Upload folder using huggingface_hub

.gitattributes

@@ -81,3 +81,4 @@ behavioral-gguf/systems_architecture-behavioral-lora-f16.gguf filter=lfs diff=lf
 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
+philosophy/checkpoint-228/tokenizer.json filter=lfs diff=lfs merge=lfs -text

philosophy/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: philosophy
 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 philosophy
 
-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

philosophy/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",

philosophy/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f5736e4506b531e9854ba1665d1158f21ae960b343bd8307efefe604b3aadbb
+oid sha256:3047e32fe90a51117346b3c05ea4258b7eaa106ed77bfd54620c1c3445d4967f
 size 27297544

philosophy/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

philosophy/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
+}

philosophy/checkpoint-228/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3047e32fe90a51117346b3c05ea4258b7eaa106ed77bfd54620c1c3445d4967f
+size 27297544

philosophy/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 %}

philosophy/checkpoint-228/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18e058d789664e07b808e98687b45a9c22ffe4e7c8bcaa4333b742f8dbe3e6d
+size 54745547

philosophy/checkpoint-228/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13238fafb0f9a3e2b69ad70ca4b281ba3b3064a2c57f6de255899e4a4f7c77f1
+size 14645

philosophy/checkpoint-228/scheduler.pt

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

philosophy/checkpoint-228/tokenizer.json

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

philosophy/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"
+}

philosophy/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": 2.627858597040176,
+      "epoch": 0.132890365448505,
+      "grad_norm": 0.4140625,
+      "learning_rate": 9.90950226244344e-05,
+      "loss": 3.281603240966797,
+      "mean_token_accuracy": 0.42344720363616944,
+      "num_tokens": 20982.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.1496767520904543,
+      "epoch": 0.26578073089701,
+      "grad_norm": 0.5390625,
+      "learning_rate": 9.457013574660634e-05,
+      "loss": 2.1261198043823244,
+      "mean_token_accuracy": 0.5675000421702862,
+      "num_tokens": 42010.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.9435457497835159,
+      "epoch": 0.39867109634551495,
+      "grad_norm": 0.52734375,
+      "learning_rate": 9.004524886877828e-05,
+      "loss": 0.7939486980438233,
+      "mean_token_accuracy": 0.818781553208828,
+      "num_tokens": 63166.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.3076884038746357,
+      "epoch": 0.53156146179402,
+      "grad_norm": 0.33203125,
+      "learning_rate": 8.552036199095023e-05,
+      "loss": 0.26673619747161864,
+      "mean_token_accuracy": 0.9458289206027984,
+      "num_tokens": 84195.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.2058968674391508,
+      "epoch": 0.6644518272425249,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 8.099547511312218e-05,
+      "loss": 0.18524067401885985,
+      "mean_token_accuracy": 0.9660053923726082,
+      "num_tokens": 105340.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.19422067441046237,
+      "epoch": 0.7973421926910299,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 7.647058823529411e-05,
+      "loss": 0.1933828353881836,
+      "mean_token_accuracy": 0.9657216846942902,
+      "num_tokens": 126241.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.16568151414394378,
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 7.194570135746607e-05,
+      "loss": 0.14261871576309204,
+      "mean_token_accuracy": 0.9713236495852471,
+      "num_tokens": 147218.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.15153879692425598,
+      "epoch": 1.053156146179402,
+      "grad_norm": 0.130859375,
+      "learning_rate": 6.742081447963802e-05,
+      "loss": 0.13155369758605956,
+      "mean_token_accuracy": 0.9722981001879718,
+      "num_tokens": 166631.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.14830529168248177,
+      "epoch": 1.1860465116279069,
+      "grad_norm": 0.1435546875,
+      "learning_rate": 6.289592760180995e-05,
+      "loss": 0.12116929292678832,
+      "mean_token_accuracy": 0.9780257821083069,
+      "num_tokens": 187649.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.13870706800371407,
+      "epoch": 1.3189368770764118,
+      "grad_norm": 0.12109375,
+      "learning_rate": 5.8371040723981906e-05,
+      "loss": 0.11448854207992554,
+      "mean_token_accuracy": 0.9788252308964729,
+      "num_tokens": 208795.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.15203072875738144,
+      "epoch": 1.451827242524917,
+      "grad_norm": 0.1484375,
+      "learning_rate": 5.384615384615385e-05,
+      "loss": 0.12993549108505248,
+      "mean_token_accuracy": 0.9745954066514969,
+      "num_tokens": 229763.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.13043909054249525,
+      "epoch": 1.584717607973422,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 4.9321266968325794e-05,
+      "loss": 0.0995155155658722,
+      "mean_token_accuracy": 0.9799957603216172,
+      "num_tokens": 250778.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.10511146020144224,
+      "epoch": 1.717607973421927,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 4.479638009049774e-05,
+      "loss": 0.08581982254981994,
+      "mean_token_accuracy": 0.9801228925585747,
+      "num_tokens": 271851.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.09703388176858425,
+      "epoch": 1.850498338870432,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 4.027149321266969e-05,
+      "loss": 0.07891285419464111,
+      "mean_token_accuracy": 0.9808570235967636,
+      "num_tokens": 292872.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.11622757650911808,
+      "epoch": 1.9833887043189369,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 3.574660633484163e-05,
+      "loss": 0.09897525906562805,
+      "mean_token_accuracy": 0.9752027481794358,
+      "num_tokens": 313652.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.09941257214224017,
+      "epoch": 2.106312292358804,
+      "grad_norm": 0.119140625,
+      "learning_rate": 3.1221719457013576e-05,
+      "loss": 0.06984617114067078,
+      "mean_token_accuracy": 0.9803445774155695,
+      "num_tokens": 333042.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.11502268332988023,
+      "epoch": 2.2392026578073088,
+      "grad_norm": 0.244140625,
+      "learning_rate": 2.6696832579185523e-05,
+      "loss": 0.0865199089050293,
+      "mean_token_accuracy": 0.9757023945450782,
+      "num_tokens": 354089.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.09293185379356146,
+      "epoch": 2.3720930232558137,
+      "grad_norm": 0.11474609375,
+      "learning_rate": 2.2171945701357466e-05,
+      "loss": 0.0643591821193695,
+      "mean_token_accuracy": 0.9808020308613777,
+      "num_tokens": 375245.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.09169571977108718,
+      "epoch": 2.5049833887043187,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 0.06409262418746949,
+      "mean_token_accuracy": 0.9799414560198784,
+      "num_tokens": 396237.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.09077364690601826,
+      "epoch": 2.6378737541528237,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 1.3122171945701359e-05,
+      "loss": 0.06247810125350952,
+      "mean_token_accuracy": 0.9806646406650543,
+      "num_tokens": 417157.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.1132825130596757,
+      "epoch": 2.770764119601329,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 8.597285067873303e-06,
+      "loss": 0.07793914675712585,
+      "mean_token_accuracy": 0.9766241118311882,
+      "num_tokens": 438013.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.09127289839088917,
+      "epoch": 2.903654485049834,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 4.072398190045249e-06,
+      "loss": 0.06017053723335266,
+      "mean_token_accuracy": 0.9806799024343491,
+      "num_tokens": 459185.0,
+      "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": 2.194774810312704e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

philosophy/checkpoint-228/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf611ec0452b48738de14f1d65be0fb054b1ed2308f1d1c9592a851ffe5f0916
+size 5649