Upload folder using huggingface_hub

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-76/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.3
+---
+
+# 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 0.10.0

checkpoint-76/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-76/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb9060a90f9d59c89f89ef7788ec114ab0161074731cf8bf273a83718431afd5
+size 335604696

checkpoint-76/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb30f4496893edaf1811b1f60ef50944169b674417f744383f0e0a0311292892
+size 671364090

checkpoint-76/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48da1126c653afed0e044f186d0b49f1e65c77952d648ee33d6c6c4855796131
+size 14512

checkpoint-76/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9578ee48d006eead2fecbbe47daf1daedbf65e31ed3b6e12601b72af605797ab
+size 14512

checkpoint-76/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:869be1b688bd945109320a2a0a85a6a4361d496077d7dfbf1f735bc3bd3fb012
+size 1064

checkpoint-76/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
+  }
+}

checkpoint-76/tokenizer.model

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

checkpoint-76/trainer_state.json

@@ -0,0 +1,593 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9934640522875817,
+  "eval_steps": 19,
+  "global_step": 76,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.5949503183364868,
+      "learning_rate": 2e-05,
+      "loss": 0.6013,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 0.6381258368492126,
+      "eval_runtime": 227.2126,
+      "eval_samples_per_second": 0.99,
+      "eval_steps_per_second": 0.251,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.64601069688797,
+      "learning_rate": 4e-05,
+      "loss": 0.576,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.6663902997970581,
+      "learning_rate": 6e-05,
+      "loss": 0.6185,
+      "step": 3
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5505500435829163,
+      "learning_rate": 8e-05,
+      "loss": 0.6262,
+      "step": 4
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.48474058508872986,
+      "learning_rate": 0.0001,
+      "loss": 0.4706,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.38366734981536865,
+      "learning_rate": 0.00012,
+      "loss": 0.4193,
+      "step": 6
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.4141893982887268,
+      "learning_rate": 0.00014,
+      "loss": 0.4098,
+      "step": 7
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.34236717224121094,
+      "learning_rate": 0.00016,
+      "loss": 0.3945,
+      "step": 8
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.39320266246795654,
+      "learning_rate": 0.00018,
+      "loss": 0.275,
+      "step": 9
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.2930893898010254,
+      "learning_rate": 0.0002,
+      "loss": 0.2816,
+      "step": 10
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3190990388393402,
+      "learning_rate": 0.00019997552766852432,
+      "loss": 0.3329,
+      "step": 11
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.2727949917316437,
+      "learning_rate": 0.00019990212265199738,
+      "loss": 0.2907,
+      "step": 12
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.26549383997917175,
+      "learning_rate": 0.00019977982087825713,
+      "loss": 0.2683,
+      "step": 13
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.25718459486961365,
+      "learning_rate": 0.00019960868220749448,
+      "loss": 0.3263,
+      "step": 14
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.21319492161273956,
+      "learning_rate": 0.00019938879040295508,
+      "loss": 0.2356,
+      "step": 15
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.21261896193027496,
+      "learning_rate": 0.00019912025308994148,
+      "loss": 0.2944,
+      "step": 16
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.17002587020397186,
+      "learning_rate": 0.0001988032017031364,
+      "loss": 0.2497,
+      "step": 17
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2019287794828415,
+      "learning_rate": 0.00019843779142227256,
+      "loss": 0.2193,
+      "step": 18
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.17646998167037964,
+      "learning_rate": 0.0001980242010961803,
+      "loss": 0.3043,
+      "step": 19
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.23305918276309967,
+      "eval_runtime": 228.0462,
+      "eval_samples_per_second": 0.987,
+      "eval_steps_per_second": 0.25,
+      "step": 19
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.19342155754566193,
+      "learning_rate": 0.0001975626331552507,
+      "loss": 0.2639,
+      "step": 20
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2633172273635864,
+      "learning_rate": 0.00019705331351235674,
+      "loss": 0.2531,
+      "step": 21
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.20328564941883087,
