Upload folder using huggingface_hub

README.md

@@ -0,0 +1,209 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
+- 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 0.17.0

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c07f5121879c4cadaec404d3b23f7a9725dc290d43d72b27b3ed83c91425f8
+size 335604696

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e18e1dc6c698b77ed15080de0981c7e22e0359d8e62e31896792a69006bbbcb
+size 671365003

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d1105d42c57a99667ef8275ff47ca54315e8a9807d2b17d4c6cdc6ecb9e6cc
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdeac6d1a7910e1e533a39a2d59ab67f6fb22254f41224ded16d311412dbc0b1
+size 1465

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

trainer_state.json

@@ -0,0 +1,831 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2075,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.060350030175015085,
+      "grad_norm": 0.8775522708892822,
+      "learning_rate": 8.18181818181818e-05,
+      "loss": 1.5879,
+      "mean_token_accuracy": 0.6690774387121201,
+      "num_tokens": 155085.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.12070006035003017,
+      "grad_norm": 0.9928436279296875,
+      "learning_rate": 0.00016704545454545452,
+      "loss": 0.882,
+      "mean_token_accuracy": 0.7819808393716812,
+      "num_tokens": 272168.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.18105009052504525,
+      "grad_norm": 0.6491063237190247,
+      "learning_rate": 0.0002522727272727273,
+      "loss": 0.5779,
+      "mean_token_accuracy": 0.8428267538547516,
+      "num_tokens": 424672.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.24140012070006034,
+      "grad_norm": 0.8907634615898132,
+      "learning_rate": 0.0002999887132933212,
+      "loss": 0.5317,
+      "mean_token_accuracy": 0.8538330507278442,
+      "num_tokens": 538458.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.30175015087507545,
+      "grad_norm": 0.9097657203674316,
+      "learning_rate": 0.0002998791256978121,
+      "loss": 0.3574,
+      "mean_token_accuracy": 0.8985000151395798,
+      "num_tokens": 689411.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.3621001810500905,
+      "grad_norm": 0.6912802457809448,
+      "learning_rate": 0.0002996530399366737,
+      "loss": 0.3448,
+      "mean_token_accuracy": 0.9023130792379379,
+      "num_tokens": 804866.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.4224502112251056,
+      "grad_norm": 0.5329523682594299,
+      "learning_rate": 0.00029931063174202567,
+      "loss": 0.2315,
+      "mean_token_accuracy": 0.9339979404211044,
+      "num_tokens": 957115.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.4828002414001207,
+      "grad_norm": 0.759782075881958,
+      "learning_rate": 0.00029885216726118104,
+      "loss": 0.2336,
+      "mean_token_accuracy": 0.9350438743829728,
+      "num_tokens": 1073977.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.5431502715751357,
+      "grad_norm": 0.3837663531303406,
+      "learning_rate": 0.00029827800284977474,
+      "loss": 0.189,
+      "mean_token_accuracy": 0.9478910142183303,
+      "num_tokens": 1225658.0,
+      "step": 225
+    },
+    {
+      "epoch": 0.6035003017501509,
+      "grad_norm": 0.7154819369316101,
+      "learning_rate": 0.00029758858479477575,
+      "loss": 0.192,
+      "mean_token_accuracy": 0.9470360428094864,
+      "num_tokens": 1340933.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.663850331925166,
