Upload 8 files

README.md

@@ -1,3 +1,202 @@
 ---
-license: apache-2.0
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 ---
+
+# 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 0.7.1

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20
+  ],
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d960598619162338285f6d98665643cd3e5ebd01c40b8076e365f1b597eec39
+size 8956728

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": "<unk>",
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 128,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,721 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.26504108136761195,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 11.295464515686035,
+      "learning_rate": 9e-06,
+      "loss": 11.8817,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 19.111797332763672,
+      "learning_rate": 9e-06,
+      "loss": 11.3974,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 9.346492767333984,
+      "learning_rate": 9e-06,
+      "loss": 10.7775,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 14.614985466003418,
+      "learning_rate": 9e-06,
+      "loss": 11.4679,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.3655669689178467,
+      "learning_rate": 9e-06,
+      "loss": 10.9678,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.735344409942627,
+      "learning_rate": 9e-06,
+      "loss": 11.2729,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.9105610847473145,
+      "learning_rate": 9e-06,
+      "loss": 10.2641,
+      "step": 70
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.147580146789551,
+      "learning_rate": 9e-06,
+      "loss": 11.013,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.199955701828003,
+      "learning_rate": 9e-06,
+      "loss": 10.386,
+      "step": 90
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.2018721103668213,
+      "learning_rate": 9e-06,
+      "loss": 10.5926,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.837686061859131,
+      "learning_rate": 9e-06,
+      "loss": 10.262,
+      "step": 110
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 16.972187042236328,
+      "learning_rate": 9e-06,
+      "loss": 10.9497,
+      "step": 120
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.3430895805358887,
+      "learning_rate": 9e-06,
+      "loss": 10.873,
+      "step": 130
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.7084295749664307,
+      "learning_rate": 9e-06,
+      "loss": 11.4798,
+      "step": 140
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 9.110677719116211,
+      "learning_rate": 9e-06,
+      "loss": 11.5311,
+      "step": 150
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.313033103942871,
+      "learning_rate": 9e-06,
+      "loss": 10.7384,
+      "step": 160
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.9622620344161987,
+      "learning_rate": 9e-06,
+      "loss": 10.6241,
+      "step": 170
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 5.918550968170166,
+      "learning_rate": 9e-06,
+      "loss": 10.3353,
+      "step": 180
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 8.934325218200684,
+      "learning_rate": 9e-06,
+      "loss": 10.6227,
+      "step": 190
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.5179646015167236,
+      "learning_rate": 9e-06,
+      "loss": 11.893,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 7.267765522003174,
+      "learning_rate": 9e-06,
+      "loss": 10.7318,
+      "step": 210
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.953799247741699,
+      "learning_rate": 9e-06,
+      "loss": 10.3503,
+      "step": 220
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 8.167949676513672,
+      "learning_rate": 9e-06,
+      "loss": 11.0659,
+      "step": 230
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.700347423553467,
+      "learning_rate": 9e-06,
+      "loss": 10.3495,
+      "step": 240
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 3.486212730407715,
+      "learning_rate": 9e-06,
+      "loss": 10.0343,
+      "step": 250
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.664926052093506,
+      "learning_rate": 9e-06,
+      "loss": 10.977,
+      "step": 260
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.2788758277893066,
+      "learning_rate": 9e-06,
+      "loss": 10.7265,
+      "step": 270
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.547367811203003,
+      "learning_rate": 9e-06,
+      "loss": 10.5965,
+      "step": 280
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.828494548797607,
+      "learning_rate": 9e-06,
+      "loss": 10.5825,
+      "step": 290
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.869746446609497,
+      "learning_rate": 9e-06,
+      "loss": 10.6817,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 6.566542625427246,
+      "learning_rate": 9e-06,
+      "loss": 11.4166,
+      "step": 310
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.2000067234039307,
+      "learning_rate": 9e-06,
