Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,4 @@ checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-88/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-92/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-84/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
 library_name: peft
-model_name: codewraith-lora-3b-v3
+model_name: codewraith-lora-3b-v4
 tags:
 - base_model:adapter:unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
 - lora
@@ -13,7 +13,7 @@ licence: license
 pipeline_tag: text-generation
 ---
 
-# Model Card for codewraith-lora-3b-v3
+# Model Card for codewraith-lora-3b-v4
 
 This model is a fine-tuned version of [unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit).
 It has been trained using [TRL](https://github.com/huggingface/trl).

adapter_config.json

@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
     "gate_proj",
     "down_proj",
-    "k_proj",
-    "o_proj",
     "v_proj",
-    "up_proj",
-    "q_proj"
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c659345a3e6ba4af5995c288a4f8b48ed2f1a3efd1c4e960324fd32e634840
+oid sha256:043556955c06ce77ec2285df5a6365178f0161acbe642dc71c6d9ffb4fae6e7e
 size 194563400

checkpoint-50/adapter_config.json

@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
     "gate_proj",
     "down_proj",
-    "k_proj",
-    "o_proj",
     "v_proj",
-    "up_proj",
-    "q_proj"
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

checkpoint-50/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ca364b702fdc30af6ee41a5b1b35afdb277e700fb904415f613062bd68310f
+oid sha256:a4ceb6e8ebb4e899283eef788d1ac6790995984509ebeb2f745ef060e7c3efb5
 size 194563400

checkpoint-50/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0f04c9a525f450698453b8e38228dc913d4eb40ad0dc52bf0eefd379c83c1c
+oid sha256:112f1b01a84bf4b8dd831a309471616b9ebf2afddcd70e5943bcc26d45d436ed
 size 99240133

checkpoint-50/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e83120c3d881127dc484d1212b5e3f3be4cd0790780c0656a6b861052dbc0838
+oid sha256:6cea7375002e99c9ab5a0a69923c54abb9561c3b0f4fd32fe6b0258894dd81f6
 size 14645

checkpoint-50/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8879d2112d2d2a6843b2de6db12b1d27f886b71db0d9f863b5b077dcd30027c2
+oid sha256:277d557f73460820092ea86679478b7daf0a4f93e11bb07094838ab694f56629
 size 1465

checkpoint-50/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1777777777777776,
+  "epoch": 2.3855421686746987,
   "eval_steps": 500,
   "global_step": 50,
   "is_hyper_param_search": false,
@@ -10,78 +10,78 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.2222222222222222,
-      "grad_norm": 0.3584189713001251,
-      "learning_rate": 8e-05,
-      "loss": 1.0947793006896973,
+      "epoch": 0.24096385542168675,
+      "grad_norm": 0.28208473324775696,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 1.0793883323669433,
       "step": 5
     },
     {
-      "epoch": 0.4444444444444444,
-      "grad_norm": 0.32905852794647217,
-      "learning_rate": 0.00018,
-      "loss": 0.935941219329834,
+      "epoch": 0.4819277108433735,
+      "grad_norm": 0.28007975220680237,
+      "learning_rate": 0.0002,
+      "loss": 1.037606430053711,
       "step": 10
     },
     {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 0.3259493410587311,
-      "learning_rate": 0.0001902439024390244,
-      "loss": 0.8043601036071777,
+      "epoch": 0.7228915662650602,
+      "grad_norm": 0.20863637328147888,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 1.014635181427002,
       "step": 15
     },
     {
-      "epoch": 0.8888888888888888,
-      "grad_norm": 0.29462185502052307,
-      "learning_rate": 0.00017804878048780488,
-      "loss": 0.8039141654968261,
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.21166877448558807,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.8656803131103515,
       "step": 20
     },
     {
-      "epoch": 1.0888888888888888,
-      "grad_norm": 0.24384929239749908,
-      "learning_rate": 0.00016585365853658536,
-      "loss": 0.781571626663208,
+      "epoch": 1.1927710843373494,
+      "grad_norm": 0.20437344908714294,
+      "learning_rate": 0.00016,
+      "loss": 0.7858738899230957,
       "step": 25
     },
     {
-      "epoch": 1.3111111111111111,
-      "grad_norm": 0.22671706974506378,
-      "learning_rate": 0.00015365853658536586,
-      "loss": 0.7156254768371582,
+      "epoch": 1.4337349397590362,
+      "grad_norm": 0.2418038249015808,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.8250644683837891,
       "step": 30
     },
     {
-      "epoch": 1.5333333333333332,
-      "grad_norm": 0.24103912711143494,
-      "learning_rate": 0.00014146341463414634,
-      "loss": 0.6995349407196045,
+      "epoch": 1.6746987951807228,
+      "grad_norm": 0.22985580563545227,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.7688564777374267,
       "step": 35
     },
     {
-      "epoch": 1.7555555555555555,
-      "grad_norm": 0.3071809709072113,
-      "learning_rate": 0.00012926829268292684,
-      "loss": 0.6471355438232422,
+      "epoch": 1.9156626506024095,
+      "grad_norm": 0.25983402132987976,
+      "learning_rate": 0.00012,
+      "loss": 0.7662355899810791,
       "step": 40
     },
     {
-      "epoch": 1.9777777777777779,
-      "grad_norm": 0.30578622221946716,
-      "learning_rate": 0.00011707317073170732,
-      "loss": 0.6253304481506348,
+      "epoch": 2.144578313253012,
+      "grad_norm": 0.24481230974197388,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.7485552787780761,
       "step": 45
     },
     {
-      "epoch": 2.1777777777777776,
-      "grad_norm": 0.28660672903060913,
-      "learning_rate": 0.00010487804878048781,
-      "loss": 0.6118562698364258,
+      "epoch": 2.3855421686746987,
+      "grad_norm": 0.2914965748786926,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.6992795467376709,
       "step": 50
     }
   ],
   "logging_steps": 5,
-  "max_steps": 92,
+  "max_steps": 84,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 4,
   "save_steps": 50,
@@ -97,7 +97,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7334951315990528e+16,
+  "total_flos": 1.9059574215542784e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-50/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b399b89e9ae5eb79e30ecf35667d9ec0c6f34f86e26f2e5d8843612a5d31a4d
+oid sha256:21802bdae0f32f165e782237bf70a9c814806ab8591a6154639b25c94b1e3158
 size 5713

