Migrated from latest commit: Upload task output e5439073-3144-4ed0-aa87-6f301d440db4

README.md

@@ -0,0 +1,202 @@
+---
+base_model: diagonalge/Covenant72B
+library_name: peft
+---
+
+# 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 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "diagonalge/Covenant72B",
+  "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": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4892ecf77014d44e0eda3c2af83fc44c8f5da1a6bf4a4bc65b134b63a0b495db
+size 3313655720

loss.txt

@@ -0,0 +1 @@
+856,1.2667760848999023

trainer_state.json

@@ -0,0 +1,1255 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9953379953379953,
+  "eval_steps": 500,
+  "global_step": 856,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011655011655011656,
+      "grad_norm": 5.380261825460372,
+      "learning_rate": 9.237540571428572e-06,
+      "loss": 4.2109,
+      "step": 5
+    },
+    {
+      "epoch": 0.023310023310023312,
+      "grad_norm": 1.4502882732797857,
+      "learning_rate": 2.0784466285714287e-05,
+      "loss": 3.9981,
+      "step": 10
+    },
+    {
+      "epoch": 0.03496503496503497,
+      "grad_norm": 0.9652384253156429,
+      "learning_rate": 3.2331392000000005e-05,
+      "loss": 3.2711,
+      "step": 15
+    },
+    {
+      "epoch": 0.046620046620046623,
+      "grad_norm": 1.1395250787625393,
+      "learning_rate": 4.3878317714285716e-05,
+      "loss": 2.6312,
+      "step": 20
+    },
+    {
+      "epoch": 0.05827505827505827,
+      "grad_norm": 3.4845160401616764,
+      "learning_rate": 5.542524342857144e-05,
+      "loss": 2.1284,
+      "step": 25
+    },
+    {
+      "epoch": 0.06993006993006994,
+      "grad_norm": 1.9051485411146671,
+      "learning_rate": 6.697216914285716e-05,
+      "loss": 1.8294,
+      "step": 30
+    },
+    {
+      "epoch": 0.08158508158508158,
+      "grad_norm": 0.33187533324621077,
+      "learning_rate": 7.851909485714286e-05,
+      "loss": 1.7266,
+      "step": 35
+    },
+    {
+      "epoch": 0.09324009324009325,
+      "grad_norm": 0.44248932276377023,
+      "learning_rate": 8.082695323179129e-05,
+      "loss": 1.7283,
+      "step": 40
+    },
+    {
+      "epoch": 0.1048951048951049,
+      "grad_norm": 1.2160485145535014,
+      "learning_rate": 8.082075099954982e-05,
+      "loss": 1.7117,
+      "step": 45
+    },
+    {
+      "epoch": 0.11655011655011654,
+      "grad_norm": 65.29684577693374,
+      "learning_rate": 8.080977885578941e-05,
+      "loss": 1.8952,
+      "step": 50
+    },
+    {
+      "epoch": 0.1282051282051282,
+      "grad_norm": 1.15546734315769,
+      "learning_rate": 8.079403852760764e-05,
+      "loss": 3.1909,
+      "step": 55
+    },
+    {
+      "epoch": 0.13986013986013987,
+      "grad_norm": 2.634452844296507,
+      "learning_rate": 8.077353249265015e-05,
+      "loss": 1.6638,
+      "step": 60
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 0.32202059804233973,
+      "learning_rate": 8.07482639787204e-05,
+      "loss": 1.6088,
+      "step": 65
+    },
+    {
+      "epoch": 0.16317016317016317,
+      "grad_norm": 0.3642353360782208,
+      "learning_rate": 8.071823696327185e-05,
+      "loss": 1.5268,
+      "step": 70
+    },
+    {
+      "epoch": 0.17482517482517482,
+      "grad_norm": 0.34692958418989034,
+      "learning_rate": 8.068345617278169e-05,
+      "loss": 1.5875,
+      "step": 75
+    },
+    {
+      "epoch": 0.1864801864801865,
+      "grad_norm": 38.12513649812565,
+      "learning_rate": 8.06439270820069e-05,
+      "loss": 1.7234,
+      "step": 80
+    },
+    {
+      "epoch": 0.19813519813519814,
+      "grad_norm": 0.3217004898392202,
+      "learning_rate": 8.059965591312254e-05,
+      "loss": 1.4259,
+      "step": 85
+    },
+    {
+      "epoch": 0.2097902097902098,
+      "grad_norm": 0.24719946255426536,
+      "learning_rate": 8.055064963474229e-05,
+      "loss": 1.4095,
+      "step": 90
+    },
+    {
+      "epoch": 0.22144522144522144,