+      "grad_norm": 0.32724520564079285,
+      "learning_rate": 0.0002967844489675963,
+      "loss": 0.1544,
+      "mean_token_accuracy": 0.9575115633010864,
+      "num_tokens": 1492525.0,
+      "step": 275
+    },
+    {
+      "epoch": 0.724200362100181,
+      "grad_norm": 0.7199254035949707,
+      "learning_rate": 0.00029586622040756957,
+      "loss": 0.1512,
+      "mean_token_accuracy": 0.9590712755918502,
+      "num_tokens": 1609549.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.7845503922751962,
+      "grad_norm": 0.5064759850502014,
+      "learning_rate": 0.0002948346128361186,
+      "loss": 0.127,
+      "mean_token_accuracy": 0.9652698183059693,
+      "num_tokens": 1760812.0,
+      "step": 325
+    },
+    {
+      "epoch": 0.8449004224502112,
+      "grad_norm": 0.9060899615287781,
+      "learning_rate": 0.00029369042810199416,
+      "loss": 0.1295,
+      "mean_token_accuracy": 0.9658441722393036,
+      "num_tokens": 1878082.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.9052504526252263,
+      "grad_norm": 0.39403802156448364,
+      "learning_rate": 0.0002924345555580135,
+      "loss": 0.124,
+      "mean_token_accuracy": 0.96674849152565,
+      "num_tokens": 2030379.0,
+      "step": 375
+    },
+    {
+      "epoch": 0.9656004828002414,
+      "grad_norm": 0.510175347328186,
+      "learning_rate": 0.000291067971369783,
+      "loss": 0.1175,
+      "mean_token_accuracy": 0.9700243002176285,
+      "num_tokens": 2145568.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.12158163636922836,
+      "eval_mean_token_accuracy": 0.9679943664653882,
+      "eval_num_tokens": 2223513.0,
+      "eval_runtime": 60.3991,
+      "eval_samples_per_second": 6.109,
+      "eval_steps_per_second": 3.063,
+      "step": 415
+    },
+    {
+      "epoch": 1.024140012070006,
+      "grad_norm": 0.406086802482605,
+      "learning_rate": 0.0002895917377569438,
+      "loss": 0.1273,
+      "mean_token_accuracy": 0.9658442354693855,
+      "num_tokens": 2291474.0,
+      "step": 425
+    },
+    {
+      "epoch": 1.0844900422450212,
+      "grad_norm": 0.5659676790237427,
+      "learning_rate": 0.00028800700216752875,
+      "loss": 0.0838,
+      "mean_token_accuracy": 0.9784896957874298,
+      "num_tokens": 2426520.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.1448400724200363,
+      "grad_norm": 0.35416120290756226,
+      "learning_rate": 0.00028631499638607285,
+      "loss": 0.1106,
+      "mean_token_accuracy": 0.9712809121608734,
+      "num_tokens": 2559490.0,
+      "step": 475
+    },
+    {
+      "epoch": 1.2051901025950513,
+      "grad_norm": 0.4320279657840729,
+      "learning_rate": 0.0002845170355761712,
+      "loss": 0.0828,
+      "mean_token_accuracy": 0.9781204652786255,
+      "num_tokens": 2692836.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.2655401327700664,
+      "grad_norm": 0.2252548485994339,
+      "learning_rate": 0.0002826145172582274,
+      "loss": 0.1078,
+      "mean_token_accuracy": 0.972182622551918,
+      "num_tokens": 2824220.0,
+      "step": 525
+    },
+    {
+      "epoch": 1.3258901629450814,
+      "grad_norm": 0.5526081323623657,
+      "learning_rate": 0.00028060892022318764,
+      "loss": 0.0859,
+      "mean_token_accuracy": 0.9773634171485901,
+      "num_tokens": 2957350.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.3862401931200965,