+      "learning_rate": 0.00019649649145228102,
+      "loss": 0.2239,
+      "step": 22
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.21121543645858765,
+      "learning_rate": 0.00019589243950970402,
+      "loss": 0.2192,
+      "step": 23
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.20558255910873413,
+      "learning_rate": 0.00019524145333581317,
+      "loss": 0.2398,
+      "step": 24
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1567656546831131,
+      "learning_rate": 0.00019454385155359702,
+      "loss": 0.2308,
+      "step": 25
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1913561373949051,
+      "learning_rate": 0.00019379997560189675,
+      "loss": 0.2772,
+      "step": 26
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.17273519933223724,
+      "learning_rate": 0.00019301018956828964,
+      "loss": 0.2506,
+      "step": 27
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.17341050505638123,
+      "learning_rate": 0.00019217488001088784,
+      "loss": 0.3025,
+      "step": 28
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.16498418152332306,
+      "learning_rate": 0.00019129445576913888,
+      "loss": 0.2379,
+      "step": 29
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.18727342784404755,
+      "learning_rate": 0.0001903693477637204,
+      "loss": 0.1984,
+      "step": 30
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.16094434261322021,
+      "learning_rate": 0.00018940000878562758,
+      "loss": 0.274,
+      "step": 31
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.19264625012874603,
+      "learning_rate": 0.0001883869132745561,
+      "loss": 0.166,
+      "step": 32
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.20498374104499817,
+      "learning_rate": 0.00018733055708668926,
+      "loss": 0.2288,
+      "step": 33
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.2155662328004837,
+      "learning_rate": 0.00018623145725200278,
+      "loss": 0.2285,
+      "step": 34
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.15915091335773468,
+      "learning_rate": 0.00018509015172120621,
+      "loss": 0.1889,
+      "step": 35
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.307817280292511,
+      "learning_rate": 0.00018390719910244487,
+      "loss": 0.2761,
+      "step": 36
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.16877825558185577,
+      "learning_rate": 0.00018268317838789088,
+      "loss": 0.1846,
+      "step": 37
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.1811710000038147,
+      "learning_rate": 0.00018141868867035745,
+      "loss": 0.2089,
+      "step": 38
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.21359780430793762,
+      "eval_runtime": 230.1518,
+      "eval_samples_per_second": 0.978,
+      "eval_steps_per_second": 0.248,
+      "step": 38
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.1842685490846634,
+      "learning_rate": 0.00018011434885007482,
+      "loss": 0.2266,
+      "step": 39
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.14146481454372406,
+      "learning_rate": 0.00017877079733177184,
+      "loss": 0.2139,
+      "step": 40
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.1733115017414093,
+      "learning_rate": 0.00017738869171221068,
+      "loss": 0.1732,
+      "step": 41
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.15819582343101501,
+      "learning_rate": 0.0001759687084583285,
+      "loss": 0.2481,
+      "step": 42
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.1295730471611023,
+      "learning_rate": 0.00017451154257614287,
+      "loss": 0.17,
+      "step": 43
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.146436408162117,
+      "learning_rate": 0.00017301790727058345,
+      "loss": 0.175,
+      "step": 44
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.16391891241073608,
+      "learning_rate": 0.00017148853359641626,
+      "loss": 0.2264,
+      "step": 45
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.1425042748451233,
+      "learning_rate": 0.00016992417010043142,
+      "loss": 0.2043,
+      "step": 46
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.13763852417469025,
+      "learning_rate": 0.00016832558245506935,
+      "loss": 0.2073,
+      "step": 47
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.15860064327716827,
+      "learning_rate": 0.0001666935530836651,
+      "loss": 0.252,
+      "step": 48
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.135626882314682,
+      "learning_rate": 0.0001650288807774937,
+      "loss": 0.2388,
+      "step": 49
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.168660506606102,
+      "learning_rate": 0.0001633323803048047,
+      "loss": 0.2523,
+      "step": 50
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.16346889734268188,
+      "learning_rate": 0.00016160488201203644,