+      "grad_norm": 0.5042383844039631,
+      "learning_rate": 8.049691596082148e-05,
+      "loss": 1.6829,
+      "step": 95
+    },
+    {
+      "epoch": 0.2331002331002331,
+      "grad_norm": 0.2641927692422699,
+      "learning_rate": 8.043846334944299e-05,
+      "loss": 1.6542,
+      "step": 100
+    },
+    {
+      "epoch": 0.24475524475524477,
+      "grad_norm": 0.2525842272998614,
+      "learning_rate": 8.03753010014858e-05,
+      "loss": 1.5055,
+      "step": 105
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 0.2848401355775407,
+      "learning_rate": 8.030743885917666e-05,
+      "loss": 1.5441,
+      "step": 110
+    },
+    {
+      "epoch": 0.2680652680652681,
+      "grad_norm": 0.2578389420241452,
+      "learning_rate": 8.023488760452522e-05,
+      "loss": 1.5164,
+      "step": 115
+    },
+    {
+      "epoch": 0.27972027972027974,
+      "grad_norm": 0.384485780217046,
+      "learning_rate": 8.01576586576425e-05,
+      "loss": 1.4309,
+      "step": 120
+    },
+    {
+      "epoch": 0.2913752913752914,
+      "grad_norm": 0.3005538892717842,
+      "learning_rate": 8.007576417494336e-05,
+      "loss": 1.4464,
+      "step": 125
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 0.3038129052309793,
+      "learning_rate": 7.998921704723294e-05,
+      "loss": 1.308,
+      "step": 130
+    },
+    {
+      "epoch": 0.3146853146853147,
+      "grad_norm": 0.27857195778115285,
+      "learning_rate": 7.989803089767754e-05,
+      "loss": 1.3887,
+      "step": 135
+    },
+    {
+      "epoch": 0.32634032634032634,
+      "grad_norm": 0.2852295677864667,
+      "learning_rate": 7.980222007966029e-05,
+      "loss": 1.4992,
+      "step": 140
+    },
+    {
+      "epoch": 0.337995337995338,
+      "grad_norm": 0.2744064066208899,
+      "learning_rate": 7.970179967452175e-05,
+      "loss": 1.4618,
+      "step": 145
+    },
+    {
+      "epoch": 0.34965034965034963,
+      "grad_norm": 0.24802775085025972,
+      "learning_rate": 7.959678548918605e-05,
+      "loss": 1.3894,
+      "step": 150
+    },
+    {
+      "epoch": 0.3613053613053613,
+      "grad_norm": 0.25341971271489,
+      "learning_rate": 7.948719405367275e-05,
+      "loss": 1.402,
+      "step": 155
+    },
+    {
+      "epoch": 0.372960372960373,
+      "grad_norm": 0.24564392308719407,
+      "learning_rate": 7.937304261849485e-05,
+      "loss": 1.3474,
+      "step": 160
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.28202938683817624,
+      "learning_rate": 7.925434915194349e-05,
+      "loss": 1.4338,
+      "step": 165
+    },
+    {
+      "epoch": 0.3962703962703963,
+      "grad_norm": 0.310609971889877,
+      "learning_rate": 7.913113233725954e-05,
+      "loss": 1.4238,
+      "step": 170
+    },
+    {
+      "epoch": 0.40792540792540793,
+      "grad_norm": 0.27009263717875037,
+      "learning_rate": 7.90034115696928e-05,
+      "loss": 1.3496,
+      "step": 175
+    },
+    {
+      "epoch": 0.4195804195804196,
+      "grad_norm": 0.2710853328115736,
+      "learning_rate": 7.887120695344898e-05,
+      "loss": 1.4584,
+      "step": 180
+    },
+    {
+      "epoch": 0.43123543123543123,
+      "grad_norm": 0.25152522039701575,
+      "learning_rate": 7.873453929852514e-05,
+      "loss": 1.3774,
+      "step": 185
+    },
+    {
+      "epoch": 0.4428904428904429,
+      "grad_norm": 0.2835745821601218,
+      "learning_rate": 7.85934301174341e-05,
+      "loss": 1.4099,
+      "step": 190
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 1.0519805093542818,
+      "learning_rate": 7.844790162181818e-05,
+      "loss": 1.437,
+      "step": 195
+    },
+    {
+      "epoch": 0.4662004662004662,
+      "grad_norm": 0.8265825248892074,
+      "learning_rate": 7.829797671895288e-05,
+      "loss": 1.4522,
+      "step": 200
+    },
+    {
+      "epoch": 0.47785547785547783,
+      "grad_norm": 0.7862211345050619,
+      "learning_rate": 7.814367900814116e-05,
+      "loss": 1.4808,
+      "step": 205