+      "grad_norm": 0.28977397084236145,
+      "learning_rate": 0.0002785018033831051,
+      "loss": 0.1003,
+      "mean_token_accuracy": 0.9744341260194779,
+      "num_tokens": 3089488.0,
+      "step": 575
+    },
+    {
+      "epoch": 1.4465902232951118,
+      "grad_norm": 0.3141675591468811,
+      "learning_rate": 0.0002762948045594276,
+      "loss": 0.0791,
+      "mean_token_accuracy": 0.9794832402467728,
+      "num_tokens": 3223359.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.5069402534701268,
+      "grad_norm": 0.2956194579601288,
+      "learning_rate": 0.0002739896392099502,
+      "loss": 0.0973,
+      "mean_token_accuracy": 0.9747027105093002,
+      "num_tokens": 3356289.0,
+      "step": 625
+    },
+    {
+      "epoch": 1.567290283645142,
+      "grad_norm": 0.20789697766304016,
+      "learning_rate": 0.00027158809909542307,
+      "loss": 0.0799,
+      "mean_token_accuracy": 0.9793938374519349,
+      "num_tokens": 3492136.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.627640313820157,
+      "grad_norm": 0.2433897703886032,
+      "learning_rate": 0.00026909205088685,
+      "loss": 0.1014,
+      "mean_token_accuracy": 0.9734487825632095,
+      "num_tokens": 3626915.0,
+      "step": 675
+    },
+    {
+      "epoch": 1.687990343995172,
+      "grad_norm": 0.7531152367591858,
+      "learning_rate": 0.0002665034347145612,
+      "loss": 0.0712,
+      "mean_token_accuracy": 0.9815128433704376,
+      "num_tokens": 3763997.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.748340374170187,
+      "grad_norm": 0.2832512855529785,
+      "learning_rate": 0.000263824262660187,
+      "loss": 0.0906,
+      "mean_token_accuracy": 0.9767874735593796,
+      "num_tokens": 3899136.0,
+      "step": 725
+    },
+    {
+      "epoch": 1.8086904043452021,
+      "grad_norm": 0.25026917457580566,
+      "learning_rate": 0.0002610566171927056,
+      "loss": 0.0738,
+      "mean_token_accuracy": 0.9808795565366745,
+      "num_tokens": 4035090.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.8690404345202172,
+      "grad_norm": 0.2247888296842575,
+      "learning_rate": 0.00025820264954977976,
+      "loss": 0.0924,
+      "mean_token_accuracy": 0.9755205953121185,
+      "num_tokens": 4170738.0,
+      "step": 775
+    },
+    {
+      "epoch": 1.9293904646952322,
+      "grad_norm": 0.2288103550672531,
+      "learning_rate": 0.00025526457806564136,
+      "loss": 0.0689,
+      "mean_token_accuracy": 0.9819435960054398,
+      "num_tokens": 4304690.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.9897404948702473,
+      "grad_norm": 0.3063240647315979,
+      "learning_rate": 0.00025224468644682245,
+      "loss": 0.0848,
+      "mean_token_accuracy": 0.9782917034626007,
+      "num_tokens": 4428594.0,
+      "step": 825
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.08532727509737015,
+      "eval_mean_token_accuracy": 0.978298093499364,
+      "eval_num_tokens": 4447026.0,
+      "eval_runtime": 60.4972,
+      "eval_samples_per_second": 6.099,
+      "eval_steps_per_second": 3.058,
+      "step": 830
+    },
+    {
+      "epoch": 2.048280024140012,
+      "grad_norm": 0.292191743850708,
+      "learning_rate": 0.00024914532199707444,
+      "loss": 0.0742,
+      "mean_token_accuracy": 0.9807861385886202,
+      "num_tokens": 4570802.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.1086300543150274,
+      "grad_norm": 0.12266981601715088,
