Add files using upload-large-folder tool

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:408687b31491b8632769dbdb99afac6b742671a321bbdb08d9b687441156222e
+size 319876032

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328797e5ab2f0227fb719b1ecf9634409bcece8d08da552eeb7d7e7b43ed53b3
+size 319876032

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed384eaeb38bed9ef8d60ca40aa0ad91f3fe154ee7859eb8ab2c06ede5e21e4
+size 640016419

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df8ccd717c0a7221fc49d898241d974c90450f081ad463f3890a1f8bca9f9ab
+size 14645

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c057cde13a3bd504dd54b949c621026d56c256c36c01e0fffcccd635df398f6c
+size 1465

checkpoint-100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00365a4cc96eaeff8b9bf3b6f24a4c5bec58ca652f39e144d932a15f1785688b
+size 5777

checkpoint-117/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392cf3040c4328708e82cd1b00fb393a08d73f91e64eb1486b11ab38fbefdbb5
+size 319876032

checkpoint-117/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1dc875d4c52756435dedee3a5641879bcaa9ede37df0a26cd535e5d1be7159
+size 640016419

checkpoint-117/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3200224ac04a754bf4a82e5e6e0d27facab938161315c0a15a9dc3937060af66
+size 14645

checkpoint-117/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:638f53840b41e0451f47cee5c0a7ff16a51ddad38dc7bfd4d5021ecd97e48bc6
+size 1465

checkpoint-117/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

checkpoint-117/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea7c13411aa97090633c7975ecf214249c1039e515f5dd38a768452c7afeea1
+size 5777

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a71b10f9d15a6b7fa92233c08f80e720a488393b969773518651407cb5f4d9
+size 319876032

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0d6be2c8aaffb2f083bf7c95cb1bb2bc61b2c37abda814417888796e6864ef
+size 640016419

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf94385fad0d9f36f2f74907f87bb5ee3912b9514c93bdf445305c43f91a135
+size 14645

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1e43b7176c9ce67f0456dc095e8a5c3a12fad8f9010474f392ecb44c3dabea
+size 1465

checkpoint-200/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00365a4cc96eaeff8b9bf3b6f24a4c5bec58ca652f39e144d932a15f1785688b
+size 5777

checkpoint-30/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb84f2bb30be203dc4eca156d24a3d3d28a47083f491aa0612cc6ab59473c5f
+size 319876032

checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:792a1fc53707d96c117e1a79df021c2b8896ae5a89eeda5751e758a3b41923b9
+size 640016419

checkpoint-30/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2f5523bc70654d46a5ce51d29e54a53db160e65355d6b9f3204d6563cba893
+size 14645

checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc12e11a207334b7494b121f35732b7fcbe80093c3fe15b3f6574cfce8b3a24
+size 1465

checkpoint-30/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946725f131b73c2c1fc740a0a47104f82d1740334b3073affbeb1184449191ed
+size 5777

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9183d4c0cb01e6744939bb1ceea1dae491aa103637e567f852edbc2eef2ee0a9
+size 319876032

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e753bdb046ef186cee096199fb8b1739c7596a7cd80eef51b81ef93068d24be
+size 640016419

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2dd0147fd94e5765e29f13b5c4fcf242ba9ccf08702e45835f68c5e112e54a9
+size 14645

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2c1875c60dc17534606d53f931a9d980639fc83f75f47f4a92361e1fac7920
+size 1465

checkpoint-300/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00365a4cc96eaeff8b9bf3b6f24a4c5bec58ca652f39e144d932a15f1785688b
+size 5777

checkpoint-400/README.md

@@ -0,0 +1,207 @@
+---
+base_model: codellama/CodeLlama-7b-Instruct-hf
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:codellama/CodeLlama-7b-Instruct-hf
+- lora
+- transformers
+---
+
+# 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 0.18.0

checkpoint-400/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:408687b31491b8632769dbdb99afac6b742671a321bbdb08d9b687441156222e
+size 319876032

checkpoint-400/chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb03705a726ddc56d5b84912718ef97d26b63d62585e621d3a3ba21a9edef5f
+size 640016419

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522c6e6ff76e0e64527f2883b8cefe80a72d1b7c2e10e191cef3d846b1768b6c
+size 14645