+    },
+    {
+      "epoch": 0.48951048951048953,
+      "grad_norm": 2.729527753162334,
+      "learning_rate": 7.79850327769987e-05,
+      "loss": 1.3966,
+      "step": 210
+    },
+    {
+      "epoch": 0.5011655011655012,
+      "grad_norm": 0.5270917240760644,
+      "learning_rate": 7.78220629976309e-05,
+      "loss": 1.4515,
+      "step": 215
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.2370434474197243,
+      "learning_rate": 7.765479532270198e-05,
+      "loss": 1.354,
+      "step": 220
+    },
+    {
+      "epoch": 0.5244755244755245,
+      "grad_norm": 0.302576280537011,
+      "learning_rate": 7.748325608139717e-05,
+      "loss": 1.4122,
+      "step": 225
+    },
+    {
+      "epoch": 0.5361305361305362,
+      "grad_norm": 0.26006318976574305,
+      "learning_rate": 7.730747227527824e-05,
+      "loss": 1.4065,
+      "step": 230
+    },
+    {
+      "epoch": 0.5477855477855478,
+      "grad_norm": 0.25033459622615245,
+      "learning_rate": 7.712747157403322e-05,
+      "loss": 1.3791,
+      "step": 235
+    },
+    {
+      "epoch": 0.5594405594405595,
+      "grad_norm": 0.22820286614092533,
+      "learning_rate": 7.694328231112112e-05,
+      "loss": 1.339,
+      "step": 240
+    },
+    {
+      "epoch": 0.5710955710955711,
+      "grad_norm": 0.2808234577155991,
+      "learning_rate": 7.675493347931184e-05,
+      "loss": 1.391,
+      "step": 245
+    },
+    {
+      "epoch": 0.5827505827505828,
+      "grad_norm": 0.248396781368916,
+      "learning_rate": 7.656245472612264e-05,
+      "loss": 1.3796,
+      "step": 250
+    },
+    {
+      "epoch": 0.5944055944055944,
+      "grad_norm": 0.24239687758201922,
+      "learning_rate": 7.636587634915133e-05,
+      "loss": 1.2704,
+      "step": 255
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.2889579270489845,
+      "learning_rate": 7.616522929130724e-05,
+      "loss": 1.3738,
+      "step": 260
+    },
+    {
+      "epoch": 0.6177156177156177,
+      "grad_norm": 0.37773683176723527,
+      "learning_rate": 7.596054513594051e-05,
+      "loss": 1.2168,
+      "step": 265
+    },
+    {
+      "epoch": 0.6293706293706294,
+      "grad_norm": 0.2507614413849896,
+      "learning_rate": 7.575185610187072e-05,
+      "loss": 1.2799,
+      "step": 270
+    },
+    {
+      "epoch": 0.6410256410256411,
+      "grad_norm": 0.2519925650582622,
+      "learning_rate": 7.553919503831533e-05,
+      "loss": 1.3737,
+      "step": 275
+    },
+    {
+      "epoch": 0.6526806526806527,
+      "grad_norm": 0.25693488058335956,
+      "learning_rate": 7.532259541971902e-05,
+      "loss": 1.3132,
+      "step": 280
+    },
+    {
+      "epoch": 0.6643356643356644,
+      "grad_norm": 0.2654099769032578,
+      "learning_rate": 7.510209134048455e-05,
+      "loss": 1.336,
+      "step": 285
+    },
+    {
+      "epoch": 0.675990675990676,
+      "grad_norm": 0.2991450312535211,
+      "learning_rate": 7.4877717509606e-05,
+      "loss": 1.3136,
+      "step": 290
+    },
+    {
+      "epoch": 0.6876456876456877,
+      "grad_norm": 0.7936383565363224,
+      "learning_rate": 7.46495092452054e-05,
+      "loss": 1.3218,
+      "step": 295
+    },
+    {
+      "epoch": 0.6993006993006993,
+      "grad_norm": 0.2833344928086715,
+      "learning_rate": 7.441750246897328e-05,
+      "loss": 1.3775,
+      "step": 300
+    },
+    {
+      "epoch": 0.710955710955711,
+      "grad_norm": 0.23315264052796472,
+      "learning_rate": 7.418173370051446e-05,
+      "loss": 1.3401,
+      "step": 305
+    },
+    {
+      "epoch": 0.7226107226107226,
+      "grad_norm": 0.27055343448065056,
+      "learning_rate": 7.394224005159947e-05,
+      "loss": 1.3282,
+      "step": 310
+    },
+    {
+      "epoch": 0.7342657342657343,
+      "grad_norm": 0.2480849022059861,
+      "learning_rate": 7.369905922032295e-05,
+      "loss": 1.2888,
+      "step": 315
+    },
+    {
+      "epoch": 0.745920745920746,
+      "grad_norm": 0.31945412606809426,
