grad_norm": 6.100285530090332,
+      "learning_rate": 0.000165,
+      "loss": 0.1897,
+      "mean_token_accuracy": 0.925,
+      "num_tokens": 402140.0,
+      "step": 180
+    },
+    {
+      "epoch": 3.8911917098445596,
+      "grad_norm": 5.842983245849609,
+      "learning_rate": 0.00014,
+      "loss": 0.1615,
+      "mean_token_accuracy": 0.94375,
+      "num_tokens": 426084.0,
+      "step": 190
+    },
+    {
+      "epoch": 4.082901554404145,
+      "grad_norm": 3.3988146781921387,
+      "learning_rate": 0.000115,
+      "loss": 0.0874,
+      "mean_token_accuracy": 0.9628378378378378,
+      "num_tokens": 446213.0,
+      "step": 200
+    },
+    {
+      "epoch": 4.082901554404145,
+      "eval_loss": 0.054177138954401016,
+      "eval_mean_token_accuracy": 1.0,
+      "eval_num_tokens": 446213.0,
+      "eval_runtime": 0.1261,
+      "eval_samples_per_second": 7.932,
+      "eval_steps_per_second": 7.932,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 245,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1697812807680000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7566347047128724837030b344620160dadce5a7abdbc2cca891de51714f0c49
+size 6673

checkpoint-245/adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "v_proj",
-    "down_proj",
     "q_proj",
-    "k_proj",
-    "up_proj",
+    "down_proj",
+    "o_proj",
     "gate_proj",
-    "o_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

checkpoint-245/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b79a5b9cffdde7ceedcb715b5540cc100666cd87fa311c359e36a4853ca21ac
+oid sha256:6e869615ff2340983558be9b97c0732e48da8ae95512d1d9e7f323467267f50d
 size 40422168

checkpoint-245/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a63ff7a522e6ca2720a7d43b6ddb8fdd1045590c31cff3dcfa95dba8a60568e7
+oid sha256:bb82bf4cbe011e81dd0570be3e7fba7e1f52e2ec8fd8e59f6cbacac84d1183ea
 size 81070011