+      "loss": 10.5373,
+      "step": 320
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 14.10906982421875,
+      "learning_rate": 9e-06,
+      "loss": 10.1794,
+      "step": 330
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 6.793337345123291,
+      "learning_rate": 9e-06,
+      "loss": 11.0996,
+      "step": 340
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.9148030281066895,
+      "learning_rate": 9e-06,
+      "loss": 10.0792,
+      "step": 350
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 8.041594505310059,
+      "learning_rate": 9e-06,
+      "loss": 10.761,
+      "step": 360
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.987390041351318,
+      "learning_rate": 9e-06,
+      "loss": 10.8053,
+      "step": 370
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.1856467723846436,
+      "learning_rate": 9e-06,
+      "loss": 10.7451,
+      "step": 380
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.973601818084717,
+      "learning_rate": 9e-06,
+      "loss": 10.9992,
+      "step": 390
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 4.062169551849365,
+      "learning_rate": 9e-06,
+      "loss": 10.761,
+      "step": 400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 3.9612374305725098,
+      "learning_rate": 9e-06,
+      "loss": 10.311,
+      "step": 410
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 7.710612773895264,
+      "learning_rate": 9e-06,
+      "loss": 10.5532,
+      "step": 420
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 3.7663562297821045,
+      "learning_rate": 9e-06,
+      "loss": 10.7776,
+      "step": 430
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.825556755065918,
+      "learning_rate": 9e-06,
+      "loss": 9.9882,
+      "step": 440
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.759881019592285,
+      "learning_rate": 9e-06,
+      "loss": 9.8141,
+      "step": 450
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.936343193054199,
+      "learning_rate": 9e-06,
+      "loss": 11.3302,
+      "step": 460
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.308138370513916,
+      "learning_rate": 9e-06,
+      "loss": 10.2812,
+      "step": 470
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.4589219093322754,
+      "learning_rate": 9e-06,
+      "loss": 10.6503,
+      "step": 480
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.5036466121673584,
+      "learning_rate": 9e-06,
+      "loss": 10.599,
+      "step": 490
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.5134172439575195,
+      "learning_rate": 9e-06,
+      "loss": 10.6681,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.047601699829102,
+      "learning_rate": 9e-06,
+      "loss": 10.5657,
+      "step": 510
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.227710247039795,
+      "learning_rate": 9e-06,
+      "loss": 10.1521,
+      "step": 520
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.6789393424987793,
+      "learning_rate": 9e-06,
+      "loss": 11.3919,
+      "step": 530
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.670515537261963,
+      "learning_rate": 9e-06,
+      "loss": 11.0344,
+      "step": 540
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 2.813408851623535,
+      "learning_rate": 9e-06,
+      "loss": 10.0968,
+      "step": 550
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.232144832611084,
+      "learning_rate": 9e-06,
+      "loss": 10.745,
+      "step": 560
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 9.7771635055542,
+      "learning_rate": 9e-06,
+      "loss": 11.311,
+      "step": 570
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 8.114048957824707,
+      "learning_rate": 9e-06,
+      "loss": 10.2083,
+      "step": 580
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.147491455078125,
+      "learning_rate": 9e-06,
+      "loss": 10.2984,
+      "step": 590
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 8.014413833618164,
+      "learning_rate": 9e-06,
+      "loss": 10.1533,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 11.841456413269043,
+      "learning_rate": 9e-06,
+      "loss": 10.4205,
+      "step": 610
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.5549516677856445,
+      "learning_rate": 9e-06,
+      "loss": 10.5929,
+      "step": 620
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 3.713442325592041,
+      "learning_rate": 9e-06,
+      "loss": 9.9718,
+      "step": 630
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 6.863169193267822,
+      "learning_rate": 9e-06,
+      "loss": 10.6209,
+      "step": 640
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.174696445465088,
+      "learning_rate": 9e-06,
+      "loss": 10.6878,
+      "step": 650
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.71444034576416,
+      "learning_rate": 9e-06,
+      "loss": 10.4567,
+      "step": 660
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.523930072784424,
+      "learning_rate": 9e-06,