+      "learning_rate": 7.345222948516969e-05,
+      "loss": 1.4228,
+      "step": 320
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 0.2576143196799571,
+      "learning_rate": 7.320178969898926e-05,
+      "loss": 1.3058,
+      "step": 325
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.43520117132833047,
+      "learning_rate": 7.294777928288031e-05,
+      "loss": 1.3131,
+      "step": 330
+    },
+    {
+      "epoch": 0.7808857808857809,
+      "grad_norm": 0.2882495350884511,
+      "learning_rate": 7.26902382199854e-05,
+      "loss": 1.32,
+      "step": 335
+    },
+    {
+      "epoch": 0.7925407925407926,
+      "grad_norm": 0.33796460872196393,
+      "learning_rate": 7.242920704919733e-05,
+      "loss": 1.3031,
+      "step": 340
+    },
+    {
+      "epoch": 0.8041958041958042,
+      "grad_norm": 0.2549144290343736,
+      "learning_rate": 7.216472685877808e-05,
+      "loss": 1.2656,
+      "step": 345
+    },
+    {
+      "epoch": 0.8158508158508159,
+      "grad_norm": 0.6420737440392777,
+      "learning_rate": 7.189683927989109e-05,
+      "loss": 1.3621,
+      "step": 350
+    },
+    {
+      "epoch": 0.8275058275058275,
+      "grad_norm": 0.25149854473667893,
+      "learning_rate": 7.162558648004833e-05,
+      "loss": 1.3055,
+      "step": 355
+    },
+    {
+      "epoch": 0.8391608391608392,
+      "grad_norm": 0.8756690609514122,
+      "learning_rate": 7.13510111564727e-05,
+      "loss": 1.306,
+      "step": 360
+    },
+    {
+      "epoch": 0.8508158508158508,
+      "grad_norm": 0.27473178820064537,
+      "learning_rate": 7.107315652937733e-05,
+      "loss": 1.3125,
+      "step": 365
+    },
+    {
+      "epoch": 0.8624708624708625,
+      "grad_norm": 5.526242806524436,
+      "learning_rate": 7.079206633516216e-05,
+      "loss": 1.2443,
+      "step": 370
+    },
+    {
+      "epoch": 0.8741258741258742,
+      "grad_norm": 0.2859887823856341,
+      "learning_rate": 7.050778481952977e-05,
+      "loss": 1.3051,
+      "step": 375
+    },
+    {
+      "epoch": 0.8857808857808858,
+      "grad_norm": 0.26065360686340344,
+      "learning_rate": 7.022035673052052e-05,
+      "loss": 1.2533,
+      "step": 380
+    },
+    {
+      "epoch": 0.8974358974358975,
+      "grad_norm": 0.28515419529118324,
+      "learning_rate": 6.992982731146909e-05,
+      "loss": 1.292,
+      "step": 385
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.2521847950964824,
+      "learning_rate": 6.963624229388268e-05,
+      "loss": 1.3149,
+      "step": 390
+    },
+    {
+      "epoch": 0.9207459207459208,
+      "grad_norm": 0.24378682997123743,
+      "learning_rate": 6.933964789024263e-05,
+      "loss": 1.299,
+      "step": 395
+    },
+    {
+      "epoch": 0.9324009324009324,
+      "grad_norm": 0.22312967942400147,
+      "learning_rate": 6.904009078673016e-05,
+      "loss": 1.2422,
+      "step": 400
+    },
+    {
+      "epoch": 0.9440559440559441,
+      "grad_norm": 0.22503476475625694,
+      "learning_rate": 6.873761813587769e-05,
+      "loss": 1.2913,
+      "step": 405
+    },
+    {
+      "epoch": 0.9557109557109557,
+      "grad_norm": 0.22697946460375637,
+      "learning_rate": 6.843227754914657e-05,
+      "loss": 1.29,
+      "step": 410
+    },
+    {
+      "epoch": 0.9673659673659674,
+      "grad_norm": 0.3144384632248903,
+      "learning_rate": 6.812411708943284e-05,
+      "loss": 1.2395,
+      "step": 415
+    },
+    {
+      "epoch": 0.9790209790209791,
+      "grad_norm": 0.24364089502734793,
+      "learning_rate": 6.781318526350156e-05,
+      "loss": 1.4002,
+      "step": 420
+    },
+    {
+      "epoch": 0.9906759906759907,
+      "grad_norm": 0.23043000137266378,
+      "learning_rate": 6.749953101435168e-05,
+      "loss": 1.2886,
+      "step": 425
+    },
+    {
+      "epoch": 0.9976689976689976,
+      "eval_loss": 1.346985936164856,
+      "eval_runtime": 41.4179,
+      "eval_samples_per_second": 1.69,
+      "eval_steps_per_second": 0.217,