+      "learning_rate": 0.00024596889379285353,
+      "loss": 0.0583,
+      "mean_token_accuracy": 0.9852461409568787,
+      "num_tokens": 4693406.0,
+      "step": 875
+    },
+    {
+      "epoch": 2.1689800844900424,
+      "grad_norm": 0.2619573473930359,
+      "learning_rate": 0.00024271787081079228,
+      "loss": 0.0675,
+      "mean_token_accuracy": 0.9823181647062301,
+      "num_tokens": 4840920.0,
+      "step": 900
+    },
+    {
+      "epoch": 2.2293301146650575,
+      "grad_norm": 0.3071349859237671,
+      "learning_rate": 0.00023939478000861117,
+      "loss": 0.0618,
+      "mean_token_accuracy": 0.9843161147832871,
+      "num_tokens": 4963388.0,
+      "step": 925
+    },
+    {
+      "epoch": 2.2896801448400725,
+      "grad_norm": 0.19022433459758759,
+      "learning_rate": 0.00023600220436096318,
+      "loss": 0.073,
+      "mean_token_accuracy": 0.9802478235960007,
+      "num_tokens": 5109242.0,
+      "step": 950
+    },
+    {
+      "epoch": 2.3500301750150876,
+      "grad_norm": 0.21214531362056732,
+      "learning_rate": 0.00023254278085173684,
+      "loss": 0.058,
+      "mean_token_accuracy": 0.985277818441391,
+      "num_tokens": 5233880.0,
+      "step": 975
+    },
+    {
+      "epoch": 2.4103802051901027,
+      "grad_norm": 0.27143731713294983,
+      "learning_rate": 0.00022901919842437972,
+      "loss": 0.0696,
+      "mean_token_accuracy": 0.9813511747121811,
+      "num_tokens": 5379872.0,
+      "step": 1000
+    },
+    {
+      "epoch": 2.4707302353651177,
+      "grad_norm": 0.22756575047969818,
+      "learning_rate": 0.00022543419589183397,
+      "loss": 0.0557,
+      "mean_token_accuracy": 0.9860703033208847,
+      "num_tokens": 5503533.0,
+      "step": 1025
+    },
+    {
+      "epoch": 2.5310802655401328,
+      "grad_norm": 0.20393149554729462,
+      "learning_rate": 0.00022179055980770993,
+      "loss": 0.0714,
+      "mean_token_accuracy": 0.9812053245306015,
+      "num_tokens": 5648709.0,
+      "step": 1050
+    },
+    {
+      "epoch": 2.591430295715148,
+      "grad_norm": 0.1682002693414688,
+      "learning_rate": 0.0002180911223003513,
+      "loss": 0.0573,
+      "mean_token_accuracy": 0.9854411727190018,
+      "num_tokens": 5771477.0,
+      "step": 1075
+    },
+    {
+      "epoch": 2.651780325890163,
+      "grad_norm": 0.17297177016735077,
+      "learning_rate": 0.00021433875887147627,
+      "loss": 0.0684,
+      "mean_token_accuracy": 0.9818347871303559,
+      "num_tokens": 5917022.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.712130356065178,
+      "grad_norm": 0.3354227840900421,
+      "learning_rate": 0.00021053638616110525,
+      "loss": 0.056,
+      "mean_token_accuracy": 0.9859032183885574,
+      "num_tokens": 6040041.0,
+      "step": 1125
+    },
+    {
+      "epoch": 2.772480386240193,
+      "grad_norm": 0.17890885472297668,
+      "learning_rate": 0.00020668695968051274,
+      "loss": 0.0644,
+      "mean_token_accuracy": 0.9828311365842819,
+      "num_tokens": 6183440.0,
+      "step": 1150
+    },
+    {
+      "epoch": 2.832830416415208,
+      "grad_norm": 0.19668501615524292,
+      "learning_rate": 0.00020279347151496482,
+      "loss": 0.0572,
+      "mean_token_accuracy": 0.9856607836484909,
+      "num_tokens": 6307206.0,
+      "step": 1175
+    },
+    {
+      "epoch": 2.8931804465902236,
+      "grad_norm": 0.12178179621696472,
+      "learning_rate": 0.00019885894799802922,
+      "loss": 0.0626,