checkpoint-84/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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

checkpoint-84/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-84/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043556955c06ce77ec2285df5a6365178f0161acbe642dc71c6d9ffb4fae6e7e
+size 194563400

checkpoint-84/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- 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 %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- 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 #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\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 %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- 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 %}

checkpoint-84/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5650634684e032957534f6dcad7702d32bb733e8eadbb52a6f5723754c369548
+size 99240133

checkpoint-84/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd5d0829f9631beffb92aa0e6cfa88a108349da8da768753136700d49de5c3a
+size 14645

checkpoint-84/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9bc9a38486c58ac27b0158e1e1443ad50b7e5bb529123e259ccf4c661ed068
+size 1465

checkpoint-84/tokenizer.json

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

checkpoint-84/tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "from_slow": true,
+  "is_local": false,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

checkpoint-84/trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 84,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 0.28208473324775696,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 1.0793883323669433,
+      "step": 5
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 0.28007975220680237,
+      "learning_rate": 0.0002,
+      "loss": 1.037606430053711,
+      "step": 10
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 0.20863637328147888,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 1.014635181427002,
+      "step": 15
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.21166877448558807,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.8656803131103515,
+      "step": 20
+    },
+    {
+      "epoch": 1.1927710843373494,
+      "grad_norm": 0.20437344908714294,
+      "learning_rate": 0.00016,
+      "loss": 0.7858738899230957,
+      "step": 25
+    },
+    {
+      "epoch": 1.4337349397590362,
+      "grad_norm": 0.2418038249015808,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.8250644683837891,
+      "step": 30
+    },
+    {
+      "epoch": 1.6746987951807228,
+      "grad_norm": 0.22985580563545227,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.7688564777374267,
+      "step": 35
+    },
+    {
+      "epoch": 1.9156626506024095,
+      "grad_norm": 0.25983402132987976,
+      "learning_rate": 0.00012,
+      "loss": 0.7662355899810791,
+      "step": 40
+    },
+    {
+      "epoch": 2.144578313253012,
+      "grad_norm": 0.24481230974197388,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.7485552787780761,
+      "step": 45
+    },
+    {
+      "epoch": 2.3855421686746987,
+      "grad_norm": 0.2914965748786926,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.6992795467376709,
+      "step": 50
+    },
+    {
+      "epoch": 2.6265060240963853,
+      "grad_norm": 0.32068315148353577,
+      "learning_rate": 8e-05,
+      "loss": 0.6396950721740723,
+      "step": 55
+    },
+    {
+      "epoch": 2.8674698795180724,
+      "grad_norm": 0.25515061616897583,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.6195734024047852,
+      "step": 60
+    },
+    {
+      "epoch": 3.0963855421686746,
+      "grad_norm": 0.24448628723621368,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.6165074825286865,
+      "step": 65
+    },
+    {
+      "epoch": 3.337349397590361,
+      "grad_norm": 0.34485942125320435,
+      "learning_rate": 4e-05,
+      "loss": 0.5609269618988038,
+      "step": 70
+    },
+    {
+      "epoch": 3.5783132530120483,
+      "grad_norm": 0.3577536344528198,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.6185156345367432,
+      "step": 75
+    },
+    {
+      "epoch": 3.819277108433735,
+      "grad_norm": 0.3738943338394165,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.5909633159637451,
+      "step": 80
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 84,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.1773171341666304e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-84/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21802bdae0f32f165e782237bf70a9c814806ab8591a6154639b25c94b1e3158
+size 5713