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a90ceb2c5fcaedc8f51e68705faf7e039c8d5c2423eef7c410181e794bf1be4
+size 1465

checkpoint-400/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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
+  }
+}

checkpoint-400/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

checkpoint-400/trainer_state.json

@@ -0,0 +1,626 @@
+{
+  "best_global_step": 400,
+  "best_metric": 0.34772011637687683,
+  "best_model_checkpoint": "./luau-model/checkpoint-400",
+  "epoch": 2.7777777777777777,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.034722222222222224,
+      "grad_norm": 0.19553522765636444,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.5215,
+      "step": 5
+    },
+    {
+      "epoch": 0.06944444444444445,
+      "grad_norm": 0.18851090967655182,
+      "learning_rate": 3.6e-05,
+      "loss": 1.4318,
+      "step": 10
+    },
+    {
+      "epoch": 0.10416666666666667,
+      "grad_norm": 0.2147289365530014,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.4315,
+      "step": 15
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 0.22880084812641144,
+      "learning_rate": 7.6e-05,
+      "loss": 1.3475,
+      "step": 20
+    },
+    {
+      "epoch": 0.1736111111111111,
+      "grad_norm": 0.27205583453178406,
+      "learning_rate": 9.6e-05,
+      "loss": 1.3244,
+      "step": 25
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.2366049736738205,
+      "learning_rate": 0.000116,
+      "loss": 1.3784,
+      "step": 30
+    },
+    {
+      "epoch": 0.24305555555555555,
+      "grad_norm": 0.2528875768184662,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.3578,
+      "step": 35
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 0.2789267897605896,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 1.2761,
+      "step": 40
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.36334967613220215,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 1.3073,
+      "step": 45
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 0.3194734454154968,
+      "learning_rate": 0.000196,
+      "loss": 1.2374,
+      "step": 50
+    },
+    {
+      "epoch": 0.3819444444444444,
+      "grad_norm": 0.4422107934951782,
+      "learning_rate": 0.00019790575916230367,
+      "loss": 1.2243,
+      "step": 55
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.36031872034072876,
+      "learning_rate": 0.00019528795811518326,
+      "loss": 1.236,
+      "step": 60
+    },
+    {
+      "epoch": 0.4513888888888889,
+      "grad_norm": 0.40430501103401184,
+      "learning_rate": 0.00019267015706806283,
+      "loss": 1.1484,
+      "step": 65
+    },
+    {
+      "epoch": 0.4861111111111111,
+      "grad_norm": 0.39032667875289917,
+      "learning_rate": 0.00019005235602094243,
+      "loss": 1.1352,
+      "step": 70
+    },
+    {
+      "epoch": 0.5208333333333334,
+      "grad_norm": 0.3691488206386566,
+      "learning_rate": 0.00018743455497382202,
+      "loss": 1.0341,
+      "step": 75
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.3820245563983917,
+      "learning_rate": 0.00018481675392670156,
+      "loss": 0.9911,
+      "step": 80
+    },
+    {
+      "epoch": 0.5902777777777778,
+      "grad_norm": 0.40899762511253357,
+      "learning_rate": 0.00018219895287958115,
+      "loss": 1.077,
+      "step": 85
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.3846423029899597,
+      "learning_rate": 0.00017958115183246075,
+      "loss": 1.1241,
+      "step": 90
+    },
+    {
+      "epoch": 0.6597222222222222,
+      "grad_norm": 0.43537914752960205,
+      "learning_rate": 0.00017696335078534032,
+      "loss": 1.0522,
+      "step": 95
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 0.40991654992103577,
+      "learning_rate": 0.0001743455497382199,
+      "loss": 1.0116,
+      "step": 100
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "eval_loss": 1.053038239479065,
+      "eval_runtime": 19.8507,
+      "eval_samples_per_second": 9.622,
+      "eval_steps_per_second": 1.612,
