Upload folder using huggingface_hub

.gitattributes

@@ -80,3 +80,4 @@ behavioral-gguf/multi_perspective-behavioral-lora-f16.gguf filter=lfs diff=lfs m
 behavioral-gguf/systems_architecture-behavioral-lora-f16.gguf filter=lfs diff=lfs merge=lfs -text
 behavioral-gguf/orchestrator-behavioral-lora-f16.gguf filter=lfs diff=lfs merge=lfs -text
 davinci/checkpoint-228/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+empathy/checkpoint-228/tokenizer.json filter=lfs diff=lfs merge=lfs -text

empathy/README.md

@@ -1,9 +1,9 @@
 ---
-base_model: meta-llama/Llama-3.1-8B-Instruct
+base_model: Raiff1982/codette-llama-3.1-8b-merged
 library_name: peft
 model_name: empathy
 tags:
-- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
+- base_model:adapter:Raiff1982/codette-llama-3.1-8b-merged
 - lora
 - sft
 - transformers
@@ -14,7 +14,7 @@ pipeline_tag: text-generation
 
 # Model Card for empathy
 
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).
+This model is a fine-tuned version of [Raiff1982/codette-llama-3.1-8b-merged](https://huggingface.co/Raiff1982/codette-llama-3.1-8b-merged).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -39,10 +39,10 @@ This model was trained with SFT.
 ### Framework versions
 
 - PEFT 0.18.1
-- TRL: 0.29.1
-- Transformers: 5.3.0
-- Pytorch: 2.10.0
-- Datasets: 4.8.3
+- TRL: 1.0.0
+- Transformers: 5.5.0
+- Pytorch: 2.11.0
+- Datasets: 4.8.4
 - Tokenizers: 0.22.2
 
 ## Citations

empathy/adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "base_model_name_or_path": "Raiff1982/codette-llama-3.1-8b-merged",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -29,10 +29,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "v_proj",
     "q_proj",
-    "k_proj"
+    "k_proj",
+    "o_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

empathy/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:135a18e8e1dac45587863efd24951eb569a086873f671a9374855ee9eae569bc
+oid sha256:ed353a8323ee5b89e5def7ac43a55760dc1799b9ff48c4a1f9e02558771147ad
 size 27297544

empathy/checkpoint-228/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Raiff1982/codette-llama-3.1-8b-merged
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Raiff1982/codette-llama-3.1-8b-merged
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

empathy/checkpoint-228/adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Raiff1982/codette-llama-3.1-8b-merged",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

empathy/checkpoint-228/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed353a8323ee5b89e5def7ac43a55760dc1799b9ff48c4a1f9e02558771147ad
+size 27297544

empathy/checkpoint-228/chat_template.jinja

@@ -0,0 +1,109 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- set date_string = "26 Jul 2024" %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message + builtin tools #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if builtin_tools is defined or tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{%- if builtin_tools is defined %}
+    {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- "<|python_tag|>" + tool_call.name + ".call(" }}
+            {%- for arg_name, arg_val in tool_call.arguments | items %}
+                {{- arg_name + '="' + arg_val + '"' }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- endif %}
+                {%- endfor %}
+            {{- ")" }}
+        {%- else  %}
+            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+            {{- '{"name": "' + tool_call.name + '", ' }}
+            {{- '"parameters": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- "}" }}
+        {%- endif %}
+        {%- if builtin_tools is defined %}
+            {#- This means we're in ipython mode #}
+            {{- "<|eom_id|>" }}
+        {%- else %}
+            {{- "<|eot_id|>" }}
+        {%- endif %}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

empathy/checkpoint-228/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008267caa58a651331963e616098cf1e6a8311c3362595b674b6644fe5f82411
+size 54745547

empathy/checkpoint-228/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638861aa567cc15d755d4622336ed84b7edc1a5f7c4a9c2f772ff95cb9ec5fe4
+size 14645

empathy/checkpoint-228/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baefc67045d1894d210d322bc132560ab40a0eb5ccb2a19ad1a2ab3158282df4
+size 1465

empathy/checkpoint-228/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

empathy/checkpoint-228/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "TokenizersBackend"
+}