+      "step": 428
+    },
+    {
+      "epoch": 1.0023310023310024,
+      "grad_norm": 0.6370362893316296,
+      "learning_rate": 6.718320371351193e-05,
+      "loss": 1.2846,
+      "step": 430
+    },
+    {
+      "epoch": 1.013986013986014,
+      "grad_norm": 0.26814660795194867,
+      "learning_rate": 6.686425315326941e-05,
+      "loss": 1.0865,
+      "step": 435
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.23807462749178174,
+      "learning_rate": 6.654272953883189e-05,
+      "loss": 1.1612,
+      "step": 440
+    },
+    {
+      "epoch": 1.0372960372960374,
+      "grad_norm": 0.23960120741081306,
+      "learning_rate": 6.621868348042517e-05,
+      "loss": 1.1393,
+      "step": 445
+    },
+    {
+      "epoch": 1.048951048951049,
+      "grad_norm": 0.2601814951485897,
+      "learning_rate": 6.58921659853266e-05,
+      "loss": 1.2539,
+      "step": 450
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 0.2489367328385621,
+      "learning_rate": 6.55632284498362e-05,
+      "loss": 1.1934,
+      "step": 455
+    },
+    {
+      "epoch": 1.0722610722610724,
+      "grad_norm": 0.26068816228316616,
+      "learning_rate": 6.523192265118652e-05,
+      "loss": 1.252,
+      "step": 460
+    },
+    {
+      "epoch": 1.083916083916084,
+      "grad_norm": 0.2681555770705724,
+      "learning_rate": 6.489830073939237e-05,
+      "loss": 1.2231,
+      "step": 465
+    },
+    {
+      "epoch": 1.0955710955710956,
+      "grad_norm": 0.24692924998707827,
+      "learning_rate": 6.456241522904223e-05,
+      "loss": 1.1952,
+      "step": 470
+    },
+    {
+      "epoch": 1.1072261072261071,
+      "grad_norm": 0.24530619885017255,
+      "learning_rate": 6.422431899103189e-05,
+      "loss": 1.1665,
+      "step": 475
+    },
+    {
+      "epoch": 1.118881118881119,
+      "grad_norm": 0.2677189175766508,
+      "learning_rate": 6.388406524424222e-05,
+      "loss": 1.176,
+      "step": 480
+    },
+    {
+      "epoch": 1.1305361305361306,
+      "grad_norm": 0.2411887554782912,
+      "learning_rate": 6.35417075471622e-05,
+      "loss": 1.1704,
+      "step": 485
+    },
+    {
+      "epoch": 1.1421911421911422,
+      "grad_norm": 0.2541256840409212,
+      "learning_rate": 6.319729978945832e-05,
+      "loss": 1.1782,
+      "step": 490
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 0.24850101976269176,
+      "learning_rate": 6.285089618349196e-05,
+      "loss": 1.1847,
+      "step": 495
+    },
+    {
+      "epoch": 1.1655011655011656,
+      "grad_norm": 0.2672134029476264,
+      "learning_rate": 6.250255125578597e-05,
+      "loss": 1.0407,
+      "step": 500
+    },
+    {
+      "epoch": 1.1655011655011656,
+      "eval_loss": 1.335543155670166,
+      "eval_runtime": 41.117,
+      "eval_samples_per_second": 1.702,
+      "eval_steps_per_second": 0.219,
+      "step": 500
+    },
+    {
+      "epoch": 1.1771561771561772,
+      "grad_norm": 0.24056303633515866,
+      "learning_rate": 6.21523198384418e-05,
+      "loss": 1.223,
+      "step": 505
+    },
+    {
+      "epoch": 1.1888111888111887,
+      "grad_norm": 0.25656987276961235,
+      "learning_rate": 6.18002570605085e-05,
+      "loss": 1.1589,
+      "step": 510
+    },
+    {
+      "epoch": 1.2004662004662006,
+      "grad_norm": 0.25884269499583334,
+      "learning_rate": 6.144641833930498e-05,
+      "loss": 1.1185,
+      "step": 515
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 0.24120488400409848,
+      "learning_rate": 6.109085937169695e-05,
+      "loss": 1.2347,
+      "step": 520
+    },
+    {
+      "epoch": 1.2237762237762237,
+      "grad_norm": 0.24337953823169015,
+      "learning_rate": 6.0733636125329776e-05,
+      "loss": 1.0777,
+      "step": 525
+    },
+    {
+      "epoch": 1.2354312354312353,
+      "grad_norm": 0.2553344373947113,
+      "learning_rate": 6.0374804829818786e-05,
+      "loss": 1.1297,
+      "step": 530
+    },
+    {
+      "epoch": 1.2470862470862472,