+      "step": 100
+    },
+    {
+      "epoch": 0.7291666666666666,
+      "grad_norm": 0.4987630248069763,
+      "learning_rate": 0.00017172774869109948,
+      "loss": 0.9179,
+      "step": 105
+    },
+    {
+      "epoch": 0.7638888888888888,
+      "grad_norm": 0.44468897581100464,
+      "learning_rate": 0.00016910994764397907,
+      "loss": 1.0694,
+      "step": 110
+    },
+    {
+      "epoch": 0.7986111111111112,
+      "grad_norm": 0.4741359055042267,
+      "learning_rate": 0.00016649214659685867,
+      "loss": 1.024,
+      "step": 115
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.47767335176467896,
+      "learning_rate": 0.0001638743455497382,
+      "loss": 0.9636,
+      "step": 120
+    },
+    {
+      "epoch": 0.8680555555555556,
+      "grad_norm": 0.45077380537986755,
+      "learning_rate": 0.0001612565445026178,
+      "loss": 1.0373,
+      "step": 125
+    },
+    {
+      "epoch": 0.9027777777777778,
+      "grad_norm": 0.43459218740463257,
+      "learning_rate": 0.0001586387434554974,
+      "loss": 0.9578,
+      "step": 130
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.5079038739204407,
+      "learning_rate": 0.00015602094240837696,
+      "loss": 0.8932,
+      "step": 135
+    },
+    {
+      "epoch": 0.9722222222222222,
+      "grad_norm": 0.48626700043678284,
+      "learning_rate": 0.00015340314136125656,
+      "loss": 0.9151,
+      "step": 140
+    },
+    {
+      "epoch": 1.0069444444444444,
+      "grad_norm": 0.5171248316764832,
+      "learning_rate": 0.00015078534031413612,
+      "loss": 0.9027,
+      "step": 145
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.6200463175773621,
+      "learning_rate": 0.00014816753926701572,
+      "loss": 0.6928,
+      "step": 150
+    },
+    {
+      "epoch": 1.0763888888888888,
+      "grad_norm": 0.48823609948158264,
+      "learning_rate": 0.00014554973821989531,
+      "loss": 0.7165,
+      "step": 155
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.5404874086380005,
+      "learning_rate": 0.00014293193717277485,
+      "loss": 0.6827,
+      "step": 160
+    },
+    {
+      "epoch": 1.1458333333333333,
+      "grad_norm": 0.46143069863319397,
+      "learning_rate": 0.00014031413612565445,
+      "loss": 0.7171,
+      "step": 165
+    },
+    {
+      "epoch": 1.1805555555555556,
+      "grad_norm": 0.5935544371604919,
+      "learning_rate": 0.00013769633507853404,
+      "loss": 0.7044,
+      "step": 170
+    },
+    {
+      "epoch": 1.2152777777777777,
+      "grad_norm": 0.5715068578720093,
+      "learning_rate": 0.0001350785340314136,
+      "loss": 0.6636,
+      "step": 175
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.585377037525177,
+      "learning_rate": 0.0001324607329842932,
+      "loss": 0.679,
+      "step": 180
+    },
+    {
+      "epoch": 1.2847222222222223,
+      "grad_norm": 0.5465496182441711,
+      "learning_rate": 0.00012984293193717277,
+      "loss": 0.647,
+      "step": 185
+    },
+    {
+      "epoch": 1.3194444444444444,
+      "grad_norm": 0.5915805697441101,
+      "learning_rate": 0.00012722513089005237,
+      "loss": 0.6305,
+      "step": 190
+    },
+    {
+      "epoch": 1.3541666666666667,
+      "grad_norm": 0.5672898888587952,
+      "learning_rate": 0.00012460732984293196,
+      "loss": 0.6799,
+      "step": 195
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 0.735905110836029,
+      "learning_rate": 0.00012198952879581151,
+      "loss": 0.6022,
+      "step": 200
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "eval_loss": 0.7630631327629089,
+      "eval_runtime": 19.802,
+      "eval_samples_per_second": 9.646,
+      "eval_steps_per_second": 1.616,
+      "step": 200
+    },
+    {
+      "epoch": 1.4236111111111112,
+      "grad_norm": 0.6561821699142456,
+      "learning_rate": 0.0001193717277486911,
+      "loss": 0.6586,
+      "step": 205
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 0.5606387853622437,
+      "learning_rate": 0.00011675392670157068,
+      "loss": 0.5827,
+      "step": 210
+    },
+    {