empathy/checkpoint-228/trainer_state.json

@@ -0,0 +1,254 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 228,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.9285874366760254,
+      "epoch": 0.132890365448505,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.90950226244344e-05,
+      "loss": 3.6041332244873048,
+      "mean_token_accuracy": 0.37587286084890364,
+      "num_tokens": 19311.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.308431553840637,
+      "epoch": 0.26578073089701,
+      "grad_norm": 0.78515625,
+      "learning_rate": 9.457013574660634e-05,
+      "loss": 2.2647274017333983,
+      "mean_token_accuracy": 0.5038292273879051,
+      "num_tokens": 38598.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.9602926149964333,
+      "epoch": 0.39867109634551495,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.004524886877828e-05,
+      "loss": 0.798987340927124,
+      "mean_token_accuracy": 0.8073456197977066,
+      "num_tokens": 58173.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.2912808794528246,
+      "epoch": 0.53156146179402,
+      "grad_norm": 0.265625,
+      "learning_rate": 8.552036199095023e-05,
+      "loss": 0.2674523591995239,
+      "mean_token_accuracy": 0.9458165615797043,
+      "num_tokens": 77528.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.22087961584329605,
+      "epoch": 0.6644518272425249,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 8.099547511312218e-05,
+      "loss": 0.19720486402511597,
+      "mean_token_accuracy": 0.9631471112370491,
+      "num_tokens": 96805.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.1830143578350544,
+      "epoch": 0.7973421926910299,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 7.647058823529411e-05,
+      "loss": 0.1690774917602539,
+      "mean_token_accuracy": 0.967066015303135,
+      "num_tokens": 116167.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.1772829983383417,
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.15625,
+      "learning_rate": 7.194570135746607e-05,
+      "loss": 0.15653250217437745,
+      "mean_token_accuracy": 0.9682745844125747,
+      "num_tokens": 135497.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.16197623272199888,
+      "epoch": 1.053156146179402,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 6.742081447963802e-05,
+      "loss": 0.1426864504814148,
+      "mean_token_accuracy": 0.9697337488870363,
+      "num_tokens": 153149.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.16248531267046928,
+      "epoch": 1.1860465116279069,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 6.289592760180995e-05,
+      "loss": 0.13200528621673585,
+      "mean_token_accuracy": 0.9731017708778381,
+      "num_tokens": 172504.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.1513056695461273,
+      "epoch": 1.3189368770764118,
+      "grad_norm": 0.1513671875,
+      "learning_rate": 5.8371040723981906e-05,
+      "loss": 0.1254744529724121,
+      "mean_token_accuracy": 0.9750225186347962,
+      "num_tokens": 191988.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.1512659251689911,
+      "epoch": 1.451827242524917,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 5.384615384615385e-05,
+      "loss": 0.12104312181472779,
+      "mean_token_accuracy": 0.9769940406084061,
+      "num_tokens": 211266.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.1487934708595276,
+      "epoch": 1.584717607973422,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 4.9321266968325794e-05,
+      "loss": 0.11645747423171997,
+      "mean_token_accuracy": 0.9768159419298172,
+      "num_tokens": 230491.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.1666957575827837,
+      "epoch": 1.717607973421927,
+      "grad_norm": 0.123046875,
+      "learning_rate": 4.479638009049774e-05,
+      "loss": 0.171037757396698,
+      "mean_token_accuracy": 0.9710833907127381,
+      "num_tokens": 249887.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.12373456507921218,
+      "epoch": 1.850498338870432,
+      "grad_norm": 0.15625,
+      "learning_rate": 4.027149321266969e-05,
+      "loss": 0.10014293193817139,
+      "mean_token_accuracy": 0.9773356303572655,
+      "num_tokens": 269183.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.1014734748750925,
+      "epoch": 1.9833887043189369,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 3.574660633484163e-05,
+      "loss": 0.09062700867652893,
+      "mean_token_accuracy": 0.9770520135760308,
+      "num_tokens": 288506.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.12846573925501592,
+      "epoch": 2.106312292358804,
+      "grad_norm": 0.10791015625,
+      "learning_rate": 3.1221719457013576e-05,
+      "loss": 0.1143355131149292,
+      "mean_token_accuracy": 0.9726925524505409,
+      "num_tokens": 306151.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.11329343989491462,
+      "epoch": 2.2392026578073088,
+      "grad_norm": 0.12060546875,
+      "learning_rate": 2.6696832579185523e-05,
+      "loss": 0.07976673245429992,
+      "mean_token_accuracy": 0.9779384687542916,
+      "num_tokens": 325472.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.10458720978349448,
+      "epoch": 2.3720930232558137,
+      "grad_norm": 0.12890625,
+      "learning_rate": 2.2171945701357466e-05,
+      "loss": 0.07534474730491639,
+      "mean_token_accuracy": 0.9776975959539413,
+      "num_tokens": 344880.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.10106674693524838,
+      "epoch": 2.5049833887043187,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 0.07265635728836059,
+      "mean_token_accuracy": 0.9769708752632141,
+      "num_tokens": 364175.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.1042721638455987,
+      "epoch": 2.6378737541528237,
+      "grad_norm": 0.11669921875,
+      "learning_rate": 1.3122171945701359e-05,
+      "loss": 0.07031703591346741,
+      "mean_token_accuracy": 0.9772119835019112,
+      "num_tokens": 383562.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.10177183672785758,
+      "epoch": 2.770764119601329,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 8.597285067873303e-06,
+      "loss": 0.06731207370758056,
+      "mean_token_accuracy": 0.9782579615712166,
+      "num_tokens": 402992.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.10153268091380596,
+      "epoch": 2.903654485049834,
+      "grad_norm": 0.11279296875,
+      "learning_rate": 4.072398190045249e-06,
+      "loss": 0.06839914917945862,
+      "mean_token_accuracy": 0.9789570987224578,
+      "num_tokens": 422221.0,
+      "step": 220
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 228,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.007517650591744e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

empathy/checkpoint-228/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66490225b087f357a87a72a44a0836c0c748d09b0561c8cc3b4fdbcc8f01df4c
+size 5649