+      "loss": 0.2764,
+      "step": 51
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.1559883952140808,
+      "learning_rate": 0.00015984723141740576,
+      "loss": 0.2011,
+      "step": 52
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.16393092274665833,
+      "learning_rate": 0.0001580602887970721,
+      "loss": 0.2131,
+      "step": 53
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.16602680087089539,
+      "learning_rate": 0.0001562449287640781,
+      "loss": 0.2719,
+      "step": 54
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.14725206792354584,
+      "learning_rate": 0.00015440203984027324,
+      "loss": 0.1635,
+      "step": 55
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.16429893672466278,
+      "learning_rate": 0.00015253252402142988,
+      "loss": 0.2428,
+      "step": 56
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.1661713421344757,
+      "learning_rate": 0.0001506372963357644,
+      "loss": 0.1932,
+      "step": 57
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.20187948644161224,
+      "eval_runtime": 229.6445,
+      "eval_samples_per_second": 0.98,
+      "eval_steps_per_second": 0.248,
+      "step": 57
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.15299098193645477,
+      "learning_rate": 0.00014871728439607966,
+      "loss": 0.2265,
+      "step": 58
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.18591280281543732,
+      "learning_rate": 0.00014677342794574817,
+      "loss": 0.1976,
+      "step": 59
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.16052399575710297,
+      "learning_rate": 0.00014480667839875786,
+      "loss": 0.1962,
+      "step": 60
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.14768967032432556,
+      "learning_rate": 0.00014281799837404552,
+      "loss": 0.2543,
+      "step": 61
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.17109468579292297,
+      "learning_rate": 0.0001408083612243465,
+      "loss": 0.1847,
+      "step": 62
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.14455659687519073,
+      "learning_rate": 0.00013877875055979023,
+      "loss": 0.2847,
+      "step": 63
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.15863843262195587,
+      "learning_rate": 0.00013673015976647568,
+      "loss": 0.2151,
+      "step": 64
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.12969669699668884,
+      "learning_rate": 0.00013466359152026195,
+      "loss": 0.1925,
+      "step": 65
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.13628815114498138,
+      "learning_rate": 0.00013258005729601177,
+      "loss": 0.255,
+      "step": 66
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.12767894566059113,
+      "learning_rate": 0.00013048057687252865,
+      "loss": 0.2161,
+      "step": 67
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.17236588895320892,
+      "learning_rate": 0.0001283661778334297,
+      "loss": 0.1951,
+      "step": 68
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.1588594615459442,
+      "learning_rate": 0.0001262378950641979,
+      "loss": 0.2506,
+      "step": 69
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.13196192681789398,
+      "learning_rate": 0.00012409677024566144,
+      "loss": 0.1636,
+      "step": 70
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.127383291721344,
+      "learning_rate": 0.00012194385134414608,
+      "loss": 0.2257,
+      "step": 71
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1441836953163147,
+      "learning_rate": 0.00011978019209855174,
+      "loss": 0.2278,
+      "step": 72
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.15123869478702545,
+      "learning_rate": 0.00011760685150460362,
+      "loss": 0.2141,
+      "step": 73
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.1521189659833908,
+      "learning_rate": 0.00011542489329653024,
+      "loss": 0.1782,
+      "step": 74
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.20674781501293182,
+      "learning_rate": 0.00011323538542642227,
+      "loss": 0.1973,
+      "step": 75
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.1552877575159073,
+      "learning_rate": 0.000111039399541527,
+      "loss": 0.2315,
+      "step": 76
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 0.19675016403198242,
+      "eval_runtime": 229.2135,
+      "eval_samples_per_second": 0.982,
+      "eval_steps_per_second": 0.249,
+      "step": 76
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 152,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 76,
+  "total_flos": 1.0754940954948403e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-76/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b2dcab169e2e00ba6ec3514abd0d723f2af79cba950a2f09041beca2670615
+size 5816

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32768
+}

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