+      "grad_norm": 0.26618655203985797,
+      "learning_rate": 6.001442196789827e-05,
+      "loss": 1.1129,
+      "step": 535
+    },
+    {
+      "epoch": 1.2587412587412588,
+      "grad_norm": 0.2631162852747018,
+      "learning_rate": 5.965254426653072e-05,
+      "loss": 1.2239,
+      "step": 540
+    },
+    {
+      "epoch": 1.2703962703962703,
+      "grad_norm": 0.23274413800511448,
+      "learning_rate": 5.928922868797752e-05,
+      "loss": 1.103,
+      "step": 545
+    },
+    {
+      "epoch": 1.282051282051282,
+      "grad_norm": 0.23157161304838858,
+      "learning_rate": 5.892453242083273e-05,
+      "loss": 1.0679,
+      "step": 550
+    },
+    {
+      "epoch": 1.2937062937062938,
+      "grad_norm": 0.28740045332560504,
+      "learning_rate": 5.855851287102113e-05,
+      "loss": 1.1891,
+      "step": 555
+    },
+    {
+      "epoch": 1.3053613053613053,
+      "grad_norm": 0.2970846582151576,
+      "learning_rate": 5.81912276527621e-05,
+      "loss": 1.1354,
+      "step": 560
+    },
+    {
+      "epoch": 1.317016317016317,
+      "grad_norm": 0.2630829061530002,
+      "learning_rate": 5.7822734579500705e-05,
+      "loss": 1.1793,
+      "step": 565
+    },
+    {
+      "epoch": 1.3286713286713288,
+      "grad_norm": 0.24952577498784723,
+      "learning_rate": 5.745309165480747e-05,
+      "loss": 1.0412,
+      "step": 570
+    },
+    {
+      "epoch": 1.3403263403263403,
+      "grad_norm": 0.29261484653650605,
+      "learning_rate": 5.7082357063248116e-05,
+      "loss": 1.1266,
+      "step": 575
+    },
+    {
+      "epoch": 1.351981351981352,
+      "grad_norm": 0.27423549595827834,
+      "learning_rate": 5.671058916122493e-05,
+      "loss": 1.1526,
+      "step": 580
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.26193784576015794,
+      "learning_rate": 5.6337846467790995e-05,
+      "loss": 1.1818,
+      "step": 585
+    },
+    {
+      "epoch": 1.3752913752913754,
+      "grad_norm": 0.2536711363621732,
+      "learning_rate": 5.596418765543887e-05,
+      "loss": 1.1099,
+      "step": 590
+    },
+    {
+      "epoch": 1.386946386946387,
+      "grad_norm": 0.25809295106016567,
+      "learning_rate": 5.55896715408651e-05,
+      "loss": 1.1281,
+      "step": 595
+    },
+    {
+      "epoch": 1.3986013986013985,
+      "grad_norm": 0.2964280224538696,
+      "learning_rate": 5.521435707571199e-05,
+      "loss": 1.1209,
+      "step": 600
+    },
+    {
+      "epoch": 1.4102564102564101,
+      "grad_norm": 0.2535619637821886,
+      "learning_rate": 5.483830333728829e-05,
+      "loss": 1.0736,
+      "step": 605
+    },
+    {
+      "epoch": 1.421911421911422,
+      "grad_norm": 0.2834714269145168,
+      "learning_rate": 5.4461569519269803e-05,
+      "loss": 1.0904,
+      "step": 610
+    },
+    {
+      "epoch": 1.4335664335664335,
+      "grad_norm": 0.26457948671956855,
+      "learning_rate": 5.4084214922382015e-05,
+      "loss": 1.1718,
+      "step": 615
+    },
+    {
+      "epoch": 1.4452214452214451,
+      "grad_norm": 0.30016622504388313,
+      "learning_rate": 5.370629894506561e-05,
+      "loss": 1.1222,
+      "step": 620
+    },
+    {
+      "epoch": 1.456876456876457,
+      "grad_norm": 0.24560811509210745,
+      "learning_rate": 5.332788107412684e-05,
+      "loss": 1.1179,
+      "step": 625
+    },
+    {
+      "epoch": 1.4685314685314685,
+      "grad_norm": 0.27129656920581763,
+      "learning_rate": 5.294902087537369e-05,
+      "loss": 1.1379,
+      "step": 630
+    },
+    {
+      "epoch": 1.4801864801864801,
+      "grad_norm": 0.26155557293622045,
+      "learning_rate": 5.256977798423988e-05,
+      "loss": 1.1354,
+      "step": 635
+    },
+    {
+      "epoch": 1.491841491841492,
+      "grad_norm": 0.2542515790861205,
+      "learning_rate": 5.2190212096397825e-05,
+      "loss": 1.0926,
+      "step": 640
+    },
+    {
+      "epoch": 1.5034965034965035,
+      "grad_norm": 0.2846310062143532,