+      "epoch": 1.4930555555555556,
+      "grad_norm": 0.7301760315895081,
+      "learning_rate": 0.00011413612565445027,
+      "loss": 0.6343,
+      "step": 215
+    },
+    {
+      "epoch": 1.5277777777777777,
+      "grad_norm": 0.6215537190437317,
+      "learning_rate": 0.00011151832460732985,
+      "loss": 0.6967,
+      "step": 220
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 0.5844612121582031,
+      "learning_rate": 0.00010890052356020943,
+      "loss": 0.5831,
+      "step": 225
+    },
+    {
+      "epoch": 1.5972222222222223,
+      "grad_norm": 0.6531478762626648,
+      "learning_rate": 0.00010628272251308901,
+      "loss": 0.5586,
+      "step": 230
+    },
+    {
+      "epoch": 1.6319444444444444,
+      "grad_norm": 0.6617570519447327,
+      "learning_rate": 0.0001036649214659686,
+      "loss": 0.4622,
+      "step": 235
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.5876675844192505,
+      "learning_rate": 0.00010104712041884816,
+      "loss": 0.4863,
+      "step": 240
+    },
+    {
+      "epoch": 1.7013888888888888,
+      "grad_norm": 0.6678897142410278,
+      "learning_rate": 9.842931937172776e-05,
+      "loss": 0.4397,
+      "step": 245
+    },
+    {
+      "epoch": 1.7361111111111112,
+      "grad_norm": 0.6826710104942322,
+      "learning_rate": 9.581151832460732e-05,
+      "loss": 0.4996,
+      "step": 250
+    },
+    {
+      "epoch": 1.7708333333333335,
+      "grad_norm": 0.651406466960907,
+      "learning_rate": 9.319371727748692e-05,
+      "loss": 0.6108,
+      "step": 255
+    },
+    {
+      "epoch": 1.8055555555555556,
+      "grad_norm": 0.6858854293823242,
+      "learning_rate": 9.05759162303665e-05,
+      "loss": 0.4929,
+      "step": 260
+    },
+    {
+      "epoch": 1.8402777777777777,
+      "grad_norm": 0.6023811101913452,
+      "learning_rate": 8.795811518324608e-05,
+      "loss": 0.4669,
+      "step": 265
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.615983784198761,
+      "learning_rate": 8.534031413612566e-05,
+      "loss": 0.59,
+      "step": 270
+    },
+    {
+      "epoch": 1.9097222222222223,
+      "grad_norm": 0.7829121351242065,
+      "learning_rate": 8.272251308900524e-05,
+      "loss": 0.5846,
+      "step": 275
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 0.6411824226379395,
+      "learning_rate": 8.010471204188482e-05,
+      "loss": 0.413,
+      "step": 280
+    },
+    {
+      "epoch": 1.9791666666666665,
+      "grad_norm": 0.6091701984405518,
+      "learning_rate": 7.74869109947644e-05,
+      "loss": 0.4117,
+      "step": 285
+    },
+    {
+      "epoch": 2.013888888888889,
+      "grad_norm": 0.5939719080924988,
+      "learning_rate": 7.486910994764398e-05,
+      "loss": 0.3464,
+      "step": 290
+    },
+    {
+      "epoch": 2.048611111111111,
+      "grad_norm": 0.8333393335342407,
+      "learning_rate": 7.225130890052356e-05,
+      "loss": 0.2968,
+      "step": 295
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.5424718260765076,
+      "learning_rate": 6.963350785340315e-05,
+      "loss": 0.2427,
+      "step": 300
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "eval_loss": 0.5089412927627563,
+      "eval_runtime": 19.8357,
+      "eval_samples_per_second": 9.629,
+      "eval_steps_per_second": 1.613,
+      "step": 300
+    },
+    {
+      "epoch": 2.1180555555555554,
+      "grad_norm": 0.6733362078666687,
+      "learning_rate": 6.701570680628273e-05,
+      "loss": 0.2759,
+      "step": 305
+    },
+    {
+      "epoch": 2.1527777777777777,
+      "grad_norm": 0.63869708776474,
+      "learning_rate": 6.439790575916231e-05,
+      "loss": 0.2387,
+      "step": 310
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 0.5781670808792114,
+      "learning_rate": 6.178010471204189e-05,
+      "loss": 0.2465,
+      "step": 315
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.6625104546546936,
+      "learning_rate": 5.916230366492147e-05,
+      "loss": 0.2452,
+      "step": 320
+    },
+    {
+      "epoch": 2.2569444444444446,