checkpoint-245/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 50,
-  "best_metric": 0.8024441003799438,
-  "best_model_checkpoint": "/home/ricoiban/GEMMA/mnlp_chatsplaining/safety_model_output/checkpoint-50",
+  "best_global_step": 200,
+  "best_metric": 0.054177138954401016,
+  "best_model_checkpoint": "/home/ricoiban/GEMMA/mnlp_chatsplaining/safety_model_output/checkpoint-200",
   "epoch": 5.0,
   "eval_steps": 50,
   "global_step": 245,
@@ -11,257 +11,257 @@
   "log_history": [
     {
       "epoch": 0.20725388601036268,
-      "grad_norm": 4.4248785972595215,
+      "grad_norm": 2.7763237953186035,
       "learning_rate": 0.0005899999999999999,
-      "loss": 8.2557,
-      "mean_token_accuracy": 0.384375,
+      "loss": 8.1874,
+      "mean_token_accuracy": 0.390625,
       "num_tokens": 21984.0,
       "step": 10
     },
     {
       "epoch": 0.41450777202072536,
-      "grad_norm": 1.9055719375610352,
+      "grad_norm": 1.8894965648651123,
       "learning_rate": 0.000565,
-      "loss": 0.7267,
-      "mean_token_accuracy": 0.634375,
+      "loss": 0.7121,
+      "mean_token_accuracy": 0.64375,
       "num_tokens": 44111.0,
       "step": 20
     },
     {
       "epoch": 0.6217616580310881,
-      "grad_norm": 2.149226427078247,
+      "grad_norm": 2.1179754734039307,
       "learning_rate": 0.00054,
-      "loss": 0.6712,
-      "mean_token_accuracy": 0.671875,
+      "loss": 0.6903,
+      "mean_token_accuracy": 0.659375,
       "num_tokens": 68120.0,
       "step": 30
     },
     {
       "epoch": 0.8290155440414507,
-      "grad_norm": 1.9442976713180542,
+      "grad_norm": 2.2939863204956055,
       "learning_rate": 0.0005149999999999999,
-      "loss": 0.7079,
-      "mean_token_accuracy": 0.678125,
+      "loss": 0.677,
+      "mean_token_accuracy": 0.653125,
       "num_tokens": 89669.0,
       "step": 40
     },
     {
       "epoch": 1.0207253886010363,
-      "grad_norm": 67.3375473022461,
+      "grad_norm": 2.18673038482666,
       "learning_rate": 0.00049,
-      "loss": 0.7584,
-      "mean_token_accuracy": 0.6182432432432432,
+      "loss": 0.6974,
+      "mean_token_accuracy": 0.6655405405405406,
       "num_tokens": 111297.0,
       "step": 50
     },
     {
       "epoch": 1.0207253886010363,
-      "eval_loss": 0.8024441003799438,
+      "eval_loss": 0.7593430876731873,
       "eval_mean_token_accuracy": 0.5,
       "eval_num_tokens": 111297.0,
-      "eval_runtime": 0.1286,
-      "eval_samples_per_second": 7.775,
-      "eval_steps_per_second": 7.775,
+      "eval_runtime": 0.1338,
+      "eval_samples_per_second": 7.475,
+      "eval_steps_per_second": 7.475,
       "step": 50
     },
     {
       "epoch": 1.2279792746113989,
-      "grad_norm": 6.444717884063721,
+      "grad_norm": 3.68613338470459,
       "learning_rate": 0.00046499999999999997,
-      "loss": 0.6147,
+      "loss": 0.6289,
       "mean_token_accuracy": 0.703125,
       "num_tokens": 133338.0,
       "step": 60
     },
     {
       "epoch": 1.4352331606217616,
-      "grad_norm": 17.345895767211914,
+      "grad_norm": 5.129226207733154,
       "learning_rate": 0.0004399999999999999,
-      "loss": 0.5632,
-      "mean_token_accuracy": 0.771875,
+      "loss": 0.5701,
+      "mean_token_accuracy": 0.75625,
       "num_tokens": 156589.0,
       "step": 70
     },
     {
       "epoch": 1.6424870466321244,
-      "grad_norm": 4.307793617248535,
+      "grad_norm": 3.548778772354126,
       "learning_rate": 0.00041499999999999995,
-      "loss": 0.537,
-      "mean_token_accuracy": 0.7875,
+      "loss": 0.5314,
+      "mean_token_accuracy": 0.765625,
       "num_tokens": 178995.0,
       "step": 80
     },
     {
       "epoch": 1.849740932642487,
-      "grad_norm": 3.7696592807769775,
+      "grad_norm": 4.861147403717041,
       "learning_rate": 0.00039,
-      "loss": 0.5935,
-      "mean_token_accuracy": 0.746875,
+      "loss": 0.5636,
+      "mean_token_accuracy": 0.771875,
       "num_tokens": 203491.0,
       "step": 90
     },
     {
       "epoch": 2.0414507772020727,
-      "grad_norm": 3.7574870586395264,
+      "grad_norm": 3.220465660095215,
       "learning_rate": 0.00036499999999999993,
-      "loss": 0.494,
+      "loss": 0.4901,
       "mean_token_accuracy": 0.7905405405405406,
       "num_tokens": 223362.0,
       "step": 100
     },
     {
       "epoch": 2.0414507772020727,
-      "eval_loss": 1.1921323537826538,
+      "eval_loss": 0.6653734445571899,
       "eval_mean_token_accuracy": 0.5,
       "eval_num_tokens": 223362.0,
-      "eval_runtime": 0.1254,
-      "eval_samples_per_second": 7.977,
-      "eval_steps_per_second": 7.977,
+      "eval_runtime": 0.161,
+      "eval_samples_per_second": 6.212,
+      "eval_steps_per_second": 6.212,
       "step": 100
     },
     {
       "epoch": 2.2487046632124352,
-      "grad_norm": 5.195500373840332,
+      "grad_norm": 3.534886360168457,
       "learning_rate": 0.00033999999999999997,
-      "loss": 0.3184,
-      "mean_token_accuracy": 0.88125,
+      "loss": 0.323,
+      "mean_token_accuracy": 0.86875,
       "num_tokens": 245475.0,
       "step": 110
     },
     {
       "epoch": 2.4559585492227978,
-      "grad_norm": 2.6721720695495605,
+      "grad_norm": 2.073479413986206,
       "learning_rate": 0.00031499999999999996,
-      "loss": 0.3147,
-      "mean_token_accuracy": 0.86875,
+      "loss": 0.3263,
+      "mean_token_accuracy": 0.875,
       "num_tokens": 268345.0,
       "step": 120
     },
     {