+      "learning_rate": 5.181038295836196e-05,
+      "loss": 1.206,
+      "step": 645
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 0.2578892076658671,
+      "learning_rate": 5.143035035808435e-05,
+      "loss": 1.1348,
+      "step": 650
+    },
+    {
+      "epoch": 1.526806526806527,
+      "grad_norm": 0.2677065667604314,
+      "learning_rate": 5.1050174115543476e-05,
+      "loss": 1.1376,
+      "step": 655
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.2623622010580359,
+      "learning_rate": 5.066991407332825e-05,
+      "loss": 1.147,
+      "step": 660
+    },
+    {
+      "epoch": 1.5501165501165501,
+      "grad_norm": 0.2924192984321144,
+      "learning_rate": 5.028963008721822e-05,
+      "loss": 1.2343,
+      "step": 665
+    },
+    {
+      "epoch": 1.5617715617715617,
+      "grad_norm": 0.25879469972966473,
+      "learning_rate": 4.990938201676194e-05,
+      "loss": 1.1271,
+      "step": 670
+    },
+    {
+      "epoch": 1.5734265734265733,
+      "grad_norm": 0.2738138873868371,
+      "learning_rate": 4.952922971585451e-05,
+      "loss": 1.0558,
+      "step": 675
+    },
+    {
+      "epoch": 1.5850815850815851,
+      "grad_norm": 0.24373153596626246,
+      "learning_rate": 4.914923302331625e-05,
+      "loss": 1.1583,
+      "step": 680
+    },
+    {
+      "epoch": 1.5967365967365967,
+      "grad_norm": 0.26700970389535894,
+      "learning_rate": 4.87694517534735e-05,
+      "loss": 1.0228,
+      "step": 685
+    },
+    {
+      "epoch": 1.6083916083916083,
+      "grad_norm": 0.29201876514809744,
+      "learning_rate": 4.838994568674351e-05,
+      "loss": 1.1897,
+      "step": 690
+    },
+    {
+      "epoch": 1.6200466200466201,
+      "grad_norm": 0.2731368722942658,
+      "learning_rate": 4.801077456022443e-05,
+      "loss": 1.2347,
+      "step": 695
+    },
+    {
+      "epoch": 1.6317016317016317,
+      "grad_norm": 0.24941385151182885,
+      "learning_rate": 4.763199805829236e-05,
+      "loss": 1.0522,
+      "step": 700
+    },
+    {
+      "epoch": 1.6433566433566433,
+      "grad_norm": 0.2601913077602386,
+      "learning_rate": 4.7253675803206544e-05,
+      "loss": 1.1047,
+      "step": 705
+    },
+    {
+      "epoch": 1.6550116550116551,
+      "grad_norm": 0.2627466378538171,
+      "learning_rate": 4.687586734572431e-05,
+      "loss": 1.2039,
+      "step": 710
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.33292973388136243,
+      "learning_rate": 4.649863215572747e-05,
+      "loss": 1.0949,
+      "step": 715
+    },
+    {
+      "epoch": 1.6783216783216783,
+      "grad_norm": 0.28930444872767674,
+      "learning_rate": 4.612202961286117e-05,
+      "loss": 1.1411,
+      "step": 720
+    },
+    {
+      "epoch": 1.68997668997669,
+      "grad_norm": 0.2811673269560653,
+      "learning_rate": 4.574611899718721e-05,
+      "loss": 1.1188,
+      "step": 725
+    },
+    {
+      "epoch": 1.7016317016317015,
+      "grad_norm": 0.2624778144533447,
+      "learning_rate": 4.537095947985282e-05,
+      "loss": 1.2099,
+      "step": 730
+    },
+    {
+      "epoch": 1.7132867132867133,
+      "grad_norm": 0.31909240386960064,
+      "learning_rate": 4.499661011377677e-05,
+      "loss": 1.1953,
+      "step": 735
+    },
+    {
+      "epoch": 1.724941724941725,
+      "grad_norm": 0.45177444374511333,
+      "learning_rate": 4.46231298243539e-05,
+      "loss": 1.1496,
+      "step": 740
+    },
+    {
+      "epoch": 1.7365967365967365,
+      "grad_norm": 0.3304135322652554,
+      "learning_rate": 4.425057740017993e-05,
+      "loss": 1.1407,
+      "step": 745
+    },
+    {
+      "epoch": 1.7482517482517483,
+      "grad_norm": 0.26814860174828314,
+      "learning_rate": 4.38790114837976e-05,
+      "loss": 1.0907,
+      "step": 750
+    },
+    {
+      "epoch": 1.75990675990676,
+      "grad_norm": 0.29715139148195335,
+      "learning_rate": 4.350849056246595e-05,
+      "loss": 1.1766,
+      "step": 755
+    },
+    {
+      "epoch": 1.7715617715617715,