+      "mean_token_accuracy": 0.9839641106128693,
+      "num_tokens": 6451936.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.9535304767652386,
+      "grad_norm": 0.14492283761501312,
+      "learning_rate": 0.00019488644735926396,
+      "loss": 0.0533,
+      "mean_token_accuracy": 0.9867338234186173,
+      "num_tokens": 6574944.0,
+      "step": 1225
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.06949137151241302,
+      "eval_mean_token_accuracy": 0.9829865713377257,
+      "eval_num_tokens": 6670539.0,
+      "eval_runtime": 60.3936,
+      "eval_samples_per_second": 6.11,
+      "eval_steps_per_second": 3.063,
+      "step": 1245
+    },
+    {
+      "epoch": 3.012070006035003,
+      "grad_norm": 0.18783801794052124,
+      "learning_rate": 0.00019087905734711452,
+      "loss": 0.0609,
+      "mean_token_accuracy": 0.984156120683729,
+      "num_tokens": 6706398.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0724200362100182,
+      "grad_norm": 0.2086067646741867,
+      "learning_rate": 0.00018683989282886613,
+      "loss": 0.046,
+      "mean_token_accuracy": 0.9881435281038284,
+      "num_tokens": 6848066.0,
+      "step": 1275
+    },
+    {
+      "epoch": 3.1327700663850333,
+      "grad_norm": 0.2123444378376007,
+      "learning_rate": 0.0001827720933695173,
+      "loss": 0.0552,
+      "mean_token_accuracy": 0.9860709112882614,
+      "num_tokens": 6975273.0,
+      "step": 1300
+    },
+    {
+      "epoch": 3.1931200965600484,
+      "grad_norm": 0.11279409378767014,
+      "learning_rate": 0.00017867882079145627,
+      "loss": 0.0455,
+      "mean_token_accuracy": 0.9881318390369416,
+      "num_tokens": 7117546.0,
+      "step": 1325
+    },
+    {
+      "epoch": 3.2534701267350634,
+      "grad_norm": 0.177442729473114,
+      "learning_rate": 0.00017456325671683724,
+      "loss": 0.0546,
+      "mean_token_accuracy": 0.9862780523300171,
+      "num_tokens": 7244543.0,
+      "step": 1350
+    },
+    {
+      "epoch": 3.3138201569100785,
+      "grad_norm": 0.10142289847135544,
+      "learning_rate": 0.00017042860009456638,
+      "loss": 0.0445,
+      "mean_token_accuracy": 0.988534786105156,
+      "num_tokens": 7384967.0,
+      "step": 1375
+    },
+    {
+      "epoch": 3.3741701870850935,
+      "grad_norm": 0.15665322542190552,
+      "learning_rate": 0.00016627806471382066,
+      "loss": 0.0532,
+      "mean_token_accuracy": 0.9868290704488755,
+      "num_tokens": 7509226.0,
+      "step": 1400
+    },
+    {
+      "epoch": 3.4345202172601086,
+      "grad_norm": 0.15646246075630188,
+      "learning_rate": 0.00016211487670603078,
+      "loss": 0.0456,
+      "mean_token_accuracy": 0.9882669430971146,
+      "num_tokens": 7648911.0,
+      "step": 1425
+    },
+    {
+      "epoch": 3.4948702474351236,
+      "grad_norm": 0.16921687126159668,
+      "learning_rate": 0.0001579422720372715,
+      "loss": 0.0568,
+      "mean_token_accuracy": 0.9850279080867768,
+      "num_tokens": 7777925.0,
+      "step": 1450
+    },
+    {
+      "epoch": 3.5552202776101387,
+      "grad_norm": 0.10589733719825745,
+      "learning_rate": 0.00015376349399300745,
+      "loss": 0.0446,
+      "mean_token_accuracy": 0.9881089746952056,
+      "num_tokens": 7922053.0,
+      "step": 1475
+    },
+    {
+      "epoch": 3.6155703077851538,
+      "grad_norm": 0.2955225110054016,
+      "learning_rate": 0.0001495817906571492,
+      "loss": 0.0544,