+      "grad_norm": 0.6529480218887329,
+      "learning_rate": 5.654450261780106e-05,
+      "loss": 0.1973,
+      "step": 325
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 0.5636107325553894,
+      "learning_rate": 5.3926701570680624e-05,
+      "loss": 0.2354,
+      "step": 330
+    },
+    {
+      "epoch": 2.326388888888889,
+      "grad_norm": 0.4926435649394989,
+      "learning_rate": 5.130890052356021e-05,
+      "loss": 0.1707,
+      "step": 335
+    },
+    {
+      "epoch": 2.361111111111111,
+      "grad_norm": 0.6436705589294434,
+      "learning_rate": 4.869109947643979e-05,
+      "loss": 0.245,
+      "step": 340
+    },
+    {
+      "epoch": 2.3958333333333335,
+      "grad_norm": 0.6189023852348328,
+      "learning_rate": 4.6073298429319374e-05,
+      "loss": 0.2417,
+      "step": 345
+    },
+    {
+      "epoch": 2.4305555555555554,
+      "grad_norm": 0.6670970320701599,
+      "learning_rate": 4.3455497382198955e-05,
+      "loss": 0.2047,
+      "step": 350
+    },
+    {
+      "epoch": 2.4652777777777777,
+      "grad_norm": 0.47659561038017273,
+      "learning_rate": 4.0837696335078535e-05,
+      "loss": 0.1757,
+      "step": 355
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.4434764087200165,
+      "learning_rate": 3.8219895287958116e-05,
+      "loss": 0.1829,
+      "step": 360
+    },
+    {
+      "epoch": 2.5347222222222223,
+      "grad_norm": 0.5809481143951416,
+      "learning_rate": 3.56020942408377e-05,
+      "loss": 0.1696,
+      "step": 365
+    },
+    {
+      "epoch": 2.5694444444444446,
+      "grad_norm": 0.6467562317848206,
+      "learning_rate": 3.298429319371728e-05,
+      "loss": 0.1939,
+      "step": 370
+    },
+    {
+      "epoch": 2.6041666666666665,
+      "grad_norm": 0.8204236030578613,
+      "learning_rate": 3.036649214659686e-05,
+      "loss": 0.2066,
+      "step": 375
+    },
+    {
+      "epoch": 2.638888888888889,
+      "grad_norm": 0.6346448659896851,
+      "learning_rate": 2.7748691099476443e-05,
+      "loss": 0.2022,
+      "step": 380
+    },
+    {
+      "epoch": 2.673611111111111,
+      "grad_norm": 0.5839046835899353,
+      "learning_rate": 2.513089005235602e-05,
+      "loss": 0.2746,
+      "step": 385
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 0.7604065537452698,
+      "learning_rate": 2.25130890052356e-05,
+      "loss": 0.206,
+      "step": 390
+    },
+    {
+      "epoch": 2.7430555555555554,
+      "grad_norm": 0.5631184577941895,
+      "learning_rate": 1.9895287958115183e-05,
+      "loss": 0.188,
+      "step": 395
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.5149999260902405,
+      "learning_rate": 1.7277486910994763e-05,
+      "loss": 0.1844,
+      "step": 400
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "eval_loss": 0.34772011637687683,
+      "eval_runtime": 19.7739,
+      "eval_samples_per_second": 9.659,
+      "eval_steps_per_second": 1.618,
+      "step": 400
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 432,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.852700659705446e+16,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00365a4cc96eaeff8b9bf3b6f24a4c5bec58ca652f39e144d932a15f1785688b
+size 5777

checkpoint-432/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04909fe22ad3d1de859842b60dc8906843c9f9a07ebf345e5803f06e53df232
+size 319876032

checkpoint-432/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66c7b4aeb4fa1291d79b80364c163e9b8bb305cf24c9ce9bc81f1804bfb6f71
+size 640016419

checkpoint-432/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d00c9363841e76147f17942985b6f7eb9b9edca1c76071bda75180321d152c7
+size 14645

checkpoint-432/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d840452b716219325ea816b9ec4fc643053c1aedf63d49697008401402ac2189
+size 1465

checkpoint-432/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

checkpoint-432/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00365a4cc96eaeff8b9bf3b6f24a4c5bec58ca652f39e144d932a15f1785688b
+size 5777

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058