+      "grad_norm": 0.274851580699654,
+      "learning_rate": 4.313907295895397e-05,
+      "loss": 1.1497,
+      "step": 760
+    },
+    {
+      "epoch": 1.7832167832167833,
+      "grad_norm": 0.30500141557968397,
+      "learning_rate": 4.277081682236013e-05,
+      "loss": 1.0404,
+      "step": 765
+    },
+    {
+      "epoch": 1.7948717948717947,
+      "grad_norm": 2.9176458727968746,
+      "learning_rate": 4.240378011895935e-05,
+      "loss": 1.0777,
+      "step": 770
+    },
+    {
+      "epoch": 1.8065268065268065,
+      "grad_norm": 0.32004127534889776,
+      "learning_rate": 4.2038020623078596e-05,
+      "loss": 1.1521,
+      "step": 775
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.38996610677191895,
+      "learning_rate": 4.1673595908002826e-05,
+      "loss": 1.0999,
+      "step": 780
+    },
+    {
+      "epoch": 1.8298368298368297,
+      "grad_norm": 0.39155093719025963,
+      "learning_rate": 4.131056333691247e-05,
+      "loss": 1.1836,
+      "step": 785
+    },
+    {
+      "epoch": 1.8414918414918415,
+      "grad_norm": 0.2765149318590016,
+      "learning_rate": 4.094898005385408e-05,
+      "loss": 1.1018,
+      "step": 790
+    },
+    {
+      "epoch": 1.8531468531468531,
+      "grad_norm": 0.22839762225047938,
+      "learning_rate": 4.058890297474543e-05,
+      "loss": 1.1704,
+      "step": 795
+    },
+    {
+      "epoch": 1.8648018648018647,
+      "grad_norm": 0.269742896374976,
+      "learning_rate": 4.023038877841649e-05,
+      "loss": 1.0703,
+      "step": 800
+    },
+    {
+      "epoch": 1.8764568764568765,
+      "grad_norm": 0.29602473720606215,
+      "learning_rate": 3.987349389768777e-05,
+      "loss": 1.1029,
+      "step": 805
+    },
+    {
+      "epoch": 1.8881118881118881,
+      "grad_norm": 0.2609207540513949,
+      "learning_rate": 3.951827451048737e-05,
+      "loss": 1.2367,
+      "step": 810
+    },
+    {
+      "epoch": 1.8997668997668997,
+      "grad_norm": 0.2508364860523673,
+      "learning_rate": 3.916478653100816e-05,
+      "loss": 1.0849,
+      "step": 815
+    },
+    {
+      "epoch": 1.9114219114219115,
+      "grad_norm": 1.2856984958855535,
+      "learning_rate": 3.881308560090648e-05,
+      "loss": 1.1273,
+      "step": 820
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.24270883363297913,
+      "learning_rate": 3.846322708054368e-05,
+      "loss": 1.1128,
+      "step": 825
+    },
+    {
+      "epoch": 1.9347319347319347,
+      "grad_norm": 0.26881059124314843,
+      "learning_rate": 3.811526604027204e-05,
+      "loss": 1.2133,
+      "step": 830
+    },
+    {
+      "epoch": 1.9463869463869465,
+      "grad_norm": 0.2878909720257614,
+      "learning_rate": 3.7769257251766225e-05,
+      "loss": 1.1629,
+      "step": 835
+    },
+    {
+      "epoch": 1.958041958041958,
+      "grad_norm": 0.31812523517669944,
+      "learning_rate": 3.742525517940187e-05,
+      "loss": 1.149,
+      "step": 840
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 0.27576941685401857,
+      "learning_rate": 3.708331397168247e-05,
+      "loss": 1.1484,
+      "step": 845
+    },
+    {
+      "epoch": 1.9813519813519813,
+      "grad_norm": 0.27263251333241223,
+      "learning_rate": 3.674348745271595e-05,
+      "loss": 1.1931,
+      "step": 850
+    },
+    {
+      "epoch": 1.993006993006993,
+      "grad_norm": 0.263716889490106,
+      "learning_rate": 3.6405829113742405e-05,
+      "loss": 1.1308,
+      "step": 855
+    },
+    {
+      "epoch": 1.9953379953379953,
+      "eval_loss": 1.2667760848999023,
+      "eval_runtime": 41.1775,
+      "eval_samples_per_second": 1.7,
+      "eval_steps_per_second": 0.219,
+      "step": 856
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1287,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 887872819298304.0,
+  "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 sha256:1a800d03b526d467e2fcadee0f29680d19088aff8322ac8a7f79b8cca003b2c5
+size 7480