+      "loss": 10.0833,
+      "step": 670
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 6.862795352935791,
+      "learning_rate": 9e-06,
+      "loss": 10.2016,
+      "step": 680
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.1852409839630127,
+      "learning_rate": 9e-06,
+      "loss": 10.5172,
+      "step": 690
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 6.443986415863037,
+      "learning_rate": 9e-06,
+      "loss": 10.7537,
+      "step": 700
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 11.400566101074219,
+      "learning_rate": 9e-06,
+      "loss": 11.0483,
+      "step": 710
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 7.702329635620117,
+      "learning_rate": 9e-06,
+      "loss": 10.727,
+      "step": 720
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 4.16178035736084,
+      "learning_rate": 9e-06,
+      "loss": 10.6055,
+      "step": 730
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.605968475341797,
+      "learning_rate": 9e-06,
+      "loss": 10.355,
+      "step": 740
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 14.701130867004395,
+      "learning_rate": 9e-06,
+      "loss": 10.4721,
+      "step": 750
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 7.835628509521484,
+      "learning_rate": 9e-06,
+      "loss": 10.4347,
+      "step": 760
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 7.356694221496582,
+      "learning_rate": 9e-06,
+      "loss": 11.3509,
+      "step": 770
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.329432487487793,
+      "learning_rate": 9e-06,
+      "loss": 10.0169,
+      "step": 780
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 19.973756790161133,
+      "learning_rate": 9e-06,
+      "loss": 10.0255,
+      "step": 790
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 2.803788185119629,
+      "learning_rate": 9e-06,
+      "loss": 10.7273,
+      "step": 800
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 14.293676376342773,
+      "learning_rate": 9e-06,
+      "loss": 9.9237,
+      "step": 810
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 16.294631958007812,
+      "learning_rate": 9e-06,
+      "loss": 10.4007,
+      "step": 820
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.3935439586639404,
+      "learning_rate": 9e-06,
+      "loss": 10.448,
+      "step": 830
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.49714469909668,
+      "learning_rate": 9e-06,
+      "loss": 10.4483,
+      "step": 840
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 10.630420684814453,
+      "learning_rate": 9e-06,
+      "loss": 10.897,
+      "step": 850
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 5.770751476287842,
+      "learning_rate": 9e-06,
+      "loss": 9.9405,
+      "step": 860
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 8.110162734985352,
+      "learning_rate": 9e-06,
+      "loss": 11.0845,
+      "step": 870
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 7.8067426681518555,
+      "learning_rate": 9e-06,
+      "loss": 10.547,
+      "step": 880
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.9901771545410156,
+      "learning_rate": 9e-06,
+      "loss": 10.4107,
+      "step": 890
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 8.162439346313477,
+      "learning_rate": 9e-06,
+      "loss": 11.4275,
+      "step": 900
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.2310473918914795,
+      "learning_rate": 9e-06,
+      "loss": 10.7262,
+      "step": 910
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 18.924705505371094,
+      "learning_rate": 9e-06,
+      "loss": 10.9865,
+      "step": 920
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.149799823760986,
+      "learning_rate": 9e-06,
+      "loss": 10.5479,
+      "step": 930
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 9.203178405761719,
+      "learning_rate": 9e-06,
+      "loss": 10.5654,
+      "step": 940
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 7.544803619384766,
+      "learning_rate": 9e-06,
+      "loss": 9.6395,
+      "step": 950
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.45569372177124,
+      "learning_rate": 9e-06,
+      "loss": 10.9773,
+      "step": 960
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 10.091376304626465,
+      "learning_rate": 9e-06,
+      "loss": 10.9838,
+      "step": 970
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 10.069650650024414,
+      "learning_rate": 9e-06,
+      "loss": 10.5794,
+      "step": 980
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.327217102050781,
+      "learning_rate": 9e-06,
+      "loss": 10.3056,
+      "step": 990
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 20.91196060180664,
+      "learning_rate": 9e-06,
+      "loss": 10.8614,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 3.2776227127296e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34129deabd5d692a6819c9f36f90bf1e7d2cb4415154628c8ae20143cf21ef50
+size 4928