+      "mean_token_accuracy": 0.9862786346673965,
+      "num_tokens": 8049528.0,
+      "step": 1500
+    },
+    {
+      "epoch": 3.675920337960169,
+      "grad_norm": 0.0742836520075798,
+      "learning_rate": 0.00014540041238738055,
+      "loss": 0.0456,
+      "mean_token_accuracy": 0.9878502124547959,
+      "num_tokens": 8190743.0,
+      "step": 1525
+    },
+    {
+      "epoch": 3.736270368135184,
+      "grad_norm": 0.12437008321285248,
+      "learning_rate": 0.00014122260928871734,
+      "loss": 0.0535,
+      "mean_token_accuracy": 0.9863007247447968,
+      "num_tokens": 8316676.0,
+      "step": 1550
+    },
+    {
+      "epoch": 3.796620398310199,
+      "grad_norm": 0.08342117071151733,
+      "learning_rate": 0.00013705162868726396,
+      "loss": 0.0447,
+      "mean_token_accuracy": 0.9884078222513198,
+      "num_tokens": 8457403.0,
+      "step": 1575
+    },
+    {
+      "epoch": 3.856970428485214,
+      "grad_norm": 0.17910127341747284,
+      "learning_rate": 0.00013289071260612855,
+      "loss": 0.052,
+      "mean_token_accuracy": 0.9868350481986999,
+      "num_tokens": 8583976.0,
+      "step": 1600
+    },
+    {
+      "epoch": 3.9173204586602295,
+      "grad_norm": 0.06760319322347641,
+      "learning_rate": 0.00012874309524546083,
+      "loss": 0.045,
+      "mean_token_accuracy": 0.9878969532251358,
+      "num_tokens": 8727702.0,
+      "step": 1625
+    },
+    {
+      "epoch": 3.9776704888352445,
+      "grad_norm": 0.15349148213863373,
+      "learning_rate": 0.00012461200046857084,
+      "loss": 0.0508,
+      "mean_token_accuracy": 0.987232791185379,
+      "num_tokens": 8849683.0,
+      "step": 1650
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.0635647177696228,
+      "eval_mean_token_accuracy": 0.9845431846541327,
+      "eval_num_tokens": 8894052.0,
+      "eval_runtime": 60.4472,
+      "eval_samples_per_second": 6.105,
+      "eval_steps_per_second": 3.061,
+      "step": 1660
+    },
+    {
+      "epoch": 4.036210018105009,
+      "grad_norm": 0.1430218666791916,
+      "learning_rate": 0.00012050063929608123,
+      "loss": 0.0441,
+      "mean_token_accuracy": 0.9887785659622901,
+      "num_tokens": 8992417.0,
+      "step": 1675
+    },
+    {
+      "epoch": 4.096560048280024,
+      "grad_norm": 0.08819396048784256,
+      "learning_rate": 0.0001164122074100633,
+      "loss": 0.0406,
+      "mean_token_accuracy": 0.9898108446598053,
+      "num_tokens": 9122219.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.15691007845504,
+      "grad_norm": 0.08506345748901367,
+      "learning_rate": 0.00011234988267009415,
+      "loss": 0.0457,
+      "mean_token_accuracy": 0.9884944796562195,
+      "num_tokens": 9262178.0,
+      "step": 1725
+    },
+    {
+      "epoch": 4.217260108630055,
+      "grad_norm": 0.08111756294965744,
+      "learning_rate": 0.00010831682264316787,
+      "loss": 0.0416,
+      "mean_token_accuracy": 0.989647062420845,
+      "num_tokens": 9391026.0,
+      "step": 1750
+    },
+    {
+      "epoch": 4.27761013880507,
+      "grad_norm": 0.07644202560186386,
+      "learning_rate": 0.00010431616214937911,
+      "loss": 0.046,
+      "mean_token_accuracy": 0.9881355553865433,
+      "num_tokens": 9531921.0,
+      "step": 1775
+    },
+    {
+      "epoch": 4.337960168980085,
+      "grad_norm": 0.03971414268016815,
+      "learning_rate": 0.00010035101082528777,
+      "loss": 0.0413,
+      "mean_token_accuracy": 0.9894955778121948,