       "epoch": 2.6632124352331608,
-      "grad_norm": 5.788036823272705,
+      "grad_norm": 5.83317756652832,
       "learning_rate": 0.00029,
-      "loss": 0.414,
-      "mean_token_accuracy": 0.81875,
+      "loss": 0.3978,
+      "mean_token_accuracy": 0.84375,
       "num_tokens": 292072.0,
       "step": 130
     },
     {
       "epoch": 2.8704663212435233,
-      "grad_norm": 2.9962568283081055,
+      "grad_norm": 3.23555064201355,
       "learning_rate": 0.000265,
-      "loss": 0.3293,
-      "mean_token_accuracy": 0.8625,
+      "loss": 0.2859,
+      "mean_token_accuracy": 0.871875,
       "num_tokens": 314093.0,
       "step": 140
     },
     {
       "epoch": 3.062176165803109,
-      "grad_norm": 2.9766643047332764,
+      "grad_norm": 1.8520785570144653,
       "learning_rate": 0.00023999999999999998,
-      "loss": 0.1989,
-      "mean_token_accuracy": 0.9087837837837838,
+      "loss": 0.4766,
+      "mean_token_accuracy": 0.8885135135135135,
       "num_tokens": 334669.0,
       "step": 150
     },
     {
       "epoch": 3.062176165803109,
-      "eval_loss": 3.510432481765747,
+      "eval_loss": 1.3390449285507202,
       "eval_mean_token_accuracy": 0.5,
       "eval_num_tokens": 334669.0,
-      "eval_runtime": 0.1277,
-      "eval_samples_per_second": 7.833,
-      "eval_steps_per_second": 7.833,
+      "eval_runtime": 0.2104,
+      "eval_samples_per_second": 4.753,
+      "eval_steps_per_second": 4.753,
       "step": 150
     },
     {
       "epoch": 3.2694300518134716,
-      "grad_norm": 10.293326377868652,
+      "grad_norm": 13.872314453125,
       "learning_rate": 0.000215,
-      "loss": 0.1508,
-      "mean_token_accuracy": 0.9375,
+      "loss": 0.1519,
+      "mean_token_accuracy": 0.928125,
       "num_tokens": 358016.0,
       "step": 160
     },
     {
       "epoch": 3.476683937823834,
-      "grad_norm": 7.3945698738098145,
+      "grad_norm": 4.716925144195557,
       "learning_rate": 0.00018999999999999998,
-      "loss": 0.1329,
-      "mean_token_accuracy": 0.953125,
+      "loss": 0.1854,
+      "mean_token_accuracy": 0.934375,
       "num_tokens": 380340.0,
       "step": 170
     },
     {
       "epoch": 3.6839378238341967,
-      "grad_norm": 1.260176181793213,
+      "grad_norm": 6.100285530090332,
       "learning_rate": 0.000165,
-      "loss": 0.1821,
-      "mean_token_accuracy": 0.934375,
+      "loss": 0.1897,
+      "mean_token_accuracy": 0.925,
       "num_tokens": 402140.0,
       "step": 180
     },
     {
       "epoch": 3.8911917098445596,
-      "grad_norm": 3.2304484844207764,
+      "grad_norm": 5.842983245849609,
       "learning_rate": 0.00014,
-      "loss": 0.139,
-      "mean_token_accuracy": 0.946875,
+      "loss": 0.1615,
+      "mean_token_accuracy": 0.94375,
       "num_tokens": 426084.0,
       "step": 190
     },
     {
       "epoch": 4.082901554404145,
-      "grad_norm": 0.6160839796066284,
+      "grad_norm": 3.3988146781921387,
       "learning_rate": 0.000115,
-      "loss": 0.0729,
-      "mean_token_accuracy": 0.9695945945945946,
+      "loss": 0.0874,
+      "mean_token_accuracy": 0.9628378378378378,
       "num_tokens": 446213.0,
       "step": 200
     },
     {
       "epoch": 4.082901554404145,
-      "eval_loss": 4.188155174255371,
-      "eval_mean_token_accuracy": 0.5,
+      "eval_loss": 0.054177138954401016,
+      "eval_mean_token_accuracy": 1.0,
       "eval_num_tokens": 446213.0,
-      "eval_runtime": 0.1101,
-      "eval_samples_per_second": 9.082,
-      "eval_steps_per_second": 9.082,
+      "eval_runtime": 0.1261,
+      "eval_samples_per_second": 7.932,
+      "eval_steps_per_second": 7.932,
       "step": 200
     },
     {
       "epoch": 4.290155440414508,
-      "grad_norm": 0.4012514650821686,
+      "grad_norm": 4.433862686157227,
       "learning_rate": 8.999999999999999e-05,
-      "loss": 0.0634,
-      "mean_token_accuracy": 0.975,
+      "loss": 0.0692,
+      "mean_token_accuracy": 0.978125,
       "num_tokens": 469234.0,
       "step": 210
     },
     {
       "epoch": 4.4974093264248705,
-      "grad_norm": 0.04510807245969772,
+      "grad_norm": 18.63327980041504,
       "learning_rate": 6.5e-05,
-      "loss": 0.027,
-      "mean_token_accuracy": 0.9875,
+      "loss": 0.0986,
+      "mean_token_accuracy": 0.9625,
       "num_tokens": 492700.0,
       "step": 220
     },
     {
       "epoch": 4.704663212435233,
-      "grad_norm": 1.0606855154037476,
+      "grad_norm": 2.435386896133423,
       "learning_rate": 3.9999999999999996e-05,
-      "loss": 0.0887,
-      "mean_token_accuracy": 0.965625,
+      "loss": 0.0937,
+      "mean_token_accuracy": 0.9625,
       "num_tokens": 514671.0,
       "step": 230
     },
     {
       "epoch": 4.9119170984455955,
-      "grad_norm": 1.3937901258468628,
+      "grad_norm": 14.27245807647705,
       "learning_rate": 1.4999999999999999e-05,
-      "loss": 0.0852,
-      "mean_token_accuracy": 0.978125,
+      "loss": 0.0743,
+      "mean_token_accuracy": 0.971875,
       "num_tokens": 537299.0,
       "step": 240
     }

checkpoint-245/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0c67709a00f240ad0d45340b4e4703d76c9b176db80e252a07293fdbffaf64
+oid sha256:7566347047128724837030b344620160dadce5a7abdbc2cca891de51714f0c49
 size 6673

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0c67709a00f240ad0d45340b4e4703d76c9b176db80e252a07293fdbffaf64
+oid sha256:7566347047128724837030b344620160dadce5a7abdbc2cca891de51714f0c49
 size 6673