+      "num_tokens": 9661664.0,
+      "step": 1800
+    },
+    {
+      "epoch": 4.3983101991551,
+      "grad_norm": 0.07305199652910233,
+      "learning_rate": 9.642445070685809e-05,
+      "loss": 0.0435,
+      "mean_token_accuracy": 0.9884718316793442,
+      "num_tokens": 9801214.0,
+      "step": 1825
+    },
+    {
+      "epoch": 4.458660229330115,
+      "grad_norm": 0.07561074942350388,
+      "learning_rate": 9.253953383385157e-05,
+      "loss": 0.0411,
+      "mean_token_accuracy": 0.9890134006738662,
+      "num_tokens": 9929511.0,
+      "step": 1850
+    },
+    {
+      "epoch": 4.51901025950513,
+      "grad_norm": 0.12152893096208572,
+      "learning_rate": 8.869927987753459e-05,
+      "loss": 0.0442,
+      "mean_token_accuracy": 0.9886808878183365,
+      "num_tokens": 10069489.0,
+      "step": 1875
+    },
+    {
+      "epoch": 4.579360289680145,
+      "grad_norm": 0.05834532529115677,
+      "learning_rate": 8.490667379354661e-05,
+      "loss": 0.0417,
+      "mean_token_accuracy": 0.9894009435176849,
+      "num_tokens": 10197956.0,
+      "step": 1900
+    },
+    {
+      "epoch": 4.63971031985516,
+      "grad_norm": 0.08154677599668503,
+      "learning_rate": 8.116466350175079e-05,
+      "loss": 0.0437,
+      "mean_token_accuracy": 0.9884669744968414,
+      "num_tokens": 10335860.0,
+      "step": 1925
+    },
+    {
+      "epoch": 4.700060350030175,
+      "grad_norm": 0.07408758997917175,
+      "learning_rate": 7.747615759487304e-05,
+      "loss": 0.0411,
+      "mean_token_accuracy": 0.989289864897728,
+      "num_tokens": 10464303.0,
+      "step": 1950
+    },
+    {
+      "epoch": 4.76041038020519,
+      "grad_norm": 0.0779808983206749,
+      "learning_rate": 7.38440230777085e-05,
+      "loss": 0.0453,
+      "mean_token_accuracy": 0.9880505865812301,
+      "num_tokens": 10601511.0,
+      "step": 1975
+    },
+    {
+      "epoch": 4.820760410380205,
+      "grad_norm": 0.046579256653785706,
+      "learning_rate": 7.027108313865378e-05,
+      "loss": 0.0401,
+      "mean_token_accuracy": 0.9896253395080566,
+      "num_tokens": 10732156.0,
+      "step": 2000
+    },
+    {
+      "epoch": 4.88111044055522,
+      "grad_norm": 0.07918152213096619,
+      "learning_rate": 6.676011495529687e-05,
+      "loss": 0.042,
+      "mean_token_accuracy": 0.9889346659183502,
+      "num_tokens": 10873235.0,
+      "step": 2025
+    },
+    {
+      "epoch": 4.941460470730235,
+      "grad_norm": 0.04908803850412369,
+      "learning_rate": 6.331384753577056e-05,
+      "loss": 0.0408,
+      "mean_token_accuracy": 0.9895875388383866,
+      "num_tokens": 11001827.0,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.22838693857192993,
+      "learning_rate": 5.993495959754631e-05,
+      "loss": 0.0452,
+      "mean_token_accuracy": 0.9885991817897128,
+      "num_tokens": 11117565.0,
+      "step": 2075
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.06391309201717377,
+      "eval_mean_token_accuracy": 0.9852847150854163,
+      "eval_num_tokens": 11117565.0,
+      "eval_runtime": 60.3576,
+      "eval_samples_per_second": 6.114,
+      "eval_steps_per_second": 3.065,
+      "step": 2075
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 2905,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.8080321362273075e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6de366ac315839abd567edca47f98a08a1256a4f1baddaab0d0cfffba2f28f
+size 5969